A variational graph-partitioning approach to modeling protein liquid-liquid phase separation.

IF 7.9 2区 综合性期刊 Q1 CHEMISTRY, MULTIDISCIPLINARY
Gaoyuan Wang, Jonathan Warrell, Suchen Zheng, Mark Gerstein
{"title":"A variational graph-partitioning approach to modeling protein liquid-liquid phase separation.","authors":"Gaoyuan Wang, Jonathan Warrell, Suchen Zheng, Mark Gerstein","doi":"10.1016/j.xcrp.2024.102292","DOIUrl":null,"url":null,"abstract":"<p><p>Graph neural networks (GNNs) have emerged as powerful tools for representation learning. Their efficacy depends on their having an optimal underlying graph. In many cases, the most relevant information comes from specific subgraphs. In this work, we introduce a GNN-based framework (graph-partitioned GNN [GP-GNN]) to partition the GNN graph to focus on the most relevant subgraphs. Our approach jointly learns task-dependent graph partitions and node representations, making it particularly effective when critical features reside within initially unidentified subgraphs. Protein liquid-liquid phase separation (LLPS) is a problem especially well-suited to GP-GNNs because intrinsically disordered regions (IDRs) are known to function as protein subdomains in it, playing a key role in the phase separation process. In this study, we demonstrate how GP-GNN accurately predicts LLPS by partitioning protein graphs into task-relevant subgraphs consistent with known IDRs. Our model achieves state-of-the-art accuracy in predicting LLPS and offers biological insights valuable for downstream investigation.</p>","PeriodicalId":9703,"journal":{"name":"Cell Reports Physical Science","volume":"5 11","pages":""},"PeriodicalIF":7.9000,"publicationDate":"2024-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11760192/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cell Reports Physical Science","FirstCategoryId":"103","ListUrlMain":"https://doi.org/10.1016/j.xcrp.2024.102292","RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CHEMISTRY, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

Abstract

Graph neural networks (GNNs) have emerged as powerful tools for representation learning. Their efficacy depends on their having an optimal underlying graph. In many cases, the most relevant information comes from specific subgraphs. In this work, we introduce a GNN-based framework (graph-partitioned GNN [GP-GNN]) to partition the GNN graph to focus on the most relevant subgraphs. Our approach jointly learns task-dependent graph partitions and node representations, making it particularly effective when critical features reside within initially unidentified subgraphs. Protein liquid-liquid phase separation (LLPS) is a problem especially well-suited to GP-GNNs because intrinsically disordered regions (IDRs) are known to function as protein subdomains in it, playing a key role in the phase separation process. In this study, we demonstrate how GP-GNN accurately predicts LLPS by partitioning protein graphs into task-relevant subgraphs consistent with known IDRs. Our model achieves state-of-the-art accuracy in predicting LLPS and offers biological insights valuable for downstream investigation.

蛋白质液-液相分离模型的变分图划分方法。
图神经网络(gnn)已经成为表征学习的强大工具。它们的功效取决于它们有一个最优的底层图。在许多情况下,最相关的信息来自于特定的子图。在这项工作中,我们引入了一个基于GNN的框架(图分区GNN [GP-GNN])来划分GNN图,以关注最相关的子图。我们的方法联合学习任务相关的图分区和节点表示,使其在关键特征位于最初未识别的子图中时特别有效。蛋白质液-液相分离(LLPS)是一个特别适合gp - gnn的问题,因为已知内在无序区(IDRs)在其中作为蛋白质亚结构域起作用,在相分离过程中起关键作用。在这项研究中,我们展示了GP-GNN如何通过将蛋白质图划分为与已知idr一致的任务相关子图来准确预测LLPS。我们的模型在预测LLPS方面达到了最先进的精度,并为下游研究提供了有价值的生物学见解。
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 求助全文
来源期刊
Cell Reports Physical Science
Cell Reports Physical Science Energy-Energy (all)
CiteScore
11.40
自引率
2.20%
发文量
388
审稿时长
62 days
期刊介绍: Cell Reports Physical Science, a premium open-access journal from Cell Press, features high-quality, cutting-edge research spanning the physical sciences. It serves as an open forum fostering collaboration among physical scientists while championing open science principles. Published works must signify significant advancements in fundamental insight or technological applications within fields such as chemistry, physics, materials science, energy science, engineering, and related interdisciplinary studies. In addition to longer articles, the journal considers impactful short-form reports and short reviews covering recent literature in emerging fields. Continually adapting to the evolving open science landscape, the journal reviews its policies to align with community consensus and best practices.
×
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