{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T12:33:56Z","timestamp":1786365236676,"version":"build-2736575974"},"reference-count":52,"publisher":"American Chemical Society (ACS)","issue":"15","license":[{"start":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T00:00:00Z","timestamp":1784764800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T00:00:00Z","timestamp":1784764800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T00:00:00Z","timestamp":1784764800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/100017380","name":"Science and Technology Foundation of Shenzhen City","doi-asserted-by":"publisher","award":["JCYJ20241202130212016"],"award-info":[{"award-number":["JCYJ20241202130212016"]}],"id":[{"id":"10.13039\/100017380","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62502050"],"award-info":[{"award-number":["62502050"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,8,10]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Predicting Drug\u2013Target Interactions (DTIs) is a crucial task in drug discovery. Recent advances in deep learning, particularly the application of Large Language Models (LLMs), have shown promise in encoding sequential information from SMILES strings and protein sequences. However, integrating these diverse modalities remains a challenge. In this paper, we propose TextDTI, a multimodal framework that simultaneously exploits sequential and structural representations. First, TextDTI utilizes Pretrained Language Models (PLMs) to generate functional description texts for proteins represented by their amino acid sequences, which includes biological functions, molecular mechanisms, and pathway involvement. Next, the generated texts and the SMILES sequences of drugs are encoded into corresponding feature representations by other separate LLMs. Third, drug and target characteristics are fused through convolutional and graph-based modules. Finally, unidentified drug-target interactions are classified using a multilayer perceptron neural network. We further enhance feature alignment through adversarial learning and contrastive loss, resulting in robust and high-performance DTI prediction. Experiments conducted on multiple data sets in both single-domain and cross-domain settings demonstrate that our model outperforms other baseline methods. The source code and data sets are available at https:\/\/github.com\/xiaoyiliu-usc\/TextDTI.<\/jats:p>","DOI":"10.1021\/acs.jcim.6c01435","type":"journal-article","created":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T09:44:38Z","timestamp":1784799878000},"page":"9698-9708","source":"Crossref","is-referenced-by-count":0,"title":["TextDTI: A Multimodal\nContext Representation Learning\nFramework for Drug\u2013Target Interaction Prediction"],"prefix":"10.1021","volume":"66","author":[{"given":"Jiaqi","family":"Deng","sequence":"first","affiliation":[{"name":"Southern University of Science and Technology , , 1068 Xueyuan Avenue , Nanshan, ,","place":["Shenzhen, China, 518055"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Senyu","family":"Tang","sequence":"additional","affiliation":[{"name":"Shenzhen University , , 3688 Nanhai Blvd, Nanshan , ,","place":["Shenzhen, China, 518055"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jijun","family":"Tang","sequence":"additional","affiliation":[{"name":"Shenzhen University of Advanced Technology , , 1068 Xueyuan Avenue , Nanshan, ,","place":["Shenzhen, China, 518107"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3435-2075","authenticated-orcid":true,"given":"Xiaoyi","family":"Liu","sequence":"additional","affiliation":[{"name":"Beijing University of Chinese Medicine , , 11 N Third Ring E Rd , Chaoyang, ,","place":["Beijing, China, 100013"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,7,23]]},"reference":[{"key":"2026081008095082300_cit1","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1093\/bfgp\/elab031","article-title":"Current status\nand future prospects of drug\u2013target interaction prediction","volume":"20","author":"Ru","year":"2021","journal-title":"Briefings Funct. Genomics"},{"key":"2026081008095082300_cit2","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1038\/nbt1284","article-title":"Relating protein pharmacology by\nligand chemistry","volume":"25","author":"Keiser","year":"2007","journal-title":"Nat. Biotechnol."