{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T05:12:40Z","timestamp":1773465160350,"version":"3.50.1"},"reference-count":42,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:00:00Z","timestamp":1761004800000},"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. Bioinform."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Accurately predicting drug-target interactions (DTIs) is crucial for accelerating drug discovery and repurposing. Despite recent advances in deep learning-based methods, challenges remain in effectively capturing the complex relationships between drugs and targets while incorporating prior biological knowledge.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We introduce a novel framework that combines graph neural networks with knowledge integration for DTI prediction. Our approach learns representations from molecular structures and protein sequences through a customized graph-based message passing scheme. We integrate domain knowledge from biomedical ontologies and databases using a knowledge-based regularization strategy to infuse biological context into the learned representations.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>We evaluated our model on multiple benchmark datasets, achieving an average AUC of 0.98 and an average AUPR of 0.89, surpassing existing state-of-the-art methods by a considerable margin. Visualization of learned attention weights identified salient molecular substructures and protein motifs driving the predicted interactions, demonstrating model interpretability.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>We validated the practical utility by predicting novel DTIs for FDA-approved drugs and experimentally confirming a high proportion of predictions. Our framework offers a powerful and interpretable solution for DTI prediction with the potential to substantially accelerate the identification of new drug candidates and therapeutic targets.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fbinf.2025.1649337","type":"journal-article","created":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T06:18:29Z","timestamp":1761027509000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Enhancing drug-target interaction prediction with graph representation learning and knowledge-based regularization"],"prefix":"10.3389","volume":"5","author":[{"given":"Qihuan","family":"Yao","sequence":"first","affiliation":[]},{"given":"Zhen","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Ye","family":"Cao","sequence":"additional","affiliation":[]},{"given":"Huijing","family":"Hu","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2025,10,21]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"105194","DOI":"10.1016\/j.meegid.2021.105194","article-title":"Computational identification of plasmodium falciparum rna pseudouridylate synthase as a viable drug target, its physicochemical properties, 3d structure prediction and prediction of potential inhibitors","volume":"97","author":"Afolabi","year":"2022","journal-title":"Infect. Genet. Evol."},{"key":"B2","doi-asserted-by":"publisher","first-page":"iyad031","DOI":"10.1093\/genetics\/iyad031","article-title":"The gene ontology knowledgebase in 2023","volume":"224","author":"Aleksander","year":"2023","journal-title":"Genetics"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00117-024-01414-w","article-title":"Diffusion tensor imaging features of white matter pathways in the brain after covid-19 infection","author":"Balsak","year":"2025","journal-title":"Die Radiol."},{"key":"B4","doi-asserted-by":"publisher","first-page":"107536","DOI":"10.1016\/j.compbiolchem.2021.107536","article-title":"Efficient machine learning model for predicting drug-target interactions with case study for covid-19","volume":"93","author":"El-Behery","year":"2021","journal-title":"Comput. Biol. Chem."},{"key":"B5","doi-asserted-by":"publisher","first-page":"D587","DOI":"10.1093\/nar\/gkac963","article-title":"Kegg for taxonomy-based analysis of pathways and genomes","volume":"51","author":"Kanehisa","year":"2023","journal-title":"Nucleic Acids Res."},{"key":"B6","doi-asserted-by":"publisher","first-page":"107707","DOI":"10.1016\/j.compbiolchem.2022.107707","article-title":"Dtip-tc2a: an analytical framework for drug-target interactions prediction methods","volume":"99","author":"Keyvanpour","year":"2022","journal-title":"Comput. Biol. Chem."},{"key":"B7","doi-asserted-by":"publisher","first-page":"e217","DOI":"10.1002\/cpz1.217","article-title":"Exploring chemical information in pubchem","volume":"1","author":"Kim","year":"2021","journal-title":"Curr. Protoc."},{"key":"B8","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1002\/9783527830497.ch2","article-title":"Pubchem: a large-scale public chemical database for drug discovery","volume-title":"Open access databases and datasets for drug discovery","author":"Kim","year":"2024"},{"key":"B9","doi-asserted-by":"publisher","first-page":"D1265","DOI":"10.1093\/nar\/gkad976","article-title":"Drugbank 6.0: the drugbank knowledgebase for 2024","volume":"52","author":"Knox","year":"2024","journal-title":"Nucleic Acids Res."},{"key":"B10","doi-asserted-by":"publisher","first-page":"D1075","DOI":"10.1093\/nar\/gkv1075","article-title":"The sider database of drugs and side effects","volume":"44","author":"Kuhn","year":"2016","journal-title":"Nucleic Acids Res."