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

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}
引用次数: 0

摘要

药物相互作用(DDIs)会导致各种药理变化,这些变化可分为不同的类别,称为药物相互作用事件(DDIIEs)。近年来,以前未观察/未见的 DDIEs 不断涌现,当未见类别在训练阶段没有标注实例时,就会产生新的分类任务,这就是零次 DDIE 预测(ZS-DDIE)任务。然而,现有的计算方法并不能直接适用于 ZS-DDIE,它有两个主要挑战:获得合适的 DDIE 表示和处理类不平衡问题。为了克服这些挑战,我们针对ZS-DDIE任务提出了一种名为ZeroDDI的新方法。具体来说,我们设计了一种生物语义增强型DDIE表征学习模块,该模块强调关键的生物语义,并提炼出与分子亚结构相关的区分性语义,用于DDIE表征学习。此外,我们还提出了一种双模态均匀配准策略,将药物配对表征和DDIE语义表征均匀分布在一个单位球内,并对匹配的表征进行配准,从而缓解了类不平衡问题。广泛的实验表明,ZeroDDI超越了基线,表明它是检测未见DDIE的一种有前途的工具。我们的代码已发布在 https://github.com/wzy-Sarah/ZeroDDI 上。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
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.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信