Plot feature proportions

Description

This plot is available only for a group design, i.e., a design that is equivalent to multiple group fitting.

Usage

plotProportions(x, ...)

## S4 method for signature 'dmDSfit'
plotProportions(x, gene_id, group_variable,
  plot_type = "barplot", order_features = TRUE, order_samples = TRUE,
  plot_fit = TRUE, plot_main = TRUE, group_colors = NULL,
  feature_colors = NULL)

## S4 method for signature 'dmSQTLfit'
plotProportions(x, gene_id, snp_id,
  plot_type = "boxplot1", order_features = TRUE, order_samples = TRUE,
  plot_fit = FALSE, plot_main = TRUE, group_colors = NULL,
  feature_colors = NULL)

Arguments

Details

In the QTL analysis, plotting of fitted proportions is deactivated even when plot_fit = TRUE. It is due to the fact that neither fitted values nor regression coefficients are returned by the dmFit function as they occupy a lot of memory.

Value

For a given gene, plot the observed and estimated with Dirichlet-multinomial model feature proportions in each group. Estimated group proportions are marked with diamond shapes.

Author(s)

Malgorzata Nowicka

See Also

plotData, plotPrecision, plotPValues

Examples

# --------------------------------------------------------------------------
# Create dmDSdata object 
# --------------------------------------------------------------------------
## Get kallisto transcript counts from the 'PasillaTranscriptExpr' package

library(PasillaTranscriptExpr)

data_dir  <- system.file("extdata", package = "PasillaTranscriptExpr")

## Load metadata
pasilla_metadata <- read.table(file.path(data_dir, "metadata.txt"), 
header = TRUE, as.is = TRUE)

## Load counts
pasilla_counts <- read.table(file.path(data_dir, "counts.txt"), 
header = TRUE, as.is = TRUE)

## Create a pasilla_samples data frame
pasilla_samples <- data.frame(sample_id = pasilla_metadata$SampleName, 
  group = pasilla_metadata$condition)
levels(pasilla_samples$group)

## Create a dmDSdata object
d <- dmDSdata(counts = pasilla_counts, samples = pasilla_samples)

## Use a subset of genes, which is defined in the following file
gene_id_subset <- readLines(file.path(data_dir, "gene_id_subset.txt"))

d <- d[names(d) %in% gene_id_subset, ]

# --------------------------------------------------------------------------
# Differential transcript usage analysis - simple two group comparison 
# --------------------------------------------------------------------------

## Filtering
## Check what is the minimal number of replicates per condition 
table(samples(d)$group)

d <- dmFilter(d, min_samps_gene_expr = 7, min_samps_feature_expr = 3,
  min_gene_expr = 10, min_feature_expr = 10)

plotData(d)

## Create the design matrix
design_full <- model.matrix(~ group, data = samples(d))

## To make the analysis reproducible
set.seed(123)
## Calculate precision
d <- dmPrecision(d, design = design_full)

plotPrecision(d)

head(mean_expression(d))
common_precision(d)
head(genewise_precision(d))

## Fit full model proportions
d <- dmFit(d, design = design_full)

## Get fitted proportions
head(proportions(d))
## Get the DM regression coefficients (gene-level) 
head(coefficients(d))
## Get the BB regression coefficients (feature-level) 
head(coefficients(d), level = "feature")

## Fit null model proportions and perform the LR test to detect DTU
d <- dmTest(d, coef = "groupKD")

## Plot the gene-level p-values
plotPValues(d)

## Get the gene-level results
head(results(d))

## Plot feature proportions for a top DTU gene
res <- results(d)
res <- res[order(res$pvalue, decreasing = FALSE), ]

top_gene_id <- res$gene_id[1]

plotProportions(d, gene_id = top_gene_id, group_variable = "group")

plotProportions(d, gene_id = top_gene_id, group_variable = "group", 
  plot_type = "lineplot")

plotProportions(d, gene_id = top_gene_id, group_variable = "group", 
  plot_type = "ribbonplot")