GSE72408 Processing Pipeline

Publication

The Journal of experimental medicine (2022) — PMID 35593887

Dataset

The transcription factors ZEB2 and T-bet cooperate to program cytotoxic T cell terminal differentiation

1. 1

   Utilized R::beadarray package with the readIdatFiles and normaliseIllumina functions to extract raw and normalised (neqc, log2 transformed) values.

   R vNot specified GitHub

   $ Bash example

   # Install R and Bioconductor (if not already installed)
   # sudo apt update
   # sudo apt install -y r-base
   # R -e 'if (!requireNamespace("BiocManager", quietly = TRUE)) install.packages("BiocManager", repos = "https://cloud.r-project.org"); BiocManager::install("beadarray", update = FALSE, ask = FALSE)'
   
   # Create a directory for input IDAT files and a dummy sample sheet for demonstration
   mkdir -p input_idat_files
   # NOTE: Replace with actual IDAT files and SampleSheet.csv
   # For a real run, you would place your .idat files in input_idat_files/
   # and your SampleSheet.csv in the working directory or specified path.
   # Example dummy SampleSheet.csv (adjust columns as per your actual data)
   cat <<EOF > input_sample_sheet.csv
   [Header]
   Investigator Name,John Doe
   Project Name,MyProject
   Experiment Name,IlluminaArrayExperiment
   Date,2023-10-27
   [Data]
   Sample_ID,Array_ID,Sentrix_ID,Sentrix_Position,Sample_Group
   Sample1,1,200000000001,R01C01,Control
   Sample2,2,200000000002,R01C02,Treatment
   EOF
   
   # Create the R script
   cat << 'EOF' > process_illumina.R
   # Load the beadarray package
   library(beadarray)
   
   # Define input/output paths using environment variables for flexibility
   idat_files_dir <- Sys.getenv("IDAT_FILES_DIR", "input_idat_files")
   sample_sheet_path <- Sys.getenv("SAMPLE_SHEET_PATH", "input_sample_sheet.csv")
   
   output_raw_file <- Sys.getenv("OUTPUT_RAW_FILE", "raw_expression_values.csv")
   output_normalized_file <- Sys.getenv("OUTPUT_NORMALIZED_FILE", "normalized_expression_values.csv")
   
   # Check if input directory and sample sheet exist
   if (!dir.exists(idat_files_dir)) {
     stop(paste("Input IDAT files directory not found:", idat_files_dir))
   }
   if (!file.exists(sample_sheet_path)) {
     stop(paste("Sample sheet not found:", sample_sheet_path))
   }
   
   message(paste("Reading IDAT files from:", idat_files_dir))
   message(paste("Using sample sheet:", sample_sheet_path))
   
   # Read raw data from IDAT files
   # This function returns an 'illuminaChannelList' object
   raw_data_obj <- readIdatFiles(path = idat_files_dir, sampleSheet = sample_sheet_path)
   
   # Extract and save raw expression values
   # For Illumina arrays, raw values are typically the intensities from the green (Grn) or red (Red) channel.
   # We'll extract the green channel intensities as a representative "raw value" matrix.
   # If the array is two-color, one might save both or a combined signal.
   message("Extracting and saving raw (green channel) expression values...")
   raw_expression_matrix <- getBeadData(raw_data_obj, what = "Grn")
   write.csv(raw_expression_matrix, file = output_raw_file, row.names = TRUE)
   message(paste("Raw expression values saved to:", output_raw_file))
   
   # Normalise data using neqc method
   # The neqc method inherently performs background correction and log2 transformation.
   message("Normalizing data using neqc method (log2 transformed)...")
   normalized_data_obj <- normaliseIllumina(raw_data_obj, method = "neqc")
   
   # Extract normalized expression matrix
   normalized_expression_matrix <- exprs(normalized_data_obj)
   
   # Save normalized expression values
   write.csv(normalized_expression_matrix, file = output_normalized_file, row.names = TRUE)
   message(paste("Normalized (neqc, log2) expression values saved to:", output_normalized_file))
   EOF
   
   # Set environment variables for input/output paths (optional, defaults are used if not set)
   # export IDAT_FILES_DIR="path/to/your/idat_files"
   # export SAMPLE_SHEET_PATH="path/to/your/sample_sheet.csv"
   # export OUTPUT_RAW_FILE="my_raw_expression.csv"
   # export OUTPUT_NORMALIZED_FILE="my_normalized_expression.csv"
   
   # Execute the R script
   Rscript process_illumina.R

   Copy View on GitHub

Tools Used