Comparative gene prediction based on gene structure conservation

Authors:
Shu Ju Hsieh;Chun Yuan Lin;Ning Han Liu;Chuan Yi Tang
Affiliations:
Department of Computer Science;Institute of Molecular and Cellular Biology, National Tsing-Hua University, Hsinchu, Taiwan, ROC;Department of Computer Science;Department of Computer Science
Venue:
PRIB'06 Proceedings of the 2006 international conference on Pattern Recognition in Bioinformatics
Year:
2006

Citing 7
Cited 0

Neural Network Prediction of Translation Initiation Sites in Eukaryotes: Perspectives for EST and Genome Analysis

Proceedings of the 5th International Conference on Intelligent Systems for Molecular Biology
Gene structure prediction from consensus spliced alignment of multiple ESTs matching the same genomic locus

Bioinformatics
ExonHunter: a comprehensive approach to gene finding

Bioinformatics
Prediction of splice sites with dependency graphs and their expanded bayesian networks

Bioinformatics
GMAP: a genomic mapping and alignment program for mRNA and EST sequences

Bioinformatics
JIGSAW: integration of multiple sources of evidence for gene prediction

Bioinformatics
Comparative Exon Prediction based on Heuristic Coding Region Alignment

ISPAN '05 Proceedings of the 8th International Symposium on Parallel Architectures,Algorithms and Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Identifying protein coding genes is one of most important task in newly sequenced genomes. With increasing numbers of gene annotations verified by experiments, it is feasible to identify genes in newly sequenced genomes by comparing with genes annotated on phylogenetically close organisms. Here, we propose a program, GeneAlign, which predicts the genes on one sequence by measuring the similarity between the predicted sequence and related genes annotated on another genome. The program applies CORAL, a heuristic linear time alignment tool, to determine whether the regions flanked by candidate signals are similar with the annotated exons or not. The approach, which employs the conservation of gene structures and sequence homologies between protein coding regions, increases the prediction accuracy. GeneAlign was tested on Projector data set of 449 human-mouse homologous sequence pairs. At the gene level, the sensitivity and specificity of GeneAlign are 80%, and larger than 96% at the exon level.