{ "organization": "CleverThis", "base_processing_dir": "./dataset_processing", "huggingface_repo_prefix": "CleverThis", "datasets": { "wordnet": { "short_name": "wordnet", "full_name": "WordNet RDF", "description": "Lexical database of semantic relations between words (English WordNet 2024)", "category": "small", "download": { "url": "https://en-word.net/static/english-wordnet-2024.ttl.gz", "format": "turtle", "compression": "gz", "extraction_command": "gunzip", "size_gb": 0.21, "compressed_size_gb": 0.014 }, "metadata": { "entities": "~120K synsets", "triples": "~2M", "license": "CC BY 4.0", "recommended_for": "Quick validation, linguistic relationships, small-scale testing", "notes": "Compressed download, automatic extraction. English WordNet 2024 from en-word.net" }, "huggingface": { "repository": "CleverThis/wordnet", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "standard", "streaming": false, "chunk_size": 10000 } }, "schema-org": { "short_name": "schema-org", "full_name": "Schema.org", "description": "Vocabulary schemas for structured data on the web", "category": "small", "download": { "url": "https://schema.org/version/latest/schemaorg-current-https.ttl", "format": "turtle", "compression": null, "extraction_command": null, "size_gb": 0.01, "compressed_size_gb": null }, "metadata": { "entities": "~2K types", "triples": "~15K", "license": "CC BY-SA 3.0", "recommended_for": "Ontology understanding, vocabulary learning, small-scale testing", "notes": "Direct download, no extraction needed" }, "huggingface": { "repository": "CleverThis/schema-org", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "standard", "streaming": false, "chunk_size": 10000 } }, "yago-4.5": { "short_name": "yago45", "full_name": "YAGO 4.5", "description": "Knowledge base combining Wikipedia, WordNet, and GeoNames", "category": "medium", "download": { "url": "https://yago-knowledge.org/data/yago4.5/yago-4.5.0.2-tiny.zip", "format": "turtle", "compression": "zip", "extraction_command": "unzip", "size_gb": 10.0, "compressed_size_gb": 0.2 }, "metadata": { "entities": "~2.5M", "triples": "~50M", "license": "CC BY-SA 3.0", "recommended_for": "Balanced size/quality, general knowledge, initial training", "notes": "YAGO 4.5 tiny version. Good balance for initial experiments. ZIP distribution." }, "huggingface": { "repository": "CleverThis/yago-4.5", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 50000 } }, "yago-4.5-full": { "short_name": "yago45full", "full_name": "YAGO 4.5 Full", "description": "Complete YAGO 4.5 dataset with all facts", "category": "medium", "download": { "url": "https://yago-knowledge.org/data/yago4.5/yago-4.5.0.2.zip", "format": "turtle", "compression": "zip", "extraction_command": "unzip", "size_gb": 15.0, "compressed_size_gb": 12.0 }, "metadata": { "entities": "~50M", "triples": "~109M", "license": "CC BY-SA 3.0", "recommended_for": "Complete entity information with type hierarchies", "notes": "YAGO 4.5 complete version. Format changed to ZIP distribution with multiple files." }, "huggingface": { "repository": "CleverThis/yago-4.5-full", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 50000 } }, "dbpedia-labels-en": { "short_name": "dbpedialabels", "full_name": "DBpedia English Labels", "description": "Entity labels from DBpedia (English)", "category": "medium", "download": { "url": "https://downloads.dbpedia.org/repo/dbpedia/generic/labels/2022.12.01/labels_lang=en.ttl.bz2", "format": "turtle", "compression": "bz2", "extraction_command": "bunzip2", "size_gb": 1.0, "compressed_size_gb": 0.16 }, "metadata": { "entities": "~9.5M", "triples": "~9.5M", "license": "CC BY-SA 3.0", "recommended_for": "Entity naming, label learning, medium-scale training", "notes": null }, "huggingface": { "repository": "CleverThis/dbpedia-labels-en", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 50000 } }, "dbpedia-ontology": { "short_name": "dbpediaonto", "full_name": "DBpedia Ontology", "description": "DBpedia ontology classes and properties", "category": "medium", "download": { "url": "https://downloads.dbpedia.org/repo/dbpedia/mappings/instance-types/2022.12.01/instance-types_lang=en_transitive.ttl.bz2", "format": "turtle", "compression": "bz2", "extraction_command": "bunzip2", "size_gb": 0.8, "compressed_size_gb": 0.14 }, "metadata": { "entities": "~9.5M", "triples": "~40M", "license": "CC BY-SA 3.0", "recommended_for": "Type classification, ontology learning", "notes": "Uses transitive closure of instance types for complete type hierarchy" }, "huggingface": { "repository": "CleverThis/dbpedia-ontology", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 50000 } }, "dbpedia-core-en": { "short_name": "dbpediacore", "full_name": "DBpedia Core (English)", "description": "Core facts from Wikipedia (English)", "category": "large", "download": { "url": "https://downloads.dbpedia.org/repo/dbpedia/mappings/mappingbased-objects/2022.12.01/mappingbased-objects_lang=en.ttl.bz2", "format": "turtle", "compression": "bz2", "extraction_command": "bunzip2", "size_gb": 1.8, "compressed_size_gb": 0.18 }, "metadata": { "entities": "~9.5M", "triples": "~50-60M", "license": "CC BY-SA 3.0", "recommended_for": "Wikipedia-based knowledge, production training", "notes": "Core DBpedia facts extracted from Wikipedia infoboxes" }, "huggingface": { "repository": "CleverThis/dbpedia-core-en", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "wikidata-truthy": { "short_name": "wikidatatruthy", "full_name": "Wikidata Truthy", "description": "Core facts from Wikidata (preferred statements only)", "category": "large", "download": { "url": "https://dumps.wikimedia.org/wikidatawiki/entities/latest-truthy.nt.bz2", "format": "ntriples", "compression": "bz2", "extraction_command": "bunzip2", "size_gb": 100.0, "compressed_size_gb": 40.0 }, "metadata": { "entities": "~100M", "triples": "~2B", "license": "CC0 1.0", "recommended_for": "Best general knowledge, production training, multilingual support", "notes": "Most comprehensive general knowledge base, recommended for production. Now uses bz2 compression." }, "huggingface": { "repository": "CleverThis/wikidata-truthy", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "freebase": { "short_name": "freebase", "full_name": "Freebase", "description": "Large-scale knowledge base (archived by Google)", "category": "large", "download": { "url": "http://commondatastorage.googleapis.com/freebase-public/rdf/freebase-rdf-latest.gz", "format": "ntriples", "compression": "gz", "extraction_command": "gunzip", "size_gb": 300.0, "compressed_size_gb": 30.0 }, "metadata": { "entities": "~50M", "triples": "~3B", "license": "CC BY 2.5", "recommended_for": "Historical knowledge base, large-scale training", "notes": "Archived dataset from 2014, very comprehensive but historical" }, "huggingface": { "repository": "CleverThis/freebase", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "wikidata-full": { "short_name": "wikidatafull", "full_name": "Wikidata Full", "description": "Complete Wikidata dump with all statements", "category": "xlarge", "download": { "url": "https://dumps.wikimedia.org/wikidatawiki/entities/20251215/wikidata-20251215-all-BETA.ttl.gz", "format": "turtle", "compression": "bz2", "extraction_command": "bunzip2", "size_gb": 1500.0, "compressed_size_gb": 120.0 }, "metadata": { "entities": "~100M", "triples": "~17-20B", "license": "CC0 1.0", "recommended_for": "Advanced large-scale training, research", "notes": "Very large dataset, requires significant storage and processing power" }, "huggingface": { "repository": "CleverThis/wikidata-full", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "conceptnet": { "short_name": "conceptnet", "full_name": "ConceptNet 5.7", "description": "Common-sense knowledge graph with everyday facts and relationships", "category": "small", "download": { "url": "https://s3.amazonaws.com/conceptnet/downloads/2019/edges/conceptnet-assertions-5.7.0.csv.gz", "format": "csv", "compression": "gz", "extraction_command": "gunzip", "size_gb": 1.2, "compressed_size_gb": 0.6 }, "metadata": { "entities": "~8M nodes", "triples": "~21M edges", "license": "CC BY-SA 4.0", "recommended_for": "Common-sense reasoning, NLP tasks, multilingual knowledge", "notes": "CSV format (tab-separated), requires conversion to RDF. Crowdsourced with confidence scores." }, "huggingface": { "repository": "CleverThis/conceptnet", "private": false, "readme_template": "conceptnet_specific" }, "processing": { "converter": "conceptnet_specialized", "streaming": false, "chunk_size": 10000 } }, "framenet": { "short_name": "framenet", "full_name": "FrameNet Sample", "description": "Sample frame semantic database with semantic frames and roles (demonstration dataset)", "category": "small", "download": { "url": "file:///app/dataset_processing/sample_data/framenet_sample.ttl", "format": "turtle", "compression": null, "extraction_command": null, "size_gb": 0.001, "compressed_size_gb": null }, "metadata": { "entities": "3 frames, 9 lexical units, 10 frame elements", "triples": "~50", "license": "BSD 3-Clause", "recommended_for": "Frame semantics demonstration, semantic role labeling examples", "notes": "Sample FrameNet-style data demonstrating semantic frames, frame elements, and lexical units." }, "huggingface": { "repository": "CleverThis/framenet", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "standard", "streaming": false, "chunk_size": 10000 } }, "gene-ontology": { "short_name": "geneontology", "full_name": "Gene Ontology", "description": "Biological ontology for gene function hierarchy", "category": "small", "download": { "url": "http://purl.obolibrary.org/obo/go.owl", "format": "xml", "compression": null, "extraction_command": null, "size_gb": 0.05, "compressed_size_gb": null }, "metadata": { "entities": "~44K GO concepts", "triples": "~853K", "license": "CC BY 4.0", "recommended_for": "Biological ontology, gene function annotation", "notes": "Monthly updates. OWL format with reasoning support." }, "huggingface": { "repository": "CleverThis/gene-ontology", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "standard", "streaming": false, "chunk_size": 10000 } }, "uniprotkb_reviewed_eukaryota_opisthokonta_metazoa_33208_0": { "short_name": "uniprotkb_reviewed_eukaryota_opisthokonta_metazoa_33208_0", "full_name": "uniprotkb_reviewed_eukaryota_opisthokonta_metazoa_33208_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_eukaryota_opisthokonta_metazoa_33208_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_eukaryota_opisthokonta_metazoa_33208_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_obsolete_entries_0": { "short_name": "uniprotkb_obsolete_entries_0", "full_name": "uniprotkb_obsolete_entries_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_obsolete_entries_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_obsolete_entries_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_obsolete_entries_10000000": { "short_name": "uniprotkb_obsolete_entries_10000000", "full_name": "uniprotkb_obsolete_entries_10000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_obsolete_entries_10000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_obsolete_entries_10000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_obsolete_entries_20000000": { "short_name": "uniprotkb_obsolete_entries_20000000", "full_name": "uniprotkb_obsolete_entries_20000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_obsolete_entries_20000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_obsolete_entries_20000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_obsolete_entries_30000000": { "short_name": "uniprotkb_obsolete_entries_30000000", "full_name": "uniprotkb_obsolete_entries_30000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_obsolete_entries_30000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_obsolete_entries_30000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_obsolete_entries_40000000": { "short_name": "uniprotkb_obsolete_entries_40000000", "full_name": "uniprotkb_obsolete_entries_40000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_obsolete_entries_40000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_obsolete_entries_40000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_obsolete_entries_50000000": { "short_name": "uniprotkb_obsolete_entries_50000000", "full_name": "uniprotkb_obsolete_entries_50000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_obsolete_entries_50000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_obsolete_entries_50000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_obsolete_entries_60000000": { "short_name": "uniprotkb_obsolete_entries_60000000", "full_name": "uniprotkb_obsolete_entries_60000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_obsolete_entries_60000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_obsolete_entries_60000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_obsolete_entries_70000000": { "short_name": "uniprotkb_obsolete_entries_70000000", "full_name": "uniprotkb_obsolete_entries_70000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_obsolete_entries_70000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_obsolete_entries_70000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_obsolete_entries_80000000": { "short_name": "uniprotkb_obsolete_entries_80000000", "full_name": "uniprotkb_obsolete_entries_80000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_obsolete_entries_80000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_obsolete_entries_80000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_obsolete_entries_90000000": { "short_name": "uniprotkb_obsolete_entries_90000000", "full_name": "uniprotkb_obsolete_entries_90000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_obsolete_entries_90000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_obsolete_entries_90000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_obsolete_entries_100000000": { "short_name": "uniprotkb_obsolete_entries_100000000", "full_name": "uniprotkb_obsolete_entries_100000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_obsolete_entries_100000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_obsolete_entries_100000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_obsolete_entries_110000000": { "short_name": "uniprotkb_obsolete_entries_110000000", "full_name": "uniprotkb_obsolete_entries_110000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_obsolete_entries_110000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_obsolete_entries_110000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_obsolete_entries_120000000": { "short_name": "uniprotkb_obsolete_entries_120000000", "full_name": "uniprotkb_obsolete_entries_120000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_obsolete_entries_120000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_obsolete_entries_120000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_obsolete_entries_130000000": { "short_name": "uniprotkb_obsolete_entries_130000000", "full_name": "uniprotkb_obsolete_entries_130000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_obsolete_entries_130000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_obsolete_entries_130000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_obsolete_entries_140000000": { "short_name": "uniprotkb_obsolete_entries_140000000", "full_name": "uniprotkb_obsolete_entries_140000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_obsolete_entries_140000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_obsolete_entries_140000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_obsolete_entries_150000000": { "short_name": "uniprotkb_obsolete_entries_150000000", "full_name": "uniprotkb_obsolete_entries_150000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_obsolete_entries_150000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_obsolete_entries_150000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_obsolete_entries_160000000": { "short_name": "uniprotkb_obsolete_entries_160000000", "full_name": "uniprotkb_obsolete_entries_160000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_obsolete_entries_160000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_obsolete_entries_160000