Preprocessing functions added.

DESCRIPTION

@@ -6,9 +6,9 @@ Author: Leon-Charles Tranchevent
 Maintainer: Leon-Charles Tranchevent <leon-charles.tranchevent@uni.lu>
 Description: This package contains functions to analyse microarray data.
     It is more a set of useful functions than a real package.
-License: The Unlicense
+License: The Unlicense (see LICENSE)
 Encoding: UTF-8
 LazyData: true
 Imports:
-  utils,affy,Biobase,arrayQualityMetrics
+    utils,affy,Biobase,arrayQualityMetrics,SCAN.UPC,doParallel
 RoxygenNote: 6.1.1

R/load_clinical_data.R

+#' @title Loads a table containing clinical data.
+#'
+#' @description This function loads the clinical data associated with a dataset. It returns an annotated
+#' data-frame that contains the clinical data.
+#'
+#' Note: the function assumes that a TSV file containing the clinical data exists. In
+#' particular, it does not check for the existence of folders or files.
+#'
+#' @param data_dir A string representing the folder that contains the clinical data.
+#' @param clinical_file_name A string containing the file name. By default, this is 'ClinicalData.tsv'
+#' @param verbose A boolean representing whether the function should display log information. This
+#'  is TRUE by default.
+#' @return An annotated data-frame that contains the clinical data.
+load_clinical_data <- function(data_dir,
+                               clinical_file_name = "ClinicalData.tsv",
+                               verbose            = TRUE) {
+
+  # We define the I/Os.
+  clinical_data_file <- paste0(data_dir, clinical_file_name)
+  if (verbose == TRUE) {
+    message(paste0("[", Sys.time(), "] File set to ", clinical_data_file))
+  }
+
+  # We load the clinical data.
+  pheno_data <- Biobase::AnnotatedDataFrame(utils::read.delim(file       = clinical_data_file,
+                                                              row.names  = 1,
+                                                              colClasses = "factor"))
+
+  # We clean up and log information.
+  rm(clinical_data_file)
+  if (verbose == TRUE) {
+    data_dimensions = paste0(dim(pheno_data), collapse = " * ")
+    message(paste0("[", Sys.time(), "] Clinical data read (", data_dimensions, ")."))
+  }
+
+  # We return the clinical data.
+  return(pheno_data)
+}

R/preprocess_data_scan.R

+#' @title Preprocess a dataset with SCAN.
+#'
+#' @description This function preprocess a dataset using SCAN and saves the results in
+#' a given TSV file. In addition, it returns the ESET object.
+#'
+#' The function assumes that a folder containing the raw data exists (as cel files).
+#'
+#' Note: the function does not check for the existence of folders or files.
+#'
+#' @param input_data_dir A string representing the folder that contains the input data.
+#' @param output_data_file A string representing the file that should contain the
+#'  preprocessed data.
+#' @param correct_for_batch_effect A boolean indicating whether batch correction should
+#'  be performed, default to FALSE.
+#' @param batch_filename A string indicating where the batch information can be found,
+#'  default to 'Batch.tsv'.
+#' @param verbose A boolean representing whether the function should display log information. This
+#'  is TRUE by default.
+#' @return The expression data as an ESET object.
+preprocess_data_scan <- function(input_data_dir, output_data_file,
+                                 correct_for_batch_effect = FALSE,
+                                 batch_filename           = "Batch.tsv",
+                                 verbose                  = TRUE) {
+
+  # We define the I/Os.
+  raw_data_input_dir <- paste0(input_data_dir, "RAW/")
+
+  # We run the SCAN pre-processing method on the data.
+  # We do not run the fast analysis (by default).
+  input_data_regexp <- paste0(raw_data_input_dir, "*")
+  remove(raw_data_input_dir)
+  eset <- vector()
+  if (correct_for_batch_effect == FALSE) {
+    eset <- SCAN.UPC::SCAN(input_data_regexp, outFilePath = output_data_file)
+  } else {
+    # We define the I/Os (for batch).
+    batch_data_file <- paste0(input_data_dir, batch_filename)
+    eset <- SCAN.UPC::SCAN(input_data_regexp,
+                           outFilePath   = output_data_file,
+                           batchFilePath = batch_data_file)
+    remove(batch_data_file)
+  }
+
+  # We clean up and log information.
+  rm(input_data_regexp)
+  if (verbose == TRUE) {
+    message(paste0("[", Sys.time(), "] Expression data pre-processed with SCAN."))
+  }
+
+  # We return the created ESET.
+  return(eset)
+}

