{"id":"https://openalex.org/W4414695397","doi":"https://doi.org/10.1186/s13321-025-01092-3","title":"Chemical classification program synthesis using generative artificial intelligence","display_name":"Chemical classification program synthesis using generative artificial intelligence","publication_year":2025,"publication_date":"2025-10-01","ids":{"openalex":"https://openalex.org/W4414695397","doi":"https://doi.org/10.1186/s13321-025-01092-3","pmid":"https://pubmed.ncbi.nlm.nih.gov/41035053"},"language":"en","primary_location":{"id":"doi:10.1186/s13321-025-01092-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01092-3","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01092-3","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":["arxiv","crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01092-3","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002223413","display_name":"Chris Mungall","orcid":"https://orcid.org/0000-0002-6601-2165"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Christopher J. Mungall","raw_affiliation_strings":["Division of Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory, Berkeley, CA, 94720, USA. cjmungall@lbl.gov","Division of Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory, Berkeley, CA, 94720, USA"],"affiliations":[{"raw_affiliation_string":"Division of Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory, Berkeley, CA, 94720, USA. cjmungall@lbl.gov","institution_ids":["https://openalex.org/I148283060"]},{"raw_affiliation_string":"Division of Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory, Berkeley, CA, 94720, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031433014","display_name":"Adnan Malik","orcid":"https://orcid.org/0000-0001-8123-5351"},"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":"Adnan Malik","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridge, CB10 1SD, UK"],"affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridge, CB10 1SD, UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001438691","display_name":"Daniel Korn","orcid":"https://orcid.org/0000-0002-1780-9872"},"institutions":[{"id":"https://openalex.org/I114027177","display_name":"University of North Carolina at Chapel Hill","ror":"https://ror.org/0130frc33","country_code":"US","type":"education","lineage":["https://openalex.org/I114027177"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel R. Korn","raw_affiliation_strings":["Department of Computer Science, The University of North Carolina at Chapel Hill College of Arts and Sciences, Chapel Hill, NC, 27599, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of North Carolina at Chapel Hill College of Arts and Sciences, Chapel Hill, NC, 27599, USA","institution_ids":["https://openalex.org/I114027177"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073533486","display_name":"Justin Reese","orcid":"https://orcid.org/0000-0002-2170-2250"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Justin T. Reese","raw_affiliation_strings":["Division of Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory, Berkeley, CA, 94720, USA"],"affiliations":[{"raw_affiliation_string":"Division of Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory, Berkeley, CA, 94720, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036721569","display_name":"Noel M. O\u2019Boyle","orcid":"https://orcid.org/0000-0003-4879-2003"},"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":"Noel M. O\u2019Boyle","raw_affiliation_strings":["European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridge, CB10 1SD, UK"],"affiliations":[{"raw_affiliation_string":"European Molecular Biology Laboratory, European Bioinformatics Institute (EMBL-EBI), Wellcome Genome Campus, Hinxton, Cambridge, CB10 1SD, UK","institution_ids":["https://openalex.org/I1303153112"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044072805","display_name":"Janna Hastings","orcid":"https://orcid.org/0000-0002-3469-4923"},"institutions":[{"id":"https://openalex.org/I12708293","display_name":"SIB Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I12708293"]},{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]},{"id":"https://openalex.org/I202963720","display_name":"University of St.Gallen","ror":"https://ror.org/0561a3s31","country_code":"CH","type":"education","lineage":["https://openalex.org/I202963720"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Janna Hastings","raw_affiliation_strings":["Institute for Implementation Science in Health Care, University of Zurich, Zurich, Switzerland","School of Medicine, University of St. Gallen, St. Gallen, Switzerland","Swiss Institute of Bioinformatics, Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"Institute for Implementation Science in Health Care, University of Zurich, Zurich, Switzerland","institution_ids":["https://openalex.org/I202697423"]},{"raw_affiliation_string":"School of Medicine, University of St. Gallen, St. Gallen, Switzerland","institution_ids":["https://openalex.org/I202963720"]},{"raw_affiliation_string":"Swiss Institute of