{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T03:11:22Z","timestamp":1790565082718,"version":"4.1.0"},"reference-count":32,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T00:00:00Z","timestamp":1786492800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Chem."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Cytochrome P450 (CYP) enzymes are the predominant drug-metabolizing proteins in humans, collectively governing the structural transformation of drugs and xenobiotics while directly shaping their pharmacological activity and toxicological profiles. Accurate prediction of CYP\u2013substrate reaction sites and reaction types is therefore central to drug discovery and metabolic risk assessment. Existing computational models, however, largely depend on intrinsic molecular properties or hardcoded reaction rules, constraining their generalization across CYP isoforms.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Here we present MetaCYP, a multimodal deep learning framework that predicts bonds of metabolism (BoMs) and reaction types in CYP-mediated biotransformation. MetaCYP encodes CYP amino acid sequences with the protein language model ESM-2 and extracts bond-level substrate features using Uni-Mol, integrating both modalities through an attention-based cross-modal fusion mechanism that captures enzyme\u2013substrate interactions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>This architecture enables a single unified model to resolve isoform-specific catalytic selectivity for identical substrates. MetaCYP achieves state-of-the-art performance in BoM prediction (MCC: 0.741; ROC-AUC: 0.956) and reaction type prediction (MCC: 0.796; ROC-AUC: 0.946), outperforming current benchmarks.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>MetaCYP establishes a unified deep learning framework that models reaction sites and reaction types from enzyme\u2013substrate information, offering a mechanistically grounded and interpretable tool for elucidating CYP catalytic selectivity. Its capacity to improve the accuracy of ADME property predictions, alongside its scalability across isoforms, positions it as a practical resource for early-stage drug screening, metabolic risk assessment, and rational drug design.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fchem.2026.1869559","type":"journal-article","created":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T06:00:08Z","timestamp":1786514408000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["MetaCYP: a unified framework for prediction of cytochrome P450 metabolic sites and reaction types via multimodal deep learning"],"prefix":"10.3389","volume":"14","author":[{"given":"Jiamin","family":"Chang","sequence":"first","affiliation":[{"name":"MOE Key Laboratory of Bioinformatics, State Key Laboratory of Molecular Oncology, Beijing Frontier Research Center for Biological Structure, School of Pharmaceutical Sciences, Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuhai","family":"Huang","sequence":"additional","affiliation":[{"name":"MOE Key Laboratory of Bioinformatics, State Key Laboratory of Molecular Oncology, Beijing Frontier Research Center for Biological Structure, School of Pharmaceutical Sciences, Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boxue","family":"Tian","sequence":"additional","affiliation":[{"name":"MOE Key Laboratory of Bioinformatics, State Key Laboratory of Molecular Oncology, Beijing Frontier Research Center for Biological Structure, School of Pharmaceutical Sciences, Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,12]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"3149","DOI":"10.1021\/acs.jcim.4c00115","article-title":"DeepP450: predicting human P450 activities of small molecules by integrating pretrained protein language model and molecular representation","volume":"64","author":"Chang","year":"2024","journal-title":"J. Chem. Inf. Model"},{"key":"B2","doi-asserted-by":"publisher","first-page":"2528","DOI":"10.1021\/acs.jcim.3c01396","article-title":"Prediction of cytochrome P450 inhibition using a deep learning approach and substructure pattern recognition","volume":"64","author":"Chen","year":"2024","journal-title":"J. Chem. Inf. Model"},{"key":"B3","doi-asserted-by":"publisher","first-page":"402","DOI":"10.3389\/fchem.2019.00402","article-title":"GLORY: generator of the structures of likely cytochrome P450 metabolites based on predicted sites of metabolism","volume":"7","author":"de Bruyn Kops","year":"2019","journal-title":"Front. Chem."