Title: Understandable learning machine system design for Transmembrane or Embedded Membrane segments prediction

Authors: Hae-Jin Hu, Robert W. Harrison, Phang C. Tai, Yi Pan

Addresses: Department of Computer Science, Georgia State University, Atlanta, GA 30303, USA. ' Department of Computer Science, Georgia State University, Atlanta, GA 30303, USA; and Department of Biology, Georgia State University, Atlanta, GA 30303, USA. ' Department of Biology, Georgia State University, Atlanta, GA 30303, USA. ' Department of Computer Science, Georgia State University, Atlanta, GA 30303, USA

Abstract: We modified an existing association rule–based classifier CPAR to improve traditional black box model based learning machine approaches on Transmembrane (TM) segment prediction. The modified classifier was improved further by combining with SVM. The experimental results indicate that this hybrid scheme offers biologically meaningful rules on TM/EM segment prediction while maintaining the performance almost as well as the SVM method. The evaluation of the sturdiness and the Receiver Operating Characteristic (ROC) curve analysis proved that this new scheme is robust and competent with SVM on TM/EM segment prediction. The prediction server is available at http:/ /bmcc2.cs.gsu.edu/∼haeh2/.

Keywords: association rules; classifiers; SVM; support vector machines; transmembrane segments; embedded membrane segments; machine learning.

DOI: 10.1504/IJDMB.2011.038576

International Journal of Data Mining and Bioinformatics, 2011 Vol.5 No.1, pp.38 - 51

Received: 15 Feb 2009
Accepted: 08 Jul 2009
Published online: 24 Jan 2015 *

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