{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T20:54:29Z","timestamp":1783976069347,"version":"3.55.0"},"reference-count":37,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T00:00:00Z","timestamp":1709769600000},"content-version":"vor","delay-in-days":6,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000024","name":"Canadian Institute of Health Research","doi-asserted-by":"crossref","award":["PLL 185683"],"award-info":[{"award-number":["PLL 185683"]}],"id":[{"id":"10.13039\/501100000024","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","award":["RGPIN-2021\u201304072"],"award-info":[{"award-number":["RGPIN-2021\u201304072"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,3,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Drug\u2013target interaction (DTI) prediction aims to identify interactions between drugs and protein targets. Deep learning can automatically learn discriminative features from drug and protein target representations for DTI prediction, but challenges remain, making it an open question. Existing approaches encode drugs and targets into features using deep learning models, but they often lack explanations for underlying interactions. Moreover, limited labeled DTIs in the chemical space can hinder model generalization.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We propose an interpretable nested graph neural network for DTI prediction (iNGNN-DTI) using pre-trained molecule and protein models. The analysis is conducted on graph data representing drugs and targets by using a specific type of nested graph neural network, in which the target graphs are created based on 3D structures using Alphafold2. This architecture is highly expressive in capturing substructures of the graph data. We use a cross-attention module to capture interaction information between the substructures of drugs and targets. To improve feature representations, we integrate features learned by models that are pre-trained on large unlabeled small molecule and protein datasets, respectively. We evaluate our model on three benchmark datasets, and it shows a consistent improvement on all baseline models in all datasets. We also run an experiment with previously unseen drugs or targets in the test set, and our model outperforms all of the baselines. Furthermore, the iNGNN-DTI can provide more insights into the interaction by visualizing the weights learned by the cross-attention module.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The source code of the algorithm is available at https:\/\/github.com\/syan1992\/iNGNN-DTI.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btae135","type":"journal-article","created":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T06:02:45Z","timestamp":1709791365000},"source":"Crossref","is-referenced-by-count":50,"title":["iNGNN-DTI: prediction of drug\u2013target interaction with interpretable nested graph neural network and pretrained molecule models"],"prefix":"10.1093","volume":"40","author":[{"given":"Yan","family":"Sun","sequence":"first","affiliation":[{"name":"Department of Biochemistry, Western University , London, ON, N6G 2V4, Canada"},{"name":"Department of Computer Science, University of Manitoba , Winnipeg, MB, R3T 2N2, Canada"},{"name":"Department of Computer Science, Western University , London, ON, N6G 2V4, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9174-1396","authenticated-orcid":false,"given":"Yan Yi","family":"Li","sequence":"additional","affiliation":[{"name":"Division of Biostatistics, University of Toronto , Toronto, ON, M5T 3M7, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7541-9127","authenticated-orcid":false,"given":"Carson K","family":"Leung","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Manitoba , Winnipeg, MB, R3T 2N2, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9546-2245","authenticated-orcid":false,"given":"Pingzhao","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Biochemistry, Western University , London, ON, N6G 2V4, Canada"},{"name":"Department of Computer Science, University of Manitoba , Winnipeg, MB, R3T 2N2, Canada"},{"name":"Department of Computer Science, Western University , London, ON, N6G 2V4, Canada"},{"name":"Division of Biostatistics, University of Toronto , Toronto, ON, M5T 3M7, Canada"},{"name":"Department of Oncology, Western University , London, ON, N6G 2V4, Canada"},{"name":"Department of Epidemiology and Biostatistics, Western University , London, ON, N6G 2V4, Canada"},{"name":"The Children\u2019s Health Research Institute, Lawson Health Research Institute , London, ON, N6A 