},{"key":"B4","doi-asserted-by":"publisher","first-page":"94","DOI":"10.3390\/jox11030007","article-title":"The central role of cytochrome P450 in xenobiotic metabolism\u2014A brief review on a fascinating enzyme family","volume":"11","author":"Esteves","year":"2021","journal-title":"J. Xenobiot."},{"key":"B5","doi-asserted-by":"publisher","first-page":"W422","DOI":"10.1093\/nar\/gkae236","article-title":"ADMETlab 3.0: an updated comprehensive online ADMET prediction platform enhanced with broader coverage, improved performance, API functionality and decision support","volume":"52","author":"Fu","year":"2024","journal-title":"Nucleic Acids Res."},{"key":"B6","doi-asserted-by":"publisher","first-page":"3671","DOI":"10.1007\/s00204-020-02936-7","article-title":"Inhibition and induction of CYP enzymes in humans: an update","volume":"94","author":"Hakkola","year":"2020","journal-title":"Arch. Toxicol."},{"key":"B7","doi-asserted-by":"publisher","first-page":"358","DOI":"10.1016\/j.trechm.2025.05.002","article-title":"Computational studies on human cytochrome P450: advancing insights into drug metabolism","volume":"7","author":"Hirao","year":"2025","journal-title":"Trends Chem."},{"key":"B8","doi-asserted-by":"publisher","first-page":"3352","DOI":"10.1021\/ci4004688","article-title":"DR-predictor: incorporating flexible docking with specialized electronic reactivity and machine learning techniques to predict CYP-Mediated sites of metabolism","volume":"53","author":"Huang","year":"2013","journal-title":"J. Chem. Inf. Model"},{"key":"B9","doi-asserted-by":"publisher","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":"B10","doi-asserted-by":"publisher","first-page":"537","DOI":"10.1007\/s10822-018-0107-0","article-title":"WhichP450: a multi-class categorical model to predict the major metabolising CYP450 isoform for a compound","volume":"32","author":"Hunt","year":"2018","journal-title":"J. Comput. Aided Mol. Des."},{"key":"B11","doi-asserted-by":"publisher","first-page":"e202310728","DOI":"10.1002\/anie.202310728","article-title":"A mechanistic understanding of the distinct Regio- and chemoselectivity of multifunctional P450s by structural comparison of IkaD and CftA complexed with common substrates","volume":"62","author":"Jiang","year":"2023","journal-title":"Angew. Chem. Int. Ed."},{"key":"B12","doi-asserted-by":"publisher","first-page":"99","DOI":"10.3390\/biom14010099","article-title":"A review of CYP-mediated drug interactions: mechanisms and in vitro drug-drug interaction assessment","volume":"14","author":"Lee","year":"2024","journal-title":"Biomolecules"},{"key":"B13","doi-asserted-by":"publisher","first-page":"3829","DOI":"10.1021\/ct200462q","article-title":"IDSite: an accurate approach to predict P450-mediated drug metabolism","volume":"7","author":"Li","year":"2011","journal-title":"J. Chem. Theory Comput."},{"key":"B14","doi-asserted-by":"publisher","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":"B15","doi-asserted-by":"publisher","first-page":"3174","DOI":"10.1093\/bioinformatics\/btz037","article-title":"SMARTCyp 3.0: enhanced cytochrome P450 site-of-metabolism prediction server","volume":"35","author":"Olsen","year":"2019","journal-title":"Bioinformatics"},{"key":"B16","doi-asserted-by":"publisher","first-page":"116388","DOI":"10.1016\/j.bmc.2021.116388","article-title":"CYPlebrity: machine learning models for the prediction of inhibitors of cytochrome P450 enzymes","volume":"46","author":"Plonka","year":"2021","journal-title":"Bioorgan Med. Chem."},{"key":"B17","doi-asserted-by":"publisher","first-page":"1581","DOI":"10.1007\/s00204-024-03710-9","article-title":"Formation of potentially toxic metabolites of drugs in reactions catalyzed by human drug-metabolizing enzymes","volume":"98","author":"Rendic","year":"2024","journal-title":"Arch. Toxicol."