Identification of singular domains on nucleotidic sequences by SOFM

Molecular Biology offers an very important application field in order to test the performance of different neural architectures. The analysis of biosequences represents one of the more important tasks. Genomic sequences could be considered like noisy signals and the knowledge about the syntactical rules that regulate the gene expression are not well known. This reason induced the authors to refuse all the knowledge about the genomic feature and to make a new `blind' search on a complete sequence, in order to take in account the contextural effect on this kind of pattern recognition. An application of Kohonen's Self-Organizing Maps (KFM) to the recognition of uncommon domains on cDNA sequences is presented