differential_methy: differential_methy

In huerqiang/GeoTcgaData: Processing Various Types of Data on GEO and TCGA

differential_methy

Description

Get methylation difference gene

Usage

differential_methy(
  cpgData,
  sampleGroup,
  groupCol,
  combineMethod = "stouffer",
  missing_value = "knn",
  cpg2gene = NULL,
  normMethod = "PBC",
  region = "TSS1500",
  model = "gene",
  adjust.method = "BH",
  adjPvalCutoff = 0.05,
  ucscData = FALSE
)

Arguments

cpgData	data.frame of cpg beta value, , or SummarizedExperiment object
sampleGroup	vector of sample group
groupCol	group column
combineMethod	method to combine the cpg pvalues, a function or one of "stouffer", "fisher" and "rhoScores".
missing_value	Method to impute missing expression data, one of "zero" and "knn".
cpg2gene	data.frame to annotate cpg locus to gene
normMethod	Method to do normalization: "PBC" or "BMIQ".
region	region of genes, one of "Body", "TSS1500", "TSS200", "3'UTR", "1stExon", "5'UTR", and "IGR". Only used when cpg2gene is NULL.
model	if "cpg", step1: calculate difference cpgs; step2: calculate difference genes. if "gene", step1: calculate the methylation level of genes; step2: calculate difference genes.
adjust.method	character string specifying the method used to adjust p-values for multiple testing. See p.adjust for possible values.
adjPvalCutoff	adjusted pvalue cutoff
ucscData	Logical, whether the data comes from UCSC Xena.

Value

data.frame

Examples

# use TCGAbiolinks data
library(TCGAbiolinks)
query <- GDCquery(project = "TCGA-ACC",
    data.category = "DNA Methylation",
    data.type = "Methylation Beta Value",
    platform = "Illumina Human Methylation 450")
GDCdownload(query, method = "api", files.per.chunk = 5,
    directory = Your_Path)
merge_result <- Merge_methy_tcga(Your_Path_to_DNA_Methylation_data)
library(ChAMP) # To avoid reporting errors
differential_gene <- differential_methy(cpgData = merge_result,
    sampleGroup = sample(c("C","T"),
    ncol(merge_result[[1]]), replace = TRUE))

# use user defined data
library(ChAMP)
cpgData <- matrix(runif(2000), nrow = 200, ncol = 10)
rownames(cpgData) <- paste0("cpg", seq_len(200))
colnames(cpgData) <- paste0("sample", seq_len(10))
sampleGroup <- c(rep("group1", 5), rep("group2", 5))
names(sampleGroup) <- colnames(cpgData)
cpg2gene <- data.frame(cpg = rownames(cpgData), 
    gene = rep(paste0("gene", seq_len(20)), 10))
result <- differential_methy(cpgData, sampleGroup, 
    cpg2gene = cpg2gene, normMethod = NULL)
# use SummarizedExperiment object input
library(ChAMP)
cpgData <- matrix(runif(2000), nrow = 200, ncol = 10)
rownames(cpgData) <- paste0("cpg", seq_len(200))
colnames(cpgData) <- paste0("sample", seq_len(10))
sampleGroup <- c(rep("group1", 5), rep("group2", 5))
names(sampleGroup) <- colnames(cpgData)
cpg2gene <- data.frame(cpg = rownames(cpgData), 
    gene = rep(paste0("gene", seq_len(20)), 10))
colData <- S4Vectors::DataFrame(
    row.names = colnames(cpgData),
    group = sampleGroup
)
data <- SummarizedExperiment::SummarizedExperiment(
         assays=S4Vectors::SimpleList(counts=cpgData),
         colData = colData)
result <- differential_methy(cpgData = data, 
    groupCol = "group", normMethod = NULL, 
    cpg2gene = cpg2gene)  

huerqiang/GeoTcgaData documentation built on March 21, 2024, 1:42 a.m.