{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T22:56:26Z","timestamp":1771973786402,"version":"3.50.1"},"reference-count":47,"publisher":"Oxford University Press (OUP)","issue":"10","license":[{"start":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T00:00:00Z","timestamp":1759190400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2025M771637"],"award-info":[{"award-number":["2025M771637"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the Postdoctoral Fellowship Program of CPSF","award":["GZB20250417"],"award-info":[{"award-number":["GZB20250417"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2682025CX105"],"award-info":[{"award-number":["2682025CX105"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Computational prediction of drug\u2013target affinity (DTA) plays a critical role in modern drug discovery. However, the limited interpretability of traditional deep learning models and the heterogeneity of multimodal data from compounds and proteins hinder their reliability in practical drug development applications.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We propose a novel Uncertainty-aware Multimodal Representation Learning (UAMRL) framework to address these challenges. UAMRL employs a dual-stream encoder to learn cross-modal association mappings between drugs and targets in a latent space and integrates heterogeneous information from different modalities. Moreover, an uncertainty quantification mechanism based on the Normal-Inverse-Gamma distribution is introduced to model the reliability of heterogeneous information and suppress less trustworthy contributions during fusion. Experiments show that UAMRL achieves superior predictive accuracy on multiple public DTA datasets, improving both prediction performance and decision transparency.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>The source code is available at https:\/\/github.com\/Astraea2xu\/UAMRL.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaf512","type":"journal-article","created":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T11:56:12Z","timestamp":1758974172000},"source":"Crossref","is-referenced-by-count":1,"title":["UAMRL: multi-granularity uncertainty-aware multimodal representation learning for drug-target affinity prediction"],"prefix":"10.1093","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6141-4022","authenticated-orcid":false,"given":"Wenzhe","family":"Xu","sequence":"first","affiliation":[{"name":"School of Computer and Software Engineering, Xihua University , Chengdu 610039,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaorong","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Software Engineering, Southwest Petroleum University , Chengdu 610500,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence, Southwest Jiaotong University , Chengdu 611756,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Design, Southwest Jiaotong University , Chengdu 611756,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dongfeng","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Computing and Artificial Intelligence, Southwest Jiaotong University , Chengdu 611756,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liansong","family":"Zong","sequence":"additional","affiliation":[{"name":"School of Computer and Software Engineering, Xihua University , Chengdu 610039,","place":["China"]},{"name":"School of Computing and Artificial Intelligence, Southwest Jiaotong University , Chengdu 611756,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2025,9,30]]},"reference":[{"key":"2025102511213176400_btaf512-B1","doi-asserted-by":"crossref","first-page":"4633","DOI":"10.1093\/bioinformatics\/btaa544","article-title":"Deepcda: deep cross-domain compound\u2013protein affinity prediction through LSTM and convolutional neural networks","volume":"36","author":"Abbasi","year":"2020","journal-title":"Bioinformatics"},{"key":"2025102511213176400_btaf512-B2","author":"Barndorff-Nielsen","year":"1994"},{"key":"2025102511213176400_btaf512-B3","author":"Dai","year":"2024"},{"key":"2025102511213176400_btaf512-B4","doi-asserted-by":"crossref","first-page":"120754","DOI":"10.1016\/j.eswa.2023.120754","article-title":"Tripletmultidti: multimodal representation learning in drug-target interaction prediction with triplet loss function","volume":"232","author":"Dehghan","year":"2023","journal-title":"Expert Syst Appl"},{"key":"2025102511213176400_btaf512-B5","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1016\/j.strusafe.2008.06.020","article-title":"Aleatory or epistemic? Does it matter?","volume":"31","author":"Der Kiureghian","year":"2009","journal-title":"Struct Safety"},{"key":"2025102511213176400_btaf512-B6","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"Gretton","year":"2012","journal-title":"J Mach Learn