DOMpro: Protein Domain Prediction Using Profiles, Secondary Structure, Relative Solvent Accessibility, and Recursive Neural Networks

Authors:
Jianlin Cheng;Michael J. Sweredoski;Pierre Baldi
Affiliations:
Institute for Genomics and Bioinformatics, School of Information and Computer Sciences, University of California Irvine, Irvine, USA 92697;Institute for Genomics and Bioinformatics, School of Information and Computer Sciences, University of California Irvine, Irvine, USA 92697;Institute for Genomics and Bioinformatics, School of Information and Computer Sciences, University of California Irvine, Irvine, USA 92697
Venue:
Data Mining and Knowledge Discovery
Year:
2006

Citing 6
Cited 3

The principled design of large-scale recursive neural network architectures--dag-rnns and the protein structure prediction problem

The Journal of Machine Learning Research
Automatic prediction of protein domains from sequence information using a hybrid learning system

Bioinformatics
Arby: automatic protein structure prediction using profile--profile alignment and confidence measures

Bioinformatics
Accurate Prediction of Protein Disordered Regions by Mining Protein Structure Data

Data Mining and Knowledge Discovery
Meta-DP: domain prediction meta-server

Bioinformatics
SSEP-Domain: protein domain prediction by alignment of secondary structure elements and profiles

Bioinformatics

SPlitSSI-SVM: An algorithm to reduce the misleading and increase the strength of domain signal

Computers in Biology and Medicine
Predicting protective bacterial antigens using random forest classifiers

Proceedings of the ACM Conference on Bioinformatics, Computational Biology and Biomedicine
PPM-Dom: A novel method for domain position prediction

Computational Biology and Chemistry

Quantified Score

Hi-index	0.00

Visualization

Abstract

Protein domains are the structural and functional units of proteins. The ability to parse protein chains into different domains is important for protein classification and for understanding protein structure, function, and evolution. Here we use machine learning algorithms, in the form of recursive neural networks, to develop a protein domain predictor called DOMpro. DOMpro predicts protein domains using a combination of evolutionary information in the form of profiles, predicted secondary structure, and predicted relative solvent accessibility. DOMpro is trained and tested on a curated dataset derived from the CATH database. DOMpro correctly predicts the number of domains for 69% of the combined dataset of single and multi-domain chains. DOMpro achieves a sensitivity of 76% and specificity of 85% with respect to the single-domain proteins and sensitivity of 59% and specificity of 38% with respect to the two-domain proteins. DOMpro also achieved a sensitivity and specificity of 71% and 71% respectively in the Critical Assessment of Fully Automated Structure Prediction 4 (CAFASP-4) (Fisher et al., 1999; Saini and Fischer, 2005) and was ranked among the top ab initio domain predictors. The DOMpro server, software, and dataset are available at http://www.igb.uci.edu/servers/psss.html.