ASSIGN (version 1.8.0)

assign.summary: Summary of the model parameters estimated by the Gibbs sampling algorithm

Description

The assign.summary function computes the posterior mean of the model parameters estimated in every iteration during the Gibbs sampling.

Usage

assign.summary(test, burn_in=1000, iter=2000, adaptive_B = TRUE, adaptive_S = FALSE, 
mixture_beta = TRUE)

Arguments

test

The list object returned from the assign.mcmc function. The list components are the MCMC chains of the B, S, Delta, beta, gamma, and sigma.

burn_in

The number of burn-in iterations. These iterations are discarded when computing the posterior means of the model parameters. The default is 1000.

iter

The number of total iterations. The default is 2000.

adaptive_B

Logicals. If TRUE, the model adapts the baseline/background (B) of genomic measures for the test samples. The default is TRUE.

adaptive_S

Logicals. If TRUE, the model adapts the signatures (S) of genomic measures for the test samples. The default is FALSE.

mixture_beta

Logicals. If TRUE, elements of the pathway activation matrix are modeled by a spike-and-slab mixuture distribution. The default is TRUE.

Value

beta_pos

The N x K matrix of the posterior mean of the pathway activation level in test samples (transposed matrix A). Columns:K pathways; rows: N test samples

sigma_pos

The G x 1 vector of the posterior mean of the variance of gene.

kappa_pos

The N x K matrix of posterior mean of pathway activation level in test samples (transposed matrix A) (adjusted beta_pos scaling between 0 and 1). Columns:K pathways; rows: N test samples

gamma_pos

The N x K matrix of the posterior probability of pathways being activated in test samples.

S_pos

The G x K matrix of the posterior mean of pathway signature genes.

Delta_pos

The G x K matrix of the posterior probability of genes being significant in the associated pathways.

Details

The assign.summary function is suggested to run after the assign.convergence function, which is used to check the convergency of the MCMC chain. If the MCMC chain does not converge to a stationary phase, more iterations are required in the assign.mcmc function. The number of burn-in iterations is usually set to be half of the number of total iterations, meaning that the first half of the MCMC chain is discarded when computing the posterior means.

Examples