Clustering of chromosome fluorescence profiles by self-organising map using chromosome physical models

Abstract

The clustering by the self-organizing map algorithm of chromosome proles measured by slit-scan owcytometer is proposed. Moreover, the physical models of chromosomes have been introduced i n o r der to take into account the rotation of chromosomes in the owcytometer. The self-organizing map algorithm has been improved so that it can modify the characteristic parameters of chromosome physical models. By this modication, the lengths of chromosomes and the intensity distribution of chromosome uorescence c an be estimated f r om chromosome prole data measured b y the owcytometer. The estimated lengths of chromosomes have been almost equal to known values of the lengths of chromosomes. The clustering results by the above method have been compared with the clustering results of the same data by K-mean method and an agglomerative hierarchical clustering.