Listy Biometryczne - Biometrical Letters, Vol. 40 (2003), No. 2, 37-56


Show full-size cover
KOHONEN'S SELF-ORGANIZING MAPS AS APPLIED TO GRAPHICAL
VISUALIZATION OF SOME YEAST DNA DATA

Anna Bartkowiak1, Adam Szustalewicz1, Stanislaw Cebrat2,
Pawel Mackiewicz2

1Institute of Computer Science, University of Wroclaw,
Przesmyckiego 20, 50-151 Wroclaw
2Institute of Genetics and Microbiology, University of Wroclaw,
Przybyszewskiego 63/77, 51-148 Wroclaw


We analyze a set of data describing 3300 yeast genes, each gene characterized by 13 variables (traits). First we performed an explorative data analysis and stated a high multivariate kurtosis. Next we clustered the data and visualized them using Kohonen's self-organizing maps. This permitted us to get an idea how the data are distributed in the multivariate space.


explorative analysis, clustering, self-organizing maps, yeast genome.