期刊
PROTEINS-STRUCTURE FUNCTION AND BIOINFORMATICS
卷 89, 期 5, 页码 493-501出版社
WILEY
DOI: 10.1002/prot.26033
关键词
equivariant neural network; physics‐ aware machine learning; protein docking; representation learning
资金
- Air Force Office of Scientific Research [FA9550-16-1-0082]
- Intel Corporation
- Stanford Bio-X
- U.S. Department of Energy Office of Science
The study introduces a machine learning method that learns directly from the atomic coordinates of protein complexes to identify accurate models without predefined assumptions. The neural network architecture presented combines various elements to enable end-to-end learning from molecular structures containing tens
Predicting the structure of multi-protein complexes is a grand challenge in biochemistry, with major implications for basic science and drug discovery. Computational structure prediction methods generally leverage predefined structural features to distinguish accurate structural models from less accurate ones. This raises the question of whether it is possible to learn characteristics of accurate models directly from atomic coordinates of protein complexes, with no prior assumptions. Here we introduce a machine learning method that learns directly from the 3D positions of all atoms to identify accurate models of protein complexes, without using any precomputed physics-inspired or statistical terms. Our neural network architecture combines multiple ingredients that together enable end-to-end learning from molecular structures containing tens of thousands of atoms: a point-based representation of atoms, equivariance with respect to rotation and translation, local convolutions, and hierarchical subsampling operations. When used in combination with previously developed scoring functions, our network substantially improves the identification of accurate structural models among a large set of possible models. Our network can also be used to predict the accuracy of a given structural model in absolute terms. The architecture we present is readily applicable to other tasks involving learning on 3D structures of large atomic systems.
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