Display Settings:


Send to:

Choose Destination
See comment in PubMed Commons below
Genome Biol. 2007;8(12):R269.

CONTRAST: a discriminative, phylogeny-free approach to multiple informant de novo gene prediction.

Author information

  • 1Computer Science Department, Stanford University, Stanford, CA, USA. ssgross@cs.stanford.edu


We describe CONTRAST, a gene predictor which directly incorporates information from multiple alignments rather than employing phylogenetic models. This is accomplished through the use of discriminative machine learning techniques, including a novel training algorithm. We use a two-stage approach, in which a set of binary classifiers designed to recognize coding region boundaries is combined with a global model of gene structure. CONTRAST predicts exact coding region structures for 65% more human genes than the previous state-of-the-art method, misses 46% fewer exons and displays comparable gains in specificity.

[PubMed - indexed for MEDLINE]
Free PMC Article

Images from this publication.See all images (6)Free text

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
PubMed Commons home

PubMed Commons

How to join PubMed Commons

    Supplemental Content

    Full text links

    Icon for BioMed Central Icon for PubMed Central
    Write to the Help Desk