{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T22:29:57Z","timestamp":1791412197039,"version":"4.3.3"},"reference-count":28,"publisher":"Oxford University Press (OUP)","issue":"Supplement_1","license":[{"start":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T00:00:00Z","timestamp":1783382400000},"content-version":"vor","delay-in-days":6,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009122","name":"Ministry of Education","doi-asserted-by":"publisher","award":["RS-2025\u201316652968"],"award-info":[{"award-number":["RS-2025\u201316652968"]}],"id":[{"id":"10.13039\/100009122","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["NRF-2023R1A2C3004176"],"award-info":[{"award-number":["NRF-2023R1A2C3004176"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["HR20C002103"],"award-info":[{"award-number":["HR20C002103"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Korea Machine Learning Ledger Orchestration for Drug Discovery"},{"DOI":"10.13039\/100008903","name":"Ministry of Health and Welfare","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008903","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Republic of Korea","award":["RS-2024\u201300462471"],"award-info":[{"award-number":["RS-2024\u201300462471"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,7,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Identifying metabolic sites where cytochrome P450 enzymes metabolize small-molecule drugs is essential for drug discovery. Although existing computational approaches have been proposed for site-of-metabolism prediction, they typically ignore cytochrome P450 isoform identity or model isoforms independently, thereby failing to fully capture inherent cross-isoform metabolic patterns. In addition, prior evaluations often rely on top-k metrics, where false positive atoms may be included among the top predictions, underscoring the need for complementary metrics that more directly assess binary atom-level discrimination under severe class imbalance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We propose ATTNSOM, an atom-level site-of-metabolism prediction framework that integrates intrinsic molecular reactivity with cross-isoform relationships. The model combines a shared graph encoder, molecule-conditioned atom representations, and a cross-attention mechanism to capture correlated metabolic patterns across cytochrome P450 isoforms. The model is evaluated on two benchmark datasets annotated with site-of-metabolism labels at atom resolution. Across these benchmarks, the model achieves consistently strong top-k performance across multiple cytochrome P450 isoforms. Relative to ablated variants, the model yields higher Matthews correlation coefficient, indicating improved discrimination of true metabolic sites. These results support the importance of explicitly modeling cross-isoform relationships for site-of-metabolism prediction.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>The code and datasets are available at https:\/\/github.com\/dmis-lab\/ATTNSOM.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btag314","type":"journal-article","created":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T16:30:15Z","timestamp":1783441815000},"source":"Crossref","is-referenced-by-count":1,"title":["ATTNSOM: learning cross-isoform attention for cytochrome P450 site-of-metabolism prediction"],"prefix":"10.1093","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3209-3494","authenticated-orcid":false,"given":"Hajung","family":"Kim","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Korea University , Seoul, 02841,","place":["South Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eunha","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Korea University , Seoul, 02841,","place":["South Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sohyun","family":"Chung","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Korea University , Seoul, 02841,","place":["South Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jueon","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Korea University , Seoul, 02841,","place":["South Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seungheun","family":"Baek","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Korea University , Seoul, 02841,","place":["South Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6798-9106","authenticated-orcid":false,"given":"Jaewoo","family":"Kang","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Korea University , Seoul, 02841,","place":["South Korea"]},{"name":"AIGEN Sciences , Seoul, 04778,","place":["South Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,7,7]]},"reference":[{"key":"2026071008222375500_btag314-B1","first-page":"48","author":"Bergeron","year":"2008"},{"key":"2026071008222375500_btag314-B2","doi-asserted-by":"crossref","first-page":"6772","DOI":"10.1021\/acs.molpharmaceut.5c00740","article-title":"Metabolite identification data in drug discovery, part 2: site-of-metabolism annotation, analysis, and exploration for machine learning","volume":"22","author":"Chen","year":"2025","journal-title":"Mol Pharm"},{"key":"2026071008222375500_btag314-B3","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1186\/s12864-019-6413-7","article-title":"The advantages of the Matthews correlation coefficient (mcc) over f1 score and accuracy in binary classification evaluation","volume":"21","author":"Chicco","year":"2020","journal-title":"BMC Genomics"},{"key":"2026071008222375500_btag314-B5","doi-asserted-by":"crossref","first-page":"562","DOI":"10.1038\/s41573-023-00703-8","article-title":"Deuterium in drug discovery: progress, opportunities and challenges","volume":"22","author":"Di Martino","year":"2023","journal-title":"Nat Rev Drug Discov"},{"key":"2026071008222375500_btag314-B6","doi-asserted-by":"crossref","first-page":"E101","DOI":"10.1208\/aapsj080112","article-title":"Cytochrome p450s and other enzymes in drug metabolism and toxicity","volume":"8","author":"Guengerich","year":"2006","journal-title":"Aaps J"},{"key":"2026071008222375500_btag314-B7","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1021\/tx700079z","article-title":"Cytochrome p450 and chemical toxicology","volume":"21","author":"Guengerich","year":"2008","journal-title":"Chem Res