{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:15:20Z","timestamp":1774415720035,"version":"3.50.1"},"reference-count":39,"publisher":"Oxford University Press (OUP)","issue":"Supplement_1","license":[{"start":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T00:00:00Z","timestamp":1752537600000},"content-version":"vor","delay-in-days":14,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000057","name":"National Institute of General Medical Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000057","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R35GM133657"],"award-info":[{"award-number":["R35GM133657"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100008973","name":"University of North Texas","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008973","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,7,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>The accurate prediction of drug\u2013target interactions (DTI) is a crucial step in drug discovery, providing a foundation for identifying novel therapeutics. Traditional drug development is both costly and time-consuming, often spanning over a decade. Computational approaches help narrow the pool of compound candidates, offering significant starting points for experimental validation. In this study, we propose a Top-DTI framework for predicting DTI by integrating topological data analysis (TDA) with large language models (LLMs). Top-DTI leverages persistent homology to extract topological features from protein contact maps and drug molecular images. Simultaneously, protein and drug LLMs generate semantically rich embeddings that capture sequential and contextual information from protein sequences and drug SMILES strings. By combining these complementary features, Top-DTI enhances predictive performance and robustness.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Experimental results on the public BioSNAP and Human DTI benchmark datasets demonstrate that the proposed Top-DTI model outperforms state-of-the-art approaches across multiple evaluation metrics, including AUROC, AUPRC, sensitivity, and specificity. Furthermore, the Top-DTI model achieves superior performance in the challenging cold-split scenario, where the test and validation sets contain drugs or targets absent from the training set. This setting simulates real-world scenarios and highlights the robustness of the model. Notably, incorporating topological features alongside LLM embeddings significantly improves predictive performance, underscoring the value of integrating structural and sequence-based representations.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The data and source code of Top-DTI are available at https:\/\/github.com\/bozdaglab\/Top_DTI under the Creative Commons Attribution NonCommercial 4.0 International Public License.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaf183","type":"journal-article","created":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T13:02:02Z","timestamp":1752584522000},"page":"i133-i141","source":"Crossref","is-referenced-by-count":2,"title":["Top-DTI: integrating topological deep learning and large language models for drug\u2013target interaction prediction"],"prefix":"10.1093","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1595-5681","authenticated-orcid":false,"given":"Muhammed","family":"Talo","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, University of North Texas , Denton 76207, TX,","place":["United States"]},{"name":"BioDiscovery Institute, University of North Texas , Denton, TX 76207,","place":["United States"]},{"name":"Center for Computational Life Sciences, University of North Texas , Denton, TX 76207,","place":["United States"]}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4813-4310","authenticated-orcid":false,"given":"Serdar","family":"Bozdag","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of North Texas , Denton 76207, TX,","place":["United States"]},{"name":"BioDiscovery Institute, University of North Texas , Denton, TX 76207,","place":["United States"]},{"name":"Center for Computational Life Sciences, University of North Texas , Denton, TX 76207,","place":["United States"]},{"name":"Department of Mathematics, University of North Texas , Denton, TX 76207,","place":["United States"]}]}],"member":"286","published-online":{"date-parts":[[2025,7,15]]},"reference":[{"key":"2025071509015706600_btaf183-B1","author":"Ahmad","year":"2022"},{"key":"2025071509015706600_btaf183-B2","doi-asserted-by":"crossref","first-page":"e0284820","DOI":"10.1371\/journal.pone.0284820","article-title":"Genomics data analysis via spectral shape and topology","volume":"18","author":"Am\u00e9zquita","year":"2023","journal-title":"PLoS One"},{"key":"2025071509015706600_btaf183-B3","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":"Nature Mach