IDENTIFICATION OF SINGULAR DOMAINS ON CDNA SEQUENCES BY KOHONEN'S FEATURES MAPS

The availability of new ‘non-Von Neumann’ hardware architectures, and the consequent speed-up of the performance permits the development and implementation of more efficient algorithms in order to perform massive analysis of biosequences. At the present, one of the successful classes of new computational methodologies is the Artificial Neural Networks. In this paper we present an application of Kohonen's Self-Organizing Maps (KFM) to the recognition of uncommon domains on cDNA sequences by using FPS 500 EA vectorial computer.