},{"key":"2026081008095082300_cit3","doi-asserted-by":"publisher","first-page":"i232","DOI":"10.1093\/bioinformatics\/btn162","article-title":"Prediction\nof drug\u2013target interaction networks from the integration of\nchemical and genomic spaces","volume":"24","author":"Yamanishi","year":"2008","journal-title":"Bioinformatics"},{"key":"2026081008095082300_cit4","doi-asserted-by":"publisher","first-page":"696","DOI":"10.1093\/bib\/bbv066","article-title":"Drug\u2013target\ninteraction prediction: databases,\nweb servers and computational models","volume":"17","author":"Chen","year":"2016","journal-title":"Briefings\nBioinf."},{"key":"2026081008095082300_cit5","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/j.ymeth.2019.04.008","article-title":"Deep learning in bioinformatics:\nIntroduction, application, and perspective\nin the big data era","volume":"166","author":"Li","year":"2019","journal-title":"Methods"},{"key":"2026081008095082300_cit6","first-page":"14","article-title":"High-throughput screening for drug\ndiscovery","volume":"384","author":"Broach","year":"1996","journal-title":"Nature"},{"key":"2026081008095082300_cit7","doi-asserted-by":"publisher","first-page":"1728","DOI":"10.1021\/acs.jcim.8b00832","article-title":"Advances and challenges\nin computational target prediction","volume":"59","author":"Sydow","year":"2019","journal-title":"J. Chem.\nInf. Model."},{"key":"2026081008095082300_cit8","doi-asserted-by":"publisher","first-page":"4331","DOI":"10.3390\/ijms20184331","article-title":"Molecular docking:\nshifting paradigms in drug discovery","volume":"20","author":"Pinzi","year":"2019","journal-title":"Int. J.\nMol. Sci."},{"key":"2026081008095082300_cit9","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1007\/s13755-024-00287-6","article-title":"A review of\nmachine learning-based methods for predicting drug\u2013target interactions","volume":"12","author":"Shi","year":"2024","journal-title":"Health Inf. Sci. Syst."},{"key":"2026081008095082300_cit10","doi-asserted-by":"publisher","first-page":"131230","DOI":"10.1016\/j.eswa.2026.131230","article-title":"RefProGen:\nA Reference-Guided Molecular Generation Model with Protein-Ligand\nJoint Representation for Property-Aware Drug Design","volume":"309","author":"Liu","year":"2026","journal-title":"Expert Syst. Appl."},{"key":"2026081008095082300_cit11","doi-asserted-by":"publisher","first-page":"i821","DOI":"10.1093\/bioinformatics\/bty593","article-title":"DeepDTA: deep drug\u2013target\nbinding affinity prediction","volume":"34","author":"O\u0308ztu\u0308rk","year":"2018","journal-title":"Bioinformatics"},{"key":"2026081008095082300_cit12","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1093\/bioinformatics\/btaa921","article-title":"GraphDTA:\npredicting drug\u2013target binding affinity with graph neural networks","volume":"37","author":"Nguyen","year":"2021","journal-title":"Bioinformatics"},{"key":"2026081008095082300_cit13","doi-asserted-by":"publisher","first-page":"830","DOI":"10.1093\/bioinformatics\/btaa880","article-title":"MolTrans: molecular\ninteraction transformer for drug\u2013target interaction prediction","volume":"37","author":"Huang","year":"2021","journal-title":"Bioinformatics"},{"key":"2026081008095082300_cit14","doi-asserted-by":"publisher","DOI":"10.1002\/qub2.70014","article-title":"others\nLarge language models for bioinformatics","volume":"14","author":"Ruan","year":"2026","journal-title":"Quant.\nBiol."},{"key":"2026081008095082300_cit15","doi-asserted-by":"publisher","first-page":"19580","DOI":"10.1609\/aaai.v40i24.39037","article-title":"PharmaQA: Prompt-Based\nMolecular Representation Learning via Pharmacophore-Oriented Question\nAnswering","volume":"40","author":"Ai","year":"2026","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"2026081008095082300_cit16","doi-asserted-by":"publisher","first-page":"4486","DOI":"10.1109\/JBHI.2025.3530794","article-title":"The large\nlanguage models on biomedical\ndata analysis: a survey","volume":"29","author":"Lan","year":"2025","journal-title":"IEEE J. Biomed. Health\nInform."