{"doi":"10.1093/nar/gky1049","title":"UniProt: a worldwide hub of protein knowledge","abstract":null,"journal":"Nucleic Acids Research","year":2019,"id":12792,"datarank":18.884809551475886,"base_score":9.029657471850737,"endowment":9.029657471850737,"self_citation_contribution":1.3544486207776107,"citation_network_contribution":17.530360930698276,"self_endowment_contribution":1.3544486207776107,"citer_contribution":17.530360930698276,"corpus_percentile":93.24654190398698,"corpus_rank":84,"citation_count":8346,"citer_count":200,"citers_with_citation_signal":200,"citers_with_endowment":200,"datacite_reuse_total":0,"is_dataset":true,"is_dataset_confidence":0.8703,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2019-01-08","fair_score":53.75,"fair_percentile":79.99120492524186,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[],"reference_count":31,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-03-01T18:20:47.508186Z","pmid":"30395287","pmcid":"PMC6323992","fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":"gold","license":"cc-by","views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":77.5,"fair_a":50.0,"fair_i":37.5,"fair_r":50.0,"fair_zscore":0.7724,"fair_rationale":{"fair_score":53.75,"has_llm":true,"dimensions":{"F":{"name":"Findable","score":77.5,"criteria":[{"key":"f_has_doi","label":"Has a persistent DOI","kind":"deterministic","weight":1.0,"fraction":1.0,"signal":"DOI present","rationale":null},{"key":"f_repository_presence","label":"Indexed in repositories / literature DBs","kind":"deterministic","weight":1.0,"fraction":1.0,"signal":"datacite=0, pmcid=True, pmid=True","rationale":null},{"key":"f_persistent_ids","label":"Resolvable scholarly identifiers (OpenAlex)","kind":"deterministic","weight":0.5,"fraction":0.0,"signal":"no OpenAlex id","rationale":null},{"key":"f_metadata_richness","label":"Rich, machine-readable metadata","kind":"llm","weight":1.0,"fraction":0.75,"signal":null,"rationale":"The paper describes rich metadata (sequences, annotations, GO terms, evidence codes) and provides structured vocabularies, but does not explicitly confirm machine-readability of the metadata (e.g., RDF, JSON-LD)."}]},"A":{"name":"Accessible","score":50.0,"criteria":[{"key":"a_open_access","label":"Open Access / files deposited","kind":"deterministic","weight":1.5,"fraction":0.0,"signal":"not open access","rationale":null},{"key":"a_retrievable","label":"Free full text retrievable","kind":"deterministic","weight":1.0,"fraction":0.0,"signal":"0 OA location(s)","rationale":null},{"key":"a_access_protocol","label":"Clear data/code access protocol","kind":"llm","weight":1.0,"fraction":1.0,"signal":null,"rationale":"Clear access protocols are given: web access (https://www.uniprot.org/), FTP, Proteins API, and the data are under a CC-BY 4.0 license."}]},"I":{"name":"Interoperable","score":37.5,"criteria":[{"key":"i_linked_data","label":"Linked datasets / DataCite relations","kind":"deterministic","weight":1.0,"fraction":0.0,"signal":"linked_datasets=0, datacite=0","rationale":null},{"key":"i_standard_ids","label":"References data via standard accessions","kind":"deterministic","weight":1.0,"fraction":0.0,"signal":"accessions=0, trials=0","rationale":null},{"key":"i_standards","label":"Standard formats, vocabularies & identifiers","kind":"llm","weight":1.0,"fraction":0.75,"signal":null,"rationale":"The paper uses standard identifiers (UniProtKB, GO, ChEBI, INSDC) and formats (FASTA, XML), but does not mention compliance with formal interoperability standards like W3C DCAT or schema.org."}]},"R":{"name":"Reusable","score":50.0,"criteria":[{"key":"r_license","label":"Clear, open reuse license","kind":"deterministic","weight":1.5,"fraction":0.0,"signal":"no license","rationale":null},{"key":"r_downloads","label":"Demonstrated reuse (downloads)","kind":"deterministic","weight":0.5,"fraction":0.0,"signal":"downloads=0","rationale":null},{"key":"r_version","label":"Versioned / maintained","kind":"deterministic","weight":0.5,"fraction":0.0,"signal":"no version chain","rationale":null},{"key":"r_dataset","label":"Classified as a data resource","kind":"deterministic","weight":0.5,"fraction":1.0,"signal":"is_dataset","rationale":null},{"key":"r_reusability","label":"Data-availability statement, license & reproducibility","kind":"llm","weight":2.0,"fraction":0.833,"signal":null,"rationale":"A clear data-availability statement (CC-BY 4.0) is provided and the resource is accessible for reuse, but reproducibility details (e.g., software version, exact code/data snapshots) are not fully described."}]}},"suggestions":["Publish formal ontology metadata (e.g., using DCAT, schema.org) to enhance machine-readability for findability.","Provide example programmatic queries (e.g., SPARQL endpoint) for metadata retrieval.","Include explicit versioning and DOI for each data release to enable precise citation and reproducibility.","Add a reproducibility section specifying exact software and pipeline versions used for automated annotation.","Implement a structured license and attribution statement in machine-readable format (e.g., JSON-LD) on the website."],"model":"deepseek/deepseek-v4-flash","agent_version":"fair_agent_v2","fulltext_source":"epmc_xml"},"fair_model":"deepseek/deepseek-v4-flash","fair_agent_version":"fair_agent_v2","fair_fulltext_source":"epmc_xml","fair_has_llm":true,"fair_computed_at":"2026-06-18T00:26:39.775281Z","clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}