Toxicol"},{"key":"2026071008222375500_btag314-B8","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1021\/acs.jcim.3c01250","article-title":"Chemprop: a machine learning package for chemical property prediction","volume":"64","author":"Heid","year":"2024","journal-title":"J Chem Inf Model"},{"key":"2026071008222375500_btag314-B9","doi-asserted-by":"crossref","first-page":"2322","DOI":"10.1021\/acs.jcim.4c02051","article-title":"Glmcyp: a deep learning-based method for cyp450-mediated reaction site prediction","volume":"65","author":"Huang","year":"2025","journal-title":"J Chem Inf Model"},{"key":"2026071008222375500_btag314-B10","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1007\/s00210-003-0819-z","article-title":"Human drug metabolising cytochrome p450 enzymes: properties and polymorphisms","volume":"369","author":"Ingelman-Sundberg","year":"2004","journal-title":"Naunyn Schmiedebergs Arch Pharmacol"},{"key":"2026071008222375500_btag314-B11","author":"Kim","year":"2025"},{"key":"2026071008222375500_btag314-B12","author":"Kipf","year":"2016"},{"key":"2026071008222375500_btag314-B13","doi-asserted-by":"crossref","first-page":"1123","DOI":"10.1126\/science.ade2574","article-title":"Evolutionary-scale prediction of atomic-level protein structure with a language model","volume":"379","author":"Lin","year":"2023","journal-title":"Science"},{"key":"2026071008222375500_btag314-B14","first-page":"83","article-title":"Fda approves next-generation triple therapy for cystic fibrosis","volume":"24","author":"Mullard","year":"2025","journal-title":"Nat Rev Drug Discov"},{"key":"2026071008222375500_btag314-B15","doi-asserted-by":"crossref","first-page":"4328","DOI":"10.3390\/ijms20184328","article-title":"Differing membrane interactions of two highly similar drug-metabolizing cytochrome p450 isoforms: cyp 2c9 and cyp 2c19","volume":"20","author":"Mustafa","year":"2019","journal-title":"Int J Mol Sci"},{"key":"2026071008222375500_btag314-B4","volume-title":"Cytochrome P450: Structure, Mechanism, and Biochemistry","author":"Ortiz De Montellano","year":"2007"},{"key":"2026071008222375500_btag314-B16","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1021\/tx500444e","article-title":"Survey of human oxidoreductases and cytochrome p450 enzymes involved in the metabolism of xenobiotic and natural chemicals","volume":"28","author":"Rendic","year":"2015","journal-title":"Chem Res Toxicol"},{"key":"2026071008222375500_btag314-B17","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1021\/ml100016x","article-title":"Smartcyp: a 2d method for prediction of cytochrome p450-mediated drug metabolism","volume":"1","author":"Rydberg","year":"2010","journal-title":"ACS Med Chem Lett"},{"key":"2026071008222375500_btag314-B18","doi-asserted-by":"crossref","first-page":"3400","DOI":"10.1021\/acs.jcim.9b00376","article-title":"Fame 3: predicting the sites of metabolism in synthetic compounds and natural products for phase 1 and phase 2 metabolic enzymes","volume":"59","author":"\u0160\u00edcho","year":"2019","journal-title":"J Chem Inf Model"},{"key":"2026071008222375500_btag314-B19","doi-asserted-by":"crossref","first-page":"4273","DOI":"10.1021\/acs.jmedchem.7b00969","article-title":"Di. Relevance of half-life in drug design: miniperspective","volume":"61","author":"Smith","year":"2017","journal-title":"J Med Chem"},{"key":"2026071008222375500_btag314-B20","doi-asserted-by":"crossref","first-page":"33","DOI":"10.2307\/1217208","article-title":"The comparison of dendrograms by objective methods","volume":"11","author":"Sokal","year":"1962","journal-title":"Taxon"},{"key":"2026071008222375500_btag314-B21","first-page":"10","article-title":"Graph attention networks","volume":"1050","author":"Velickovic","year":"2017","journal-title":"Stat"},{"key":"2026071008222375500_btag314-B22","doi-asserted-by":"crossref","first-page":"364","DOI":"10.1124\/dmd.118.085340","article-title":"Induction of cytochrome p450 involved in the accelerated blood clearance phenomenon induced by pegylated liposomes in vivo","volume":"47","author":"Wang","year":"2019","journal-title":"Drug Metab Dispos"},{"key":"2026071008222375500_btag314-B23","author":"Xu","year":"2018"},{"key":"2026071008222375500_btag314-B24","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1016\/j.eng.2025.07.029","article-title":"Elucidating the substrate specificity of cytochrome p450 enzymes: insights into n-and s-containing small-molecule metabolism","volume":"54","author":"Yan","year":"2025","journal-title":"Engineering"},{"key":"2026071008222375500_btag314-B25","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1016\/j.pharmthera.2012.12.007","article-title":"Cytochrome p450 enzymes in drug metabolism: regulation of gene expression, enzyme activities, and impact of genetic variation","volume":"138","author":"Zanger","year":"2013","journal-title":"Pharmacol Ther"},{"key":"2026071008222375500_btag314-B26","doi-asserted-by":"crossref","first-page":"1667","DOI":"10.1021\/ci2000488","article-title":"Rs-predictor: a new tool for predicting sites of cytochrome p450-mediated metabolism applied to cyp 3a4","volume":"51","author":"Zaretzki","year":"2011","journal-title":"J Chem Inf Model"},{"key":"2026071008222375500_btag314-B27","doi-asserted-by":"crossref","first-page":"3373","DOI":"10.1021\/ci400518g","article-title":"Xenosite: accurately predicting cyp-mediated sites of metabolism with neural networks","volume":"53","author":"Zaretzki","year":"2013","journal-title":"J Chem Inf Model"},{"key":"2026071008222375500_btag314-B28","volume-title":"International Conference on Learning Representations (ICLR)","author":"Zhou","year":"2023"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/Supplement_1\/btag314\/68709192\/btag314.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/Supplement_1\/btag314\/68709192\/btag314.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T12:22:33Z","timestamp":1783686153000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btag314\/8726294"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,1]]},"references-count":28,"journal-issue":{"issue":"Supplement_1","published-print":{"date-parts":[[2026,7,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btag314","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,7]]},"published":{"date-parts":[[2026,7,1]]},"article-number":"btag314"}}