vignettes/load_dshendriks2014.R

In LBMC/RAPToR: Real Age Prediction from Transcriptome staging On Reference

geo_dshendriks2014 <- "GSE52861"

g_url_dshendriks2014 <- GEOquery::getGEOSuppFiles(geo_dshendriks2014, 
                                                  makeDirectory = FALSE, 
                                                  fetch_files = FALSE)
g_file_dshendriks2014 <- paste0(data_folder, "dshendriks2014.txt.gz")
utils::download.file(url = as.character(g_url_dshendriks2014$url[2]), 
                     destfile = g_file_dshendriks2014)

X_dshendriks2014 <- read.table(gzfile(g_file_dshendriks2014), 
                               h=T, sep = '\t', stringsAsFactors = F, 
                               row.names = 1)

# convert to tpm & wb_id
X_dshendriks2014 <- X_dshendriks2014[
  rownames(X_dshendriks2014)%in%wormRef::Cel_genes$wb_id,]
X_dshendriks2014 <- raw2tpm(
  rawcounts = X_dshendriks2014, 
  genelengths = wormRef::Cel_genes$transcript_length[
    match(rownames(X_dshendriks2014), wormRef::Cel_genes$wb_id)])


# pheno data
P_dshendriks2014 <- Biobase::pData(GEOquery::getGEO(geo_dshendriks2014, 
                                                    getGPL = F)[[1]])

# filter relevant fields/samples
P_dshendriks2014 <- P_dshendriks2014[
  (P_dshendriks2014$`strain:ch1` == 'N2') & 
  (P_dshendriks2014$`growth protocol:ch1` == 'Continuous'), ]

P_dshendriks2014 <- P_dshendriks2014[, c("title", "geo_accession", 
                                         "time in development:ch1")]

# get age from sample name
P_dshendriks2014$age <- as.numeric(
  sub('(\\d+)\\shours', '\\1', P_dshendriks2014$`time in development:ch1`))


# formatting
P_dshendriks2014$title <- gsub('RNASeq_polyA_', '', 
                               gsub('hr', 'h', 
                                    gsub('-', '.', fixed = T, 
                                         as.character(P_dshendriks2014$title))))
colnames(X_dshendriks2014) <- gsub('RNASeq_polyA_','', 
                                   colnames(X_dshendriks2014))
X_dshendriks2014 <- X_dshendriks2014[, P_dshendriks2014$title]

# save data
dshendriks2014 <- list(g = X_dshendriks2014, p = P_dshendriks2014)
save(dshendriks2014, file = paste0(data_folder, "dshendriks2014.RData"), 
     compress = "xz")

# cleanup
file.remove(g_file_dshendriks2014)
rm(geo_dshendriks2014, g_url_dshendriks2014, g_file_dshendriks2014, 
   X_dshendriks2014, P_dshendriks2014)