Protein sequence classification using probabilistic motifs and neural networks

  • Authors:

  • Konstantinos Blekas;Dimitrios I. Fotiadis;Aristidis Likas

  • Affiliations:

  • Department of Computer Science, University of Ioannina, Ioannina, Greece and Biomedical Research Institute, FORTH - Hellas, Ioannina, Greece;Department of Computer Science, University of Ioannina, Ioannina, Greece and Biomedical Research Institute, FORTH - Hellas, Ioannina, Greece;Department of Computer Science, University of Ioannina, Ioannina, Greece and Biomedical Research Institute, FORTH - Hellas, Ioannina, Greece

  • Venue:
  • ICANN/ICONIP'03 Proceedings of the 2003 joint international conference on Artificial neural networks and neural information processing
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

The basic issue concerning the construction of neural network systems for protein classification is the sequence encoding scheme that must be used in order to feed the network. To deal with this problem we propose a method that maps a protein sequence into a numerical feature space using the matching local scores of the sequence to groups of conserved patterns (called motifs). We consider two alternative schemes for discovering a group of D motifs within a set of K-class sequences. We also evaluate the impact of the background features (2-grams) to the performance of the neural system. Experimental results on real datasets indicate that the proposed method is superior to other known protein classification approaches.