Author:
Misiura Mikita,Shroff Raghav,Thyer Ross,Kolomeisky Anatoly B.
Abstract
AbstractPrediction of side chain conformations of amino acids in proteins (also termed ‘packing’) is an important and challenging part of protein structure prediction with many interesting applications in protein design. A variety of methods for packing have been developed but more accurate ones are still needed. Machine learning (ML) methods have recently become a powerful tool for solving various problems in diverse areas of science, including structural biology. In this work we evaluate the potential of Deep Neural Networks (DNNs) for prediction of amino acid side chain conformations. We formulate the problem as image-to-image transformation and train a U-net style DNN to solve the problem. We show that our method outperforms other physics-based methods by a significant margin: reconstruction RMSDs for most amino acids are about 20% smaller compared to SCWRL4 and Rosetta Packer with RMSDs for bulky hydrophobic amino acids Phe, Tyr and Trp being up to 50% smaller.
Publisher
Cold Spring Harbor Laboratory
Reference59 articles.
1. Improved prediction of protein side-chain conformations with scwrl4;Proteins: Structure, Function, and Bioinformatics,2009
2. Protein side chain conformation predictions with an mmgbsa energy function;Proteins: Structure, Function, and Bioinformatics,2016
3. Computational reconstruction of atomistic protein structures from coarse-grained models;Computational and structural biotechnology journal,2020
4. Protein side-chain modeling with a protein-dependent optimized rotamer library;Proteins: Structure, Function, and Bioinformatics,2014
5. Accurate calculation of side chain packing and free energy with applications to protein molecular dynamics;PLoS computational biology,2018
Cited by
7 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献