R/run_quality_control_on_preprocessed.R

+#' @title Executes a quality control of a given microarray dataset (preprocessed data).
+#'
+#' @description This function executes a quality control of the dataset defined by the input parameters.
+#' It starts by loading the clinical data associated to annotate the preprocessed data and
+#' then runs the quality control of the annotated data. The function assumes that a folder with
+#' the clinical data exists. It then creates a report that contains various quality
+#' indicators and is stored as an HTML document. It does not return any value.
+#'
+#' Note: the function does not check for the existence of folders or files.
+#'
+#' @param eset An ESET object that contains the preprocessed expression data.
+#' @param input_data_dir A string representing the folder that contains the input data (clinical data).
+#' @param output_data_dir A string representing the folder that will contain the output of the QC.
+#' @param phenotype_groups A list of phenotype factor names that can be used to highlight the
+#'  samples in the QC report. This is none by default.
+#' @param verbose A boolean representing whether the function should display log information. This
+#'  is TRUE by default.
+#' @return NULL
+run_quality_control_on_preprocessed <- function(eset, input_data_dir, output_data_dir,
+                                                phenotype_groups = vector(),
+                                                verbose          = TRUE) {
+
+  # We load the clinical data as to annotate the ESET object and make QC more useful.
+  pheno_data <- ArrayUtils::load_clinical_data(input_data_dir, verbose = verbose)
+  Biobase::phenoData(eset) <- pheno_data
+  remove(pheno_data)
+
+  # Now, we do the QC on the normalized data.
+  arrayQualityMetrics::arrayQualityMetrics(expressionset   = eset,
+                                           outdir          = output_data_dir,
+                                           force           = TRUE,
+                                           do.logtransform = TRUE,
+                                           intgroup        = phenotype_groups)
+
+  # We clean up and log information.
+  rm(eset)
+  if (verbose == TRUE) {
+    message(paste0("[", Sys.time(), "] QC analysis performed (preprocessed data)."))
+  }
+}

R/run_quality_control.R → R/run_quality_control_on_raw.R

-#' @title Executes a quality control of a given micro-array dataset.
+#' @title Executes a quality control of a given microarray dataset (raw data).
+#'
 #' @description This function executes a quality control of the dataset defined by the input parameters.
 #' It starts by loading the clinical data associated with the dataset, then loads the raw data and
-#' last runs the quality control of the annotated data.
-#'
-#' The function assumes that the dataset is associated with a unique name (e.g., GEO identifier)
-#' and that a folder with this name exists and contains both the clinical data ('ClinicalData.tsv')
-#' and the raw data (as cel files in a '/RAW/' folder).
+#' last runs the quality control of the annotated data. The function assumes that a folder with
+#' both the clinical data and the raw data exists (in a subfolder '/RAW/'). It then creates a report
+#' that contains various quality indicators and is stored as an HTML document. It does not return
+#' any value.
 #'
-#' It then creates a report that contains various quality indicators and is stored as an HTML
-#' document. It does not return any value.
+#' Note: the function does not check for the existence of folders or files.
 #'
-#' Note: the function does not check for the existence of folders and files (not a real package
-#' function).
-#'
-#' @param dataset_name A string representing the name of the dataset to analyse.
-#' @param raw_data_dir A string representing the folder that contains the input data.
+#' @param input_data_dir A string representing the folder that contains the input data.
 #' @param output_data_dir A string representing the folder that contains the output data.
 #' @param compressed  A boolean representing whether the raw data are compressed or not. This is
 #'  TRUE by default.
@@ -22,29 +17,18 @@
 #'  samples in the QC report. This is none by default.
 #' @param verbose A boolean representing whether the function should display log information. This
 #'  is TRUE by default.
-#'  @return NULL
-run_quality_control <- function(dataset_name,
-                                raw_data_dir,
+#' @return NULL
+run_quality_control_on_raw <- function(input_data_dir,
                                 output_data_dir,
                                 compressed       = TRUE,
-                                phenotype_groups = c(),
+                                phenotype_groups = vector(),
                                 verbose          = TRUE) {
 
   # We define the I/Os.
-  clinical_data_file <- paste0(raw_data_dir, dataset_name, "/", "ClinicalData.tsv")
-  raw_data_input_dir <- paste0(raw_data_dir, dataset_name, "/", "RAW/")
-  data_output_dir <- paste0(output_data_dir, dataset_name, "/")
+  raw_data_input_dir <- paste0(input_data_dir, "RAW/")
 
   # We load the clinical data as to annotate the AffyBatch object and make QC more useful.
-  pheno_data <- Biobase::AnnotatedDataFrame(utils::read.delim(file       = clinical_data_file,
-                                                       row.names  = 1,
-                                                       colClasses = "factor"))
-
-  # We clean up and log information.
-  rm(clinical_data_file)
-  if (verbose == TRUE) {
-    message(paste0("[", Sys.time(), "][", dataset_name, "] Phenotypic data read."))
-  }
+  pheno_data <- ArrayUtils::load_clinical_data(input_data_dir, verbose = verbose)
 
   # We load the CEL files to create the affyBatch object and then attach the clinical data.
   raw_file_list <- affy::list.celfiles(raw_data_input_dir, full.names = TRUE)
@@ -54,19 +38,19 @@ run_quality_control <- function(dataset_name,
   # We clean up and log information.
   rm(raw_file_list, pheno_data, raw_data_input_dir)
   if (verbose == TRUE) {
-    message(paste0("[", Sys.time(), "][", dataset_name, "] Expression data read."))
+    message(paste0("[", Sys.time(), "] Expression data read."))
   }
 
   # We run the quality control itself.
   arrayQualityMetrics::arrayQualityMetrics(expressionset   = batch,
-                                           outdir          = data_output_dir,
+                                           outdir          = output_data_dir,
                                            force           = TRUE,
                                            do.logtransform = TRUE,
                                            intgroup        = phenotype_groups)
 
   # We clean up and log information.
-  rm(data_output_dir, batch)
+  rm(batch)
   if (verbose == TRUE) {
-    message(paste0("[", Sys.time(), "][", dataset_name, "] QC analysis performed."))
+    message(paste0("[", Sys.time(), "] QC analysis performed (raw data)."))
   }
 }