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

Author

Rampone, Salvatore

Author_Institution

Dpt. of Sci. Fisiche E.R. Caianiello, Salerno Univ., Italy

Volume

1

fYear

1998

fDate

4-8 May 1998

Firstpage

774

Abstract

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 disjunctive normal form 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

Keywords

DNA; computational complexity; genetics; learning (artificial intelligence); neural nets; pattern classification; BRAIN learning algorithm; Boolean formulae; DNA; disjunctive normal form formulae; exons; gene sequences; introns; neural network hybrid approach; protein creation; splice-junction recognition; DNA; Inference algorithms; Iterative algorithms; Machine learning; Machine learning algorithms; Optimized production technology; Organisms; Proteins; Sequences; Splicing;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks Proceedings, 1998. IEEE World Congress on Computational Intelligence. The 1998 IEEE International Joint Conference on

Conference_Location

Anchorage, AK

ISSN

1098-7576

Print_ISBN

0-7803-4859-1

Type

conf

DOI

10.1109/IJCNN.1998.682379

Filename

682379