inst/data-raw/process/PMID28761107_Sebastiani-2017/process.R

In avucoh/nPOD: What the Package Does (One Line, Title Case)

library(readxl)
library(tidyr)
library(dplyr)

# (1) miR _PB_ Treg dataset --------------------------------------------------------------------------------------------#

# Data for controls - PB Treg
PB.6140 <- read_xlsx("miRNA_profiling_nPOD_samples.xlsx", sheet = "CTR PB Treg ", range = "A3:G388") %>%
  select(miR = `Target Name`, dCT = `Mean dCT`)

PB.6178 <- read_xlsx("miRNA_profiling_nPOD_samples.xlsx", sheet = "CTR PB Treg ", range = "I3:O388") %>%
  select(miR = `Target Name`, dCT = `Mean dCT`)

PB.6162 <- read_xlsx("miRNA_profiling_nPOD_samples.xlsx", sheet = "CTR PB Treg ", range = "R3:W388")
# For some reason authors didn't calculate mean dCT for 6162 in the spreadsheet, 
# so we fill in using the same formula as with the others
PB.6162 <- PB.6162 %>% 
  mutate(`Mean dCT` = rowMeans(select(., starts_with("dCT")), na.rm = T)) %>% 
  select(miR = `Target Name`, dCT = `Mean dCT`)

# Data for T1D - PB Treg
PB.6205 <- read_xlsx("miRNA_profiling_nPOD_samples.xlsx", sheet = "T1D PB Treg ", range = "A3:G388") %>%
  select(miR = `Target Name`, dCT = `dct mean`)

PB.6223 <- read_xlsx("miRNA_profiling_nPOD_samples.xlsx", sheet = "T1D PB Treg ", range = "I3:O388") %>%
  select(miR = `Target Name`, dCT = `mean dct`)

# All rel. expression values for PB Treg dataset
miR.PB <- Reduce(function(x, y) full_join(x, y, by = "miR"), list(PB.6140, PB.6178, PB.6162, PB.6205, PB.6223))

miR.PB.t <- t(miR.PB[, 2:6])
colnames(miR.PB.t) <- miR.PB$miR
rownames(miR.PB.t) <- NULL
miR.PB.t <- cbind(ID = c(6140, 6178, 6162, 6205, 6223), miR.PB.t)
write.table(miR.PB.t, "PMID28761107_1_Sebastiani-2017.tsv", sep = "\t", quote = F, row.names = F)
  
  
# (2) miR _PLN_ Treg dataset --------------------------------------------------------------------------------------------#

# Data for controls - PLN Treg
PLN.6140 <- read_xlsx("miRNA_profiling_nPOD_samples.xlsx", sheet = "CTR PLN Treg ", range = "A3:G388") %>%
  select(miR = `Target Name`, dCT = `Mean dCT`)

PLN.6178 <- read_xlsx("miRNA_profiling_nPOD_samples.xlsx", sheet = "CTR PLN Treg ", range = "I3:O388") %>%
  select(miR = `Target Name`, dCT = `Mean dCT`)

PLN.6162 <- read_xlsx("miRNA_profiling_nPOD_samples.xlsx", sheet = "CTR PLN Treg ", range = "R3:W388") %>%
  select(miR = `Target Name`, dCT = `Mean dCT`)

# Data for T1D - PLN Treg
PLN.6205 <- read_xlsx("miRNA_profiling_nPOD_samples.xlsx", sheet = "T1D PLN Treg ", range = "A3:G388") %>%
  select(miR = `Target Name`, dCT = `dct mean`)

PLN.6223 <- read_xlsx("miRNA_profiling_nPOD_samples.xlsx", sheet = "T1D PLN Treg ", range = "I3:O388") %>%
  select(miR = `Target Name`, dCT = `dct mean`)

# All rel. expression values for PB Treg dataset
miR.PLN <- Reduce(function(x, y) full_join(x, y, by = "miR"), list(PLN.6140, PLN.6178, PLN.6162, PLN.6205, PLN.6223))

miR.PLN.t <- t(miR.PLN[, 2:6])
colnames(miR.PLN.t) <- miR.PLN$miR
rownames(miR.PLN.t) <- NULL
miR.PLN.t <- cbind(ID = c(6140, 6178, 6162, 6205, 6223), miR.PLN.t)
write.table(miR.PLN.t, "PMID28761107_2_Sebastiani-2017.tsv", sep = "\t", quote = F, row.names = F)