A clustering method of chromosome fluorescence profiles using self organizing map

The clustering method by the self-organizing map algorithm of chromosome profiles measured by slit-scan flowcytometer is proposed. Chromosome profile represents the distribution of the fluorescence intensities along the lengthwise. To examine the performance of the cytometer developed in our laboratory, we made clustering experiments of the measured profiles. We developed a SOM based clustering algorithm using chromosome physical model, which can estimate the chromosome models and rotation angles, but the results were considered to be not complete. For this problem, we propose a new algorithm, which estimate the models and rotation angles step by step. We examine our algorithm using the virtual profiles and profiles measured by our cytometer.