{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:51:38Z","timestamp":1784299898053,"version":"3.55.0"},"reference-count":41,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2025,1,11]],"date-time":"2025-01-11T00:00:00Z","timestamp":1736553600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China Project","doi-asserted-by":"crossref","award":["623B2086"],"award-info":[{"award-number":["623B2086"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China Project","doi-asserted-by":"crossref","award":["U21A20427"],"award-info":[{"award-number":["U21A20427"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China Project","doi-asserted-by":"crossref","award":["WU2022A009"],"award-info":[{"award-number":["WU2022A009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,3,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Drug\u2013target interaction (DTI) prediction is crucial for drug discovery, significantly reducing costs and time in experimental searches across vast drug compound spaces. While deep learning has advanced DTI prediction accuracy, challenges remain: (i) existing methods often lack generalizability, with performance dropping significantly on unseen proteins and cross-domain settings; and (ii) current molecular relational learning often overlooks subpocket-level interactions, which are vital for a detailed understanding of binding sites.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We introduce SP-DTI, a subpocket-informed transformer model designed to address these challenges through: (i) detailed subpocket analysis using the Cavity Identification and Analysis Routine for interaction modeling at both global and local levels, and (ii) integration of pre-trained language models into graph neural networks to encode drugs and proteins, enhancing generalizability to unlabeled data. Benchmark evaluations show that SP-DTI consistently outperforms state-of-the-art models, achieving an area under the receiver operating characteristic curve of 0.873 in unseen protein settings, an 11% improvement over the best baseline.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The model scripts are available at https:\/\/github.com\/Steven51516\/SP-DTI.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaf011","type":"journal-article","created":{"date-parts":[[2025,1,11]],"date-time":"2025-01-11T19:23:04Z","timestamp":1736623384000},"source":"Crossref","is-referenced-by-count":17,"title":["SP-DTI: subpocket-informed transformer for drug\u2013target interaction prediction"],"prefix":"10.1093","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-7190-5832","authenticated-orcid":false,"given":"Sizhe","family":"Liu","sequence":"first","affiliation":[{"name":"Thomas Lord Department of Computer Science, University of Southern California , Los Angeles, CA 90089,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuchen","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Quantitative and Computational Biology, University of Southern California , Los Angeles, CA 90089,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haofeng","family":"Xu","sequence":"additional","affiliation":[{"name":"Thomas Lord Department of Computer Science, University of Southern California , Los Angeles, CA 90089,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7993-0803","authenticated-orcid":false,"given":"Jun","family":"Xia","sequence":"additional","affiliation":[{"name":"School of Engineering, Westlake University , Hangzhou 310024,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stan Z","family":"Li","sequence":"additional","affiliation":[{"name":"School of Engineering, Westlake University , Hangzhou 310024,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,1,11]]},"reference":[{"key":"2025030711573067100_btaf011-B1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2209.01712"},{"key":"2025030711573067100_btaf011-B2","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1038\/s42256-022-00605-1","article-title":"Interpretable bilinear attention network with domain adaptation improves drug\u2013target prediction","volume":"5","author":"Bai","year":"2023","journal-title":"Nat Mach Intell"},{"key":"2025030711573067100_btaf011-B3","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":". Mach Learn"},{"key":"2025030711573067100_btaf011-B4","doi-asserted-by":"crossref","first-page":"960","DOI":"10.1093\/bioinformatics\/btt072","article-title":"propy: a tool to generate various modes of chou\u2019s pseaac","volume":"29","author":"Cao","year":"2013","journal-title":"Bioinformatics"},{"key":"2025030711573067100_btaf011-B5","doi-asserted-by":"crossref","first-page":"1989","DOI":"10.1038\/s41467-023-37572-z","article-title":"Improving