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_obsolete_entries_170000000": { "short_name": "uniprotkb_obsolete_entries_170000000", "full_name": "uniprotkb_obsolete_entries_170000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_obsolete_entries_170000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_obsolete_entries_170000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_obsolete_entries_180000000": { "short_name": "uniprotkb_obsolete_entries_180000000", "full_name": "uniprotkb_obsolete_entries_180000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_obsolete_entries_180000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_obsolete_entries_180000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_obsolete_entries_190000000": { "short_name": "uniprotkb_obsolete_entries_190000000", "full_name": "uniprotkb_obsolete_entries_190000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_obsolete_entries_190000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_obsolete_entries_190000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_obsolete_entries_200000000": { "short_name": "uniprotkb_obsolete_entries_200000000", "full_name": "uniprotkb_obsolete_entries_200000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_obsolete_entries_200000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_obsolete_entries_200000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_obsolete_entries_210000000": { "short_name": "uniprotkb_obsolete_entries_210000000", "full_name": "uniprotkb_obsolete_entries_210000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_obsolete_entries_210000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_obsolete_entries_210000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_obsolete_entries_220000000": { "short_name": "uniprotkb_obsolete_entries_220000000", "full_name": "uniprotkb_obsolete_entries_220000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_obsolete_entries_220000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_obsolete_entries_220000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_obsolete_entries_230000000": { "short_name": "uniprotkb_obsolete_entries_230000000", "full_name": "uniprotkb_obsolete_entries_230000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_obsolete_entries_230000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_obsolete_entries_230000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_obsolete_entries_240000000": { "short_name": "uniprotkb_obsolete_entries_240000000", "full_name": "uniprotkb_obsolete_entries_240000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_obsolete_entries_240000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_obsolete_entries_240000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_obsolete_entries_250000000": { "short_name": "uniprotkb_obsolete_entries_250000000", "full_name": "uniprotkb_obsolete_entries_250000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_obsolete_entries_250000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_obsolete_entries_250000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_obsolete_entries_260000000": { "short_name": "uniprotkb_obsolete_entries_260000000", "full_name": "uniprotkb_obsolete_entries_260000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_obsolete_entries_260000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_obsolete_entries_260000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_obsolete_entries_270000000": { "short_name": "uniprotkb_obsolete_entries_270000000", "full_name": "uniprotkb_obsolete_entries_270000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_obsolete_entries_270000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_obsolete_entries_270000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_archea_environmental_samples_48510_0": { "short_name": "uniprotkb_reviewed_archea_environmental_samples_48510_0", "full_name": "uniprotkb_reviewed_archea_environmental_samples_48510_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_archea_environmental_samples_48510_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_archea_environmental_samples_48510_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_archea_methanobacteriati_3366610_0": { "short_name": "uniprotkb_reviewed_archea_methanobacteriati_3366610_0", "full_name": "uniprotkb_reviewed_archea_methanobacteriati_3366610_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_archea_methanobacteriati_3366610_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_archea_methanobacteriati_3366610_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_archea_nanobdellati_1783276_0": { "short_name": "uniprotkb_reviewed_archea_nanobdellati_1783276_0", "full_name": "uniprotkb_reviewed_archea_nanobdellati_1783276_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_archea_nanobdellati_1783276_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_archea_nanobdellati_1783276_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_archea_promethearchaeati_1935183_0": { "short_name": "uniprotkb_reviewed_archea_promethearchaeati_1935183_0", "full_name": "uniprotkb_reviewed_archea_promethearchaeati_1935183_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_archea_promethearchaeati_1935183_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_archea_promethearchaeati_1935183_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_archea_thermoproteati_1783275_0": { "short_name": "uniprotkb_reviewed_archea_thermoproteati_1783275_0", "full_name": "uniprotkb_reviewed_archea_thermoproteati_1783275_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_archea_thermoproteati_1783275_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_archea_thermoproteati_1783275_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_bacteria_bacillati_1783272_0": { "short_name": "uniprotkb_reviewed_bacteria_bacillati_1783272_0", "full_name": "uniprotkb_reviewed_bacteria_bacillati_1783272_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_bacteria_bacillati_1783272_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_bacteria_bacillati_1783272_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_bacteria_bacteria_incertae_sedis_2323_0": { "short_name": "uniprotkb_reviewed_bacteria_bacteria_incertae_sedis_2323_0", "full_name": "uniprotkb_reviewed_bacteria_bacteria_incertae_sedis_2323_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_bacteria_bacteria_incertae_sedis_2323_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_bacteria_bacteria_incertae_sedis_2323_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_bacteria_environmental_samples_48479_0": { "short_name": "uniprotkb_reviewed_bacteria_environmental_samples_48479_0", "full_name": "uniprotkb_reviewed_bacteria_environmental_samples_48479_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_bacteria_environmental_samples_48479_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_bacteria_environmental_samples_48479_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_bacteria_fusobacteriati_3384189_0": { "short_name": "uniprotkb_reviewed_bacteria_fusobacteriati_3384189_0", "full_name": "uniprotkb_reviewed_bacteria_fusobacteriati_3384189_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_bacteria_fusobacteriati_3384189_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_bacteria_fusobacteriati_3384189_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_bacteria_proteobacteria_acidithiobacillia_1807140_0": { "short_name": "uniprotkb_reviewed_bacteria_proteobacteria_acidithiobacillia_1807140_0", "full_name": "uniprotkb_reviewed_bacteria_proteobacteria_acidithiobacillia_1807140_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_bacteria_proteobacteria_acidithiobacillia_1807140_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_bacteria_proteobacteria_acidithiobacillia_1807140_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_bacteria_proteobacteria_alphaproteobacteria_28211_0": { "short_name": "uniprotkb_reviewed_bacteria_proteobacteria_alphaproteobacteria_28211_0", "full_name": "uniprotkb_reviewed_bacteria_proteobacteria_alphaproteobacteria_28211_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_bacteria_proteobacteria_alphaproteobacteria_28211_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_bacteria_proteobacteria_alphaproteobacteria_28211_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_bacteria_proteobacteria_betaproteobacteria_28216_0": { "short_name": "uniprotkb_reviewed_bacteria_proteobacteria_betaproteobacteria_28216_0", "full_name": "uniprotkb_reviewed_bacteria_proteobacteria_betaproteobacteria_28216_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_bacteria_proteobacteria_betaproteobacteria_28216_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_bacteria_proteobacteria_betaproteobacteria_28216_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_bacteria_proteobacteria_gammaproteobacteria_1236_0": { "short_name": "uniprotkb_reviewed_bacteria_proteobacteria_gammaproteobacteria_1236_0", "full_name": "uniprotkb_reviewed_bacteria_proteobacteria_gammaproteobacteria_1236_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_bacteria_proteobacteria_gammaproteobacteria_1236_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_bacteria_proteobacteria_gammaproteobacteria_1236_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_bacteria_proteobacteria_hydrogenophilia_2008785_0": { "short_name": "uniprotkb_reviewed_bacteria_proteobacteria_hydrogenophilia_2008785_0", "full_name": "uniprotkb_reviewed_bacteria_proteobacteria_hydrogenophilia_2008785_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_bacteria_proteobacteria_hydrogenophilia_2008785_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_bacteria_proteobacteria_hydrogenophilia_2008785_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_bacteria_proteobacteria_magnetococcia_3118669_0": { "short_name": "uniprotkb_reviewed_bacteria_proteobacteria_magnetococcia_3118669_0", "full_name": "uniprotkb_reviewed_bacteria_proteobacteria_magnetococcia_3118669_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_bacteria_proteobacteria_magnetococcia_3118669_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_bacteria_proteobacteria_magnetococcia_3118669_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_bacteria_proteobacteria_pseudomonadota_incertae_sedis_32045_0": { "short_name": "uniprotkb_reviewed_bacteria_proteobacteria_pseudomonadota_incertae_sedis_32045_0", "full_name": "uniprotkb_reviewed_bacteria_proteobacteria_pseudomonadota_incertae_sedis_32045_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_bacteria_proteobacteria_pseudomonadota_incertae_sedis_32045_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_bacteria_proteobacteria_pseudomonadota_incertae_sedis_32045_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_bacteria_pseudomonadati_3379134_0": { "short_name": "uniprotkb_reviewed_bacteria_pseudomonadati_3379134_0", "full_name": "uniprotkb_reviewed_bacteria_pseudomonadati_3379134_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_bacteria_pseudomonadati_3379134_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_bacteria_pseudomonadati_3379134_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_bacteria_thermotogati_3384194_0": { "short_name": "uniprotkb_reviewed_bacteria_thermotogati_3384194_0", "full_name": "uniprotkb_reviewed_bacteria_thermotogati_3384194_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_bacteria_thermotogati_3384194_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_bacteria_thermotogati_3384194_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_bacteria_unclassified_bacteria_49928_0": { "short_name": "uniprotkb_reviewed_bacteria_unclassified_bacteria_49928_0", "full_name": "uniprotkb_reviewed_bacteria_unclassified_bacteria_49928_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_bacteria_unclassified_bacteria_49928_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_bacteria_unclassified_bacteria_49928_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_eukaryota_amoebozoa_554915_0": { "short_name": "uniprotkb_reviewed_eukaryota_amoebozoa_554915_0", "full_name": "uniprotkb_reviewed_eukaryota_amoebozoa_554915_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_eukaryota_amoebozoa_554915_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_eukaryota_amoebozoa_554915_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_eukaryota_cryptophyceae_3027_0": { "short_name": "uniprotkb_reviewed_eukaryota_cryptophyceae_3027_0", "full_name": "uniprotkb_reviewed_eukaryota_cryptophyceae_3027_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_eukaryota_cryptophyceae_3027_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_eukaryota_cryptophyceae_3027_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_eukaryota_discoba_2611352_0": { "short_name": "uniprotkb_reviewed_eukaryota_discoba_2611352_0", "full_name": "uniprotkb_reviewed_eukaryota_discoba_2611352_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_eukaryota_discoba_2611352_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_eukaryota_discoba_2611352_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_eukaryota_glaucocystophyceae_38254_0": { "short_name": "uniprotkb_reviewed_eukaryota_glaucocystophyceae_38254_0", "full_name": "uniprotkb_reviewed_eukaryota_glaucocystophyceae_38254_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_eukaryota_glaucocystophyceae_38254_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_eukaryota_glaucocystophyceae_38254_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_eukaryota_haptista_2608109_0": { "short_name": "uniprotkb_reviewed_eukaryota_haptista_2608109_0", "full_name": "uniprotkb_reviewed_eukaryota_haptista_2608109_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_eukaryota_haptista_2608109_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_eukaryota_haptista_2608109_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_eukaryota_metamonada_2611341_0": { "short_name": "uniprotkb_reviewed_eukaryota_metamonada_2611341_0", "full_name": "uniprotkb_reviewed_eukaryota_metamonada_2611341_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_eukaryota_metamonada_2611341_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_eukaryota_metamonada_2611341_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_eukaryota_opisthokonta_choanoflagellata_28009_0": { "short_name": "uniprotkb_reviewed_eukaryota_opisthokonta_choanoflagellata_28009_0", "full_name": "uniprotkb_reviewed_eukaryota_opisthokonta_choanoflagellata_28009_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_eukaryota_opisthokonta_choanoflagellata_28009_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_eukaryota_opisthokonta_choanoflagellata_28009_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_eukaryota_opisthokonta_filasterea_2687318_0": { "short_name": "uniprotkb_reviewed_eukaryota_opisthokonta_filasterea_2687318_0", "full_name": "uniprotkb_reviewed_eukaryota_opisthokonta_filasterea_2687318_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_eukaryota_opisthokonta_filasterea_2687318_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_eukaryota_opisthokonta_filasterea_2687318_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_eukaryota_opisthokonta_fungi_4751_0": { "short_name": "uniprotkb_reviewed_eukaryota_opisthokonta_fungi_4751_0", "full_name": "uniprotkb_reviewed_eukaryota_opisthokonta_fungi_4751_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_eukaryota_opisthokonta_fungi_4751_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_eukaryota_opisthokonta_fungi_4751_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_eukaryota_opisthokonta_metazoa_33208_0": { "short_name": "uniprotkb_reviewed_eukaryota_opisthokonta_metazoa_33208_0", "full_name": "uniprotkb_reviewed_eukaryota_opisthokonta_metazoa_33208_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_eukaryota_opisthokonta_metazoa_33208_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_eukaryota_opisthokonta_metazoa_33208_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_eukaryota_rhodophyta_2763_0": { "short_name": "uniprotkb_reviewed_eukaryota_rhodophyta_2763_0", "full_name": "uniprotkb_reviewed_eukaryota_rhodophyta_2763_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