Top-down design of protein architectures with reinforcement learning

IF 44.7 1区 综合性期刊 Q1 MULTIDISCIPLINARY SCIENCES
Science Pub Date : 2023-04-20 DOI:10.1126/science.adf6591
Isaac D. Lutz, Shunzhi Wang, Christoffer Norn, Alexis Courbet, Andrew J. Borst, Yan Ting Zhao, Annie Dosey, Longxing Cao, Jinwei Xu, Elizabeth M. Leaf, Catherine Treichel, Patrisia Litvicov, Zhe Li, Alexander D. Goodson, Paula Rivera-Sánchez, Ana-Maria Bratovianu, Minkyung Baek, Neil P. King, Hannele Ruohola-Baker, David Baker
{"title":"Top-down design of protein architectures with reinforcement learning","authors":"Isaac D. Lutz,&nbsp;Shunzhi Wang,&nbsp;Christoffer Norn,&nbsp;Alexis Courbet,&nbsp;Andrew J. Borst,&nbsp;Yan Ting Zhao,&nbsp;Annie Dosey,&nbsp;Longxing Cao,&nbsp;Jinwei Xu,&nbsp;Elizabeth M. Leaf,&nbsp;Catherine Treichel,&nbsp;Patrisia Litvicov,&nbsp;Zhe Li,&nbsp;Alexander D. Goodson,&nbsp;Paula Rivera-Sánchez,&nbsp;Ana-Maria Bratovianu,&nbsp;Minkyung Baek,&nbsp;Neil P. King,&nbsp;Hannele Ruohola-Baker,&nbsp;David Baker","doi":"10.1126/science.adf6591","DOIUrl":null,"url":null,"abstract":"<div >As a result of evolutionary selection, the subunits of naturally occurring protein assemblies often fit together with substantial shape complementarity to generate architectures optimal for function in a manner not achievable by current design approaches. We describe a “top-down” reinforcement learning–based design approach that solves this problem using Monte Carlo tree search to sample protein conformers in the context of an overall architecture and specified functional constraints. Cryo–electron microscopy structures of the designed disk-shaped nanopores and ultracompact icosahedra are very close to the computational models. The icosohedra enable very-high-density display of immunogens and signaling molecules, which potentiates vaccine response and angiogenesis induction. Our approach enables the top-down design of complex protein nanomaterials with desired system properties and demonstrates the power of reinforcement learning in protein design.</div>","PeriodicalId":21678,"journal":{"name":"Science","volume":"380 6642","pages":""},"PeriodicalIF":44.7000,"publicationDate":"2023-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"14","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Science","FirstCategoryId":"103","ListUrlMain":"https://www.science.org/doi/10.1126/science.adf6591","RegionNum":1,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MULTIDISCIPLINARY SCIENCES","Score":null,"Total":0}
引用次数: 14

Abstract

As a result of evolutionary selection, the subunits of naturally occurring protein assemblies often fit together with substantial shape complementarity to generate architectures optimal for function in a manner not achievable by current design approaches. We describe a “top-down” reinforcement learning–based design approach that solves this problem using Monte Carlo tree search to sample protein conformers in the context of an overall architecture and specified functional constraints. Cryo–electron microscopy structures of the designed disk-shaped nanopores and ultracompact icosahedra are very close to the computational models. The icosohedra enable very-high-density display of immunogens and signaling molecules, which potentiates vaccine response and angiogenesis induction. Our approach enables the top-down design of complex protein nanomaterials with desired system properties and demonstrates the power of reinforcement learning in protein design.
利用强化学习自顶向下设计蛋白质结构
由于进化选择的结果,自然形成的蛋白质组装体的亚单位往往以很大的形状互补性组合在一起,从而产生了目前的设计方法无法实现的最佳功能架构。我们介绍了一种基于强化学习的 "自上而下 "设计方法,该方法利用蒙特卡洛树搜索,在整体结构和特定功能约束条件下对蛋白质构象进行采样,从而解决了这一问题。设计出的盘状纳米孔和超小型二十面体的冷冻电镜结构与计算模型非常接近。二十面体能够以极高密度显示免疫原和信号分子,从而增强疫苗反应和血管生成诱导。我们的方法能够自上而下地设计出具有所需系统特性的复杂蛋白质纳米材料,并证明了强化学习在蛋白质设计中的强大作用。
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
Science
Science 综合性期刊-综合性期刊
CiteScore
61.10
自引率
0.90%
发文量
0
审稿时长
2.1 months
期刊介绍: Science is a leading outlet for scientific news, commentary, and cutting-edge research. Through its print and online incarnations, Science reaches an estimated worldwide readership of more than one million. Science’s authorship is global too, and its articles consistently rank among the world's most cited research. Science serves as a forum for discussion of important issues related to the advancement of science by publishing material on which a consensus has been reached as well as including the presentation of minority or conflicting points of view. Accordingly, all articles published in Science—including editorials, news and comment, and book reviews—are signed and reflect the individual views of the authors and not official points of view adopted by AAAS or the institutions with which the authors are affiliated. Science seeks to publish those papers that are most influential in their fields or across fields and that will significantly advance scientific understanding. Selected papers should present novel and broadly important data, syntheses, or concepts. They should merit recognition by the wider scientific community and general public provided by publication in Science, beyond that provided by specialty journals. Science welcomes submissions from all fields of science and from any source. The editors are committed to the prompt evaluation and publication of submitted papers while upholding high standards that support reproducibility of published research. Science is published weekly; selected papers are published online ahead of print.
×
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