},{"key":"B11","doi-asserted-by":"publisher","first-page":"10","DOI":"10.48101\/ujms.v127.8562","article-title":"Can diffusion tensor imaging (dti) outperform standard magnetic resonance imaging (mri) investigations in post-covid-19 autoimmune encephalitis?","volume":"127","author":"Latini","year":"2022","journal-title":"Upsala J. Med. Sci."},{"key":"B12","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1117\/12.2274140","article-title":"Machine learning for the assessment of alzheimer\u2019s disease through dti","volume":"10396","author":"Lella","year":"2017","journal-title":"Appl. digital image Process. XL"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1444795","DOI":"10.3389\/fneur.2024.1444795","article-title":"Dominating alzheimer\u2019s disease diagnosis with deep learning on smri and dti-md","volume":"15","author":"Li","year":"2024","journal-title":"Front. Neurology"},{"key":"B14","doi-asserted-by":"publisher","first-page":"103882","DOI":"10.1016\/j.arabjc.2022.103882","article-title":"In search of novel inhibitors of anti-cancer drug target fibroblast growth factor receptors: insights from virtual screening, molecular docking, and molecular dynamics","volume":"15","author":"Mahfuz","year":"2022","journal-title":"Arabian J. Chem."},{"key":"B15","doi-asserted-by":"publisher","first-page":"107135","DOI":"10.1016\/j.asoc.2021.107135","article-title":"Drug repositioning based on similarity constrained probabilistic matrix factorization: Covid-19 as a case study","volume":"103","author":"Meng","year":"2021","journal-title":"Appl. Soft Comput."},{"key":"B16","doi-asserted-by":"publisher","first-page":"5706","DOI":"10.1039\/d3cs00056g","article-title":"Small-molecule probes from bench to bedside: advancing molecular analysis of drug\u2013target interactions toward precision medicine","volume":"52","author":"Pan","year":"2023","journal-title":"Chem. Soc. Rev."},{"key":"B17","doi-asserted-by":"publisher","first-page":"711","DOI":"10.1109\/jbhi.2024.3476120","article-title":"Dti-mvsca: an anti-over-smoothing multi-view framework with negative sample selection for predicting drug-target interactions","volume":"29","author":"Peng","year":"2024","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"B18","doi-asserted-by":"publisher","first-page":"4617","DOI":"10.1111\/bph.15919","article-title":"Formylpeptide receptor 2: nomenclature, structure, signalling and translational perspectives: iuphar review 35","volume":"179","author":"Qin","year":"2022","journal-title":"Br. J. Pharmacol."},{"key":"B19","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1186\/s12967-023-03876-3","article-title":"Deepmpf: deep learning framework for predicting drug\u2013target interactions based on multi-modal representation with meta-path semantic analysis","volume":"21","author":"Ren","year":"2023","journal-title":"J. Transl. Med."},{"key":"B20","doi-asserted-by":"publisher","first-page":"24387","DOI":"10.1109\/access.2024.3364545","article-title":"Classification study of alzheimer\u2019s disease based on self-attention mechanism and dti imaging using gcn","volume":"12","author":"Sang","year":"2024","journal-title":"IEEE Access"},{"key":"B21","doi-asserted-by":"publisher","first-page":"bbac109","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":"Briefings Bioinforma."},{"key":"B22","doi-asserted-by":"publisher","first-page":"5316","DOI":"10.1016\/j.csbj.2022.08.070","article-title":"Protein\u2013protein interaction prediction with deep learning: a comprehensive review","volume":"20","author":"Soleymani","year":"2022","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"B23","doi-asserted-by":"publisher","first-page":"1324","DOI":"10.1016\/j.csbj.2023.01.028","article-title":"Protinteract: a deep learning framework for predicting protein\u2013protein interactions","volume":"21","author":"Soleymani","year":"2023","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"B24","doi-asserted-by":"publisher","first-page":"e1568","DOI":"10.1002\/wcms.1568","article-title":"Machine learning in drug design: use of artificial intelligence to explore the chemical structure\u2013biological activity relationship","volume":"12","author":"Staszak","year":"2022","journal-title":"Wiley Interdiscip. Rev. Comput. Mol. Sci."},{"key":"B25","doi-asserted-by":"publisher","first-page":"86","DOI":"10.9781\/ijimai.2022.11.002","article-title":"Drug target interaction prediction using machine learning techniques\u2013a review","volume":"8","author":"Suruliandi","year":"2024"},{"key":"B26","doi-asserted-by":"publisher","first-page":"D638","DOI":"10.1093\/nar\/gkac1000","article-title":"The string database in 2023: protein\u2013protein association networks and functional enrichment analyses for any sequenced genome of interest","volume":"51","author":"Szklarczyk","year":"2023","journal-title":"Nucleic Acids Res."},{"key":"B27","doi-asserted-by":"publisher","first-page":"117017","DOI":"10.1016\/j.neuroimage.2020.117017","article-title":"Deepdti: High-fidelity six-direction diffusion tensor imaging using deep learning","volume":"219","author":"Tian","year":"2020","journal-title":"NeuroImage"},{"key":"B28","doi-asserted-by":"publisher","first-page":"740382","DOI":"10.3389\/fmicb.2022.740382","article-title":"Discovery of potential therapeutic drugs for covid-19 through logistic matrix factorization with kernel diffusion","volume":"13","author":"Tian","year":"2022","journal-title":"Front. Microbiol."