Computation of mutual information from Hidden Markov Models.

Journal Article (Journal Article)

Understanding evolution at the sequence level is one of the major research visions of bioinformatics. To this end, several abstract models--such as Hidden Markov Models--and several quantitative measures--such as the mutual information--have been introduced, thoroughly investigated, and applied to several concrete studies in molecular biology. With this contribution we want to undertake a first step to merge these approaches (models and measures) for easy and immediate computation, e.g. for a database of a large number of externally fitted models (such as PFAM). Being able to compute such measures is of paramount importance in data mining, model development, and model comparison. Here we describe how one can efficiently compute the mutual information of a homogenous Hidden Markov Model orders of magnitude faster than with a naive, straight-forward approach. In addition, our algorithm avoids sampling issues of real-world sequences, thus allowing for direct comparison of various models. We applied the method to genomic sequences and discuss properties as well as convergence issues.

Full Text

Duke Authors

Cited Authors

  • Reker, D; Katzenbeisser, S; Hamacher, K

Published Date

  • December 2010

Published In

Volume / Issue

  • 34 / 5-6

Start / End Page

  • 328 - 333

PubMed ID

  • 20951093

Electronic International Standard Serial Number (EISSN)

  • 1476-928X

International Standard Serial Number (ISSN)

  • 1476-9271

Digital Object Identifier (DOI)

  • 10.1016/j.compbiolchem.2010.08.005


  • eng