Protein contact map prediction using committee machine approach

Habibi, N; Saraee, MH; Korbekandi, H

Abstract

A protein contact map is a simplified representation of the protein's spatial
structure. In recent years, contact map prediction has received a great deal of attention
in Bioinformatics. Committee Machine is a machine learning method which shares the
learning task among a number of learners and divides the input space into subspaces.
Learners' responses to an input are combined to produce the system’s final response
which is more accurate than any single individual’s response. In this paper a novel
method called CMP_Model, for contact map prediction based on Committee Machine,
is proposed. In this method, the learner group is a set of neural networks. To analyze
the results of the proposed model, two other models are implemented and their results
are compared and presented. The results show considerable gain (an accuracy
improvement from 0.05 to 0.15) which is achievable by the Committee Machine
approach in the contact map prediction problem.

Citation

Habibi, N., Saraee, M., & Korbekandi, H. (2013). Protein contact map prediction using committee machine approach. International Journal of Data Mining and Bioinformatics, 7(4), 397-415. https://doi.org/10.1504/IJDMB.2013.054226

• Journal Article Type: Article
• Online Publication Date: Apr 29, 2013
• Publication Date: Apr 29, 2013
• Deposit Date: Dec 21, 2011
• Journal: International Journal of Data Mining and Bioinformatics
• Print ISSN: 1748-5673
• Publisher: Inderscience
• Peer Reviewed: Peer Reviewed
• Volume: 7
• Issue: 4
• Pages: 397-415
• DOI: https://doi.org/10.1504/IJDMB.2013.054226
• Publisher URL: http://dx.doi.org/10.1504/IJDMB.2013.054226
• Related Public URLs: http://www.inderscience.com/jhome.php?jcode=ijdmb