_eukaryota_rhodophyta_2763_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_eukaryota_rhodophyta_2763_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_eukaryota_sar_2698737_0": { "short_name": "uniprotkb_reviewed_eukaryota_sar_2698737_0", "full_name": "uniprotkb_reviewed_eukaryota_sar_2698737_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_eukaryota_sar_2698737_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_eukaryota_sar_2698737_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_eukaryota_viridiplantae_33090_0": { "short_name": "uniprotkb_reviewed_eukaryota_viridiplantae_33090_0", "full_name": "uniprotkb_reviewed_eukaryota_viridiplantae_33090_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_eukaryota_viridiplantae_33090_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_eukaryota_viridiplantae_33090_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_reviewed_viruses_10239_0": { "short_name": "uniprotkb_reviewed_viruses_10239_0", "full_name": "uniprotkb_reviewed_viruses_10239_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_reviewed_viruses_10239_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_reviewed_viruses_10239_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_archea_environmental_samples_48510_0": { "short_name": "uniprotkb_unreviewed_archea_environmental_samples_48510_0", "full_name": "uniprotkb_unreviewed_archea_environmental_samples_48510_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_archea_environmental_samples_48510_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_archea_environmental_samples_48510_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_archea_methanobacteriati_3366610_0": { "short_name": "uniprotkb_unreviewed_archea_methanobacteriati_3366610_0", "full_name": "uniprotkb_unreviewed_archea_methanobacteriati_3366610_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_archea_methanobacteriati_3366610_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_archea_methanobacteriati_3366610_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_archea_methanobacteriati_3366610_1000000": { "short_name": "uniprotkb_unreviewed_archea_methanobacteriati_3366610_1000000", "full_name": "uniprotkb_unreviewed_archea_methanobacteriati_3366610_1000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_archea_methanobacteriati_3366610_1000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_archea_methanobacteriati_3366610_1000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_archea_nanobdellati_1783276_0": { "short_name": "uniprotkb_unreviewed_archea_nanobdellati_1783276_0", "full_name": "uniprotkb_unreviewed_archea_nanobdellati_1783276_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_archea_nanobdellati_1783276_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_archea_nanobdellati_1783276_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_archea_promethearchaeati_1935183_0": { "short_name": "uniprotkb_unreviewed_archea_promethearchaeati_1935183_0", "full_name": "uniprotkb_unreviewed_archea_promethearchaeati_1935183_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_archea_promethearchaeati_1935183_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_archea_promethearchaeati_1935183_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_archea_thermoproteati_1783275_0": { "short_name": "uniprotkb_unreviewed_archea_thermoproteati_1783275_0", "full_name": "uniprotkb_unreviewed_archea_thermoproteati_1783275_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_archea_thermoproteati_1783275_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_archea_thermoproteati_1783275_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_archea_unclassified_archaea_93506_0": { "short_name": "uniprotkb_unreviewed_archea_unclassified_archaea_93506_0", "full_name": "uniprotkb_unreviewed_archea_unclassified_archaea_93506_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_archea_unclassified_archaea_93506_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_archea_unclassified_archaea_93506_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_0": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_0", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_1000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_1000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_1000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_1000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_1000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_2000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_2000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_2000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_2000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_2000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_3000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_3000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_3000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_3000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_3000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_4000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_4000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_4000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_4000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_4000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_5000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_5000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_5000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_5000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_5000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_6000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_6000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_6000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_6000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_6000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_7000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_7000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_7000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_7000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_7000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_8000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_8000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_8000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_8000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_8000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_9000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_9000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_9000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_9000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_9000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_10000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_10000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_10000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_10000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_10000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_11000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_11000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_11000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_11000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_11000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_12000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_12000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_12000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_12000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_12000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_13000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_13000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_13000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_13000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_13000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_14000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_14000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_14000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_14000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_14000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_15000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_15000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_15000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_15000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_15000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_16000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_16000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_16000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_16000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_16000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_17000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_17000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_17000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_17000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_17000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_18000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_18000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_18000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_18000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_18000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_19000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_19000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_19000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_19000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_19000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_20000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_20000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_20000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_20000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_20000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_21000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_21000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_21000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_21000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_21000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_22000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_22000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_22000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_22000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_22000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_23000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_23000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_23000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_23000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_23000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_24000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_24000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_24000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_24000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_24000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_25000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_25000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_25000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_25000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_25000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_26000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_26000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_26000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_26000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_26000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_27000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_27000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_27000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_27000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_27000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_28000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_28000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_28000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_28000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_28000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_29000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_29000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_29000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_29000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_29000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_30000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_30000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_30000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_30000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_30000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_31000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_31000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_31000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_31000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_31000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_32000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_32000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_32000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_32000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_32000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_33000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_33000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_33000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_33000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_33000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_34000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_34000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_34000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_34000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_34000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_35000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_35000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_35000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_35000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_35000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_36000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_36000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_36000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_36000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_36000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_37000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_37000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_37000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_37000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_37000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_38000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_38000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_38000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_38000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_38000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_39000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_39000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_39000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_39000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_39000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_40000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_40000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_40000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_40000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_40000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_41000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_41000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_41000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_41000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_41000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacillati_1783272_42000