Article: A new approach to gene prediction, based on the self-organising map Journal: International Journal of Medical Engineering and Informatics (IJMEI) 2010 Vol.2 No.2 pp.107 - 121 Abstract: In the present scenario, gene prediction methods use only one model to represent protein-coding regions in a genome, and so the chances of predicting the location of genes that have a typical sequence composition is rare. It is predicted that future improvements in gene finding will be based on various methods of development that can adequately deal with intra-genomic compositional variation. This work explores a new approach to gene prediction, based on the self-organising map (SOM), which has the ability to automatically identify multiple gene models within a genome. The current implementation, named codon usage information (CUI), uses relative synonymous codon usage (RSCU) as the indicator of protein-coding potential. Though the raw accuracy rate is considered less than other methods, CUI consistently identifies some genes that other methods do not, and should therefore be of interest to gene prediction software developers and people working on genome annotation. CUI is recommended for use in conjunction with, or as a complement to, other gene prediction methods. Inderscience Publishers - linking academia, business and industry through research

Title: A new approach to gene prediction, based on the self-organising map

Authors: Veera Talukdar, Amit Konar, Shibram Paria, Subhasis Maity, Tapas Kumar Pal

Addresses: NCMT-NSHM-Knowledge Campus, 124 B.L. Saha Road, Kolkata-700053, India. ' Department of Electronics and Telecommunication Engineering, Jadavpur University, Kolkata-700032, India. ' NCMT-NSHM-Knowledge Campus, 124 B.L. Saha Road, Kolkata-700053, India. ' NCMT-NSHM-Knowledge Campus, 124 B.L. Saha Road, Kolkata-700053, India. ' NCMT-NSHM-Knowledge Campus, 124 B.L. Saha Road, Kolkata-700053, India

Abstract: In the present scenario, gene prediction methods use only one model to represent protein-coding regions in a genome, and so the chances of predicting the location of genes that have a typical sequence composition is rare. It is predicted that future improvements in gene finding will be based on various methods of development that can adequately deal with intra-genomic compositional variation. This work explores a new approach to gene prediction, based on the self-organising map (SOM), which has the ability to automatically identify multiple gene models within a genome. The current implementation, named codon usage information (CUI), uses relative synonymous codon usage (RSCU) as the indicator of protein-coding potential. Though the raw accuracy rate is considered less than other methods, CUI consistently identifies some genes that other methods do not, and should therefore be of interest to gene prediction software developers and people working on genome annotation. CUI is recommended for use in conjunction with, or as a complement to, other gene prediction methods.

Keywords: codon usage; gene prediction; homology; genome annotation; computational methods; self-organising maps; protein coding; gene sequences; bioinformatics.

DOI: 10.1504/IJMEI.2010.031514

International Journal of Medical Engineering and Informatics, 2010 Vol.2 No.2, pp.107 - 121

Published online: 08 Feb 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: A new approach to gene prediction, based on the self-organising map

Keep up-to-date