},{"key":"B29","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1093\/bioinformatics\/bty543","article-title":"Neodti: neural integration of neighbor information from a heterogeneous network for discovering new drug\u2013target interactions","volume":"35","author":"Wan","year":"2019","journal-title":"Bioinformatics"},{"key":"B30","doi-asserted-by":"publisher","first-page":"846","DOI":"10.1007\/s10489-021-02454-8","article-title":"Kg-dti: a knowledge graph based deep learning method for drug-target interaction predictions and alzheimer\u2019s disease drug repositions","volume":"52","author":"Wang","year":"","journal-title":"Appl. Intell."},{"key":"B31","doi-asserted-by":"publisher","first-page":"3780","DOI":"10.3390\/ijms23073780","article-title":"Ssgraphcpi: a novel model for predicting compound-protein interactions based on deep learning","volume":"23","author":"Wang","year":"","journal-title":"Int. J. Mol. Sci."},{"key":"B32","doi-asserted-by":"publisher","first-page":"102836","DOI":"10.1016\/j.inffus.2024.102836","article-title":"Autogrn: an adaptive multi-channel graph recurrent joint optimization network with copula-based dependency modeling for spatio-temporal fusion in electrical power systems","volume":"117","author":"Wang","year":"","journal-title":"Inf. Fusion"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/tnse.2025.3590975","article-title":"Rofed-llm: robust federated learning for large language models in adversarial wireless environments","author":"Wang","year":"","journal-title":"IEEE Trans. Netw. Sci. Eng."},{"key":"B34","doi-asserted-by":"publisher","first-page":"112208","DOI":"10.1016\/j.knosys.2024.112208","article-title":"Federated semi-supervised representation augmentation with cross-institutional knowledge transfer for healthcare collaboration","volume":"300","author":"Yin","year":"2024","journal-title":"Knowledge-Based Syst."},{"key":"B35","doi-asserted-by":"publisher","first-page":"D1180","DOI":"10.1093\/nar\/gkad1004","article-title":"The chembl database in 2023: a drug discovery platform spanning multiple bioactivity data types and time periods","volume":"52","author":"Zdrazil","year":"2024","journal-title":"Nucleic Acids Res."},{"key":"B36","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1186\/s12859-023-05497-5","article-title":"Dgdta: dynamic graph attention network for predicting drug\u2013target binding affinity","volume":"24","author":"Zhai","year":"2023","journal-title":"BMC Bioinforma."},{"key":"B37","doi-asserted-by":"publisher","first-page":"105214","DOI":"10.1016\/j.compbiomed.2022.105214","article-title":"Deepmgt-dti: transformer network incorporating multilayer graph information for drug\u2013target interaction prediction","volume":"142","author":"Zhang","year":"","journal-title":"Comput. Biol. Med."},{"key":"B38","doi-asserted-by":"publisher","first-page":"102327","DOI":"10.1016\/j.sbi.2021.102327","article-title":"Graph neural network approaches for drug-target interactions","volume":"73","author":"Zhang","year":"","journal-title":"Curr. Opin. Struct. Biol."},{"key":"B39","doi-asserted-by":"publisher","first-page":"844","DOI":"10.1016\/j.future.2024.06.046","article-title":"Mvg-nrlmf: Multi-view graph neighborhood regularized logistic matrix factorization for identifying drug\u2013target interaction","volume":"160","author":"Zhang","year":"2024","journal-title":"Future Gener. Comput. Syst."},{"key":"B40","doi-asserted-by":"publisher","first-page":"btad451","DOI":"10.1093\/bioinformatics\/btad451","article-title":"Igrldti: an improved graph representation learning method for predicting drug\u2013target interactions over heterogeneous biological information network","volume":"39","author":"Zhao","year":"2023","journal-title":"Bioinformatics"},{"key":"B41","doi-asserted-by":"publisher","first-page":"4485","DOI":"10.1093\/bioinformatics\/btab473","article-title":"Multidti: drug\u2013target interaction prediction based on multi-modal representation learning to bridge the gap between new chemical entities and known heterogeneous network","volume":"37","author":"Zhou","year":"2021","journal-title":"Bioinformatics"},{"key":"B42","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1016\/j.ymeth.2024.01.018","article-title":"Gsl-dti: graph structure learning network for drug-target interaction prediction","volume":"223","author":"Zixuan","year":"2024","journal-title":"Methods"}],"container-title":["Frontiers in Bioinformatics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbinf.2025.1649337\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T06:18:30Z","timestamp":1761027510000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbinf.2025.1649337\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,21]]},"references-count":42,"alternative-id":["10.3389\/fbinf.2025.1649337"],"URL":"https:\/\/doi.org\/10.3389\/fbinf.2025.1649337","relation":{},"ISSN":["2673-7647"],"issn-type":[{"value":"2673-7647","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,21]]},"article-number":"1649337"}}