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_42000000", "full_name": "uniprotkb_unreviewed_bacteria_bacillati_1783272_42000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacillati_1783272_42000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacillati_1783272_42000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacteria_incertae_sedis_2323_0": { "short_name": "uniprotkb_unreviewed_bacteria_bacteria_incertae_sedis_2323_0", "full_name": "uniprotkb_unreviewed_bacteria_bacteria_incertae_sedis_2323_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacteria_incertae_sedis_2323_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacteria_incertae_sedis_2323_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_bacteria_incertae_sedis_2323_1000000": { "short_name": "uniprotkb_unreviewed_bacteria_bacteria_incertae_sedis_2323_1000000", "full_name": "uniprotkb_unreviewed_bacteria_bacteria_incertae_sedis_2323_1000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_bacteria_incertae_sedis_2323_1000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_bacteria_incertae_sedis_2323_1000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_candidatus_moduliflexota_3071909_0": { "short_name": "uniprotkb_unreviewed_bacteria_candidatus_moduliflexota_3071909_0", "full_name": "uniprotkb_unreviewed_bacteria_candidatus_moduliflexota_3071909_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_candidatus_moduliflexota_3071909_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_candidatus_moduliflexota_3071909_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_delta_and_epsilon_subdivisions_68525_0": { "short_name": "uniprotkb_unreviewed_bacteria_delta_and_epsilon_subdivisions_68525_0", "full_name": "uniprotkb_unreviewed_bacteria_delta_and_epsilon_subdivisions_68525_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_delta_and_epsilon_subdivisions_68525_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_delta_and_epsilon_subdivisions_68525_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_environmental_samples_48479_0": { "short_name": "uniprotkb_unreviewed_bacteria_environmental_samples_48479_0", "full_name": "uniprotkb_unreviewed_bacteria_environmental_samples_48479_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_environmental_samples_48479_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_environmental_samples_48479_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_fusobacteriati_3384189_0": { "short_name": "uniprotkb_unreviewed_bacteria_fusobacteriati_3384189_0", "full_name": "uniprotkb_unreviewed_bacteria_fusobacteriati_3384189_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_fusobacteriati_3384189_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_fusobacteriati_3384189_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_acidithiobacillia_1807140_0": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_acidithiobacillia_1807140_0", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_acidithiobacillia_1807140_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_acidithiobacillia_1807140_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_acidithiobacillia_1807140_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_0": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_0", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_1000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_1000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_1000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_1000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_1000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_2000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_2000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_2000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_2000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_2000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_3000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_3000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_3000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_3000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_3000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_4000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_4000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_4000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_4000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_4000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_5000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_5000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_5000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_5000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_5000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_6000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_6000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_6000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_6000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_6000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_7000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_7000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_7000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_7000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_7000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_8000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_8000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_8000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_8000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_8000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_9000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_9000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_9000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_9000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_9000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_10000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_10000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_10000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_10000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_10000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_11000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_11000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_11000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_11000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_11000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_12000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_12000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_12000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_12000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_alphaproteobacteria_28211_12000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_0": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_0", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_1000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_1000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_1000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_1000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_1000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_2000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_2000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_2000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_2000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_2000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_3000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_3000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_3000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_3000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_3000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_4000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_4000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_4000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_4000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_4000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_5000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_5000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_5000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_5000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_5000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_6000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_6000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_6000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_6000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_6000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_7000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_7000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_7000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_7000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_betaproteobacteria_28216_7000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_candidatius_mariprofundia_580370_0": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_candidatius_mariprofundia_580370_0", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_candidatius_mariprofundia_580370_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_candidatius_mariprofundia_580370_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_candidatius_mariprofundia_580370_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_candidatus_lambdaproteobacteria_1817794_0": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_candidatus_lambdaproteobacteria_1817794_0", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_candidatus_lambdaproteobacteria_1817794_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_candidatus_lambdaproteobacteria_1817794_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_candidatus_lambdaproteobacteria_1817794_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_candidatus_muproteobacteria_1817795_0": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_candidatus_muproteobacteria_1817795_0", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_candidatus_muproteobacteria_1817795_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_candidatus_muproteobacteria_1817795_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_candidatus_muproteobacteria_1817795_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_environmental_samples_47936_0": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_environmental_samples_47936_0", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_environmental_samples_47936_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_environmental_samples_47936_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_environmental_samples_47936_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_0": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_0", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_1000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_1000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_1000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_1000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_1000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_2000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_2000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_2000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_2000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_2000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_3000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_3000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_3000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_3000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_3000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_4000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_4000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_4000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_4000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_4000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_5000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_5000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_5000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_5000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_5000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_6000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_6000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_6000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_6000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_6000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_7000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_7000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_7000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_7000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_7000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_8000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_8000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_8000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_8000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_8000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_9000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_9000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_9000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_9000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_9000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_10000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_10000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_10000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_10000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_10000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_11000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_11000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_11000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_11000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_11000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_12000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_12000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_12000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_12000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_12000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_13000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_13000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_13000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_13000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_13000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_14000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_14000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_14000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_14000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_14000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_15000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_15000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_15000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_15000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_15000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_16000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_16000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_16000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_16000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_16000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_17000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_17000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_17000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_17000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_17000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_18000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_18000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_18000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_18000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_18000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_19000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_19000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