4V2, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,3,6]]},"reference":[{"key":"2024032203521192600_btae135-B1","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":"2024032203521192600_btae135-B2","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/MSP.2017.2693418","article-title":"Geometric deep learning: going beyond Euclidean data","volume":"34","author":"Bronstein","year":"2017","journal-title":"IEEE Signal Process Mag"},{"key":"2024032203521192600_btae135-B3","first-page":"3469","author":"Chen","year":"2022"},{"key":"2024032203521192600_btae135-B4","doi-asserted-by":"crossref","first-page":"D1152","DOI":"10.1093\/nar\/gkaa861","article-title":"DockCoV2: a drug database against SARS-CoV-2","volume":"49","author":"Chen","year":"2021","journal-title":"Nucleic Acids Res"},{"key":"2024032203521192600_btae135-B5","doi-asserted-by":"crossref","first-page":"308","DOI":"10.1109\/TCBB.2010.93","article-title":"On position-specific scoring matrix for protein function prediction","volume":"8","author":"Cheol Jeong","year":"2010","journal-title":"IEEE\/ACM Trans Comput Biol Bioinf"},{"key":"2024032203521192600_btae135-B6","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":"2024032203521192600_btae135-B8","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1186\/1471-2105-11-283","article-title":"Optimal contact definition for reconstruction of contact maps","volume":"11","author":"Duarte","year":"2010","journal-title":"BMC Bioinformatics"},{"key":"2024032203521192600_btae135-B9","doi-asserted-by":"crossref","first-page":"3891","DOI":"10.1021\/acs.jcim.1c00203","article-title":"AutoDock vina 1.2.0: new docking methods, expanded force field, and python bindings","volume":"61","author":"Eberhardt","year":"2021","journal-title":"J Chem Inf Model"},{"key":"2024032203521192600_btae135-B10","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1016\/j.sbi.2006.04.004","article-title":"Multiple sequence alignment","volume":"16","author":"Edgar","year":"2006","journal-title":"Curr Opin Struct Biol"},{"key":"2024032203521192600_btae135-B11","first-page":"1263","author":"Gilmer","year":"2017"},{"key":"2024032203521192600_btae135-B12","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1186\/s13321-017-0209-z","article-title":"SimBoost: a read-across approach for predicting drug\u2013target binding affinities using gradient boosting machines","volume":"9","author":"He","year":"2017","journal-title":"J Cheminform"},{"key":"2024032203521192600_btae135-B13","doi-asserted-by":"crossref","first-page":"5545","DOI":"10.1093\/bioinformatics\/btaa1005","article-title":"DeepPurpose: a deep learning library for drug\u2013target interaction prediction","volume":"36","author":"Huang","year":"2021","journal-title":"Bioinformatics"},{"key":"2024032203521192600_btae135-B14","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":"2024032203521192600_btae135-B15","doi-asserted-by":"crossref","first-page":"015022","DOI":"10.1088\/2632-2153\/ac3ffb","article-title":"Chemformer: a pre-trained transformer for computational chemistry","volume":"3","author":"Irwin","year":"2022","journal-title":"Mach Learn Sci Technol"},{"key":"2024032203521192600_btae135-B16","doi-asserted-by":"crossref","first-page":"20701","DOI":"10.1039\/D0RA02297G","article-title":"Drug\u2013target affinity prediction using graph neural network and contact maps","volume":"10","author":"Jiang","year":"2020","journal-title":"RSC Adv"},{"key":"2024032203521192600_btae135-B17","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":"2024032203521192600_btae135-B18","author":"Kumar"},{"key":"2024032203521192600_btae135-B19","author":"Landrum","year":"2016"},{"key":"2024032203521192600_btae135-B20","author":"Lewis","year":"2020"},{"key":"2024032203521192600_btae135-B21","author":"Zitnik","year":"2018"},{"key":"2024032203521192600_btae135-B22","doi-asserted-by":"crossref","first-page":"114303","DOI":"10.1016\/j.jep.2021.114303","article-title":"Active components in ephedra Sinica Stapf disrupt the interaction between ACE2 and SARS-CoV-2 RBD: potent COVID-19 therapeutic agents","volume":"278","author":"Mei","year":"2021","journal-title":"J Ethnopharmacol"},{"key":"2024032203521192600_btae135-B23","doi-asserted-by":"crossref","first-page":"2677","DOI":"10.1093\/bioinformatics\/bty1036","article-title":"PconsC4: fast, accurate and hassle-free contact predictions","volume":"35","author":"Michel","year":"2019","journal-title":"Bioinformatics"},{"key":"2024032203521192600_btae135-B24","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1186\/s13000-020-01017-8","article-title":"Severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) and coronavirus disease 19 (COVID-19) \u2013 anatomic pathology perspective on current knowledge","volume":"15","author":"Mohanty","year":"2020","journal-title":"Diagn