Description Usage Arguments Value Author(s) References Examples

This function fits a three-state HMM with mixture model of Negative Binomials for differential peak detection across conditions with replicates.

1 | ```
mixNBHMM(object, control)
``` |

`object` |
a mixNBHMMDataSet |

`control` |
list of control arguments from controlEM() |

The mixNBHMMDataSet with the following list as `metadata`

:

- pi
Vector of estimated initial probabilities of the HMM

- gamma
Vector of estimated transition probabilities of the HMM

- psi
Vector of estimated means and dispersion parameters pertaining to the emission distributions

- prob
Data table of window-based (rows) posterior probabilities of the HMM emission distributions (columns)

- mixProb
Data table of window-based (rows) posterior probabilities of the mixture model from each mixture component (columns)

- viterbi
Vector of Viterbi sequence of hidden states

- logF
Data table of window-based (rows) log forward probabilities from the emission distributions (columns)

- logB
Data table of window-based (rows) log backward probabilities from the emission distributions (columns)

- logLik
Data table of window-based (rows) log probabilities from the emission distributions (columns)

- parHist
Data table of parameter estimates (column) from every EM iteration (rows)

IMPORTANT: the output mixNBHMMDataSet has conditions and replicates reordered. Make sure to check `colData()`

of your output.

Pedro L. Baldoni, [email protected]

https://github.com/plbaldoni/mixNBHMM

1 2 3 |

Embedding an R snippet on your website

Add the following code to your website.

For more information on customizing the embed code, read Embedding Snippets.