Title: Protein model assessment via machine learning techniques

Authors: Anjum Reyaz-Ahmed, Robert Harrison, Yan-Qing Zhang

Addresses: Department of Computer Science, Georgia State University, Atlanta, GA 30302-3965, USA. ' Department of Computer Science, Georgia State University, Atlanta, GA 30302-3965, USA. ' Department of Computer Science, Georgia State University, Atlanta, GA 30302-3965, USA

Abstract: We attempt to solve the problem of protein model assessment using machine learning techniques and information from sequence and structure of the protein. The goal is to generate a machine that understands structures from PDB and given a new model, predicts whether or not it belongs to the class of PDB structures. We show two such machines (SVM and FDT); results appear promising for further analysis. To reduce computational overhead, multiprocessor environment and basic feature selection method is used. The prediction accuracy using improved FDT is above 80% and results are better when compared with other machine learning techniques.

Keywords: fuzzy decision tree; feature selection; fuzzy ID3; machine learning; protein 3D structures; protein model assessment; SVM; support vector machines; FDT.

DOI: 10.1504/IJFIPM.2010.039121

International Journal of Functional Informatics and Personalised Medicine, 2010 Vol.3 No.3, pp.215 - 227

Received: 24 Sep 2010
Accepted: 08 Dec 2010
Published online: 17 Mar 2011 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article