Enhancing Evolutionary Couplings with Deep Convolutional Neural Networks.

Cell Syst

Department of Computer Science, University of Illinois at Urbana-Champaign, Champaign, IL 61801, USA. Electronic address:

Published: January 2018

While genes are defined by sequence, in biological systems a protein's function is largely determined by its three-dimensional structure. Evolutionary information embedded within multiple sequence alignments provides a rich source of data for inferring structural constraints on macromolecules. Still, many proteins of interest lack sufficient numbers of related sequences, leading to noisy, error-prone residue-residue contact predictions. Here we introduce DeepContact, a convolutional neural network (CNN)-based approach that discovers co-evolutionary motifs and leverages these patterns to enable accurate inference of contact probabilities, particularly when few related sequences are available. DeepContact significantly improves performance over previous methods, including in the CASP12 blind contact prediction task where we achieved top performance with another CNN-based approach. Moreover, our tool converts hard-to-interpret coupling scores into probabilities, moving the field toward a consistent metric to assess contact prediction across diverse proteins. Through substantially improving the precision-recall behavior of contact prediction, DeepContact suggests we are near a paradigm shift in template-free modeling for protein structure prediction.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5808454PMC
http://dx.doi.org/10.1016/j.cels.2017.11.014DOI Listing

Publication Analysis

Top Keywords

contact prediction
12
convolutional neural
8
cnn-based approach
8
contact
5
enhancing evolutionary
4
evolutionary couplings
4
couplings deep
4
deep convolutional
4
neural networks
4
networks genes
4

Similar Publications

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!