{"title":"RGDA-DDI:基于残差图注意力网络和双重注意力的药物相互作用预测框架","authors":"Changjian Zhou, Xin Zhang, Jiafeng Li, Jia Song, Wensheng Xiang","doi":"arxiv-2408.15310","DOIUrl":null,"url":null,"abstract":"Recent studies suggest that drug-drug interaction (DDI) prediction via\ncomputational approaches has significant importance for understanding the\nfunctions and co-prescriptions of multiple drugs. However, the existing silico\nDDI prediction methods either ignore the potential interactions among drug-drug\npairs (DDPs), or fail to explicitly model and fuse the multi-scale drug feature\nrepresentations for better prediction. In this study, we propose RGDA-DDI, a\nresidual graph attention network (residual-GAT) and dual-attention based\nframework for drug-drug interaction prediction. A residual-GAT module is\nintroduced to simultaneously learn multi-scale feature representations from\ndrugs and DDPs. In addition, a dual-attention based feature fusion block is\nconstructed to learn local joint interaction representations. A series of\nevaluation metrics demonstrate that the RGDA-DDI significantly improved DDI\nprediction performance on two public benchmark datasets, which provides a new\ninsight into drug development.","PeriodicalId":501325,"journal":{"name":"arXiv - QuanBio - Molecular Networks","volume":"406 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"RGDA-DDI: Residual graph attention network and dual-attention based framework for drug-drug interaction prediction\",\"authors\":\"Changjian Zhou, Xin Zhang, Jiafeng Li, Jia Song, Wensheng Xiang\",\"doi\":\"arxiv-2408.15310\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Recent studies suggest that drug-drug interaction (DDI) prediction via\\ncomputational approaches has significant importance for understanding the\\nfunctions and co-prescriptions of multiple drugs. However, the existing silico\\nDDI prediction methods either ignore the potential interactions among drug-drug\\npairs (DDPs), or fail to explicitly model and fuse the multi-scale drug feature\\nrepresentations for better prediction. In this study, we propose RGDA-DDI, a\\nresidual graph attention network (residual-GAT) and dual-attention based\\nframework for drug-drug interaction prediction. A residual-GAT module is\\nintroduced to simultaneously learn multi-scale feature representations from\\ndrugs and DDPs. In addition, a dual-attention based feature fusion block is\\nconstructed to learn local joint interaction representations. A series of\\nevaluation metrics demonstrate that the RGDA-DDI significantly improved DDI\\nprediction performance on two public benchmark datasets, which provides a new\\ninsight into drug development.\",\"PeriodicalId\":501325,\"journal\":{\"name\":\"arXiv - QuanBio - Molecular Networks\",\"volume\":\"406 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-08-27\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - QuanBio - Molecular Networks\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2408.15310\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - QuanBio - Molecular Networks","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2408.15310","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
RGDA-DDI: Residual graph attention network and dual-attention based framework for drug-drug interaction prediction
Recent studies suggest that drug-drug interaction (DDI) prediction via
computational approaches has significant importance for understanding the
functions and co-prescriptions of multiple drugs. However, the existing silico
DDI prediction methods either ignore the potential interactions among drug-drug
pairs (DDPs), or fail to explicitly model and fuse the multi-scale drug feature
representations for better prediction. In this study, we propose RGDA-DDI, a
residual graph attention network (residual-GAT) and dual-attention based
framework for drug-drug interaction prediction. A residual-GAT module is
introduced to simultaneously learn multi-scale feature representations from
drugs and DDPs. In addition, a dual-attention based feature fusion block is
constructed to learn local joint interaction representations. A series of
evaluation metrics demonstrate that the RGDA-DDI significantly improved DDI
prediction performance on two public benchmark datasets, which provides a new
insight into drug development.