Artificial Intelligence Review

, Volume 24, Issue 3–4, pp 397–413

Self-Organizing Maps of Position Weight Matrices for Motif Discovery in Biological Sequences

  • Shaun Mahony
  • David Hendrix
  • Terry J. Smith
  • Aaron Golden
Article

DOI: 10.1007/s10462-005-9011-9

Cite this article as:
Mahony, S., Hendrix, D., Smith, T.J. et al. Artif Intell Rev (2005) 24: 397. doi:10.1007/s10462-005-9011-9

Abstract

The identification of overrepresented motifs in a collection of biological sequences continues to be a relevant and challenging problem in computational biology. Currently popular methods of motif discovery are based on statistical learning theory. In this paper, a machine-learning approach to the motif discovery problem is explored. The approach is based on a Self-Organizing Map (SOM) where the output layer neuron weight vectors are replaced by position weight matrices. This approach can be used to characterise features present in a set of sequences, and thus can be used as an aid in overrepresented motif discovery. The SOM approach to motif discovery is demonstrated using biological sequence datasets, both real and simulated

Keywords

biological motif discovery self-organizing map 

Copyright information

© Springer 2005

Authors and Affiliations

  • Shaun Mahony
    • 1
  • David Hendrix
    • 2
  • Terry J. Smith
    • 1
  • Aaron Golden
    • 1
    • 3
  1. 1.National Centre for Biomedical Engineering ScienceNUI GalwayGalwayIreland
  2. 2.Center for Integrative GenomicsUniversity of CaliforniaBerkeleyUSA
  3. 3.Department of Information TechnologyNUI GalwayGalwayIreland

Personalised recommendations