metaTest: Meta-analysis using several RNA-Seq statistics

In pmoulos/metaseqR2: An R package for the analysis and result reporting of RNA-Seq data by combining multiple statistical algorithms

Meta-analysis using several RNA-Seq statistics

Description

This function calculates the combined p-values when multiple statistical algorithms are applied to the input dataset. It is a helper and it requires very specific arguments so it should not be used individually

Usage

    metaTest(cpList,
        metaP = c("simes", "bonferroni", "fisher", "harmonic",
        "dperm_min", "dperm_max", "dperm_weight", "fperm", 
        "whitlock", "minp", "maxp", "weight", "pandora", 
        "none"), counts, sampleList, statistics, statArgs, 
        libsizeList, nperm = 10000, 
        weight = rep(1/length(statistics), length(statistics)), 
        pOffset = NULL, rc = NULL)

Arguments

cpList	a named list whose names are the contrasts requested from metaseqr2. Each member is a p-value matrix whose colnames are the names of the statistical tests applied to the data. See the main metaseqr2 help page.
metaP	the p-value combination method to use. See the main metaseqr2 help page.
counts	the normalized and possibly filtered read counts matrix. See the main metaseqr2 help page.
sampleList	the list containing condition names and the samples under each condition. See the main metaseqr2 help page.
statistics	the statistical algorithms used in metaseqr2. See the main metaseqr2 help page.
statArgs	the parameters for each statistical argument. See the main metaseqr2 help page.
libsizeList	a list with library sizes. See the main metaseqr2 and the stat* help pages.
nperm	the number of permutations (Monte Carlo simulations) to perform.
weight	a numeric vector of weights for each statistical algorithm.
pOffset	NULL (default) or a fixed numeric value between 0 and 1. See also the main metaseqr2 man page.
rc	the fraction of the available cores to use in a multicore system.

Details

Ideally one would want to create the same set of indices for a given dataset so as to create reproducible p-values. To achieve this, use the set.seed function prior to any calculations.

Value

A named list with combined p-values. The names are the contrasts and the list members are combined p-value vectors, one for each contrast.

Author(s)

Panagiotis Moulos

Examples

cpList <- list(a=matrix(runif(100),50,2))
metaP <- metaTest(cpList,"simes")

pmoulos/metaseqR2 documentation built on May 20, 2024, 5:48 a.m.