the generalizability of protein-ligand binding predictions with ai-bind","volume":"14","author":"Chatterjee","year":"2023","journal-title":"Nat Commun"},{"key":"2025030711573067100_btaf011-B6","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/BF00994018","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach Learn"},{"key":"2025030711573067100_btaf011-B7","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1111\/j.2517-6161.1958.tb00292.x","article-title":"The regression analysis of binary sequences","volume":"20","author":"Cox","year":"1958","journal-title":"J R Stat Soc Series B Stat Methodol"},{"key":"2025030711573067100_btaf011-B8","doi-asserted-by":"crossref","first-page":"1046","DOI":"10.1038\/nbt.1990","article-title":"Comprehensive analysis of kinase inhibitor selectivity","volume":"29","author":"Davis","year":"2011","journal-title":"Nat Biotechnol"},{"key":"2025030711573067100_btaf011-B9","doi-asserted-by":"crossref","first-page":"830","DOI":"10.1093\/bioinformatics\/btaa880","article-title":"Moltrans: molecular interaction transformer for drug\u2013target interaction prediction","volume":"37","author":"Huang","year":"2021","journal-title":"Bioinformatics"},{"key":"2025030711573067100_btaf011-B10","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1038\/s41586-021-03819-2","article-title":"Highly accurate protein structure prediction with alphafold","volume":"596","author":"Jumper","year":"2021","journal-title":"Nature"},{"key":"2025030711573067100_btaf011-B11"},{"key":"2025030711573067100_btaf011-B12","doi-asserted-by":"crossref","first-page":"e1007129","DOI":"10.1371\/journal.pcbi.1007129","article-title":"Deepconv-dti: prediction of drug-target interactions via deep learning with convolution on protein sequences","volume":"15","author":"Lee","year":"2019","journal-title":"PLoS Comput Biol"},{"key":"2025030711573067100_btaf011-B13","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1186\/s13321-022-00584-w","article-title":"Sequence-based prediction of protein binding regions and drug\u2013target interactions","volume":"14","author":"Lee","year":"2022","journal-title":"J Cheminform"},{"key":"2025030711573067100_btaf011-B14","author":"Liao","year":"2021"},{"key":"2025030711573067100_btaf011-B15","doi-asserted-by":"publisher","author":"Lin","year":"2022","DOI":"10.1101\/2022.07.20.500902"},{"key":"2025030711573067100_btaf011-B16","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":"2025030711573067100_btaf011-B17","doi-asserted-by":"publisher","author":"Liu","DOI":"10.48550\/arXiv.2410.15010"},{"key":"2025030711573067100_btaf011-B18","doi-asserted-by":"publisher","first-page":"1052","DOI":"10.1609\/aaai.v33i01.33011052","article-title":"Molecular property prediction: a multilevel quantum interactions modeling perspective","volume":"33","author":"Lu","year":"2019","journal-title":"AAAI"},{"key":"2025030711573067100_btaf011-B19","doi-asserted-by":"publisher","author":"Lu","year":"2023","DOI":"10.48550\/arXiv.2303.16982"},{"key":"2025030711573067100_btaf011-B20","doi-asserted-by":"publisher","first-page":"737","author":"Marchand","DOI":"10.1007\/s10822-021-00390-w"},{"key":"2025030711573067100_btaf011-B21","author":"Marinka Zitnik","year":"2018"},{"key":"2025030711573067100_btaf011-B22","doi-asserted-by":"crossref","first-page":"146","DOI":"10.2174\/157340911795677602","article-title":"Molecular docking: a powerful approach for structure-based drug discovery","volume":"7","author":"Meng","year":"2011","journal-title":"Curr Comput Aided Drug Des"},{"key":"2025030711573067100_btaf011-B23","doi-asserted-by":"crossref","first-page":"i821","DOI":"10.1093\/bioinformatics\/bty593","article-title":"Deepdta: deep drug-target binding affinity prediction","volume":"34","author":"\u00d6zt\u00fcrk","year":"2018","journal-title":"Bioinformatics"},{"key":"2025030711573067100_btaf011-B24","doi-asserted-by":"publisher","author":"Paszke","year":"2019","DOI":"10.48550\/arXiv.1912.01703"},{"key":"2025030711573067100_btaf011-B25","doi-asserted-by":"crossref","first-page":"4331","DOI":"10.3390\/ijms20184331","article-title":"Molecular docking: shifting paradigms in drug discovery","volume":"20","author":"Pinzi","year":"2019","journal-title":"Int J Mol Sci"},{"key":"2025030711573067100_btaf011-B26","doi-asserted-by":"crossref","first-page":"942","DOI":"10.1021\/acs.jcim.6b00740","article-title":"Protein\u2013ligand scoring with convolutional neural networks","volume":"57","author":"Ragoza","year":"2017","journal-title":"J Chem Inf Model"},{"key":"2025030711573067100_btaf011-B27","doi-asserted-by":"crossref","first-page":"2531","DOI":"10.1039\/C9SC03414E","article-title":"Deepscreen: high