MDPlot: Mean-Dispersion Plots with Curves of Fitted Negative Binomial...

In gu-mi/NBGOF: Goodness-of-Fit Tests and Model Diagnostics for Negative Binomial Regression of RNA Sequencing Data

Description

This function makes mean-dispersion plots with curves of fitted negative binomial dispersion models. We currently consider only one group and fit an intercept-only model.

Usage

MDPlot(model.vec, counts, x, title=NULL)

Arguments

model.vec	a character vector specifying the names of the NB dispersion models. Currently supported include "NBP", "NBQ", "Common", "Tagwise-Common", "Tagwise-Trend" and "Trended"
counts	an m-by-n count matrix of non-negative integers. For a typical RNA-Seq experiment, this is the read counts with m genes and n samples
x	an n-by-p design matrix
title	title of the plot

Value

A ggplot object of mean-dispersion plot with fitted NB dispersion model curves.

Author(s)

Gu Mi <[e-mail]>, Yanming Di, Daniel Schafer

References

See https://github.com/gu-mi/NBGOF/wiki/ for more details.

Examples

# load package
library(NBGOF)

# load data and subset for illustration
data(arab)
counts = arab[1:5000,1:3]
x = matrix(c(1,1,1), nr=3)

# specify what models to plot
model.vec=c("Common", "NBP", "NBQ", "Trended", "Tagwise-Common", "Tagwise-Trend")

# begin plotting
pl.arab = MDPlot(model.vec, counts, x, title="Mean-Dispersion Plot with Fitted Dispersion Models (Arabidopsis Data)")
print(pl.arab)

gu-mi/NBGOF documentation built on Oct. 25, 2020, 3:30 a.m.