Bioinformatics Vol. 18 no. 8 2002
Pages 1034-1045
© 2002 Oxford University Press
Improving gene recognition accuracy by combining predictions from two gene-finding programs
1 Computer Science Department,
The University of California at Santa Cruz, Baskin Engineering,
Santa Cruz, CA 95064, USA
2 Centre for Molecular Medicine and Therapeutics,
Children’s and Women’s Health Center of British Columbia, UBC,
Vancouver, B.C., Canada V5Z 4H4
3 Computer Science Department,
The University of British Columbia, 2366 Main Mall,
Vancouver, B.C., Canada V6T 1Z4
Received on June 10, 2001
; revised on February 16, 2002
; accepted on February 22, 2002
Motivation: Despite constant improvements in prediction accuracy, gene-finding programs are still unable to provide automatic gene discovery with desired correctness. The current programs can identify up to 75% of exons correctly and less than 50% of predicted gene structures correspond to actual genes. New approaches to computational gene-finding are clearly needed.
Results: In this paper we have explored the benefits of combining predictions from already existing gene prediction programs. We have introduced three novel methods for combining predictions from programs Genscan and HMMgene. The methods primarily aim to improve exon level accuracy of gene-finding by identifying more probable exon boundaries and by eliminating false positive exon predictions. This approach results in improved accuracy at both the nucleotide and exon level, especially the latter, where the average improvement on the newly assembled dataset is 7.9% compared to the best result obtained by Genscan and HMMgene. When tested on a long genomic multi-gene sequence, our method that maintains reading frame consistency improved nucleotide level specificity by 21.0% and exon level specificity by 32.5% compared to the best result obtained by either of the two programs individually.
Availability: The scripts implementing our methods are available from http://www.cs.ubc.ca/labs/beta/genefinding/
Contact: rogic{at}cse.ucsc.edu
* To whom correspondence should be addressed.
CiteULike 
Connotea 
Del.icio.us What's this?
This article has been cited by other articles:
|
|
 |
|
  Q. Liu, A. J. Mackey, D. S. Roos, and F. C. N. Pereira Evigan: a hidden variable model for integrating gene evidence for eukaryotic gene prediction Bioinformatics, March 1, 2008; 24(5): 597 - 605. [Abstract] [Full Text] [PDF]
|
|
|
|
 |
|
 B. Issac and G. P. S. Raghava EGPred: Prediction of Eukaryotic Genes Using Ab Initio Methods After Combining With Sequence Similarity Approaches Genome Res., September 1, 2004; 14(9): 1756 - 1766. [Abstract] [Full Text] [PDF]
|
|
|
|
|
|
J. E. Allen, M. Pertea, and S. L. Salzberg Computational Gene Prediction Using Multiple Sources of Evidence Genome Res., January 1, 2004; 14(1): 142 - 148. [Abstract] [Full Text] [PDF]
|
|
|
|
|
|
M. S. Clark, Y. J.K. Edwards, D. Peterson, S. W. Clifton, A. J. Thompson, M. Sasaki, Y. Suzuki, K. Kikuchi, S. Watabe, K. Kawakami, et al. Fugu ESTs: New Resources for Transcription Analysis and Genome Annotation Genome Res., December 1, 2003; 13(12): 2747 - 2753. [Abstract] [Full Text] [PDF]
|
|
|
|
|
|
O. Couronne, A. Poliakov, N. Bray, T. Ishkhanov, D. Ryaboy, E. Rubin, L. Pachter, and I. Dubchak Strategies and Tools for Whole-Genome Alignments Genome Res., January 1, 2003; 13(1): 73 - 80. [Abstract] [Full Text] [PDF]
|
|