{"id":"https://openalex.org/W7128682674","doi":"https://doi.org/10.1186/s13321-026-01165-x","title":"Integrating artificial intelligence and manual curation to enhance bioassay annotations in ChEMBL","display_name":"Integrating artificial intelligence and manual curation to enhance bioassay annotations in ChEMBL","publication_year":2026,"publication_date":"2026-02-12","ids":{"openalex":"https://openalex.org/W7128682674","doi":"https://doi.org/10.1186/s13321-026-01165-x","pmid":"https://pubmed.ncbi.nlm.nih.gov/41680846"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-026-01165-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-026-01165-x","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13321-026-01165-x.pdf","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://link.springer.com/content/pdf/10.1186/s13321-026-01165-x.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033510193","display_name":"Ines \u0160mit","orcid":null},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ines Smit","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridgeshire, CB101SD, UK"],"raw_orcid":"https://orcid.org/0000-0002-1772-6487","affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridgeshire, CB101SD, UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125730166","display_name":"Melissa F. Adasme","orcid":null},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Melissa F. Adasme","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridgeshire, CB101SD, UK"],"raw_orcid":"https://orcid.org/0000-0003-2217-4629","affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridgeshire, CB101SD, UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089264825","display_name":"Emma J. Manners","orcid":"https://orcid.org/0000-0001-7875-1259"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Emma Manners","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridgeshire, CB101SD, UK"],"raw_orcid":"https://orcid.org/0000-0001-7875-1259","affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridgeshire, CB101SD, UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045588751","display_name":"Sybilla Corbett","orcid":null},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sybilla Corbett","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridgeshire, CB101SD, UK"],"raw_orcid":"https://orcid.org/0000-0002-1242-1481","affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridgeshire, CB101SD, UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070971590","display_name":"Nicolas Bosc","orcid":"https://orcid.org/0000-0003-3562-1328"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nicolas Bosc","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridgeshire, CB101SD, UK"],"raw_orcid":"https://orcid.org/0000-0003-3562-1328","affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridgeshire, CB101SD, UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104254312","display_name":"Huu-Phu Do","orcid":null},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hoang-My-Anh Do","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridgeshire, CB101SD, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridgeshire, CB101SD, UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036729806","display_name":"Andrew R. Leach","orcid":"https://orcid.org/0000-0001-8178-0253"},"institutions":[{"id":"https://openalex.org/I109541847","display_name":"LifeArc","ror":"https://ror.org/01dqb0q37","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I109541847"]},{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew R. Leach","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridgeshire, CB101SD, UK","LifeArc, Accelerator Building, Open Innovation Campus, Stevenage, SG1 2FX, UK"],"raw_orcid":"https://orcid.org/0000-0001-8178-0253","affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridgeshire, CB101SD, UK","institution_ids":["https://openalex.org/I1303153112"]},{"raw_affiliation_string":"LifeArc, Accelerator Building, Open Innovation Campus, Stevenage, SG1 2FX, UK","institution_ids":["https://openalex.org/I109541847"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036721569","display_name":"Noel M. O\u2019Boyle","orcid":"https://orcid.org/0000-0003-4879-2003"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Noel M. O\u2019Boyle","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-4879-2003","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5053048742","display_name":"Barbara Zdrazil","orcid":"https://orcid.org/0000-0001-9395-1515"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Barbara Zdrazil","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridgeshire, CB101SD, UK. bzdrazil@ebi.ac.uk"],"raw_orcid":"https://orcid.org/0000-0001-9395-1515","affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridgeshire, CB101SD, UK. bzdrazil@ebi.ac.uk","institution_ids":["https://openalex.org/I1303153112"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5053048742"],"corresponding_institution_ids":["https://openalex.org/I1303153112"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":51.8564,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.99624184,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"18","issue":"1","first_page":"24","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.20579999685287476,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.20579999685287476,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.16200000047683716,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.11890000104904175,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/chembl","display_name":"chEMBL","score":0.9463000297546387},{"id":"https://openalex.org/keywords/metadata","display_name":"Metadata","score":0.6406000256538391},{"id":"https://openalex.org/keywords/cheminformatics","display_name":"Cheminformatics","score":0.5960000157356262},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5055999755859375},{"id":"https://openalex.org/keywords/data-curation","display_name":"Data curation","score":0.4871000051498413},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4020000100135803},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.3905999958515167},{"id":"https://openalex.org/keywords/bioassay","display_name":"Bioassay","score":0.3393999934196472}],"concepts":[{"id":"https://openalex.org/C63222358","wikidata":"https://www.wikidata.org/wiki/Q6120337","display_name":"chEMBL","level":3,"score":0.9463000297546387},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8169000148773193},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.6406000256538391},{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.5960000157356262},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5055999755859375},{"id":"https://openalex.org/C91632574","wikidata":"https://www.wikidata.org/wiki/Q15088675","display_name":"Data