Clustering and visualizing HIV quasispecies using Kohonen's self-organizing maps

  • Authors:

  • A. M. Mora;J. J. Merelo;C. Briones;F. Morán;J . L .J. Laredo

  • Affiliations:

  • Dept. ATC, U. Granada, Spain;Dept. ATC, U. Granada, Spain;Centro de Astrobiología, Madrid, Spain;Centro de Astrobiología, Madrid, Spain and Depto. Bioquímica, U. Complutense, Madrid, Spain;Dept. ATC, U. Granada, Spain

  • Venue:
  • IWANN'07 Proceedings of the 9th international work conference on Artificial neural networks
  • Year:
  • 2007

Quantified Score

Hi-index 0.01

Visualization

Abstract

In this paper we describe how the self-organizing map can be applied to the visualization of the evolution and change of Human Immunodeficiency Virus (HIV) quasiespecies, and how this could be converted into a predictive tool. A SOM is trained with a set of nucleic acid sequences from the HIV-1 virus, and the U-Matrix method is applied to discover what natural groups are formed within it. Results show the validity of the method, and allow to discover two groupings within these sets, and what is the evolutionary path taken in them.