diff_RNA: Do difference analysis of RNA-seq data

In GeoTcgaData: Processing various types of data on GEO and TCGA

Do difference analysis of RNA-seq data

Description

Do difference analysis of RNA-seq data

Usage

diff_RNA(
  counts,
  group,
  method = "limma",
  geneLength = NULL,
  gccontent = NULL,
  filter = TRUE,
  edgeRNorm = TRUE,
  adjust.method = "BH",
  useTopconfects = TRUE
)

Arguments

counts	a dataframe or numeric matrix of raw counts data
group	sample groups
method	one of "DESeq2", "edgeR" , "limma", "dearseq" and "Wilcoxon".
geneLength	a vector of gene length.
gccontent	a vector of gene GC content.
filter	if TRUE, use filterByExpr to filter genes.
edgeRNorm	if TRUE, use edgeR to do normalization for dearseq method.
adjust.method	character string specifying the method used to adjust p-values for multiple testing. See p.adjust for possible values.
useTopconfects	if TRUE, use topconfects to provide a more biologically useful ranked gene list.

Examples

## Not run: 
library(TCGAbiolinks)
                
query <- GDCquery(project = "TCGA-ACC",
                  data.category = "Transcriptome Profiling",
                  data.type = "Gene Expression Quantification", 
                  workflow.type = "STAR - Counts")
                  
GDCdownload(query, method = "api", files.per.chunk = 3, 
    directory = Your_Path)

dataRNA <- GDCprepare(query = query, directory = Your_Path,
                      save = TRUE, save.filename = "dataRNA.RData")
## get raw count matrix                         
dataPrep <- TCGAanalyze_Preprocessing(object = dataRNA,
                                      cor.cut = 0.6,
                                      datatype = "STAR - Counts")

# Use `diff_RNA` to do difference analysis. 
# We provide the data of human gene length and GC content in `gene_cov`.
group <- sample(c("grp1", "grp2"), ncol(dataPrep), replace = TRUE)
library(cqn) # To avoid reporting errors: there is no function "rq"
## get gene length and GC content
library(org.Hs.eg.db)
genes_bitr <- bitr(rownames(gene_cov), fromType = "ENTREZID", toType = "ENSEMBL", 
         OrgDb = org.Hs.eg.db, drop = TRUE)
genes_bitr <- genes_bitr[!duplicated(genes_bitr[,2]), ]
gene_cov2 <- gene_cov[genes_bitr$ENTREZID, ]
rownames(gene_cov2) <- genes_bitr$ENSEMBL
genes <- intersect(rownames(dataPrep), rownames(gene_cov2))
dataPrep <- dataPrep[genes, ]
geneLength <- gene_cov2(genes, "length")
gccontent <- gene_cov2(genes, "GC")
names(geneLength) <- names(gccontent) <- genes
##  Difference analysis
DEGAll <- diff_RNA(counts = dataPrep, group = group, 
                   geneLength = geneLength, gccontent = gccontent)
# Use `clusterProfiler` to do enrichment analytics:
diffGenes <- DEGAll$logFC
names(diffGenes) <- rownames(DEGAll)
diffGenes <- sort(diffGenes, decreasing = TRUE)
library(clusterProfiler)
library(enrichplot)
library(org.Hs.eg.db)
gsego <- gseGO(gene = diffGenes, OrgDb = org.Hs.eg.db, keyType = "ENSEMBL")
dotplot(gsego)                   

## End(Not run)

GeoTcgaData documentation built on Sept. 23, 2022, 9:05 a.m.