_19000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_19000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_19000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_20000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_20000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_20000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_20000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_20000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_21000000": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_21000000", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_21000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_21000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_gammaproteobacteria_1236_21000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_hydrogenophilia_2008785_0": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_hydrogenophilia_2008785_0", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_hydrogenophilia_2008785_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_hydrogenophilia_2008785_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_hydrogenophilia_2008785_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_magnetococcia_3118669_0": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_magnetococcia_3118669_0", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_magnetococcia_3118669_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_magnetococcia_3118669_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_magnetococcia_3118669_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_pseudomonadota_incertae_sedis_32045_0": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_pseudomonadota_incertae_sedis_32045_0", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_pseudomonadota_incertae_sedis_32045_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_pseudomonadota_incertae_sedis_32045_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_pseudomonadota_incertae_sedis_32045_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_proteobacteria_unclassified_pseudomonadota_81684_0": { "short_name": "uniprotkb_unreviewed_bacteria_proteobacteria_unclassified_pseudomonadota_81684_0", "full_name": "uniprotkb_unreviewed_bacteria_proteobacteria_unclassified_pseudomonadota_81684_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_proteobacteria_unclassified_pseudomonadota_81684_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_proteobacteria_unclassified_pseudomonadota_81684_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_0": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_0", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_1000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_1000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_1000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_1000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_1000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_2000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_2000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_2000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_2000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_2000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_3000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_3000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_3000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_3000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_3000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_4000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_4000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_4000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_4000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_4000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_5000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_5000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_5000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_5000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_5000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_6000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_6000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_6000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_6000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_6000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_7000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_7000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_7000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_7000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_7000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_8000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_8000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_8000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_8000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_8000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_9000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_9000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_9000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_9000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_9000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_10000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_10000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_10000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_10000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_10000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_11000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_11000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_11000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_11000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_11000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_12000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_12000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_12000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_12000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_12000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_13000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_13000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_13000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_13000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_13000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_14000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_14000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_14000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_14000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_14000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_15000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_15000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_15000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_15000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_15000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_16000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_16000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_16000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_16000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_16000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_17000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_17000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_17000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_17000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_17000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_18000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_18000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_18000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_18000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_18000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_19000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_19000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_19000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_19000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_19000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_20000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_20000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_20000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_20000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_20000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_21000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_21000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_21000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_21000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_21000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_22000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_22000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_22000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_22000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_22000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_23000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_23000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_23000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_23000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_23000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_24000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_24000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_24000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_24000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_24000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_25000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_25000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_25000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_25000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_25000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_26000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_26000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_26000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_26000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_26000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_27000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_27000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_27000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_27000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_27000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_28000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_28000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_28000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_28000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_28000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_29000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_29000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_29000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_29000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_29000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_30000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_30000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_30000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_30000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_30000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_31000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_31000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_31000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_31000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_31000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_32000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_32000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_32000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_32000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_32000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_33000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_33000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_33000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_33000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_33000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_34000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_34000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_34000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_34000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_34000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_35000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_35000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_35000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_35000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_35000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_36000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_36000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_36000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_36000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_36000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_37000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_37000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_37000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_37000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_37000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_38000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_38000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_38000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_38000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_38000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_39000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_39000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_39000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_39000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_39000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_40000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_40000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_40000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_40000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_40000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_41000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_41000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_41000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_41000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_41000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_42000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_42000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_42000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_42000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_42000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_43000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_43000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_43000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_43000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_43000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_44000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_44000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_44000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_44000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_44000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_45000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_45000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_45000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_45000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_45000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_46000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_46000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_46000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_46000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_46000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_47000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_47000