Learn R Programming

tileHMM

Methods and classes to build HMMs that are suitable for the analysis of ChIP-chip data. The provided parameter estimation methods include the Baum-Welch algorithm and Viterbi training as well as a combination of both.

Releases for this R package are available from CRAN. The source code is hosted on GitHub

Copy Link

Version

Install

install.packages('tileHMM')

Monthly Downloads

51

Version

1.0-7

License

GPL (>= 2)

Maintainer

Peter Humburg

Last Published

July 2nd, 2015

Functions in tileHMM (1.0-7)

Plotting of "contDist" Objects

initializeHMM-methods

Generate Objects of Class 'hmm'

Calculate Most Likely State Sequence Using the Viterbi Algorithm

Generate Simulated Dataset

viterbiTraining

Estimate HMM Parameters Using Viterbi Training

Create HMM from Parameter Values

Class "contDist"

Accessing Objects of Class "contHMM"

Computation of Forward and Backward Variables

Calculate 'Shrinkage t' Statistic

Class "contHMM"

Internal Functions

Efficient Estimation of HMM Parameters

Simulated ChIP-on-Chip Data

Accessing and Converting Objects of Class "dist"

initializeDist-methods

Generating Objects of Class 'dist'

Post-Processing of "tileHMM" Results

tileHMM-package

Hidden Markov Models for ChIP-on-Chip Analysis

Baum-Welch Algorithm

Calculate Posterior Probability for States of HMM

region.position

Identify Enriched Regions

State Names of Hidden Markov Model

Sample Observations from Probability Distribution

Generate Observation Sequence from HMM

Determine Length of Positive and Negative Regions

Extract Probe Calls from GFF File

Converting Information about Enriched Regions into GFF Format

Create HMM from Initial Parameter Estimates Obtained from Data

Class "discDist"

Calculate log(x + y) from log(x) and log(y)