Res"},{"key":"2025102511213176400_btaf512-B7","first-page":"905","author":"Hafner","year":"2020"},{"key":"2025102511213176400_btaf512-B8","first-page":"1025","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025102511213176400_btaf512-B9","first-page":"1122","author":"Hazarika","year":"2020"},{"key":"2025102511213176400_btaf512-B10","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":"2025102511213176400_btaf512-B11","doi-asserted-by":"crossref","first-page":"1771","DOI":"10.1162\/089976602760128018","article-title":"Training products of experts by minimizing contrastive divergence","volume":"14","author":"Hinton","year":"2002","journal-title":"Neural Comput"},{"key":"2025102511213176400_btaf512-B12","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":"2025102511213176400_btaf512-B13","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1021\/acs.jcim.7b00650","article-title":"K deep: protein\u2013ligand absolute binding affinity prediction via 3D-convolutional neural networks","volume":"58","author":"Jim\u00e9nez","year":"2018","journal-title":"J Chem Inf Model"},{"key":"2025102511213176400_btaf512-B14","doi-asserted-by":"crossref","first-page":"3329","DOI":"10.1093\/bioinformatics\/btz111","article-title":"Deepaffinity: interpretable deep learning of compound\u2013protein affinity through unified recurrent and convolutional neural networks","volume":"35","author":"Karimi","year":"2019","journal-title":"Bioinformatics"},{"key":"2025102511213176400_btaf512-B15","first-page":"421","author":"Khodayari","year":"2010"},{"key":"2025102511213176400_btaf512-B16","first-page":"2649","author":"Kim","year":"2018"},{"key":"2025102511213176400_btaf512-B17","doi-asserted-by":"crossref","first-page":"1947","DOI":"10.1021\/acs.jcim.3c00251","article-title":"Hac-net: a hybrid attention-based convolutional neural network for highly accurate protein\u2013ligand binding affinity prediction","volume":"63","author":"Kyro","year":"2023","journal-title":"J Chem Inf Model"},{"key":"2025102511213176400_btaf512-B18","first-page":"6405","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume":"30","author":"Lakshminarayanan","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025102511213176400_btaf512-B19","doi-asserted-by":"crossref","first-page":"1995","DOI":"10.1093\/bioinformatics\/btac035","article-title":"Bacpi: a bi-directional attention neural network for compound\u2013protein interaction and binding affinity prediction","volume":"38","author":"Li","year":"2022","journal-title":"Bioinformatics"},{"key":"2025102511213176400_btaf512-B20","doi-asserted-by":"crossref","first-page":"308","DOI":"10.1016\/j.cels.2020.03.002","article-title":"Monn: a multi-objective neural network for predicting compound-protein interactions and affinities","volume":"10","author":"Li","year":"2020","journal-title":"Cell Syst"},{"key":"2025102511213176400_btaf512-B21","first-page":"975","author":"Li","year":"2021"},{"key":"2025102511213176400_btaf512-B22","first-page":"303","author":"Li","year":"2019"},{"key":"2025102511213176400_btaf512-B23","doi-asserted-by":"crossref","first-page":"D198","DOI":"10.1093\/nar\/gkl999","article-title":"Bindingdb: a web-accessible database of experimentally determined protein\u2013ligand binding affinities","volume":"35","author":"Liu","year":"2007","journal-title":"Nucleic Acids Res"},{"key":"2025102511213176400_btaf512-B24","first-page":"6881","article-title":"Trustworthy multimodal regression with mixture of normal-inverse gamma distributions","volume":"34","author":"Ma","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"2025102511213176400_btaf512-B25","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1162\/neco.1992.4.3.415","article-title":"Bayesian interpolation","volume":"4","author":"MacKay","year":"1992","journal-title":"Neural Comput"},{"key":"2025102511213176400_btaf512-B26","volume-title":"Bayesian Learning for Neural Networks","author":"Neal","year":"2012"},{"key":"2025102511213176400_btaf512-B27","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":"2025102511213176400_btaf512-B28","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":"2025102511213176400_btaf512-B29","author":"\u00d6zt\u00fcrk","year":"2019"},{"key":"2025102511213176400_btaf512-B30","doi-asserted-by":"crossref","first-page":"916","DOI":"10.1038\/nature08538","article-title":"Multimodal techniques for diagnosis and prognosis of alzheimer\u2019s disease","volume":"461","author":"Perrin","year":"2009","journal-title":"Nature"},{"key":"2025102511213176400_btaf512-B31","doi-asserted-by":"crossref","first-page":"1011","DOI":"10.1214\/17-BA1083","article-title":"Big data Bayesian linear regression and variable selection by Normal-Inverse-Gamma summation","volume":"13","author":"Qian","year":"2018","journal-title":"Bayesian Anal"},{"key":"2025102511213176400_btaf512-B32","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1002\/j.1538-7305.1948.tb01338.x","article-title":"A