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_47000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_47000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_47000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_48000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_48000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_48000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_48000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_48000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_49000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_49000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_49000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_49000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_49000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_50000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_50000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_50000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_50000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_50000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_51000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_51000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_51000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_51000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_51000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_52000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_52000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_52000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_52000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_52000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_53000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_53000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_53000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_53000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_53000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_54000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_54000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_54000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_54000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_54000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_55000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_55000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_55000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_55000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_55000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_56000000": { "short_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_56000000", "full_name": "uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_56000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_56000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_pseudomonadati_3379134_56000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_thermotogati_3384194_0": { "short_name": "uniprotkb_unreviewed_bacteria_thermotogati_3384194_0", "full_name": "uniprotkb_unreviewed_bacteria_thermotogati_3384194_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_thermotogati_3384194_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_thermotogati_3384194_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_bacteria_unclassified_bacteria_49928_0": { "short_name": "uniprotkb_unreviewed_bacteria_unclassified_bacteria_49928_0", "full_name": "uniprotkb_unreviewed_bacteria_unclassified_bacteria_49928_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_bacteria_unclassified_bacteria_49928_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_bacteria_unclassified_bacteria_49928_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_amoebozoa_554915_0": { "short_name": "uniprotkb_unreviewed_eukaryota_amoebozoa_554915_0", "full_name": "uniprotkb_unreviewed_eukaryota_amoebozoa_554915_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_amoebozoa_554915_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_amoebozoa_554915_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_ancyromonadida_2686027_0": { "short_name": "uniprotkb_unreviewed_eukaryota_ancyromonadida_2686027_0", "full_name": "uniprotkb_unreviewed_eukaryota_ancyromonadida_2686027_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_ancyromonadida_2686027_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_ancyromonadida_2686027_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_apusozoa_554296_0": { "short_name": "uniprotkb_unreviewed_eukaryota_apusozoa_554296_0", "full_name": "uniprotkb_unreviewed_eukaryota_apusozoa_554296_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_apusozoa_554296_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_apusozoa_554296_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_breviatea_1401294_0": { "short_name": "uniprotkb_unreviewed_eukaryota_breviatea_1401294_0", "full_name": "uniprotkb_unreviewed_eukaryota_breviatea_1401294_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_breviatea_1401294_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_breviatea_1401294_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_crums_2608240_0": { "short_name": "uniprotkb_unreviewed_eukaryota_crums_2608240_0", "full_name": "uniprotkb_unreviewed_eukaryota_crums_2608240_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_crums_2608240_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_crums_2608240_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_cryptophyceae_3027_0": { "short_name": "uniprotkb_unreviewed_eukaryota_cryptophyceae_3027_0", "full_name": "uniprotkb_unreviewed_eukaryota_cryptophyceae_3027_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_cryptophyceae_3027_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_cryptophyceae_3027_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_discoba_2611352_0": { "short_name": "uniprotkb_unreviewed_eukaryota_discoba_2611352_0", "full_name": "uniprotkb_unreviewed_eukaryota_discoba_2611352_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_discoba_2611352_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_discoba_2611352_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_environmental_samples_61964_0": { "short_name": "uniprotkb_unreviewed_eukaryota_environmental_samples_61964_0", "full_name": "uniprotkb_unreviewed_eukaryota_environmental_samples_61964_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_environmental_samples_61964_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_environmental_samples_61964_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_eukaryota_incertae_sedis_2683617_0": { "short_name": "uniprotkb_unreviewed_eukaryota_eukaryota_incertae_sedis_2683617_0", "full_name": "uniprotkb_unreviewed_eukaryota_eukaryota_incertae_sedis_2683617_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_eukaryota_incertae_sedis_2683617_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_eukaryota_incertae_sedis_2683617_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_glaucocystophyceae_38254_0": { "short_name": "uniprotkb_unreviewed_eukaryota_glaucocystophyceae_38254_0", "full_name": "uniprotkb_unreviewed_eukaryota_glaucocystophyceae_38254_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_glaucocystophyceae_38254_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_glaucocystophyceae_38254_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_haptista_2608109_0": { "short_name": "uniprotkb_unreviewed_eukaryota_haptista_2608109_0", "full_name": "uniprotkb_unreviewed_eukaryota_haptista_2608109_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_haptista_2608109_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_haptista_2608109_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_malawimonadida_2795258_0": { "short_name": "uniprotkb_unreviewed_eukaryota_malawimonadida_2795258_0", "full_name": "uniprotkb_unreviewed_eukaryota_malawimonadida_2795258_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_malawimonadida_2795258_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_malawimonadida_2795258_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_metamonada_2611341_0": { "short_name": "uniprotkb_unreviewed_eukaryota_metamonada_2611341_0", "full_name": "uniprotkb_unreviewed_eukaryota_metamonada_2611341_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_metamonada_2611341_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_metamonada_2611341_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_aphelida_2316435_0": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_aphelida_2316435_0", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_aphelida_2316435_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_aphelida_2316435_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_aphelida_2316435_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_choanoflagellata_28009_0": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_choanoflagellata_28009_0", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_choanoflagellata_28009_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_choanoflagellata_28009_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_choanoflagellata_28009_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_filasterea_2687318_0": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_filasterea_2687318_0", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_filasterea_2687318_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_filasterea_2687318_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_filasterea_2687318_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_0": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_0", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_1000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_1000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_1000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_1000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_1000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_2000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_2000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_2000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_2000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_2000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_3000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_3000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_3000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_3000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_3000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_4000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_4000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_4000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_4000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_4000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_5000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_5000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_5000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_5000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_5000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_6000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_6000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_6000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_6000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_6000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_7000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_7000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_7000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_7000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_7000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_8000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_8000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_8000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_8000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_8000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_9000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_9000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_9000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_9000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_9000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_10000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_10000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_10000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_10000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_10000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_11000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_11000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_11000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_11000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_11000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_12000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_12000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_12000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_12000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_12000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_13000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_13000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_13000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_13000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_13000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_14000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_14000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_14000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_14000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_14000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_15000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_15000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_15000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_15000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_15000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_16000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_16000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_16000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_16000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_16000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_17000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_17000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_17000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_17000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_17000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_18000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_18000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_18000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_18000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_18000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_19000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_19000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_19000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_19000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_fungi_4751_19000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_ichthyosporea_127916_0": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_ichthyosporea_127916_0", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_ichthyosporea_127916_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_ichthyosporea_127916_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_ichthyosporea_127916_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_0": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_0", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_1000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_1000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_1000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_1000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_1000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_2000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_2000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_2000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_2000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