BNBP: Beta-Negative Binomial process modeling of sequencing count...

In siamakz/BNPseq: Bayesian Nonparametric Differential Expression Analysis of Sequencing Count Data

Description

This function fits BNBP model to counts in different conditions and returns the posterior samples of probability and dispersion parameters than can be used to assess the differential expression significance.

Usage

BNBP(y, groups, randtry = 1, Burnin = 1000L, Collections = 1000L)

Arguments

y	a matrix of counts, rows are corresponding to genes and columns are corresponding to samples.
groups	a vector of factors indicating group memberships of samples
randtry	state of set.seed
Burnin	Number of burn-in iterations in MCMC
Collections	Number of collected posterior samples after burn-in

Value

posterior samples of probability and dispersion parameters of Negative Binomial

Examples

y <- rnbinom(n = 100, size = 5, prob = 0.5)
y <- matrix(data = y, nrow = 10, ncol = 10)
groups <- factor(rep(c(1,2), each = 5))
res <- BNBP(y, groups, randtry = 1, Burnin = 1000L, Collections = 1000L)
p <- res$p_k
p <- p/(1-p)
gene.kl <- KLsym(p[,1:1000], p[,1001:2000])

siamakz/BNPseq documentation built on May 15, 2019, 4:28 p.m.