Ziyan Wang, Zhankun Xiong, Feng Huang, Xuan Liu, Wen Zhang
{"title":"ZeroDDI:采用语义增强学习和双模式统一配准的零镜头药物相互作用事件预测方法","authors":"Ziyan Wang, Zhankun Xiong, Feng Huang, Xuan Liu, Wen Zhang","doi":"arxiv-2407.00891","DOIUrl":null,"url":null,"abstract":"Drug-drug interactions (DDIs) can result in various pharmacological changes,\nwhich can be categorized into different classes known as DDI events (DDIEs). In\nrecent years, previously unobserved/unseen DDIEs have been emerging, posing a\nnew classification task when unseen classes have no labelled instances in the\ntraining stage, which is formulated as a zero-shot DDIE prediction (ZS-DDIE)\ntask. However, existing computational methods are not directly applicable to\nZS-DDIE, which has two primary challenges: obtaining suitable DDIE\nrepresentations and handling the class imbalance issue. To overcome these\nchallenges, we propose a novel method named ZeroDDI for the ZS-DDIE task.\nSpecifically, we design a biological semantic enhanced DDIE representation\nlearning module, which emphasizes the key biological semantics and distills\ndiscriminative molecular substructure-related semantics for DDIE representation\nlearning. Furthermore, we propose a dual-modal uniform alignment strategy to\ndistribute drug pair representations and DDIE semantic representations\nuniformly in a unit sphere and align the matched ones, which can mitigate the\nissue of class imbalance. Extensive experiments showed that ZeroDDI surpasses\nthe baselines and indicate that it is a promising tool for detecting unseen\nDDIEs. Our code has been released in https://github.com/wzy-Sarah/ZeroDDI.","PeriodicalId":501022,"journal":{"name":"arXiv - QuanBio - Biomolecules","volume":"33 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"ZeroDDI: A Zero-Shot Drug-Drug Interaction Event Prediction Method with Semantic Enhanced Learning and Dual-Modal Uniform Alignment\",\"authors\":\"Ziyan Wang, Zhankun Xiong, Feng Huang, Xuan Liu, Wen Zhang\",\"doi\":\"arxiv-2407.00891\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Drug-drug interactions (DDIs) can result in various pharmacological changes,\\nwhich can be categorized into different classes known as DDI events (DDIEs). In\\nrecent years, previously unobserved/unseen DDIEs have been emerging, posing a\\nnew classification task when unseen classes have no labelled instances in the\\ntraining stage, which is formulated as a zero-shot DDIE prediction (ZS-DDIE)\\ntask. However, existing computational methods are not directly applicable to\\nZS-DDIE, which has two primary challenges: obtaining suitable DDIE\\nrepresentations and handling the class imbalance issue. To overcome these\\nchallenges, we propose a novel method named ZeroDDI for the ZS-DDIE task.\\nSpecifically, we design a biological semantic enhanced DDIE representation\\nlearning module, which emphasizes the key biological semantics and distills\\ndiscriminative molecular substructure-related semantics for DDIE representation\\nlearning. Furthermore, we propose a dual-modal uniform alignment strategy to\\ndistribute drug pair representations and DDIE semantic representations\\nuniformly in a unit sphere and align the matched ones, which can mitigate the\\nissue of class imbalance. Extensive experiments showed that ZeroDDI surpasses\\nthe baselines and indicate that it is a promising tool for detecting unseen\\nDDIEs. Our code has been released in https://github.com/wzy-Sarah/ZeroDDI.\",\"PeriodicalId\":501022,\"journal\":{\"name\":\"arXiv - QuanBio - Biomolecules\",\"volume\":\"33 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-07-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - QuanBio - Biomolecules\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2407.00891\",\"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 - Biomolecules","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2407.00891","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
ZeroDDI: A Zero-Shot Drug-Drug Interaction Event Prediction Method with Semantic Enhanced Learning and Dual-Modal Uniform Alignment
Drug-drug interactions (DDIs) can result in various pharmacological changes,
which can be categorized into different classes known as DDI events (DDIEs). In
recent years, previously unobserved/unseen DDIEs have been emerging, posing a
new classification task when unseen classes have no labelled instances in the
training stage, which is formulated as a zero-shot DDIE prediction (ZS-DDIE)
task. However, existing computational methods are not directly applicable to
ZS-DDIE, which has two primary challenges: obtaining suitable DDIE
representations and handling the class imbalance issue. To overcome these
challenges, we propose a novel method named ZeroDDI for the ZS-DDIE task.
Specifically, we design a biological semantic enhanced DDIE representation
learning module, which emphasizes the key biological semantics and distills
discriminative molecular substructure-related semantics for DDIE representation
learning. Furthermore, we propose a dual-modal uniform alignment strategy to
distribute drug pair representations and DDIE semantic representations
uniformly in a unit sphere and align the matched ones, which can mitigate the
issue of class imbalance. Extensive experiments showed that ZeroDDI surpasses
the baselines and indicate that it is a promising tool for detecting unseen
DDIEs. Our code has been released in https://github.com/wzy-Sarah/ZeroDDI.