},{"key":"2026081008095082300_cit17","doi-asserted-by":"publisher","first-page":"11382","DOI":"10.1109\/TNNLS.2023.3260258","article-title":"Multiview\nsubspace clustering via\nlow-rank symmetric affinity graph","volume":"35","author":"Lan","year":"2024","journal-title":"IEEE Transact.\nNeural Networks Learn. Syst."},{"key":"2026081008095082300_cit18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3698192","article-title":"Contrastive clustering learning for multi-behavior\nrecommendation","volume":"43","author":"Lan","year":"2025","journal-title":"ACM Trans. Inf. Syst."},{"key":"2026081008095082300_cit19","doi-asserted-by":"publisher","first-page":"976","DOI":"10.1007\/s10618-014-0396-4","article-title":"Mining strong relevance between heterogeneous\nentities from unstructured biomedical data","volume":"29","author":"Ji","year":"2015","journal-title":"Data Min. Knowl. Discov."},{"key":"2026081008095082300_cit20","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.fmre.2025.01.004","article-title":"MULGONET:\nAn interpretable neural\nnetwork framework to integrate multi-omics data for cancer recurrence\nprediction and biomarker discovery","volume":"6","author":"Lan","year":"2025","journal-title":"Fundam.\nRes."},{"key":"2026081008095082300_cit21","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1109\/TCBB.2022.3144008","article-title":"CPInformer for efficient\nand robust compound-protein interaction\nprediction","volume":"20","author":"Hua","year":"2023","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinf."},{"key":"2026081008095082300_cit22","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1093\/bioinformatics\/btab715","article-title":"HyperAttentionDTI:\nimproving drug\u2013protein interaction prediction by sequence-based\ndeep learning with attention mechanism","volume":"38","author":"Zhao","year":"2022","journal-title":"Bioinformatics"},{"key":"2026081008095082300_cit23","doi-asserted-by":"publisher","first-page":"D506","DOI":"10.1093\/nar\/gky1049","article-title":"UniProt:\na worldwide hub of protein knowledge","volume":"47","author":"The UniProt Consortium.","year":"2019","journal-title":"Nucleic\nAcids Res."},{"key":"2026081008095082300_cit24","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2016239118","article-title":"Biological\nstructure and function emerge from scaling unsupervised learning to\n250 million protein sequences","volume":"118","author":"Rives","year":"2021","journal-title":"Proc. Natl. Acad.\nSci. U.S.A."},{"key":"2026081008095082300_cit25","doi-asserted-by":"crossref","unstructured":"Abdine, H.; Chatzianastasis, M.; Bouyioukos, C.; Vazirgiannis, M.\n          Prot2text: Multimodal\nprotein\u2019s function generation with gnns and transformers. In  Proceedings of the AAAI Conference on Artificial Intelligence, 2024; pp 10757\u201310765.","DOI":"10.1609\/aaai.v38i10.28948"},{"key":"2026081008095082300_cit26","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","article-title":"BioBERT: a pre-trained\nbiomedical\nlanguage representation model for biomedical text mining","volume":"36","author":"Lee","year":"2020","journal-title":"Bioinformatics"},{"key":"2026081008095082300_cit27","doi-asserted-by":"crossref","unstructured":"Wang, S.; Guo, Y.; Wang, Y.; Sun, H.; Huang, J.\n          Smiles-bert: large scale unsupervised pre-training\nfor molecular property prediction. In  Proceedings\nof the 10th ACM international conference on bioinformatics, computational\nbiology and health informatics, 2019; pp 429\u2013436.","DOI":"10.1145\/3307339.3342186"},{"key":"2026081008095082300_cit28","first-page":"4","article-title":"Rdkit documentation","volume":"1","author":"Landrum","year":"2013","journal-title":"Release"},{"key":"2026081008095082300_cit29","doi-asserted-by":"crossref","unstructured":"Chollet, F.