Bioinformatics, Lausanne, Switzerland","institution_ids":["https://openalex.org/I12708293"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5002223413"],"corresponding_institution_ids":["https://openalex.org/I148283060"],"apc_list":{"value":1290,"currency":"GBP","value_usd":1582},"apc_paid":{"value":1290,"currency":"GBP","value_usd":1582},"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27792241,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":"1","first_page":"152","last_page":"152"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10211","display_name":"Computational Drug Discovery Methods","score":0.9991999864578247,"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":0.9991999864578247,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9958999752998352,"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"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9799000024795532,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cheminformatics","display_name":"Cheminformatics","score":0.8349999785423279},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5497000217437744},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5414999723434448},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.46619999408721924},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4603999853134155},{"id":"https://openalex.org/keywords/ontology","display_name":"Ontology","score":0.44679999351501465},{"id":"https://openalex.org/keywords/drug-discovery","display_name":"Drug discovery","score":0.4138000011444092},{"id":"https://openalex.org/keywords/chemical-database","display_name":"Chemical database","score":0.3831999897956848}],"concepts":[{"id":"https://openalex.org/C68762167","wikidata":"https://www.wikidata.org/wiki/Q910164","display_name":"Cheminformatics","level":2,"score":0.8349999785423279},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8167999982833862},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7900000214576721},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6438999772071838},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5497000217437744},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5414999723434448},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.46619999408721924},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4603999853134155},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.44679999351501465},{"id":"https://openalex.org/C74187038","wikidata":"https://www.wikidata.org/wiki/Q1418791","display_name":"Drug discovery","level":2,"score":0.4138000011444092},{"id":"https://openalex.org/C203394866","wikidata":"https://www.wikidata.org/wiki/Q2881060","display_name":"Chemical database","level":2,"score":0.3831999897956848},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.33169999718666077},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.28290000557899475},{"id":"https://openalex.org/C155261790","wikidata":"https://www.wikidata.org/wiki/Q1122544","display_name":"DrugBank","level":3,"score":0.2660999894142151},{"id":"https://openalex.org/C66782513","wikidata":"https://www.wikidata.org/wiki/Q864601","display_name":"Biomedicine","level":2,"score":0.2653000056743622},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26249998807907104},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.2621999979019165},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.2597000002861023}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1186/s13321-025-01092-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01092-3","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01092-3","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:41035053","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41035053","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:oai:arXiv.org:2505.18470","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.18470","pdf_url":"https://arxiv.org/pdf/2505.18470","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},{"id":"pmh:oai:doaj.org/article:b6b5713662784291b1a0212cfbf20c42","is_oa":true,"landing_page_url":"https://doaj.org/article/b6b5713662784291b1a0212cfbf20c42","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Cheminformatics, Vol 17, Iss 1, Pp 1-23 (2025)","raw_type":"article"},{"id":"pmh:oai:escholarship.org:ark:/13030/qt8s29j3r4","is_oa":true,"landing_page_url":"https://escholarship.org/uc/item/8s29j3r4","pdf_url":null,"source":{"id":"https://openalex.org/S4306400115","display_name":"eScholarship (California Digital Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2801248553","host_organization_name":"California Digital Library","host_organization_lineage":["https://openalex.org/I2801248553"],"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":"Journal of Cheminformatics, vol 17, iss 1","raw_type":"article"},{"id":"pmh:oai:europepmc.org:11300668","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12490122","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:12490122","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12490122/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"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/s13321-025-01092-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s13321-025-01092-3","pdf_url":"https://jcheminf.biomedcentral.com/counter/pdf/10.1186/s13321-025-01092-3","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":[],"awards":[{"id":"https://openalex.org/G1351923513","display_name":null,"funder_award_id":"215906","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G5302547648","display_name":null,"funder_award_id":"10002786","funder_id":"https://openalex.org/F4320320924","funder_display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"id":"https://openalex.org/G6652677321","display_name":null,"funder_award_id":"HG010860","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"}],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320314023","display_name":"European