curation","level":2,"score":0.4871000051498413},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4020000100135803},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.3905999958515167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.365200012922287},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35920000076293945},{"id":"https://openalex.org/C104488531","wikidata":"https://www.wikidata.org/wiki/Q864212","display_name":"Bioassay","level":2,"score":0.3393999934196472},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.3257000148296356},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C99726746","wikidata":"https://www.wikidata.org/wiki/Q906396","display_name":"Chemical space","level":3,"score":0.30309998989105225},{"id":"https://openalex.org/C2775953033","wikidata":"https://www.wikidata.org/wiki/Q5276060","display_name":"Digital curation","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C2777002779","wikidata":"https://www.wikidata.org/wiki/Q42478","display_name":"Perl","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C158180186","wikidata":"https://www.wikidata.org/wiki/Q278487","display_name":"PubChem","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.28780001401901245},{"id":"https://openalex.org/C20901353","wikidata":"https://www.wikidata.org/wiki/Q4117139","display_name":"Biological database","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.26820001006126404},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26260000467300415},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.25049999356269836}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1186/s13321-026-01165-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-026-01165-x","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13321-026-01165-x.pdf","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},{"id":"pmid:41680846","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41680846","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of cheminformatics","raw_type":null},{"id":"pmh:doi:10.6084/m9.figshare.c.8307792","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Collection"},{"id":"pmh:oai:doaj.org/article:a9560ccd629a4e25991657d2d7699549","is_oa":true,"landing_page_url":"https://doaj.org/article/a9560ccd629a4e25991657d2d7699549","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 18, Iss 1 (2026)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:11709852","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12903245","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:pubmedcentral.nih.gov:12903245","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12903245/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Cheminform","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/s13321-026-01165-x","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-026-01165-x","pdf_url":"https://link.springer.com/content/pdf/10.1186/s13321-026-01165-x.pdf","source":{"id":"https://openalex.org/S180838163","display_name":"Journal of Cheminformatics","issn_l":"1758-2946","issn":["1758-2946"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Cheminformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6647945046424866,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2003881057","display_name":null,"funder_award_id":"875510","funder_id":"https://openalex.org/F4320326631","funder_display_name":"Innovative Medicines Initiative"},{"id":"https://openalex.org/G3771206209","display_name":null,"funder_award_id":"104104/A/14/Z","funder_id":"https://openalex.org/F4320311904","funder_display_name":"Wellcome Trust"},{"id":"https://openalex.org/G766232990","display_name":null,"funder_award_id":"228142/Z/23/Z","funder_id":"https://openalex.org/F4320311904","funder_display_name":"Wellcome Trust"}],"funders":[{"id":"https://openalex.org/F4320311904","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08"},{"id":"https://openalex.org/F4320326631","display_name":"Innovative Medicines Initiative","ror":"https://ror.org/019af4n30"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7128682674.pdf","grobid_xml":"https://content.openalex.org/works/W7128682674.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W959778778","https://openalex.org/W2016976521","https://openalex.org/W2045717408","https://openalex.org/W2088970363","https://openalex.org/W2105836514","https://openalex.org/W2116238734","https://openalex.org/W2128386749","https://openalex.org/W2133614244","https://openalex.org/W2143742443","https://openalex.org/W2147018385","https://openalex.org/W2163841005","https://openalex.org/W2302501749","https://openalex.org/W2462007197","https://openalex.org/W2777884179","https://openalex.org/W2805978167","https://openalex.org/W2896252085","https://openalex.org/W2984998864","https://openalex.org/W3198396834","https://openalex.org/W4307468223","https://openalex.org/W4388455891","https://openalex.org/W4392093325","https://openalex.org/W4404458588","https://openalex.org/W4404793875","https://openalex.org/W4404865467","https://openalex.org/W4411804077"],"related_works":[],"abstract_inverted_index":{"As":[0],"the":[1,41,102,133,165],"volume":[2],"and":[3,20,29,43,55,58,72,79,91,105,119,148,152,176],"diversity":[4],"of":[5,45,53,107,167],"bioactivity":[6],"data":[7],"in":[8,27,48],"ChEMBL":[9,49],"continues":[10],"to":[11,39,68,85,141],"grow,":[12],"ensuring":[13],"that":[14,112,128],"assay":[15,65,89,94],"metadata":[16,142],"is":[17,22],"standardized,":[18],"interoperable,":[19],"machine-readable":[21],"critical":[23],"for":[24,96,144],"effective":[25],"use":[26],"cheminformatics":[28],"ML":[30],"applications.":[31],"In":[32,136],"this":[33],"work,":[34],"we":[35,138],"present":[36],"recent":[37],"efforts":[38],"enhance":[40],"quality":[42],"granularity":[44],"bioassay":[46,169],"annotations":[47],"through":[50],"a":[51,63,108,124],"combination":[52],"manual":[54],"semi-manual":[56],"curation":[57],"AI-driven":[59],"approaches.":[60],"We":[61,99],"introduce":[62],"\"perfect":[64],"description\"":[66],"template":[67],"guide":[69],"consistent":[70],"annotation":[71],"demonstrate":[73],"how":[74],"natural":[75],"language":[76],"processing":[77],"techniques":[78],"multi-class":[80],"classification":[81,126],"can":[82],"be":[83],"used":[84],"automatically":[86],"extract":[87],"key":[88],"parameters":[90],"assign":[92],"broad":[93],"categories":[95],"legacy":[97],"data.":[98],"report":[100],"on":[101],"development,":[103],"validation,":[104],"application":[106],"spaCy-based":[109],"NER":[110],"model":[111,127],"identifies":[113],"experimental":[114],"methods":[115],"with":[116],"high":[117],"precision":[118],"recall,":[120],"as":[121,123,158],"well":[122],"complementary":[125],"refines":[129],"ASSAY_TYPE":[130],"categorization":[131],"beyond":[132],"existing":[134],"schema.":[135],"addition,":[137],"describe":[139],"improvements":[140],"extraction":[143],"ADME":[145],"endpoints,":[146],"organism":[147],"protein":[149],"variant":[150],"annotations,":[151],"ontology":[153],"linking":[154],"using":[155],"tools":[156],"such":[157],"text2term.":[159],"Together,":[160],"these":[161],"enhancements":[162],"significantly":[163],"advance":[164],"FAIRness":[166],"ChEMBL's":[168],"data,":[170],"enabling":[171],"more":[172,177],"robust":[173],"downstream":[174],"analyses":[175],"precise":[178],"compound-target":[179],"activity":[180],"modeling.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2026-02-13T00:00:00"}