\n          \n          Xception: Deep\nlearning with depthwise separable convolutions. In  Proceedings of the IEEE Conference on Computer Vision and Pattern\nRecognition, 2017; pp 1251\u20131258.","DOI":"10.1109\/CVPR.2017.195"},{"key":"2026081008095082300_cit30","doi-asserted-by":"publisher","first-page":"2302.00194","DOI":"10.48550\/arXiv.2302.00194","article-title":"Free lunch\nfor domain adversarial training: Environment\nlabel smoothing","author":"Zhang","year":"2023","journal-title":"arXiv"},{"key":"2026081008095082300_cit31","doi-asserted-by":"crossref","unstructured":"Wang, Z.; Wang, Z.; Yu, Z.; Deng, W.; Li, J.; Gao, T.; Wang, Z.\n          Domain\ngeneralization via shuffled style assembly for face anti-spoofing. In  Proceedings of the IEEE\/CVF Conference on Computer Vision\nand Pattern Recognition, 2022; pp 4123\u20134133.","DOI":"10.1109\/CVPR52688.2022.00409"},{"key":"2026081008095082300_cit32","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1007129","article-title":"DeepConv-DTI: Prediction of drug-target\ninteractions via deep learning with convolution on protein sequences","volume":"15","author":"Lee","year":"2019","journal-title":"PLoS Comput. Biol."},{"key":"2026081008095082300_cit33","doi-asserted-by":"publisher","first-page":"4406","DOI":"10.1093\/bioinformatics\/btaa524","article-title":"TransformerCPI: improving\ncompound\u2013protein interaction prediction by sequence-based deep\nlearning with self-attention mechanism and label reversal experiments","volume":"36","author":"Chen","year":"2020","journal-title":"Bioinformatics"},{"key":"2026081008095082300_cit34","doi-asserted-by":"publisher","first-page":"bbad082","DOI":"10.1093\/bib\/bbad082","article-title":"MCANet: shared-weight-based\nMultiheadCrossAttention network for drug\u2013target interaction\nprediction","volume":"24","author":"Bian","year":"2023","journal-title":"Briefings Bioinf."},{"key":"2026081008095082300_cit35","doi-asserted-by":"publisher","first-page":"120754","DOI":"10.1016\/j.eswa.2023.120754","article-title":"TripletMultiDTI:\nmultimodal representation learning in drug-target interaction prediction\nwith triplet loss function","volume":"232","author":"Dehghan","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"2026081008095082300_cit36","doi-asserted-by":"publisher","first-page":"btad056","DOI":"10.1093\/bioinformatics\/btad056","article-title":"MFR-DTA: a multi-functional\nand robust model for predicting drug\u2013target binding affinity\nand region","volume":"39","author":"Hua","year":"2023","journal-title":"Bioinformatics"},{"key":"2026081008095082300_cit37","doi-asserted-by":"publisher","first-page":"110887","DOI":"10.1016\/j.patcog.2024.110887","article-title":"MMDG-DTI:\nDrug\u2013target interaction prediction via multimodal feature fusion\nand domain generalization","volume":"157","author":"Hua","year":"2025","journal-title":"Pattern Recogn."},{"key":"2026081008095082300_cit38","doi-asserted-by":"publisher","first-page":"7112","DOI":"10.1109\/TPAMI.2021.3095381","article-title":"ProtTrans: Towards Cracking the Language\nof Life\u2019s\nCode through self-supervised Learning","volume":"44","author":"Elnaggar","year":"2022","journal-title":"IEEE\nTrans. Pattern Anal. Mach. Intell."},{"key":"2026081008095082300_cit39","doi-asserted-by":"publisher","first-page":"1711.05101","DOI":"10.48550\/arXiv.1711.05101","article-title":"Decoupled Weight Decay Regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv"},{"key":"2026081008095082300_cit40","doi-asserted-by":"publisher","first-page":"115516","DOI":"10.1016\/j.asoc.2026.115516","article-title":"Drug-target\nactivation\/Inhibition effects prediction based on signed networks\nand protein language model","volume":"201","author":"Lei","year":"2026","journal-title":"Appl. Soft Comput."},{"key":"2026081008095082300_cit41","doi-asserted-by":"publisher","first-page":"bbad393","DOI":"10.1093\/bib\/bbad393","article-title":"MVML-MPI: multi-view multi-label learning for metabolic pathway inference","volume":"24","author":"Liu","year":"2023","journal-title":"Briefings Bioinf."},{"key":"2026081008095082300_cit42","doi-asserted-by":"publisher","first-page":"btaf524","DOI":"10.1093\/bioinformatics\/btaf524","article-title":"HyperPhS: a pharmacophore-guided\nmultimodal representation framework for metabolic stability prediction\nthrough contrastive hypergraph learning","volume":"41","author":"Liu","year":"2025","journal-title":"Bioinformatics"},{"key":"2026081008095082300_cit43","doi-asserted-by":"crossref","unstructured":"Sun, M.; Ai, C.; Zhang, D.; Liu, X.; Meng, Q.; Ma, S.; Guo, F.