bpr_gibbs.list: Gibbs sampling for the BPR model using list x

In andreaskapou/mpgex: Methylation Profiles predict Gene Expression

Description

bpr_gibbs.list computes the posterior of the BPR model using auxiliary variable approach. Since we cannot compute the posterior analytically, a Gibbs sampling scheme is used. This method calls bpr_gibbs.matrix to process each element of the list.

Usage

## S3 method for class 'list'
bpr_gibbs(x, w_mle = NULL, basis = NULL,
  fit_feature = NULL, cpg_dens_feat = FALSE, w_0_mean = NULL,
  w_0_cov = NULL, gibbs_nsim = 20, gibbs_burn_in = 10,
  is_parallel = TRUE, no_cores = NULL, ...)

Arguments

x	A list of elements of length N, where each element is an L x 3 matrix of observations, where 1st column contains the locations. The 2nd and 3rd columns contain the total trials and number of successes at the corresponding locations, repsectively.
w_mle	A matrix of MLE estimates for the regression coefficients for each genomic region of interest.
basis	A 'basis' object. See polynomial.object
fit_feature	Additional feature on how well the profile fits the methylation data.
cpg_dens_feat	Additional feature for the CpG density across the promoter region.
w_0_mean	The prior mean hyperparameter for w
w_0_cov	The prior covariance hyperparameter for w
gibbs_nsim	Optional argument giving the number of simulations of the Gibbs sampler.
gibbs_burn_in	Optional argument giving the burn in period of the Gibbs sampler.
is_parallel	Logical, indicating if code should be run in parallel.
no_cores	Number of cores to be used, default is max_no_cores - 2.
...	Additional parameters

Value

A list containing the following elements:

• W_opt: An Nx(M+1) matrix with the optimized parameter values. Each row of the matrix corresponds to each element of the list x. The columns are of the same length as the parameter vector w (i.e. number of basis functions).

• Mus: An N x M matrix with the RBF centers if basis object is rbf.object, otherwise NULL.

• basis: The basis object.

• w: The initial values of the parameters w.

• x_extrema: The min and max values of each promoter region.

See Also

bpr_optim, bpr_optim.matrix

Examples

ex_data <- bpr_data
basis <- rbf.object(M=3)
out_opt <- bpr_gibbs(x = ex_data, is_parallel = FALSE, basis = basis)

andreaskapou/mpgex documentation built on May 12, 2019, 3:33 a.m.