Intel"},{"key":"2025071509015706600_btaf183-B4","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1146\/annurev-orgpsych-032414-111335","article-title":"ESM 2.0: state of the art and future potential of experience sampling methods in organizational research","volume":"2","author":"Beal","year":"2015","journal-title":"Annu Rev Organ Psychol Organ Behav"},{"key":"2025071509015706600_btaf183-B5","first-page":"77","article-title":"Statistical topological data analysis using persistence landscapes","volume":"16","author":"Bubenik","year":"2015","journal-title":"J Mach Learn Res"},{"key":"2025071509015706600_btaf183-B6","doi-asserted-by":"crossref","first-page":"4406","DOI":"10.1093\/bioinformatics\/btaa524","article-title":"TransformerCPI: improving compound\u2013protein interaction prediction by sequence-based deep learning with self-attention mechanism and label reversal experiments","volume":"36","author":"Chen","year":"2020","journal-title":"Bioinformatics"},{"key":"2025071509015706600_btaf183-B7","author":"Coskunuzer","year":"2024"},{"key":"2025071509015706600_btaf183-B8","first-page":"27978","article-title":"ToDD: topological compound fingerprinting in computer-aided drug discovery","volume":"35","author":"Demir","year":"2022","journal-title":"Advances In Neural Information Processing Systems"},{"key":"2025071509015706600_btaf183-B9","doi-asserted-by":"crossref","first-page":"7112","DOI":"10.1109\/TPAMI.2021.3095381","article-title":"Prottrans: toward understanding the language of life through self-supervised learning","volume":"44","author":"Elnaggar","year":"2021","journal-title":"IEEE Transact Pattern Anal Mach Intel"},{"key":"2025071509015706600_btaf183-B10","doi-asserted-by":"crossref","first-page":"1297","DOI":"10.1038\/s42256-023-00740-3","article-title":"Neural scaling of deep chemical models","volume":"5","author":"Frey","year":"2023","journal-title":"Nature Mach Intel"},{"key":"2025071509015706600_btaf183-B11","author":"Glatt","year":"2023"},{"key":"2025071509015706600_btaf183-B12","article-title":"Inductive representation learning on large graphs","author":"Hamilton"},{"key":"2025071509015706600_btaf183-B13","doi-asserted-by":"crossref","first-page":"770","DOI":"10.3389\/fphar.2020.00770","article-title":"Accelerating therapeutics for opportunities in medicine: a paradigm shift in drug discovery","volume":"11","author":"Hinkson","year":"2020","journal-title":"Front Pharmacol"},{"key":"2025071509015706600_btaf183-B14","doi-asserted-by":"crossref","first-page":"bbac446","DOI":"10.1093\/bib\/bbac446","article-title":"CoaDTI: multi-modal co-attention based framework for drug\u2013target interaction annotation","volume":"23","author":"Huang","year":"2022","journal-title":"Brief Bioinformat"},{"key":"2025071509015706600_btaf183-B15","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":"2025071509015706600_btaf183-B16","doi-asserted-by":"crossref","first-page":"1710","DOI":"10.3390\/pharmaceutics14081710","article-title":"Fine-tuning of BERT model to accurately predict drug\u2013target interactions","volume":"14","author":"Kang","year":"2022","journal-title":"Pharmaceutics"},{"key":"2025071509015706600_btaf183-B17","first-page":"4","article-title":"Rdkit documentation","volume":"1","author":"Landrum","year":"2013","journal-title":"Release"},{"key":"2025071509015706600_btaf183-B18","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1186\/s13321-024-00808-1","article-title":"DLM-DTI: a dual language model for the prediction of drug-target interaction with hint-based learning","volume":"16","author":"Lee","year":"2024","journal-title":"J Cheminfo"},{"key":"2025071509015706600_btaf183-B19","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":"2025071509015706600_btaf183-B20","doi-asserted-by":"crossref","first-page":"i221","DOI":"10.1093\/bioinformatics\/btv256","article-title":"Improving compound\u2013protein interaction prediction by building up highly credible negative samples","volume":"31","author":"Liu","year":"2015","journal-title":"Bioinformatics"},{"key":"2025071509015706600_btaf183-B21","doi-asserted-by":"crossref","first-page":"btae693","DOI":"10.1093\/bioinformatics\/btae693","article-title":"Accurate and transferable drug\u2013target interaction prediction with DrugLAMP","volume":"40","author":"Luo","year":"2024","journal-title":"Bioinformatics"},{"key":"2025071509015706600_btaf183-B22","doi-asserted-by":"crossref","first-page":"1140","DOI":"10.1093\/bioinformatics\/btaa921","article-title":"GraphDTA: predicting drug\u2013target binding affinity with graph neural networks","volume":"37","author":"Nguyen","year":"2021","journal-title":"Bioinformatics"},{"key":"2025071509015706600_btaf183-B23","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":"2025071509015706600_btaf183-B24","doi-asserted-by":"crossref","first-page":"6684","DOI":"10.1021\/acs.jcim.4c00957","article-title":"MGNDTI: a drug-target interaction prediction framework