Bayesian hidden Markov model toolkit
This toolkit provides machinery for sampling from the Bayesian posterior of hidden Markov models with various choices of prior and output models.
The easiest way to install bhmm is via the conda package manager:
conda config --add channels conda-forge
conda install bhmm
python setup.py install
See here for a manuscript describing the theory behind using Gibbs sampling to sample from Bayesian hidden Markov model posteriors.
Bayesian hidden Markov model analysis of single-molecule force spectroscopy: Characterizing kinetics under measurement uncertainty. John D. Chodera, Phillip Elms, Frank Noé, Bettina Keller, Christian M. Kaiser, Aaron Ewall-Wice, Susan Marqusee, Carlos Bustamante, Nina Singhal Hinrichs http://arxiv.org/abs/1108.1430
- Frank Noé [email protected], Freie Universität Berlin
- Martin K. Scherer [email protected], Freie Universität Berlin
- John D. Chodera [email protected], Sloan Kettering Institute