vignettes/load_dsaeschimann2017.R

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

geo_dsaeschimann2017 <- "GSE80157"

g_url_dsaeschimann2017 <- GEOquery::getGEOSuppFiles(geo_dsaeschimann2017, 
                                                    makeDirectory = FALSE, 
                                                    fetch_files = FALSE)
g_file_dsaeschimann2017 <- paste0(data_folder, "dsaeschimann2017.txt.gz")
utils::download.file(url = as.character(g_url_dsaeschimann2017$url[2]), 
                     destfile = g_file_dsaeschimann2017)

X_dsaeschimann2017 <- read.table(gzfile(g_file_dsaeschimann2017), 
                                 h=T, sep = '\t', stringsAsFactors = F, 
                                 row.names = 1)

# convert to tpm & wb_id
X_dsaeschimann2017 <- X_dsaeschimann2017[
  rownames(X_dsaeschimann2017) %in% wormRef::Cel_genes$wb_id,]

X_dsaeschimann2017 <- raw2tpm(
  rawcounts = X_dsaeschimann2017, 
  genelengths = wormRef::Cel_genes$transcript_length[
    match(rownames(X_dsaeschimann2017), wormRef::Cel_genes$wb_id)])

# pheno data
P_dsaeschimann2017 <- Biobase::pData(GEOquery::getGEO(geo_dsaeschimann2017, 
                                                      getGPL = F)[[1]])
P_dsaeschimann2017[,10:34] <- NULL
P_dsaeschimann2017[, 3:8] <- NULL

colnames(P_dsaeschimann2017)[4] <- "strain"
P_dsaeschimann2017$strain <- factor(P_dsaeschimann2017$strain)
P_dsaeschimann2017$title <- make.names(P_dsaeschimann2017$title)

# get age from sample name
P_dsaeschimann2017$age <- as.numeric(
  sub('(\\d+)\\shours', '\\1', P_dsaeschimann2017$`time in development:ch1`))

# formatting
colnames(X_dsaeschimann2017) <- gsub('RNASeq_riboM_', '', 
                                     colnames(X_dsaeschimann2017), fixed = T)
P_dsaeschimann2017$title <- gsub('RNASeq_riboM_', '', 
                                 P_dsaeschimann2017$title, fixed = T)
X_dsaeschimann2017 <- X_dsaeschimann2017[, P_dsaeschimann2017$title]

# save data
dsaeschimann2017 <- list(g = X_dsaeschimann2017, p = P_dsaeschimann2017)

save(dsaeschimann2017, file = paste0(data_folder, "dsaeschimann2017.RData"), 
     compress = "xz")

# cleanup
file.remove(g_file_dsaeschimann2017)
rm(geo_dsaeschimann2017, g_url_dsaeschimann2017, g_file_dsaeschimann2017, 
   X_dsaeschimann2017, P_dsaeschimann2017)