期刊
NATURE STRUCTURAL & MOLECULAR BIOLOGY
卷 29, 期 11, 页码 1056-+出版社
NATURE PORTFOLIO
DOI: 10.1038/s41594-022-00849-w
关键词
-
资金
- European Union [842490]
- Lundbeck Foundation [R272-2017-4528]
- Novo Nordisk Foundation [NNF18OC0033950]
- National Health and Medical Research Council of Australia [GNT1174405]
- Victorian Government's Operational Infrastructure Support Program
- Oracle Research Grant
- Russian Science Foundation (RSF) [20-14-00121]
- Swedish Research Council for Natural Science [VR-2016-06301]
- Knut and Alice Wallenber foundation
- Swedish National Initiative for computing [SNIC 2021/6-197]
- Berzelius
- Swedish E-science Research Center
- Wellcome Trust
- Spanish Science Ministry [PID2019-107043RA-I00, RYC2019-026415-I]
- NIH [DP5OD026389, R21AI156595]
- NSF [MCB2032259]
- Simons Foundation [735929LPI]
- Helmut Horten Stiftung
- ETH Zurich Foundation
- [RTI2018-096653-B-I00]
- Marie Curie Actions (MSCA) [842490] Funding Source: Marie Curie Actions (MSCA)
- Swedish Research Council [2016-06301] Funding Source: Swedish Research Council
This study evaluates the performance of AlphaFold2 in structural biology applications and finds that it performs well and can partially replace experimentally determined structures, which is of great significance for life science research.
Here, the authors evaluate the performance of AlphaFold2 and its predicted structures on common structural biological applications, including missense variants, function and ligand binding site prediction, modeling of interactions and modeling of experimental structural data. Most proteins fold into 3D structures that determine how they function and orchestrate the biological processes of the cell. Recent developments in computational methods for protein structure predictions have reached the accuracy of experimentally determined models. Although this has been independently verified, the implementation of these methods across structural-biology applications remains to be tested. Here, we evaluate the use of AlphaFold2 (AF2) predictions in the study of characteristic structural elements; the impact of missense variants; function and ligand binding site predictions; modeling of interactions; and modeling of experimental structural data. For 11 proteomes, an average of 25% additional residues can be confidently modeled when compared with homology modeling, identifying structural features rarely seen in the Protein Data Bank. AF2-based predictions of protein disorder and complexes surpass dedicated tools, and AF2 models can be used across diverse applications equally well compared with experimentally determined structures, when the confidence metrics are critically considered. In summary, we find that these advances are likely to have a transformative impact in structural biology and broader life-science research.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据