Enhanced protein domain discovery by using language modeling techniques from speech recognition.

Abstract

Most modern speech recognition uses probabilistic models to interpret a sequence of sounds. Hidden Markov models, in particular, are used to recognize words. The same techniques have been adapted to find domains in protein sequences of amino acids. To increase word accuracy in speech recognition, language models are used to capture the information that certain word combinations are more likely than others, thus improving detection based on context. However, to date, these context techniques have not been applied to protein domain discovery. Here we show that the application of statistical language modeling methods can significantly enhance domain recognition in protein sequences. As an example, we discover an unannotated Tf_Otx Pfam domain on the cone rod homeobox protein, which suggests a possible mechanism for how the V242M mutation on this protein causes cone-rod dystrophy.

• Authors: Lachlan Coin, Alex Bateman, Richard Durbin
• Journal: Proceedings of the National Academy of Sciences of the United States of America (Proc Natl Acad Sci U S A) Vol. 100 Issue 8 Pg. 4516-20 (Apr 15 2003) ISSN: 0027-8424 [Print] United States
• PMID: 12668763 (Publication Type: Journal Article, Research Support, Non-U.S. Gov't)

Chemical References

• Homeodomain Proteins
• Nerve Tissue Proteins
• Otx Transcription Factors
• Trans-Activators
• Transcription Factors
• cone rod homeobox protein

Topics

• Algorithms
• Amino Acid Sequence
• Animals
• Biophysical Phenomena
• Biophysics
• Homeodomain Proteins (chemistry, genetics)
• Humans
• Language
• Markov Chains
• Mice
• Models, Molecular
• Models, Theoretical
• Molecular Sequence Data
• Nerve Tissue Proteins (chemistry, genetics)
• Otx Transcription Factors
• Point Mutation
• Protein Structure, Tertiary
• Rats
• Sequence Homology, Amino Acid
• Speech Perception
• Trans-Activators (chemistry, genetics)
• Transcription Factors (chemistry, genetics)