based on multimodal representation learning and the gating mechanism","volume":"64","author":"Peng","year":"2024","journal-title":"J Chem Info Model"},{"key":"2025071509015706600_btaf183-B25","doi-asserted-by":"publisher","first-page":"2020","DOI":"10.1101\/2020.12.15.422761","article-title":"Transformer protein language models are unsupervised structure learners","author":"Rao","year":"2020","journal-title":"Biorxiv"},{"key":"2025071509015706600_btaf183-B26","doi-asserted-by":"crossref","first-page":"693","DOI":"10.1093\/bioinformatics\/btaa858","article-title":"MDeePred: novel multi-channel protein featurization for deep learning-based binding affinity prediction in drug discovery","volume":"37","author":"Rifaioglu","year":"2021","journal-title":"Bioinformatics"},{"key":"2025071509015706600_btaf183-B27","first-page":"37","article-title":"Unlocking the potential of generative artificial intelligence in drug discovery","author":"Romanelli","year":"2024","journal-title":"Appl Generat AI"},{"key":"2025071509015706600_btaf183-B28","doi-asserted-by":"crossref","first-page":"1256","DOI":"10.1038\/s42256-022-00580-7","article-title":"Large-scale chemical language representations capture molecular structure and properties","volume":"4","author":"Ross","year":"2022","journal-title":"Nature Mach Intel"},{"key":"2025071509015706600_btaf183-B29","doi-asserted-by":"crossref","first-page":"1243","DOI":"10.1007\/s40273-021-01065-y","article-title":"How much does it cost to research and develop a new drug? A systematic review and assessment","volume":"39","author":"Schlander","year":"2021","journal-title":"Pharmacoeconomics"},{"key":"2025071509015706600_btaf183-B30","doi-asserted-by":"crossref","first-page":"e2220778120","DOI":"10.1073\/pnas.2220778120","article-title":"Contrastive learning in protein language space predicts interactions between drugs and protein targets","volume":"120","author":"Singh","year":"2023","journal-title":"Proceed Nat Acad Sci"},{"key":"2025071509015706600_btaf183-B31","doi-asserted-by":"crossref","first-page":"2188","DOI":"10.1039\/c2mb25093d","article-title":"A ligand-based approach for the in silico discovery of multi-target inhibitors for proteins associated with HIV infection","volume":"8","author":"Speck-Planche","year":"2012","journal-title":"Molecul BioSyst"},{"key":"2025071509015706600_btaf183-B32","doi-asserted-by":"crossref","first-page":"1610","DOI":"10.1109\/BIBM58861.2023.10385822","article-title":"Histopathological cancer detection with topological signatures","author":"Yadav","year":"2023","journal-title":"2023 IEEE International Conference On Bioinformatics And Biomedicine (BIBM)"},{"key":"2025071509015706600_btaf183-B33","doi-asserted-by":"crossref","first-page":"i232","DOI":"10.1093\/bioinformatics\/btn162","article-title":"Prediction of drug\u2013target interaction networks from the integration of chemical and genomic spaces","volume":"24","author":"Yamanishi","year":"2008","journal-title":"Bioinformatics"},{"key":"2025071509015706600_btaf183-B34","doi-asserted-by":"crossref","first-page":"1053","DOI":"10.1093\/bib\/bbaa422","article-title":"Ligand-based approach for predicting drug targets and for virtual screening against COVID-19","volume":"22","author":"Yang","year":"2021","journal-title":"Briefing Bioinformat"},{"key":"2025071509015706600_btaf183-B35","doi-asserted-by":"crossref","first-page":"655","DOI":"10.1093\/bioinformatics\/btab715","article-title":"HyperAttentionDTI: improving drug\u2013protein interaction prediction by sequence-based deep learning with attention mechanism","volume":"38","author":"Zhao","year":"2022","journal-title":"Bioinformatics"},{"key":"2025071509015706600_btaf183-B36","author":"Zheng","year":"2018"},{"key":"2025071509015706600_btaf183-B37","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1007\/s10462-024-10710-9","article-title":"Topological deep learning: a review of an emerging paradigm","volume":"57","author":"Zia","year":"2024","journal-title":"Artificial Intelligence Review"},{"key":"2025071509015706600_btaf183-B38","author":"Zitnik","year":"2018"},{"key":"2025071509015706600_btaf183-B39","doi-asserted-by":"crossref","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":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/Supplement_1\/i133\/63745334\/btaf183.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/Supplement_1\/i133\/63745334\/btaf183.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T13:02:06Z","timestamp":1752584526000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/41\/Supplement_1\/i133\/8199357"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,1]]},"references-count":39,"journal-issue":{"issue":"Supplement_1","published-print":{"date-parts":[[2025,7,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaf183","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,7]]},"published":{"date-parts":[[2025,7,1]]}}}