Analysis of distance‐based protein structure prediction by deep learning in CASP13

• Published in: Proteins, structure, function, and bioinformatics Vol. 87; no. 12; pp. 1069 - 1081
• Main Authors: Xu, Jinbo, Wang, Sheng
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 01-12-2019; Wiley Subscription Services, Inc
• Subjects: Artificial neural networks; coevolution analysis; critical assessment of structure prediction; deep convolutional residual neural network; Deep learning; Machine learning; Modelling; multiple sequence alignment; Neural networks; Nucleotide sequence; Predictions; protein contact and distance prediction; protein folding; Protein structure; Servers; Three dimensional models; coevolution analysis; critical assessment of structure prediction; protein folding; deep convolutional residual neural network; protein contact and distance prediction; multiple sequence alignment
• ISSN: 0887-3585; 1097-0134
• DOI: 10.1002/prot.25810

This paper reports the CASP13 results of distance‐based contact prediction, threading, and folding methods implemented in three RaptorX servers, which are built upon the powerful deep convolutional residual neural network (ResNet) method initiated by us for contact prediction in CASP12. On the 32 CASP13 FM (free‐modeling) targets with a median multiple sequence alignment (MSA) depth of 36, RaptorX yielded the best contact prediction among 46 groups and almost the best 3D structure modeling among all server groups without time‐consuming conformation sampling. In particular, RaptorX achieved top L/5, L/2, and L long‐range contact precision of 70%, 58%, and 45%, respectively, and predicted correct folds (TMscore > 0.5) for 18 of 32 targets. Further, RaptorX predicted correct folds for all FM targets with >300 residues (T0950‐D1, T0969‐D1, and T1000‐D2) and generated the best 3D models for T0950‐D1 and T0969‐D1 among all groups. This CASP13 test confirms our previous findings: (a) predicted distance is more useful than contacts for both template‐based and free modeling; and (b) structure modeling may be improved by integrating template and coevolutionary information via deep learning. This paper will discuss progress we have made since CASP12, the strength and weakness of our methods, and why deep learning performed much better in CASP13.