MACS3.Signal.HMMR_EM module

Module description:

This code is free software; you can redistribute it and/or modify it under the terms of the BSD License (see the file LICENSE included with the distribution).

class MACS3.Signal.HMMR_EM.HMMR_EM(petrack, init_means, init_stddevs, min_fraglen=100, max_fraglen=1000, sample_percentage=10, epsilon=0.05, maxIter=20, jump=1.5, seed=12345)

Bases: object

Main HMMR EM class.

This EM trainer will find the optimal mean and stddev of three of the four modes – mono-nucleosomal, di-nucloeosomal, and three-nucleosomal fragments. Please note that the mean and stddev of the short fragment won’t be optimized in this approach and only rely on the user’s input.

converged: typedef

epsilon: typedef

fragMeans = None

fragStddevs = None

fragVars: _fake_callable

jump: typedef

maxIter: typedef

max_fraglen: typedef

min_fraglen: typedef

sample_percentage: typedef

seed: typedef

MACS3.Signal.HMMR_EM.get_weighted_density(x, m, v, w)

Description:

Parameters:

x (1.) – the observed value
m (2.) – the mean of gaussian
v (3.) – the variance of the gaussian
w (4.) – the weight

Return type:

typedef

return value:

MACS3.Signal.HMMR_EM.online_update(x, c, m, s)

Return type:: tuple

MACS3.Signal.HMMR_EM.return_greater(data)

Return the index of the largest value in an array of doubles @param data: an Array of doubles @return an integer representing thre index of the largest value in the inputted array

Return type:: typedef