},{"key":"B18","doi-asserted-by":"publisher","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":"B19","doi-asserted-by":"publisher","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":"Sicho","year":"2019","journal-title":"J. Chem. Inf. Model"},{"key":"B20","unstructured":"ADMET predictor\n          \n          \n          2020"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1282","DOI":"10.1021\/acs.jcim.8b00035","article-title":"CypReact: a software tool for in silico reactant prediction for human cytochrome P450 enzymes","volume":"58","author":"Tian","year":"2018","journal-title":"J. Chem. Inf. Model"},{"key":"B22","doi-asserted-by":"publisher","first-page":"3128","DOI":"10.1021\/acs.jcim.1c00144","article-title":"CyProduct: a software tool for accurately predicting the byproducts of human cytochrome P450 metabolism","volume":"61","author":"Tian","year":"2021","journal-title":"J. Chem. Inf. Model"},{"key":"B23","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1111\/cbdd.13445","article-title":"Computational methods and tools to predict cytochrome P450 metabolism for drug discovery","volume":"93","author":"Tyzack","year":"2019","journal-title":"Chem. Biol. Drug Des."},{"key":"B24","article-title":"Attention is all you need","volume-title":"Advances in Neural Information Processing Systems (Neurips)","author":"Vaswani","year":"2017"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.64898\/2026.03.14.711529","article-title":"MetaReact: a reaction-aware transformer for end-to-end prediction of drug metabolism","volume":"2026","author":"Wang","year":"2026","journal-title":"bioRxiv"},{"key":"B26","doi-asserted-by":"publisher","first-page":"W115","DOI":"10.1093\/nar\/gkac313","article-title":"BioTransformer 3.0-a web server for accurately predicting metabolic transformation products","volume":"50","author":"Wishart","year":"2022","journal-title":"Nucleic Acids Res."},{"key":"B27","doi-asserted-by":"publisher","first-page":"9947","DOI":"10.1021\/acs.jcim.5c01192","article-title":"Deep learning models for predicting human cytochrome P450 inhibition and induction","volume":"65","author":"Xiao","year":"2025","journal-title":"J. Chem. Inf. Model"},{"key":"B28","doi-asserted-by":"publisher","first-page":"374","DOI":"10.1016\/j.apsb.2016.07.012","article-title":"An update on the role of intestinal cytochrome P450 enzymes in drug disposition","volume":"6","author":"Xie","year":"2016","journal-title":"Acta Pharm. Sin. B"},{"key":"B29","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1093\/bioinformatics\/bts705","article-title":"RS-WebPredictor: a server for predicting CYP-Mediated sites of metabolism on drug-like molecules","volume":"29","author":"Zaretzki","year":"2013","journal-title":"Bioinformatics"},{"key":"B30","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/j.jare.2023.10.012","article-title":"P450Rdb: a manually curated database of reactions catalyzed by cytochrome P450 enzymes","volume":"63","author":"Zhang","year":"2024","journal-title":"J. Adv. Res."},{"key":"B31","doi-asserted-by":"crossref","DOI":"10.26434\/chemrxiv-2022-jjm0j-v4","article-title":"Uni-mol: a universal 3D molecular representation learning framework","volume-title":"International Conference on Learning Representations (ICLR)","author":"Zhou","year":"2023"},{"key":"B32","doi-asserted-by":"publisher","first-page":"18884","DOI":"10.1039\/d5sc04631a","article-title":"DeepMetab: a comprehensive and mechanistically informed graph learning framework for end-to-end drug metabolism prediction","volume":"16","author":"Zhou","year":"2025","journal-title":"Chem. Sci."}],"container-title":["Frontiers in Chemistry"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fchem.2026.1869559\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T06:00:10Z","timestamp":1786514410000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fchem.2026.1869559\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,12]]},"references-count":32,"alternative-id":["10.3389\/fchem.2026.1869559"],"URL":"https:\/\/doi.org\/10.3389\/fchem.2026.1869559","relation":{},"ISSN":["2296-2646"],"issn-type":[{"value":"2296-2646","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,12]]},"article-number":"1869559"}}