mathematical theory of communication","volume":"27","author":"Shannon","year":"1948","journal-title":"The Bell System Technical Journal"},{"key":"2025102511213176400_btaf512-B33","first-page":"230","author":"Shin","year":"2019"},{"key":"2025102511213176400_btaf512-B34","doi-asserted-by":"crossref","first-page":"3666","DOI":"10.1093\/bioinformatics\/bty374","article-title":"Development and evaluation of a deep learning model for protein\u2013ligand binding affinity prediction","volume":"34","author":"Stepniewska-Dziubinska","year":"2018","journal-title":"Bioinformatics"},{"key":"2025102511213176400_btaf512-B35","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"2025102511213176400_btaf512-B36","doi-asserted-by":"crossref","first-page":"160103","DOI":"10.1007\/s11432-024-4333-7","article-title":"Diagllm: multimodal reasoning with large language model for explainable bearing fault diagnosis","volume":"68","author":"Wang","year":"2025","journal-title":"Sci China Inf Sci"},{"key":"2025102511213176400_btaf512-B37","doi-asserted-by":"crossref","first-page":"bbab072","DOI":"10.1093\/bib\/bbab072","article-title":"Deepdtaf: a deep learning method to predict protein\u2013ligand binding affinity","volume":"22","author":"Wang","year":"2021","journal-title":"Brief Bioinform"},{"key":"2025102511213176400_btaf512-B38","doi-asserted-by":"crossref","first-page":"2977","DOI":"10.1021\/jm030580l","article-title":"The pdbbind database: collection of binding affinities for protein- ligand complexes with known three-dimensional structures","volume":"47","author":"Wang","year":"2004","journal-title":"J Med Chem"},{"key":"2025102511213176400_btaf512-B39","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1016\/j.ymeth.2022.08.016","article-title":"Gchn-dti: predicting drug-target interactions by graph convolution on heterogeneous networks","volume":"206","author":"Wang","year":"2022","journal-title":"Methods"},{"key":"2025102511213176400_btaf512-B40","author":"Zellinger","year":"2017"},{"key":"2025102511213176400_btaf512-B41","first-page":"64","author":"Zhao","year":"2019"},{"key":"2025102511213176400_btaf512-B42","doi-asserted-by":"crossref","first-page":"15956","DOI":"10.1021\/acsomega.9b01997","article-title":"Onionnet: a multiple-layer intermolecular-contact-based convolutional neural network for protein\u2013ligand binding affinity prediction","volume":"4","author":"Zheng","year":"2019","journal-title":"ACS Omega"},{"key":"2025102511213176400_btaf512-B43","doi-asserted-by":"crossref","first-page":"2878","DOI":"10.1021\/acs.jcim.3c00866","article-title":"Mmdta: a multimodal deep model for drug-target affinity with a hybrid fusion strategy","volume":"64","author":"Zhong","year":"2024","journal-title":"J Chem Inf Model"},{"key":"2025102511213176400_btaf512-B44","doi-asserted-by":"crossref","first-page":"110239","DOI":"10.1016\/j.engappai.2025.110239","article-title":"Drug\u2013target affinity prediction using rotary encoding and information retention mechanisms","volume":"147","author":"Zhu","year":"2025","journal-title":"Eng Appl Artif Intell"},{"key":"2025102511213176400_btaf512-B45","doi-asserted-by":"crossref","first-page":"1558","DOI":"10.1049\/cit2.12194","article-title":"Associative learning mechanism for drug-target interaction prediction","volume":"8","author":"Zhu","year":"2023","journal-title":"CAAI Trans on Intel Tech"},{"key":"2025102511213176400_btaf512-B46","doi-asserted-by":"crossref","first-page":"107621","DOI":"10.1016\/j.compbiomed.2023.107621","article-title":"Drug\u2013target affinity prediction method based on multi-scale information interaction and graph optimization","volume":"167","author":"Zhu","year":"2023","journal-title":"Comput Biol Med"},{"key":"2025102511213176400_btaf512-B47","doi-asserted-by":"crossref","first-page":"124647","DOI":"10.1016\/j.eswa.2024.124647","article-title":"Drug\u2013target binding affinity prediction model based on multi-scale diffusion and interactive learning","volume":"255","author":"Zhu","year":"2024","journal-title":"Expert Syst Appl"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaf512\/64434077\/btaf512.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/10\/btaf512\/64434077\/btaf512.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/10\/btaf512\/64434077\/btaf512.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T15:21:40Z","timestamp":1761405700000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btaf512\/8268529"}},"subtitle":[],"editor":[{"given":"Xin","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,9,30]]},"references-count":47,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,10,2]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaf512","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,10]]},"published":{"date-parts":[[2025,9,30]]},"article-number":"btaf512"}}