Inspect duplicate ids in SAMPID column

get_dupes_GTEX_ids.R

# From yarn::downloadGtexV8
pData               <- read.csv("pData_yarn_downloadGTExV8.csv")

# rMATS analysed 
samples_sra            <- as.vector(t(read.csv("samples.csv", header = FALSE)))
# From SraRunTable
meta.data   <- read.csv("SraRunTable.noCram.noExome.noWGS.totalRNA.txt", header = T)
meta.data   <- meta.data[meta.data$Run %in% samples_sra, ]
dim(meta.data)


# Reform GTEX ids in meta.data$biospecimen_repository_sample_id to match pData$SAMPID
meta.data$SAMPID <- gsub("-","." , meta.data$biospecimen_repository_sample_id)
dim(meta.data)
#[1] 8673   80

# Merge the 2 metadata tables by column SAMPID
merged <- merge(meta.data, pData, by = "SAMPID", all  = FALSE)
dim(merged)

# Isolate the two columns with the ids
id <- merged[,c("Run","SAMPID")]

# Inspect uniqueness of ids in columns SAMPID, 
janitor::get_dupes(id, SAMPID)

janitor::get_dupes(id, Run)