从多个来源的深度突变扫描数据学习蛋白质适应度景观。

IF 9 1区 生物学 Q1 BIOCHEMISTRY & MOLECULAR BIOLOGY
Lin Chen, Zehong Zhang, Zhenghao Li, Rui Li, Ruifeng Huo, Lifan Chen, Dingyan Wang, Xiaomin Luo, Kaixian Chen, Cangsong Liao, Mingyue Zheng
{"title":"从多个来源的深度突变扫描数据学习蛋白质适应度景观。","authors":"Lin Chen,&nbsp;Zehong Zhang,&nbsp;Zhenghao Li,&nbsp;Rui Li,&nbsp;Ruifeng Huo,&nbsp;Lifan Chen,&nbsp;Dingyan Wang,&nbsp;Xiaomin Luo,&nbsp;Kaixian Chen,&nbsp;Cangsong Liao,&nbsp;Mingyue Zheng","doi":"10.1016/j.cels.2023.07.003","DOIUrl":null,"url":null,"abstract":"<p><p>One of the key points of machine learning-assisted directed evolution (MLDE) is the accurate learning of the fitness landscape, a conceptual mapping from sequence variants to the desired function. Here, we describe a multi-protein training scheme that leverages the existing deep mutational scanning data from diverse proteins to aid in understanding the fitness landscape of a new protein. Proof-of-concept trials are designed to validate this training scheme in three aspects: random and positional extrapolation for single-variant effects, zero-shot fitness predictions for new proteins, and extrapolation for higher-order variant effects from single-variant effects. Moreover, our study identified previously overlooked strong baselines, and their unexpectedly good performance brings our attention to the pitfalls of MLDE. Overall, these results may improve our understanding of the association between different protein fitness profiles and shed light on developing better machine learning-assisted approaches to the directed evolution of proteins. A record of this paper's transparent peer review process is included in the supplemental information.</p>","PeriodicalId":54348,"journal":{"name":"Cell Systems","volume":"14 8","pages":"706-721.e5"},"PeriodicalIF":9.0000,"publicationDate":"2023-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Learning protein fitness landscapes with deep mutational scanning data from multiple sources.\",\"authors\":\"Lin Chen,&nbsp;Zehong Zhang,&nbsp;Zhenghao Li,&nbsp;Rui Li,&nbsp;Ruifeng Huo,&nbsp;Lifan Chen,&nbsp;Dingyan Wang,&nbsp;Xiaomin Luo,&nbsp;Kaixian Chen,&nbsp;Cangsong Liao,&nbsp;Mingyue Zheng\",\"doi\":\"10.1016/j.cels.2023.07.003\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>One of the key points of machine learning-assisted directed evolution (MLDE) is the accurate learning of the fitness landscape, a conceptual mapping from sequence variants to the desired function. Here, we describe a multi-protein training scheme that leverages the existing deep mutational scanning data from diverse proteins to aid in understanding the fitness landscape of a new protein. Proof-of-concept trials are designed to validate this training scheme in three aspects: random and positional extrapolation for single-variant effects, zero-shot fitness predictions for new proteins, and extrapolation for higher-order variant effects from single-variant effects. Moreover, our study identified previously overlooked strong baselines, and their unexpectedly good performance brings our attention to the pitfalls of MLDE. Overall, these results may improve our understanding of the association between different protein fitness profiles and shed light on developing better machine learning-assisted approaches to the directed evolution of proteins. A record of this paper's transparent peer review process is included in the supplemental information.</p>\",\"PeriodicalId\":54348,\"journal\":{\"name\":\"Cell Systems\",\"volume\":\"14 8\",\"pages\":\"706-721.e5\"},\"PeriodicalIF\":9.0000,\"publicationDate\":\"2023-08-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Cell Systems\",\"FirstCategoryId\":\"99\",\"ListUrlMain\":\"https://doi.org/10.1016/j.cels.2023.07.003\",\"RegionNum\":1,\"RegionCategory\":\"生物学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"BIOCHEMISTRY & MOLECULAR BIOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Cell Systems","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.1016/j.cels.2023.07.003","RegionNum":1,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"BIOCHEMISTRY & MOLECULAR BIOLOGY","Score":null,"Total":0}
引用次数: 0

摘要

机器学习辅助定向进化(MLDE)的关键之一是准确学习适应度景观,即从序列变体到期望函数的概念映射。在这里,我们描述了一种多蛋白质训练方案,该方案利用来自不同蛋白质的现有深度突变扫描数据来帮助理解新蛋白质的适应度景观。概念验证试验旨在从三个方面验证该训练方案:单变量效应的随机和位置外推,新蛋白质的零射击适应度预测,以及单变量效应的高阶变体效应外推。此外,我们的研究发现了以前被忽视的强大基线,它们意想不到的良好表现使我们注意到MLDE的陷阱。总的来说,这些结果可能会提高我们对不同蛋白质适应度谱之间关联的理解,并为开发更好的机器学习辅助方法来指导蛋白质的定向进化提供启示。本文的透明同行评议过程记录包含在补充信息中。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Learning protein fitness landscapes with deep mutational scanning data from multiple sources.

Learning protein fitness landscapes with deep mutational scanning data from multiple sources.

One of the key points of machine learning-assisted directed evolution (MLDE) is the accurate learning of the fitness landscape, a conceptual mapping from sequence variants to the desired function. Here, we describe a multi-protein training scheme that leverages the existing deep mutational scanning data from diverse proteins to aid in understanding the fitness landscape of a new protein. Proof-of-concept trials are designed to validate this training scheme in three aspects: random and positional extrapolation for single-variant effects, zero-shot fitness predictions for new proteins, and extrapolation for higher-order variant effects from single-variant effects. Moreover, our study identified previously overlooked strong baselines, and their unexpectedly good performance brings our attention to the pitfalls of MLDE. Overall, these results may improve our understanding of the association between different protein fitness profiles and shed light on developing better machine learning-assisted approaches to the directed evolution of proteins. A record of this paper's transparent peer review process is included in the supplemental information.

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
Cell Systems
Cell Systems Medicine-Pathology and Forensic Medicine
CiteScore
16.50
自引率
1.10%
发文量
84
审稿时长
42 days
期刊介绍: In 2015, Cell Systems was founded as a platform within Cell Press to showcase innovative research in systems biology. Our primary goal is to investigate complex biological phenomena that cannot be simply explained by basic mathematical principles. While the physical sciences have long successfully tackled such challenges, we have discovered that our most impactful publications often employ quantitative, inference-based methodologies borrowed from the fields of physics, engineering, mathematics, and computer science. We are committed to providing a home for elegant research that addresses fundamental questions in systems biology.
×
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