Abstract
Summary: Hidden Markov models (HMMs) are probabilistic models that are well-suited to solve many different classification problems in computation biology. StochHMM provides a command-line program and C++ library that can implement a traditional HMM from a simple text file. StochHMM provides researchers the flexibility to create higher-order emissions, integrate additional data sources and/or user-defined functions into multiple points within the HMM framework. Additional features include user-defined alphabets, ability to handle ambiguous characters in an emission-dependent manner, user-defined weighting of state paths and ability to tie transition probabilities to sequence.
Original language | English (US) |
---|---|
Pages (from-to) | 1625-1626 |
Number of pages | 2 |
Journal | Bioinformatics |
Volume | 30 |
Issue number | 11 |
DOIs | |
State | Published - Jun 1 2014 |
ASJC Scopus subject areas
- Biochemistry
- Molecular Biology
- Computational Theory and Mathematics
- Computer Science Applications
- Computational Mathematics
- Statistics and Probability
- Medicine(all)