_2000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_3000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_3000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_3000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_3000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_3000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_4000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_4000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_4000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_4000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_4000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_5000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_5000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_5000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_5000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_5000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_6000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_6000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_6000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_6000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_6000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_7000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_7000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_7000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_7000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_7000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_8000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_8000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_8000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_8000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_8000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_9000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_9000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_9000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_9000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_9000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_10000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_10000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_10000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_10000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_10000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_11000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_11000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_11000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_11000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_11000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_12000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_12000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_12000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_12000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_12000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_13000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_13000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_13000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_13000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_13000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_14000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_14000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_14000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_14000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_14000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_15000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_15000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_15000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_15000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_15000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_16000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_16000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_16000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_16000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_16000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_17000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_17000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_17000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_17000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_17000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_18000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_18000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_18000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_18000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_18000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_19000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_19000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_19000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_19000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_19000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_20000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_20000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_20000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_20000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_20000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_21000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_21000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_21000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_21000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_21000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_22000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_22000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_22000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_22000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_22000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_23000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_23000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_23000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_23000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_23000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_24000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_24000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_24000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_24000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_24000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_25000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_25000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_25000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_25000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_25000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_26000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_26000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_26000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_26000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_26000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_27000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_27000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_27000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_27000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_27000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_28000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_28000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_28000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_28000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_28000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_29000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_29000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_29000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_29000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_29000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_30000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_30000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_30000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_30000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_30000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_31000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_31000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_31000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_31000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_31000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_32000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_32000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_32000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_32000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_32000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_33000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_33000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_33000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_33000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_33000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_34000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_34000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_34000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_34000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_34000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_35000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_35000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_35000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_35000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_35000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_36000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_36000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_36000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_36000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_36000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_37000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_37000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_37000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_37000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_37000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_38000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_38000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_38000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_38000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_38000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_39000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_39000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_39000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_39000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_39000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_40000000": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_40000000", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_40000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_40000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_metazoa_33208_40000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_opisthokonta_incertae_sedis_42461_0": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_opisthokonta_incertae_sedis_42461_0", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_opisthokonta_incertae_sedis_42461_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_opisthokonta_incertae_sedis_42461_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_opisthokonta_incertae_sedis_42461_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_opisthokonta_rotosphaerida_2686024_0": { "short_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_rotosphaerida_2686024_0", "full_name": "uniprotkb_unreviewed_eukaryota_opisthokonta_rotosphaerida_2686024_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_opisthokonta_rotosphaerida_2686024_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_opisthokonta_rotosphaerida_2686024_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_provora_3004206_0": { "short_name": "uniprotkb_unreviewed_eukaryota_provora_3004206_0", "full_name": "uniprotkb_unreviewed_eukaryota_provora_3004206_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_provora_3004206_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_provora_3004206_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_rhodophyta_2763_0": { "short_name": "uniprotkb_unreviewed_eukaryota_rhodophyta_2763_0", "full_name": "uniprotkb_unreviewed_eukaryota_rhodophyta_2763_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_rhodophyta_2763_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_rhodophyta_2763_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_sar_2698737_0": { "short_name": "uniprotkb_unreviewed_eukaryota_sar_2698737_0", "full_name": "uniprotkb_unreviewed_eukaryota_sar_2698737_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_sar_2698737_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_sar_2698737_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_sar_2698737_1000000": { "short_name": "uniprotkb_unreviewed_eukaryota_sar_2698737_1000000", "full_name": "uniprotkb_unreviewed_eukaryota_sar_2698737_1000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_sar_2698737_1000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_sar_2698737_1000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_sar_2698737_2000000": { "short_name": "uniprotkb_unreviewed_eukaryota_sar_2698737_2000000", "full_name": "uniprotkb_unreviewed_eukaryota_sar_2698737_2000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_sar_2698737_2000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_sar_2698737_2000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_sar_2698737_3000000": { "short_name": "uniprotkb_unreviewed_eukaryota_sar_2698737_3000000", "full_name": "uniprotkb_unreviewed_eukaryota_sar_2698737_3000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_sar_2698737_3000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_sar_2698737_3000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_sar_2698737_4000000": { "short_name": "uniprotkb_unreviewed_eukaryota_sar_2698737_4000000", "full_name": "uniprotkb_unreviewed_eukaryota_sar_2698737_4000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_sar_2698737_4000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_sar_2698737_4000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_unclassified_eukaryotes_42452_0": { "short_name": "uniprotkb_unreviewed_eukaryota_unclassified_eukaryotes_42452_0", "full_name": "uniprotkb_unreviewed_eukaryota_unclassified_eukaryotes_42452_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_unclassified_eukaryotes_42452_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_unclassified_eukaryotes_42452_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_0": { "short_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_0", "full_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_1000000": { "short_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_1000000", "full_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_1000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_1000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_1000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_2000000": { "short_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_2000000", "full_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_2000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_2000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_2000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_3000000": { "short_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_3000000", "full_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_3000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_3000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_3000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_4000000": { "short_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_4000000", "full_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_4000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_4000