Please use this identifier to cite or link to this item:
Main Title: EPSILON-CP: using deep learning to combine information from multiple sources for protein contact prediction
Author(s): Stahl, Kolja
Schneider, Michael
Brock, Oliver
Type: Article
Language Code: en
Abstract: Background Accurately predicted contacts allow to compute the 3D structure of a protein. Since the solution space of native residue-residue contact pairs is very large, it is necessary to leverage information to identify relevant regions of the solution space, i.e. correct contacts. Every additional source of information can contribute to narrowing down candidate regions. Therefore, recent methods combined evolutionary and sequence-based information as well as evolutionary and physicochemical information. We develop a new contact predictor (EPSILON-CP) that goes beyond current methods by combining evolutionary, physicochemical, and sequence-based information. The problems resulting from the increased dimensionality and complexity of the learning problem are combated with a careful feature analysis, which results in a drastically reduced feature set. The different information sources are combined using deep neural networks. Results On 21 hard CASP11 FM targets, EPSILON-CP achieves a mean precision of 35.7% for top- L/10 predicted long-range contacts, which is 11% better than the CASP11 winning version of MetaPSICOV. The improvement on 1.5L is 17%. Furthermore, in this study we find that the amino acid composition, a commonly used feature, is rendered ineffective in the context of meta approaches. The size of the refined feature set decreased by 75%, enabling a significant increase in training data for machine learning, contributing significantly to the observed improvements. Conclusions Exploiting as much and diverse information as possible is key to accurate contact prediction. Simply merging the information introduces new challenges. Our study suggests that critical feature analysis can improve the performance of contact prediction methods that combine multiple information sources. EPSILON-CP is available as a webservice:
Issue Date: 17-Jun-2017
Date Available: 3-Dec-2018
DDC Class: 570 Biowissenschaften; Biologie
004 Datenverarbeitung; Informatik
Subject(s): contact prediction
meta algorithms
deep learning
Sponsor/Funder: TU Berlin, Open-Access-Publikationsfonds – 2017
Journal Title: BMC Bioinformatics
Publisher: BioMed Central
Publisher Place: London
Volume: 18
Article Number: 303
Publisher DOI: 10.1186/s12859-017-1713-x
ISSN: 1471-2105
Appears in Collections:FG Robotics » Publications

Files in This Item:
File Description SizeFormat 
s12859-017-1713-x.pdf697.49 kBAdobe PDFThumbnail

This item is licensed under a Creative Commons License Creative Commons