\n          MolInterAct:\nMultiscale Cross-Modal Interaction for Robust Molecular Representation\nLearning. In  IEEE International Conference\non Bioinformatics and Biomedicine (BIBM). 2025, 2025; pp 1215\u20131220.","DOI":"10.1109\/BIBM66473.2025.11356075"},{"key":"2026081008095082300_cit44","unstructured":"Kang, C.; Liu, X.; Guo, F.\n          Retrointext: A multimodal large language\nmodel enhanced framework for retrosynthetic planning via in-context\nrepresentation learning. In  The Thirteenth\nInternational Conference on Learning Representations, 2025."},{"key":"2026081008095082300_cit45","doi-asserted-by":"publisher","first-page":"202509","DOI":"10.70401\/cbm.2025.0003","article-title":"MediHerb: A multi-modal enhanced\nframework for disease inference\nvia herbal knowledge","volume":"1","author":"Liu","year":"2025","journal-title":"Comput. Biomed."},{"key":"2026081008095082300_cit46","doi-asserted-by":"publisher","first-page":"100190","DOI":"10.1016\/j.metrad.2025.100190","article-title":"Prompt engineering\nfor healthcare: Methodologies and applications","author":"Wang","year":"2025","journal-title":"Meta-Radiol."},{"key":"2026081008095082300_cit47","doi-asserted-by":"publisher","first-page":"10261","DOI":"10.1039\/d3ra00281k","article-title":"others 3DProtDTA: a deep learning model for\ndrug-target affinity prediction based on residue-level protein graphs","volume":"13","author":"Voitsitskyi","year":"2023","journal-title":"RSC Adv."},{"key":"2026081008095082300_cit48","doi-asserted-by":"publisher","first-page":"7407","DOI":"10.1038\/s41467-024-51844-2","article-title":"Fine-tuning protein language models\nboosts predictions across diverse tasks","volume":"15","author":"Schmirler","year":"2024","journal-title":"Nat.\nCommun."},{"key":"2026081008095082300_cit49","doi-asserted-by":"publisher","first-page":"1403","DOI":"10.1038\/s42256-025-01088-6","article-title":"Boosting the predictive\npower of protein representations with a corpus of text annotations","volume":"7","author":"Duan","year":"2025","journal-title":"Nat. Mach. Intell."},{"key":"2026081008095082300_cit50","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1093\/bioinformatics\/btab643","article-title":"Structure-aware\nprotein\u2013protein interaction site prediction using deep graph\nconvolutional network","volume":"38","author":"Yuan","year":"2021","journal-title":"Bioinformatics"},{"key":"2026081008095082300_cit51","doi-asserted-by":"publisher","first-page":"bbad079","DOI":"10.1093\/bib\/bbad079","article-title":"MHTAN-DTI:\nMetapath-based hierarchical transformer and attention network for\ndrug\u2013target interaction prediction","volume":"24","author":"Zhang","year":"2023","journal-title":"Briefings\nBioinf."},{"key":"2026081008095082300_cit52","doi-asserted-by":"publisher","first-page":"btaf445","DOI":"10.1093\/bioinformatics\/btaf445","article-title":"GS-DTI: a\ngraph-structure-aware framework leveraging large language models for\ndrug\u2013target interaction prediction","volume":"41","author":"Yu","year":"2025","journal-title":"Bioinformatics"}],"container-title":["Journal of Chemical Information\nand Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c01435","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/15\/9698\/66214030\/acs.jcim.6c01435.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/15\/9698\/66214030\/acs.jcim.6c01435.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T12:24:19Z","timestamp":1786364659000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article\/66\/15\/9698\/5230013\/TextDTI-A-Multimodal-Context-Representation"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,23]]},"references-count":52,"journal-issue":{"issue":"15","published-online":{"date-parts":[[2026,7,23]]},"published-print":{"date-parts":[[2026,8,10]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.6c01435","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,23]]}}}