Statistical Approaches to Automated Gene Identification Without Teacher.

摘要

An overview of the statistical methods of gene identification are presented. Particular attention is given to the method which need not a training set of already known genes. After analysis several statistical approaches are proposed for computational exon identification in whole genomes. For several gemones an optimal window length for averaging GC-content function and calculating codon frequencies has been found. Self-training procedure based on clustering in multidimensional codon frequencies space is proposed.