Display Settings:

Format

Send to:

Choose Destination
See comment in PubMed Commons below
Bioinformatics. 2009 Jul 1;25(13):1602-8. doi: 10.1093/bioinformatics/btp265. Epub 2009 Apr 23.

Augmented training of hidden Markov models to recognize remote homologs via simulated evolution.

Author information

  • 1Department of Computer Science, Tufts University, Medford, MA, USA. anoop.kumar@tufts.edu

Abstract

MOTIVATION:

While profile hidden Markov models (HMMs) are successful and powerful methods to recognize homologous proteins, they can break down when homology becomes too distant due to lack of sufficient training data. We show that we can improve the performance of HMMs in this domain by using a simple simulated model of evolution to create an augmented training set.

RESULTS:

We show, in two different remote protein homolog tasks, that HMMs whose training is augmented with simulated evolution outperform HMMs trained only on real data. We find that a mutation rate between 15 and 20% performs best for recognizing G-protein coupled receptor proteins in different classes, and for recognizing SCOP super-family proteins from different families.

PMID:
19389731
[PubMed - indexed for MEDLINE]
PMCID:
PMC2732314
Free PMC Article

Images from this publication.See all images (9)Free text

Fig. 1.
Fig. 2.
Fig. 3.
Fig. 4.
Fig. 5.
Fig. 6.
Fig. 7.
Fig. 8.
Fig. 9.
PubMed Commons home

PubMed Commons

0 comments
How to join PubMed Commons

    Supplemental Content

    Full text links

    Icon for HighWire Icon for PubMed Central
    Loading ...
    Write to the Help Desk