Learning from prepandemic data to forecast viral escape.
Learning from prepandemic data to forecast viral escape.
复制标题
DOI：
10.1038/s41586-023-06617-0
复制
发表时间：
2023-10
期刊：
影响因子：
64.8
通讯作者：
Marks, Debora S.
中科院分区：
文献类型：
--
作者：
Thadani, Nicole N.;Gurev, Sarah;Notin, Pascal;Youssef, Noor;Rollins, Nathan J.;Ritter, Daniel;Sander, Chris;Gal, Yarin;Marks, Debora S.
有效的大流行防范依赖于预测能够逃避宿主免疫反应的病毒突变，以促进疫苗和治疗设计。然而，目前的病毒进化预测策略在大流行早期尚不可用——实验方法需要宿主多克隆抗体进行测试，而现有的计算方法大量利用当前病毒株的流行情况来对所关注的变体做出可靠的预测。为了解决这个问题，我们开发了 EVEscape，这是一个通用的模块化框架，它将历史序列深度学习模型的适应性预测与生物物理和结构信息相结合。 EVEscape 大规模量化了突变的病毒逃逸潜力，并具有在监测测序、实验扫描或抗体复合物三维结构可用之前适用的优势。我们证明，EVEscape 在 2020 年之前可用的序列上进行训练，在预测 SARS-CoV-2 大流行变异方面与高通量实验扫描一样准确，并且可推广到其他病毒，包括流感、艾滋病毒和尚未研究的具有大流行潜力的病毒，如拉沙病毒和尼帕病毒。我们为所有当前的 SARS-CoV-2 毒株提供不断修订的逃逸评分，并预测可能的进一步突变，以预测新出现的毒株，作为持续疫苗开发的工具 (evescape.org)。 EVEscape 是一个使用深度学习和生物物理结构信息的灵活框架，能够及早识别具有大流行潜力的病毒中的相关突变，从而促进疫苗和治疗方法的开发。
Effective pandemic preparedness relies on anticipating viral mutations that are able to evade host immune responses to facilitate vaccine and therapeutic design. However, current strategies for viral evolution prediction are not available early in a pandemic—experimental approaches require host polyclonal antibodies to test against, and existing computational methods draw heavily from current strain prevalence to make reliable predictions of variants of concern. To address this, we developed EVEscape, a generalizable modular framework that combines fitness predictions from a deep learning model of historical sequences with biophysical and structural information. EVEscape quantifies the viral escape potential of mutations at scale and has the advantage of being applicable before surveillance sequencing, experimental scans or three-dimensional structures of antibody complexes are available. We demonstrate that EVEscape, trained on sequences available before 2020, is as accurate as high-throughput experimental scans at anticipating pandemic variation for SARS-CoV-2 and is generalizable to other viruses including influenza, HIV and understudied viruses with pandemic potential such as Lassa and Nipah. We provide continually revised escape scores for all current strains of SARS-CoV-2 and predict probable further mutations to forecast emerging strains as a tool for continuing vaccine development (evescape.org). EVEscape, a flexible framework using deep learning and biophysical structural information, enables early identification of concerning mutations in viruses with pandemic potential, facilitating the development of vaccines and therapeutics.
登录
查看更多内容
影响因子：
16.6
作者：
Greaney AJ;Starr TN;Barnes CO;Weisblum Y;Schmidt F;Caskey M;Gaebler C;Cho A;Agudelo M;Finkin S;Wang Z;Poston D;Muecksch F;Hatziioannou T;Bieniasz PD;Robbiani DF;Nussenzweig MC;Bjorkman PJ;Bloom JD
通讯作者：
Bloom JD
两种抗体鸡尾酒中和中和的遗传和结构基础。
影响因子：
28.3
作者：
Dong J;Zost SJ;Greaney AJ;Starr TN;Dingens AS;Chen EC;Chen RE;Case JB;Sutton RE;Gilchuk P;Rodriguez J;Armstrong E;Gainza C;Nargi RS;Binshtein E;Xie X;Zhang X;Shi PY;Logue J;Weston S;McGrath ME;Frieman MB;Brady T;Tuffy KM;Bright H;Loo YM;McTamney PM;Esser MT;Carnahan RH;Diamond MS;Bloom JD;Crowe JE Jr
通讯作者：
Crowe JE Jr
影响因子：
6.4
作者：
Borisevich, Viktoriya;Lee, Benhur;Rockx, Barry
通讯作者：
Rockx, Barry
影响因子：
64.8
作者：
CHOTHIA, C;JANIN, J
通讯作者：
JANIN, J
影响因子：
7.7
作者：
Flynn, Julia M.;Samant, Neha;Schneider-Nachum, Gily;Barkan, David T.;Yilmaz, Nese Kurt;Schiffer, Celia A.;Moquin, Stephanie A.;Dovala, Dustin;Bolon, Daniel N. A.
通讯作者：
Bolon, Daniel N. A.