Learning a generalized graph transformer for protein function prediction in dissimilar sequences.

IF 11.8 2区 生物学 Q1 MULTIDISCIPLINARY SCIENCES
Yiwei Fu, Zhonghui Gu, Xiao Luo, Qirui Guo, Luhua Lai, Minghua Deng
{"title":"Learning a generalized graph transformer for protein function prediction in dissimilar sequences.","authors":"Yiwei Fu, Zhonghui Gu, Xiao Luo, Qirui Guo, Luhua Lai, Minghua Deng","doi":"10.1093/gigascience/giae093","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>In the face of a growing disparity between high-throughput sequence data and low-throughput experimental studies, the emerging field of deep learning stands as a promising alternative. Generally, many data-driven approaches are capable of facilitating fast and accurate predictions of protein functions. Nevertheless, the inherent statistical nature of deep learning techniques may limit their generalization capabilities when applied to novel nonhomologous proteins that diverge significantly from existing ones.</p><p><strong>Results: </strong>In this work, we herein propose a novel, generalized approach named Graph Adversarial Learning with Alignment (GALA) for protein function prediction. Our GALA method integrates a graph transformer architecture with an attention pooling module to extract embeddings from both protein sequences and structures, facilitating unified learning of protein representations. Particularly noteworthy, GALA incorporates a domain discriminator conditioned on both learnable representations and predicted probabilities, which undergoes adversarial learning to ensure representation invariance across diverse environments. To optimize the model with abundant label information, we generate label embeddings in the hidden space, explicitly aligning them with protein representations. Benchmarked on datasets derived from the PDB database and Swiss-Prot database, our GALA achieves considerable performance comparable to several state-of-the-art methods. Even more, GALA demonstrates wonderful biological interpretability by identifying significant functional residues associated with Gene Ontology terms through class activation mapping.</p><p><strong>Conclusions: </strong>GALA, which leverages adversarial learning and label embedding alignment to acquire domain-invariant protein representations, exhibits outstanding generalizability in function prediction for proteins from previously unseen sequence space. By incorporating the structures predicted by AlphaFold2, GALA demonstrates significant potential for function annotation in newly discovered sequences. A detailed implementation of our GALA is available at https://github.com/fuyw-aisw/GALA.</p>","PeriodicalId":12581,"journal":{"name":"GigaScience","volume":"13 ","pages":""},"PeriodicalIF":11.8000,"publicationDate":"2024-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"GigaScience","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.1093/gigascience/giae093","RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MULTIDISCIPLINARY SCIENCES","Score":null,"Total":0}
引用次数: 0

Abstract

Background: In the face of a growing disparity between high-throughput sequence data and low-throughput experimental studies, the emerging field of deep learning stands as a promising alternative. Generally, many data-driven approaches are capable of facilitating fast and accurate predictions of protein functions. Nevertheless, the inherent statistical nature of deep learning techniques may limit their generalization capabilities when applied to novel nonhomologous proteins that diverge significantly from existing ones.

Results: In this work, we herein propose a novel, generalized approach named Graph Adversarial Learning with Alignment (GALA) for protein function prediction. Our GALA method integrates a graph transformer architecture with an attention pooling module to extract embeddings from both protein sequences and structures, facilitating unified learning of protein representations. Particularly noteworthy, GALA incorporates a domain discriminator conditioned on both learnable representations and predicted probabilities, which undergoes adversarial learning to ensure representation invariance across diverse environments. To optimize the model with abundant label information, we generate label embeddings in the hidden space, explicitly aligning them with protein representations. Benchmarked on datasets derived from the PDB database and Swiss-Prot database, our GALA achieves considerable performance comparable to several state-of-the-art methods. Even more, GALA demonstrates wonderful biological interpretability by identifying significant functional residues associated with Gene Ontology terms through class activation mapping.

Conclusions: GALA, which leverages adversarial learning and label embedding alignment to acquire domain-invariant protein representations, exhibits outstanding generalizability in function prediction for proteins from previously unseen sequence space. By incorporating the structures predicted by AlphaFold2, GALA demonstrates significant potential for function annotation in newly discovered sequences. A detailed implementation of our GALA is available at https://github.com/fuyw-aisw/GALA.

学习广义图变换器,预测不同序列中的蛋白质功能。
背景:高通量序列数据与低通量实验研究之间的差距越来越大,面对这种情况,新兴的深度学习领域成为了一种前景广阔的替代方法。一般来说,许多数据驱动的方法都能快速准确地预测蛋白质的功能。然而,当深度学习技术应用于与现有蛋白质有显著差异的新型非同源蛋白质时,其固有的统计性质可能会限制其泛化能力:在这项工作中,我们提出了一种用于蛋白质功能预测的新型通用方法,名为 "图形对抗学习与配准(GALA)"。我们的 GALA 方法集成了图转换器架构和注意力集合模块,可从蛋白质序列和结构中提取嵌入,从而促进蛋白质表征的统一学习。尤其值得注意的是,GALA 包含了一个以可学习表征和预测概率为条件的领域判别器,该判别器经过对抗学习,以确保在不同环境下的表征不变性。为了利用丰富的标签信息优化模型,我们在隐藏空间中生成了标签嵌入,明确地将它们与蛋白质表征对齐。以来自 PDB 数据库和 Swiss-Prot 数据库的数据集为基准,我们的 GALA 取得了与几种最先进方法相当的性能。此外,GALA 还通过类激活映射识别了与基因本体术语相关的重要功能残基,从而展示了出色的生物可解释性:GALA利用对抗学习和标签嵌入比对来获取领域不变的蛋白质表征,在对来自以前未见过的序列空间的蛋白质进行功能预测时表现出了出色的普适性。通过结合 AlphaFold2 预测的结构,GALA 在新发现序列的功能注释方面展现出巨大潜力。有关 GALA 的详细实现过程,请访问 https://github.com/fuyw-aisw/GALA。
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
GigaScience
GigaScience MULTIDISCIPLINARY SCIENCES-
CiteScore
15.50
自引率
1.10%
发文量
119
审稿时长
1 weeks
期刊介绍: GigaScience seeks to transform data dissemination and utilization in the life and biomedical sciences. As an online open-access open-data journal, it specializes in publishing "big-data" studies encompassing various fields. Its scope includes not only "omic" type data and the fields of high-throughput biology currently serviced by large public repositories, but also the growing range of more difficult-to-access data, such as imaging, neuroscience, ecology, cohort data, systems biology and other new types of large-scale shareable data.
×
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