Pathol"},{"key":"2024032203521192600_btae135-B25","doi-asserted-by":"crossref","first-page":"1140","DOI":"10.1093\/bioinformatics\/btaa921","article-title":"Predicting drug\u2013target binding affinity with graph neural networks","volume":"37","author":"Nguyen","year":"2021","journal-title":"Bioinformatics"},{"key":"2024032203521192600_btae135-B26","doi-asserted-by":"crossref","first-page":"1131","DOI":"10.1038\/aps.2012.109","article-title":"Computational drug discovery","volume":"33","author":"Ou-Yang","year":"2012","journal-title":"Acta Pharmacol Sin"},{"key":"2024032203521192600_btae135-B27","doi-asserted-by":"crossref","first-page":"i821","DOI":"10.1093\/bioinformatics\/bty593","article-title":"DeepDTA: deep drug\u2013target binding affinity prediction","volume":"34","author":"\u00d6zt\u00fcrk","year":"2018","journal-title":"Bioinformatics"},{"key":"2024032203521192600_btae135-B28","doi-asserted-by":"crossref","first-page":"e2016239118","DOI":"10.1073\/pnas.2016239118","article-title":"Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences","volume":"118","author":"Rives","year":"2021","journal-title":"Proc Natl Acad Sci USA"},{"key":"2024032203521192600_btae135-B29","doi-asserted-by":"crossref","first-page":"103159","DOI":"10.1016\/j.jbi.2019.103159","article-title":"A comprehensive review of feature b methods for drug target interaction prediction","volume":"93","author":"Sachdev","year":"2019","journal-title":"J Biomed Inform"},{"key":"2024032203521192600_btae135-B30","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1038\/nchembio.1199","article-title":"Target identification and mechanism of action in chemical biology and drug discovery","volume":"9","author":"Schenone","year":"2013","journal-title":"Nat Chem Biol"},{"key":"2024032203521192600_btae135-B31","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems, Long Beach, CA, USA"},{"key":"2024032203521192600_btae135-B32","doi-asserted-by":"crossref","first-page":"905248","DOI":"10.3389\/fcimb.2022.905248","article-title":"Erythromycin estolate is a potent inhibitor against HCoV-OC43 by directly inactivating the virus particle","volume":"12","author":"Wang","year":"2022","journal-title":"Front Cell Infect Microbiol"},{"key":"2024032203521192600_btae135-B1941669","doi-asserted-by":"publisher","first-page":"1401","DOI":"10.1021\/acs.jproteome.6b00618","article-title":"Deep-learning-based drug-target interaction prediction","volume":"16","author":"Wen","year":"2017","journal-title":"J Proteome Res"},{"key":"2024032203521192600_btae135-B7928788","doi-asserted-by":"crossref","first-page":"e00519","DOI":"10.1128\/mbio.00519-22","article-title":"Metalloproteinase-dependent and TMPRSS2-independent cell surface entry pathway of SARS-cov-2 requires the furin cleavage site and the S2 domain of spike protein","volume":"13","author":"Yamamoto","year":"2022","journal-title":"mBio"},{"key":"2024032203521192600_btae135-B36926687","doi-asserted-by":"publisher","first-page":"4247","DOI":"10.1021\/acs.jpclett.1c00867","article-title":"ML-DTI: Mutual learning mechanism for interpretable drug-target interaction prediction","volume":"12","author":"Yang","year":"2021","journal-title":"J Phys Chem Lett"},{"key":"2024032203521192600_btae135-B63610973","doi-asserted-by":"publisher","first-page":"5847","DOI":"10.1002\/ptr.7245","article-title":"Pseudoephedrine and its derivatives antagonize wild and mutated severe acute respiratory syndrome-cov-2 viruses through blocking virus invasion and antiinflammatory effect","volume":"35","author":"Yu","year":"2021","journal-title":"Phytother Res"},{"key":"2024032203521192600_btae135-B5222777","article-title":"An attention free transformer","author":"Zhai","year":"2021","journal-title":"arXiv Preprint Arxiv:2105.14103"},{"key":"2024032203521192600_btae135-B15458873","first-page":"15734","volume-title":"Advances in neural information processing systems","author":"Zhang","year":"2021"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btae135\/56887325\/btae135.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/3\/btae135\/57056322\/btae135.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/3\/btae135\/57056322\/btae135.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,22]],"date-time":"2024-03-22T03:52:51Z","timestamp":1711079571000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btae135\/7623585"}},"subtitle":[],"editor":[{"given":"Arne","family":"Elofsson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,3,1]]},"references-count":37,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,3,4]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btae135","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,3,1]]},"published":{"date-parts":[[2024,3,1]]},"article-number":"btae135"}}