Molecular Biology Laboratory","ror":"https://ror.org/050589e39"},{"id":"https://openalex.org/F4320320924","display_name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","ror":"https://ror.org/00yjd3n13"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"},{"id":"https://openalex.org/F4320338292","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414695397.pdf"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W1563942368","https://openalex.org/W1935434993","https://openalex.org/W1965091013","https://openalex.org/W1975147762","https://openalex.org/W2017254234","https://openalex.org/W2043198854","https://openalex.org/W2056287272","https://openalex.org/W2087563523","https://openalex.org/W2114940395","https://openalex.org/W2116034137","https://openalex.org/W2142671985","https://openalex.org/W2159482845","https://openalex.org/W2169678694","https://openalex.org/W2170973067","https://openalex.org/W2192374892","https://openalex.org/W2548357532","https://openalex.org/W2624907881","https://openalex.org/W2773987374","https://openalex.org/W2944975820","https://openalex.org/W2973232653","https://openalex.org/W2985502476","https://openalex.org/W3082081167","https://openalex.org/W3100751385","https://openalex.org/W3102771275","https://openalex.org/W3113096756","https://openalex.org/W3205065726","https://openalex.org/W4281661209","https://openalex.org/W4294216483","https://openalex.org/W4303685003","https://openalex.org/W4382397550","https://openalex.org/W4388455891","https://openalex.org/W4388735079","https://openalex.org/W4393190704","https://openalex.org/W4400191782","https://openalex.org/W4402717612","https://openalex.org/W4403458599","https://openalex.org/W4404511389","https://openalex.org/W4404719651","https://openalex.org/W4405532769","https://openalex.org/W6917786352","https://openalex.org/W6949206019","https://openalex.org/W6949593700"],"related_works":[],"abstract_inverted_index":{"Accurately":[0],"classifying":[1],"chemical":[2,35,54,87,128],"structures":[3],"is":[4,46],"essential":[5],"for":[6,21,37,90,106],"cheminformatics":[7],"and":[8,48,149,157,197,232],"bioinformatics,":[9],"including":[10,195],"tasks":[11],"such":[12],"as":[13,225],"identifying":[14],"bioactive":[15],"compounds":[16,27],"of":[17,96,111,127,175,177,188,213,227],"interest,":[18],"screening":[19],"molecules":[20],"toxicity":[22],"to":[23,50,52,84,209],"humans,":[24],"finding":[25],"non-organic":[26],"with":[28,114],"desirable":[29],"material":[30],"properties,":[31],"or":[32,40,66],"organizing":[33],"large":[34,53],"libraries":[36],"drug":[38],"discovery":[39],"environmental":[41],"monitoring.":[42],"However,":[43,183],"manual":[44],"classification":[45,64,110],"labor-intensive":[47],"difficult":[49],"scale":[51],"databases.":[55],"Existing":[56],"automated":[57],"approaches":[58],"either":[59],"rely":[60],"on":[61],"manually":[62],"constructed":[63],"rules,":[65],"are":[67],"deep":[68,154,180,192,206],"learning":[69,155,181,193,207],"methods":[70,218],"that":[71,79,190],"lack":[72],"explainability.":[73],"This":[74],"work":[75],"presents":[76],"an":[77,122,211],"approach":[78,144],"uses":[80],"generative":[81],"artificial":[82],"intelligence":[83],"automatically":[85],"write":[86],"classifier":[88],"programs":[89,102,119,221],"classes":[91],"in":[92],"the":[93,134,146,166,173,178,214,228],"Chemical":[94,136],"Entities":[95],"Biological":[97],"Interest":[98],"(ChEBI)":[99],"database.":[100],"These":[101],"can":[103,202,222],"be":[104,203,223],"used":[105,204,224],"efficient":[107],"deterministic":[108],"run-time":[109],"SMILES":[112],"structures,":[113],"natural":[115],"language":[116],"explanations.":[117],"The":[118,220],"themselves":[120],"constitute":[121],"explainable":[123],"computable":[124],"ontological":[125],"model":[126],"class":[129],"nomenclature,":[130],"which":[131],"we":[132],"call":[133],"ChEBI":[135,147],"Class":[137],"Program":[138],"Ontology":[139],"(C3PO).":[140],"We":[141],"validated":[142],"our":[143,151],"against":[145,153],"database,":[148],"compared":[150],"results":[152],"models":[156],"a":[158,186],"naive":[159,167],"SMARTS":[160],"pattern":[161],"based":[162],"classifier.":[163],"C3PO":[164,184,201],"outperforms":[165],"classifier,":[168],"but":[169],"does":[170],"not":[171],"reach":[172],"performance":[174],"state":[176],"art":[179],"methods.":[182],"has":[185],"number":[187],"strengths":[189],"complement":[191],"methods,":[194],"explainability":[196],"reduced":[198],"data":[199],"dependence.":[200],"alongside":[205],"classifiers":[208],"provide":[210],"explanation":[212],"classification,":[215],"where":[216],"both":[217],"agree.":[219],"part":[226],"ontology":[229],"development":[230],"process,":[231],"iteratively":[233],"refined":[234],"by":[235],"expert":[236],"human":[237],"curators.":[238]},"counts_by_year":[],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}