performance drug\u2013target interaction prediction with convolutional neural networks using 2-d structural compound representations","volume":"11","author":"Rifaioglu","year":"2020","journal-title":"Chem Sci"},{"key":"2025030711573067100_btaf011-B28","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1186\/1472-6807-14-18","article-title":"A simple method for finding a protein\u2019s ligand-binding pockets","volume":"14","author":"Saberi Fathi","year":"2014","journal-title":"BMC Struct Biol"},{"key":"2025030711573067100_btaf011-B29","doi-asserted-by":"publisher","first-page":"241722","DOI":"10.1063\/1.5019779","article-title":"Schnet\u2014a deep learning architecture for molecules and materials","volume":"148","author":"Sch\u00fctt","year":"2018","journal-title":"J Chem Phys"},{"key":"2025030711573067100_btaf011-B30","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1093\/bib\/bbac109","article-title":"Dti-heta: prediction of drug\u2013target interactions based on gcn and gat on heterogeneous graph","volume":"23","author":"Shao","year":"2022","journal-title":"Brief Bioinform"},{"key":"2025030711573067100_btaf011-B31","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1093\/bioinformatics\/bty535","article-title":"Compound\u2013protein interaction prediction with end-to-end learning of neural networks for graphs and sequences","volume":"35","author":"Tsubaki","year":"2019","journal-title":"Bioinformatics"},{"key":"2025030711573067100_btaf011-B32","first-page":"170","article-title":"Drugs, devices, and the FDA: part 1","volume":"1","author":"Van Norman","year":"2016","journal-title":"JACC: Basic Transl Sci"},{"key":"2025030711573067100_btaf011-B33","doi-asserted-by":"crossref","first-page":"10261","DOI":"10.1039\/D3RA00281K","article-title":"3dprotdta: a deep learning model for drug-target affinity prediction based on residue-level protein graphs","volume":"13","author":"Voitsitskyi","year":"2023","journal-title":"RSC Adv"},{"key":"2025030711573067100_btaf011-B34","doi-asserted-by":"crossref","first-page":"2041","DOI":"10.1021\/ci100241y","article-title":"Analyzing the topology of active sites: on the prediction of pockets and subpockets","volume":"50","author":"Volkamer","year":"2010","journal-title":"J Chem Inf Model"},{"key":"2025030711573067100_btaf011-B35","first-page":"5","article-title":"Deepdtaf: a deep learning method to predict protein\u2013ligand binding affinity","volume":"22","author":"Wang","year":"2021","journal-title":"Brief Bioinform"},{"key":"2025030711573067100_btaf011-B36","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1109\/icbcb52223.2021.9459231","author":"Wang","year":"2021"},{"key":"2025030711573067100_btaf011-B37","doi-asserted-by":"crossref","first-page":"18200","DOI":"10.1038\/s41598-022-23014-1","article-title":"Deeplpi: a novel deep learning-based model for protein\u2013ligand interaction prediction for drug repurposing","volume":"12","author":"Wei","year":"2022","journal-title":"Sci Rep"},{"key":"2025030711573067100_btaf011-B38","doi-asserted-by":"crossref","first-page":"bbac272","DOI":"10.1093\/bib\/bbac272","article-title":"Attentionsitedti: an interpretable graph-based model for drug-target interaction prediction using nlp sentence-level relation classification","volume":"23","author":"Yazdani-Jahromi","year":"2022","journal-title":"Brief Bioinform"},{"key":"2025030711573067100_btaf011-B39","doi-asserted-by":"publisher","author":"Zhang","year":"2023","DOI":"10.1101\/2023.09.13.557595"},{"key":"2025030711573067100_btaf011-B40","author":"Zhou"},{"key":"2025030711573067100_btaf011-B41","doi-asserted-by":"crossref","first-page":"btad560","DOI":"10.1093\/bioinformatics\/btad560","article-title":"Datadta: a multi-feature and dual-interaction aggregation framework for drug\u2013target binding affinity prediction","volume":"39","author":"Zhu","year":"2023","journal-title":"Bioinformatics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaf011\/61415030\/btaf011.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/3\/btaf011\/61415030\/btaf011.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/3\/btaf011\/61415030\/btaf011.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T11:59:15Z","timestamp":1741348755000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btaf011\/7951882"}},"subtitle":[],"editor":[{"given":"Jonathan","family":"Wren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,1,11]]},"references-count":41,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,3,4]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaf011","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,3]]},"published":{"date-parts":[[2025,1,11]]},"article-number":"btaf011"}}