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_4000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_5000000": { "short_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_5000000", "full_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_5000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_5000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_5000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_6000000": { "short_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_6000000", "full_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_6000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_6000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_6000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_7000000": { "short_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_7000000", "full_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_7000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_7000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_7000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_8000000": { "short_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_8000000", "full_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_8000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_8000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_8000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_9000000": { "short_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_9000000", "full_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_9000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_9000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_9000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_10000000": { "short_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_10000000", "full_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_10000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_10000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_10000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_11000000": { "short_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_11000000", "full_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_11000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_11000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_11000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_12000000": { "short_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_12000000", "full_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_12000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_12000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_12000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_13000000": { "short_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_13000000", "full_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_13000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_13000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_13000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_14000000": { "short_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_14000000", "full_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_14000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_14000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_14000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_15000000": { "short_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_15000000", "full_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_15000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_15000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_15000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_16000000": { "short_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_16000000", "full_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_16000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_16000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_16000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_17000000": { "short_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_17000000", "full_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_17000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_17000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_17000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_18000000": { "short_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_18000000", "full_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_18000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_18000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_18000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_19000000": { "short_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_19000000", "full_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_19000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_19000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_19000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_20000000": { "short_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_20000000", "full_name": "uniprotkb_unreviewed_eukaryota_viridiplantae_33090_20000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_20000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_eukaryota_viridiplantae_33090_20000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_other_sequences_28384_0": { "short_name": "uniprotkb_unreviewed_other_sequences_28384_0", "full_name": "uniprotkb_unreviewed_other_sequences_28384_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_other_sequences_28384_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_other_sequences_28384_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_unclassified_sequences_12908_0": { "short_name": "uniprotkb_unreviewed_unclassified_sequences_12908_0", "full_name": "uniprotkb_unreviewed_unclassified_sequences_12908_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_unclassified_sequences_12908_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_unclassified_sequences_12908_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_unclassified_sequences_12908_1000000": { "short_name": "uniprotkb_unreviewed_unclassified_sequences_12908_1000000", "full_name": "uniprotkb_unreviewed_unclassified_sequences_12908_1000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_unclassified_sequences_12908_1000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_unclassified_sequences_12908_1000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_unclassified_sequences_12908_2000000": { "short_name": "uniprotkb_unreviewed_unclassified_sequences_12908_2000000", "full_name": "uniprotkb_unreviewed_unclassified_sequences_12908_2000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_unclassified_sequences_12908_2000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_unclassified_sequences_12908_2000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_viruses_10239_0": { "short_name": "uniprotkb_unreviewed_viruses_10239_0", "full_name": "uniprotkb_unreviewed_viruses_10239_0", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_viruses_10239_0.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_viruses_10239_0", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_viruses_10239_1000000": { "short_name": "uniprotkb_unreviewed_viruses_10239_1000000", "full_name": "uniprotkb_unreviewed_viruses_10239_1000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_viruses_10239_1000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_viruses_10239_1000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_viruses_10239_2000000": { "short_name": "uniprotkb_unreviewed_viruses_10239_2000000", "full_name": "uniprotkb_unreviewed_viruses_10239_2000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_viruses_10239_2000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_viruses_10239_2000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_viruses_10239_3000000": { "short_name": "uniprotkb_unreviewed_viruses_10239_3000000", "full_name": "uniprotkb_unreviewed_viruses_10239_3000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_viruses_10239_3000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_viruses_10239_3000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "uniprotkb_unreviewed_viruses_10239_4000000": { "short_name": "uniprotkb_unreviewed_viruses_10239_4000000", "full_name": "uniprotkb_unreviewed_viruses_10239_4000000", "description": "Comprehensive protein knowledgebase with functional annotations", "category": "large", "download": { "url": "ftp://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf/uniprotkb_unreviewed_viruses_10239_4000000.rdf.xz", "format": "rdf", "compression": "xz", "extraction_command": "xz -d", "size_gb": 0.392, "compressed_size_gb": 0.392 }, "metadata": { "entities": "~90M protein entries", "triples": "~3.4B", "license": "CC BY 4.0", "recommended_for": "Protein research, molecular biology, functional genomics", "notes": "High quality with manual curation for Swiss-Prot entries. Updated every 8 weeks." }, "huggingface": { "repository": "CleverThis/uniprotkb_unreviewed_viruses_10239_4000000", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000 } }, "geonames": { "short_name": "geonames", "full_name": "GeoNames RDF", "description": "World geographic database with place names and coordinates", "category": "small", "download": { "url": "http://download.geonames.org/all-geonames-rdf.zip", "format": "xml", "compression": "zip", "extraction_command": "unzip", "size_gb": 3.0, "compressed_size_gb": 3.0 }, "metadata": { "entities": "~11M places", "triples": "~123M", "license": "CC BY 4.0", "recommended_for": "Geographic data, location-based services", "notes": "Community-contributed. Daily updates with periodic RDF dumps." }, "huggingface": { "repository": "CleverThis/geonames", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 50000 } }, "dblp": { "short_name": "dblp", "full_name": "DBLP Bibliography", "description": "Computer science publications and citations", "category": "medium", "download": { "url": "https://dblp.org/rdf/release/dblp-2024-01-01.nt.gz", "format": "ntriples", "compression": "gz", "extraction_command": "gunzip", "size_gb": 12.0, "compressed_size_gb": 3.5 }, "metadata": { "entities": "~6M publications, ~2.6M authors", "triples": "~1.2-1.5B", "license": "CC0 1.0", "recommended_for": "Academic publication graphs, citation analysis", "notes": "Monthly RDF snapshots. High accuracy with complete CS coverage." }, "huggingface": { "repository": "CleverThis/dblp", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 50000 } }, "opencyc": { "short_name": "opencyc", "full_name": "OpenCyc 4.0", "description": "Common-sense ontology subset from Cycorp", "category": "small", "download": { "url": "https://github.com/asanchez75/opencyc/raw/master/opencyc-latest.owl.gz", "format": "xml", "compression": "gz", "extraction_command": "gunzip", "size_gb": 0.35, "compressed_size_gb": 0.026 }, "metadata": { "entities": "~239K concepts", "triples": "~2.09M", "license": "Apache 2.0", "recommended_for": "Common-sense reasoning, upper ontology", "notes": "Discontinued 2017. Mirror from GitHub repository. Latest version (2012-05-10)." }, "huggingface": { "repository": "CleverThis/opencyc", "private": false, "readme_template": "standard_rdf" }, "processing": { "converter": "standard", "streaming": false, "chunk_size": 10000 } }, "fb15k-237": { "short_name": "fb15k237", "full_name": "FB15k-237", "description": "Link prediction benchmark from Freebase (cleaned)", "category": "small", "download": { "url": "https://download.microsoft.com/download/8/7/0/8700516a-ab3d-4850-b4bb-805c515aece1/FB15K-237.2.zip", "format": "tsv", "compression": "zip", "extraction_command": "unzip", "size_gb": 0.14, "compressed_size_gb": 0.14 }, "metadata": { "entities": "14,541", "triples": "310,116", "license": "CC BY 2.5", "recommended_for": "Link prediction benchmarking, KG embedding research", "notes": "Microsoft Research dataset. Contains KB relation triples and textual mentions from ClueWeb12 corpus. TSV format with Freebase IDs." }, "huggingface": { "repository": "CleverThis/fb15k-237", "private": false, "readme_template": "benchmark_dataset" }, "processing": { "converter": "fb15k237_specialized", "streaming": false, "chunk_size": 10000 } }, "wn18rr": { "short_name": "wn18rr", "full_name": "WN18RR", "description": "WordNet-based link prediction benchmark (improved) - derived from WN18 with test-set leakage removed", "category": "small", "download": { "url": "https://figshare.com/ndownloader/files/21844185", "format": "tsv", "compression": "zip", "extraction_command": "unzip", "size_gb": 0.004, "compressed_size_gb": 0.001 }, "metadata": { "entities": "40,943", "triples": "93,003", "license": "Apache 2.0", "recommended_for": "Lexical knowledge graph benchmarking, embedding evaluation", "notes": "Static benchmark (2018). TSV format with pre-split train/valid/test files. Contains 11 relation types. Format: subjectrelationobject" }, "huggingface": { "repository": "CleverThis/wn18rr", "private": false, "readme_template": "benchmark_dataset" }, "processing": { "converter": "standard_tsv", "streaming": false, "chunk_size": 10000 } }, "nell-995": { "short_name": "nell995", "full_name": "NELL-995", "description": "Never-Ending Learning subset for link prediction", "category": "small", "download": { "url": "https://github.com/wenhuchen/KB-Reasoning-Data/archive/refs/heads/master.zip", "format": "tsv", "compression": "zip", "extraction_command": "unzip", "size_gb": 0.12, "compressed_size_gb": 0.03 }, "metadata": { "entities": "~75,492", "triples": "154,213", "license": "CC BY-NC", "recommended_for": "Semi-supervised learning benchmarks, noisy data experiments", "notes": "NAACL18 paper dataset. Contains raw.kb file with triples and evaluation splits. Format: tab-separated triples." }, "huggingface": { "repository": "CleverThis/nell-995", "private": false, "readme_template": "benchmark_dataset" }, "processing": { "converter": "nell995_specialized", "streaming": false, "chunk_size": 10000 } } }, "readme_templates": { "standard_rdf": { "sections": [ "title", "description", "dataset_format", "loading_instructions", "conversion_instructions", "metadata", "citation", "license" ] }, "benchmark_dataset": { "sections": [ "title", "description", "benchmark_details", "dataset_format", "loading_instructions", "evaluation_metrics", "metadata", "citation", "license" ] }, "conceptnet_specific": { "sections": [ "title", "description", "conceptnet_format", "dataset_format", "loading_instructions", "confidence_scores", "multilingual_support", "metadata", "citation", "license" ] } }, "processing_defaults": { "small_datasets": { "converter": "standard", "streaming": false, "chunk_size": 10000, "memory_limit_gb": 2 }, "medium_datasets": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 50000, "memory_limit_gb": 4 }, "large_datasets": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000, "memory_limit_gb": 8 }, "xlarge_datasets": { "converter": "streaming_parallel", "streaming": true, "chunk_size": 100000, "memory_limit_gb": 16 } }, "converters": { "standard": { "script": "convert_rdf_to_hf_dataset.py", "supports_formats": [ "turtle", "ntriples", "xml", "n3", "trig", "nquads" ] }, "streaming_parallel": { "script": "convert_rdf_to_hf_dataset_streaming_parallel.py", "supports_formats": [ "turtle", "ntriples", "xml", "n3", "trig", "nquads" ] }, "conceptnet_specialized": { "script": "convert_conceptnet_to_hf.py", "supports_formats": ["csv"] }, "fb15k237_specialized": { "script": "convert_fb15k237_to_hf.py", "supports_formats": ["tsv"] }, "nell995_specialized": { "script": "convert_nell995_to_hf.py", "supports_formats": ["tsv"] }, "standard_tsv": { "script": "convert_rdf_to_hf_dataset.py", "supports_formats": ["tsv"] } }, "format_mappings": { "turtle": "turtle", "ntriples": "nt", "rdf/xml": "xml", "xml": "xml", "n3": "n3", "trig": "trig", "nquads": "nquads", "tsv": "tsv", "csv": "csv" }, "license_mappings": { "wordnet license": "other", "cc by 4.0": "cc-by-4.0", "cc by-sa 4.0": "cc-by-sa-4.0", "cc by-sa 3.0": "cc-by-sa-3.0", "cc by 3.0": "cc-by-3.0", "cc by 2.5": "cc-by-2.5", "cc by-nc 4.0": "cc-by-nc-4.0", "cc0 1.0": "cc0-1.0", "odbl": "other", "odbl 1.0": "other", "mit": "mit", "apache 2.0": "apache-2.0", "apache-2.0": "apache-2.0", "bsd-3-clause": "bsd-3-clause" } }