Heterogeneous graph convolutional neural network for protein-ligand scoring

Kevin Crampon, Alexis Giorkallos, X. Vigouroux, S. Baud, L. Steffenel
{"title":"Heterogeneous graph convolutional neural network for protein-ligand scoring","authors":"Kevin Crampon, Alexis Giorkallos, X. Vigouroux, S. Baud, L. Steffenel","doi":"10.37349/eds.2023.00010","DOIUrl":null,"url":null,"abstract":"Aim: Drug discovery is a long process, often taking decades of research endeavors. It is still an active area of research in both academic and industrial sectors with efforts on reducing time and cost. Computational simulations like molecular docking enable fast exploration of large databases of compounds and extract the most promising molecule candidates for further in vitro and in vivo tests. Structure-based molecular docking is a complex process mixing both surface exploration and energy estimation to find the minimal free energy of binding corresponding to the best interaction location.\nMethods: Hereafter, heterogeneous graph score (HGScore), a new scoring function is proposed and is developed in the context of a protein-small compound-complex. Each complex is represented by a heterogeneous graph allowing to separate edges according to their class (inter- or intra-molecular). Then a heterogeneous graph convolutional network (HGCN) is used allowing the discrimination of the information according to the edge crossed. In the end, the model produces the affinity score of the complex.\nResults: HGScore has been tested on the comparative assessment of scoring functions (CASF) 2013 and 2016 benchmarks for scoring, ranking, and docking powers. It has achieved good performances by outperforming classical methods and being among the best artificial intelligence (AI) methods.\nConclusions: Thus, HGScore brings a new way to represent protein-ligand interactions. Using a representation that involves classical graph neural networks (GNNs) and splitting the learning process regarding the edge type makes the proposed model to be the best adapted for future transfer learning on other (protein-DNA, protein-sugar, protein-protein, etc.) biological complexes.","PeriodicalId":72998,"journal":{"name":"Exploration of drug science","volume":"50 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2023-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Exploration of drug science","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.37349/eds.2023.00010","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Aim: Drug discovery is a long process, often taking decades of research endeavors. It is still an active area of research in both academic and industrial sectors with efforts on reducing time and cost. Computational simulations like molecular docking enable fast exploration of large databases of compounds and extract the most promising molecule candidates for further in vitro and in vivo tests. Structure-based molecular docking is a complex process mixing both surface exploration and energy estimation to find the minimal free energy of binding corresponding to the best interaction location. Methods: Hereafter, heterogeneous graph score (HGScore), a new scoring function is proposed and is developed in the context of a protein-small compound-complex. Each complex is represented by a heterogeneous graph allowing to separate edges according to their class (inter- or intra-molecular). Then a heterogeneous graph convolutional network (HGCN) is used allowing the discrimination of the information according to the edge crossed. In the end, the model produces the affinity score of the complex. Results: HGScore has been tested on the comparative assessment of scoring functions (CASF) 2013 and 2016 benchmarks for scoring, ranking, and docking powers. It has achieved good performances by outperforming classical methods and being among the best artificial intelligence (AI) methods. Conclusions: Thus, HGScore brings a new way to represent protein-ligand interactions. Using a representation that involves classical graph neural networks (GNNs) and splitting the learning process regarding the edge type makes the proposed model to be the best adapted for future transfer learning on other (protein-DNA, protein-sugar, protein-protein, etc.) biological complexes.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
蛋白质配体评分的异构图卷积神经网络
目的:药物发现是一个漫长的过程,通常需要几十年的研究努力。它仍然是一个活跃的研究领域,在学术界和工业界的努力,以减少时间和成本。像分子对接这样的计算模拟可以快速探索大型化合物数据库,并提取最有希望的候选分子,用于进一步的体外和体内测试。基于结构的分子对接是寻找最佳相互作用位置对应的最小结合自由能的复杂过程。方法:本文提出了一种新的评分函数HGScore (heterogeneous graph score),并在蛋白质-小化合物-复合物的背景下进行了开发。每个复合体由一个异构图表示,允许根据它们的类别(分子间或分子内)分离边缘。然后利用异构图卷积网络(HGCN),根据交叉的边缘进行信息判别。最后,该模型生成复合物的亲和度评分。结果:HGScore在评分函数比较评估(CASF) 2013和2016基准上进行了评分、排名和对接能力的测试。它超越了经典方法,成为最好的人工智能(AI)方法之一,取得了良好的性能。结论:HGScore为表达蛋白质与配体相互作用提供了一种新的方法。使用涉及经典图神经网络(gnn)的表示,并根据边缘类型划分学习过程,使所提出的模型最适合未来在其他(蛋白质- dna,蛋白质-糖,蛋白质-蛋白质等)生物复合物上的迁移学习。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Enhanced breast cancer cell targeting: RGD integrin ligand potentiates RWQWRWQWR’s cytotoxicity and inhibits migration Plants and fungi metabolites as novel autophagy inducers and senescence inhibitors Pain management for the neurosurgical patient in spinal procedures: overview of historic and new modalities Interaction of norsecurinine-type monomeric and dimeric alkaloids with α-tubulin: a molecular docking study Stryphnodendron adstringens have a modulatory effect on inflammatory cytokines markers of in vitro activated macrophages
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1