Wenzhe Xu, Xiaorong Liu, Jie Wang, Fan Zhang, Dongfeng Hu, Dongfeng Hu
{"title":"基于多粒度不确定性感知的多模态表示学习的药物-靶点亲和力预测。","authors":"Wenzhe Xu, Xiaorong Liu, Jie Wang, Fan Zhang, Dongfeng Hu, Dongfeng Hu","doi":"10.1093/bioinformatics/btaf512","DOIUrl":null,"url":null,"abstract":"<p><strong>Motivation: </strong>Computational prediction of drug-target 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.</p><p><strong>Results: </strong>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.</p><p><strong>Availability: </strong>The source code is available at https://github.com/Astraea2xu/UAMRL.</p><p><strong>Supplementary information: </strong>Supplementary data are available at Bioinformatics online.</p>","PeriodicalId":93899,"journal":{"name":"Bioinformatics (Oxford, England)","volume":" ","pages":""},"PeriodicalIF":5.4000,"publicationDate":"2025-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"UAMRL: Multi-Granularity Uncertainty-Aware Multimodal Representation Learning for Drug-Target Affinity Prediction.\",\"authors\":\"Wenzhe Xu, Xiaorong Liu, Jie Wang, Fan Zhang, Dongfeng Hu, Dongfeng Hu\",\"doi\":\"10.1093/bioinformatics/btaf512\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Motivation: </strong>Computational prediction of drug-target 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.</p><p><strong>Results: </strong>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.</p><p><strong>Availability: </strong>The source code is available at https://github.com/Astraea2xu/UAMRL.</p><p><strong>Supplementary information: </strong>Supplementary data are available at Bioinformatics online.</p>\",\"PeriodicalId\":93899,\"journal\":{\"name\":\"Bioinformatics (Oxford, England)\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":5.4000,\"publicationDate\":\"2025-09-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Bioinformatics (Oxford, England)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1093/bioinformatics/btaf512\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Bioinformatics (Oxford, England)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1093/bioinformatics/btaf512","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
UAMRL: Multi-Granularity Uncertainty-Aware Multimodal Representation Learning for Drug-Target Affinity Prediction.
Motivation: Computational prediction of drug-target 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.
Results: 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.
Availability: The source code is available at https://github.com/Astraea2xu/UAMRL.
Supplementary information: Supplementary data are available at Bioinformatics online.