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

@inproceedings{Kumar2009AugmentedTO,
  title={Augmented training of hidden Markov models to recognize remote homologs via simulated evolution},
  author={A. John Sanjeev Kumar and Lenore Cowen},
  booktitle={Bioinformatics},
  year={2009}
}
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… CONTINUE READING

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • 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.

Similar Papers

Citations

Publications citing this paper.
SHOWING 1-10 OF 20 CITATIONS

Identifying Affinity Classes of Inorganic Materials Binding Sequences via a Graph-Based Model

  • IEEE/ACM Transactions on Computational Biology and Bioinformatics
  • 2015
VIEW 8 EXCERPTS
CITES RESULTS, BACKGROUND & METHODS
HIGHLY INFLUENCED

Discriminative Motif Discovery via Simulated Evolution and Random Under-Sampling

  • PloS one
  • 2014
VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Identifying inorganic material affinity classes for peptide sequences based on context learning

  • 2015 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)
  • 2015

MRFy: Remote Homology Detection for Beta-Structural Proteins Using Markov Random Fields and Stochastic Search

  • IEEE/ACM Transactions on Computational Biology and Bioinformatics
  • 2015
VIEW 2 EXCERPTS
CITES BACKGROUND & METHODS

References

Publications referenced by this paper.
SHOWING 1-10 OF 28 REFERENCES

Where did the BLOSUM62 alignment score matrix come from?

  • Nature Biotechnology
  • 2004
VIEW 1 EXCERPT
HIGHLY INFLUENTIAL

The PROSITE database

  • Nucleic Acids Research
  • 2006
VIEW 1 EXCERPT