Title: Improving deep learning-based protein distance prediction in CASP14

Abstract

Motivation. Accurate prediction of residue–residue distances is important for protein structure prediction. We developed several protein distance predictors based on a deep learning distance prediction method and blindly tested them in the 14th Critical Assessment of Protein Structure Prediction (CASP14). The prediction method uses deep residual neural networks with the channel-wise attention mechanism to classify the distance between every two residues into multiple distance intervals. The input features for the deep learning method include co-evolutionary features as well as other sequence-based features derived from multiple sequence alignments (MSAs). Three alignment methods are used with multiple protein sequence/profile databases to generate MSAs for input feature generation. Based on different configurations and training strategies of the deep learning method, five MULTICOM distance predictors were created to participate in the CASP14 experiment. Results. Benchmarked on 37 hard CASP14 domains, the best performing MULTICOM predictor is ranked 5th out of 30 automated CASP14 distance prediction servers in terms of precision of top L/5 long-range contact predictions [i.e. classifying distances between two residues into two categories: in contact (<8 Angstrom) and not in contact otherwise] and performs better than the best CASP13 distance prediction method. The best performing MULTICOM predictor is also ranked 6th amongmore » automated server predictors in classifying inter-residue distances into 10 distance intervals defined by CASP14 according to the precision of distance classification. The results show that the quality and depth of MSAs depend on alignment methods and sequence databases and have a significant impact on the accuracy of distance prediction. Using larger training datasets and multiple complementary features improves prediction accuracy. However, the number of effective sequences in MSAs is only a weak indicator of the quality of MSAs and the accuracy of predicted distance maps. In contrast, there is a strong correlation between the accuracy of contact/distance predictions and the average probability of the predicted contacts, which can therefore be more effectively used to estimate the confidence of distance predictions and select predicted distance maps.« less

Authors:

Guo, Zhiye; Wu, Tianqi; Liu, Jian; Hou, Jie; Cheng, Jianlin ;

• Search DOE PAGES for author "Cheng, Jianlin"
• Search DOE PAGES for ORCID "0000-0003-0305-2853"

Martelli, ed., Pier Luigi

Publication Date:

Fri May 07 00:00:00 EDT 2021

Research Org.:

Georgia Institute of Technology, Atlanta, GA (United States); Donald Danforth Plant Science Center, St. Louis, MO (United States)

Sponsoring Org.:

USDOE Office of Science (SC), Basic Energy Sciences (BES). Scientific User Facilities (SUF); National Science Foundation (NSF); National Institutes of Health (NIH); USDOE Office of Science (SC), Biological and Environmental Research (BER)

OSTI Identifier:

1826198

Alternate Identifier(s):

OSTI ID: 1787924; OSTI ID: 1839183; OSTI ID: 2278966; OSTI ID: 2318538

Grant/Contract Number:  

SC0020400; SC0021303; BIF132

Resource Type:

Published Article

Journal Name:

Bioinformatics

Additional Journal Information:

Journal Name: Bioinformatics Journal Volume: 37 Journal Issue: 19; Journal ID: ISSN 1367-4803

Publisher:

Oxford University Press

Country of Publication:

United Kingdom

Language:

English

Subject:

59 BASIC BIOLOGICAL SCIENCES