{"doi":"10.1093/nar/gky1075","title":"ChEMBL: towards direct deposition of bioassay data","abstract":"ChEMBL is a large, open-access bioactivity database (https://www.ebi.ac.uk/chembl), previously described in the 2012, 2014 and 2017 Nucleic Acids Research Database Issues. In the last two years, several important improvements have been made to the database and are described here. These include more robust capture and representation of assay details; a new data deposition system, allowing updating of data sets and deposition of supplementary data; and a completely redesigned web interface, with enhanced search and filtering capabilities.","journal":"Nucleic Acids Research","year":2018,"id":8751,"datarank":12.71781266989593,"base_score":7.7266536648476425,"endowment":7.7266536648476425,"self_citation_contribution":1.1589980497271466,"citation_network_contribution":11.558814620168782,"self_endowment_contribution":1.1589980497271466,"citer_contribution":11.558814620168782,"corpus_percentile":84.21480878763222,"corpus_rank":195,"citation_count":2389,"citer_count":192,"citers_with_citation_signal":192,"citers_with_endowment":192,"datacite_reuse_total":25,"is_dataset":true,"is_dataset_confidence":0.9508,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2018-11-06","fair_score":67.5,"fair_percentile":96.41600703605981,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":75386,"name":"Anna Gaulton","orcid":"0000-0003-2634-7400","position":1,"is_corresponding":false},{"id":75387,"name":"A. Patrícia Bento","orcid":"0000-0003-1424-480X","position":2,"is_corresponding":false},{"id":75388,"name":"Jon Chambers","orcid":null,"position":3,"is_corresponding":false},{"id":75389,"name":"Marleen De Veij","orcid":"0000-0003-2587-8752","position":4,"is_corresponding":false},{"id":75390,"name":"Eloy Félix","orcid":"0000-0002-5512-6810","position":5,"is_corresponding":false},{"id":75391,"name":"María Paula Magariños","orcid":"0000-0003-2769-4105","position":6,"is_corresponding":false},{"id":75392,"name":"Juan F Mosquera","orcid":null,"position":7,"is_corresponding":false},{"id":75393,"name":"Prudence Mutowo","orcid":"0000-0002-4646-4172","position":8,"is_corresponding":false},{"id":75394,"name":"Michał Nowotka","orcid":null,"position":9,"is_corresponding":false},{"id":75395,"name":"María Gordillo-Marañón","orcid":null,"position":10,"is_corresponding":false},{"id":34541,"name":"Fiona Hunter","orcid":"0000-0001-7160-1880","position":11,"is_corresponding":false},{"id":75396,"name":"Laura Junco","orcid":null,"position":12,"is_corresponding":false},{"id":75397,"name":"Grace Mugumbate","orcid":"0000-0002-2829-9425","position":13,"is_corresponding":false},{"id":75398,"name":"Milagros Rodriguez-Lopez","orcid":null,"position":14,"is_corresponding":false},{"id":75399,"name":"Francis Atkinson","orcid":"0000-0003-4688-959X","position":15,"is_corresponding":false},{"id":75400,"name":"Nicolas Bosc","orcid":"0000-0003-3562-1328","position":16,"is_corresponding":false},{"id":75401,"name":"Chris J. Radoux","orcid":"0000-0002-7903-7310","position":17,"is_corresponding":false},{"id":75402,"name":"Aldo Segura-Cabrera","orcid":null,"position":18,"is_corresponding":false},{"id":75403,"name":"Anne Hersey","orcid":"0000-0003-4679-6211","position":19,"is_corresponding":false},{"id":75404,"name":"Andrew R. Leach","orcid":"0000-0001-8178-0253","position":20,"is_corresponding":false},{"id":75405,"name":"David Méndez","orcid":"0000-0002-0294-5484","position":21,"is_corresponding":false},{"id":75406,"name":"María Gordillo‐Marañón","orcid":"0000-0003-2993-6577","position":22,"is_corresponding":false},{"id":75407,"name":"M. Rodríguez-López","orcid":"0000-0002-5691-3971","position":23,"is_corresponding":false},{"id":75408,"name":"Aldo Segura‐Cabrera","orcid":"0000-0003-3044-8028","position":24,"is_corresponding":false},{"id":75385,"name":"David Mendez","orcid":null,"position":0,"is_corresponding":true}],"reference_count":26,"raw_metadata":{"citation_network_status":"fetched"},"created_at":"2026-03-01T18:20:47.508186Z","pmid":"30398643","pmcid":"PMC6323927","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":67.5,"fair_i":75.0,"fair_r":50.0,"fair_zscore":2.0161,"fair_rationale":{"fair_score":67.5,"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=25, 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":"Paper mentions use of controlled vocabularies, ontologies (e.g., Cell Line Ontology, BioAssay Ontology), and machine-readable file formats (Mol, InChI), but does not detail machine-readable metadata standards like structured JSON-LD or schema.org for all data entries."}]},"A":{"name":"Accessible","score":67.5,"criteria":[{"key":"a_open_access","label":"Open Access / files deposited","kind":"deterministic","weight":1.5,"fraction":1.0,"signal":"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":0.75,"signal":null,"rationale":"Data access is available via web interface, web services (RESTful), FTP downloads, and APIs, with documentation, but the paper does not specify authentication or authorization mechanisms for programmatic access."}]},"I":{"name":"Interoperable","score":75.0,"criteria":[{"key":"i_linked_data","label":"Linked datasets / DataCite relations","kind":"deterministic","weight":1.0,"fraction":1.0,"signal":"linked_datasets=0, datacite=25","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":1.0,"signal":null,"rationale":"Uses standard formats (Mol, InChI, RDF, FASTA), ontologies (CLO, Uberon, BAO, EFO), and identifiers (UniProt, DOI), demonstrating strong interoperability practices."}]},"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":"Data are available under a Creative Commons license (CC BY-SA 3.0), with DOIs for datasets, detailed deposition documentation, and regular releases, but the paper lacks explicit details on code licensing and complete reproducibility of specific analyses."}]}},"suggestions":["Provide explicit metadata schemas (e.g., JSON-LD) for automated discovery of all entities.","Specify standard authentication methods (e.g., API keys) for web services access.","Add formal licensing information for the software tools (e.g., Apache 2 license for web services) more prominently in data availability section.","Include structured data availability statements with persistent identifiers for all deposited datasets.","Document complete computational workflows for reproducibility of reported analyses."],"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":"2026-06-18T00:30:07.153768Z","clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}