Splice-junction recognition on gene sequences (DNA) by BRAIN learning algorithm

Splice junctions are points on a DNA sequence at which 'superfluous' DNA is removed during the process of protein creation in higher organisms. The problem afforded in this paper is to recognize, given a sequence of DNA, the boundaries between exons (the parts of the DNA sequence retained after splicing) and introns (the parts of the DNA sequence that are spliced out). This is achieved by means of a new learning algorithm (BRAIN), described in the paper, inferring Boolean formulae from examples, and by considering the splicing rules as DNF formulae. The formula terms are computed in an iterative way, by identifying from the training set a relevance coefficient for each attribute. The classification accuracy is then refined by a neural network hybrid approach.