Description

This track shows protein-coding gene predictions generated by CONTRAST. Each predicted exon is colored according to confidence level: green (high confidence), orange (medium confidence), or red (low confidence).

Methods

CONTRAST predicts protein-coding genes from a multiple genomic alignment using a combination of discriminative machine learning techniques. A two-stage approach is used, in which output from local classifiers is combined with a global model of gene structure. CONTRAST is trained using a novel procedure designed to maximize expected coding region boundary detection accuracy.

Please see the CONTRAST web site for details on how these predictions were generated and an estimate of accuracy.

Credits

Thanks to Samuel Gross of the Batzoglou lab at Stanford University for providing these predictions.

References

Gross SS, Do CB, Sirota M, Batzoglou S. CONTRAST: a discriminative, phylogeny-free approach to multiple informant de novo gene prediction. Genome Biol. 2007;8(12):R269. PMID: 18096039; PMC: PMC2246271