Thursday, January 28, 2021

“ResPRE: high-accuracy protein contact prediction by coupling precision matrix with deep residual neural networks”

12:00 PM to 1:00 PM

Zoom Live Stream

Tools & Technology Seminar Series
by Yang Li (Computational Medicine & Bioinformatics)

Abstract

Contact-map of a protein sequence dictates the global topology of structural fold. Accurate prediction of the contact-map is thus essential to protein 3D structure prediction, which is particularly useful for the protein sequences that do not have close homology templates in the Protein Data Bank.  In this talk, we present a new method, ResPRE, to predict residue-level protein contacts using inverse covariance matrix (or precision matrix) of multiple sequence alignments (MSAs) through deep residual convolutional neural network training. Detailed data analyses show that the major advantage of ResPRE lies at the utilization of precision matrix that helps rule out transitional noises of contact-maps compared with the previously used covariance matrix. Meanwhile, the residual network with parallel shortcut layer connections increases the learning ability of deep neural network training. It was also found that appropriate collection of MSAs can further improve the accuracy of final contact-map predictions.