Added a function to run a quality control test.

.gitignore

+.Rproj.user/*
+.Rbuildignore
+ArrayUtils.Rproj
+man/*

DESCRIPTION

+Package: ArrayUtils
+Type: Package
+Title: Utils For Array Processing
+Version: 0.0.1
+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
+Encoding: UTF-8
+LazyData: true
+Imports:
+  utils,affy,Biobase,arrayQualityMetrics
+RoxygenNote: 6.1.1

LICENSE

+This is free and unencumbered software released into the public domain.
+
+Anyone is free to copy, modify, publish, use, compile, sell, or
+distribute this software, either in source code form or as a compiled
+binary, for any purpose, commercial or non-commercial, and by any
+means.
+
+In jurisdictions that recognize copyright laws, the author or authors
+of this software dedicate any and all copyright interest in the
+software to the public domain. We make this dedication for the benefit
+of the public at large and to the detriment of our heirs and
+successors. We intend this dedication to be an overt act of
+relinquishment in perpetuity of all present and future rights to this
+software under copyright law.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE AUTHORS BE LIABLE FOR ANY CLAIM, DAMAGES OR
+OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+OTHER DEALINGS IN THE SOFTWARE.
+
+For more information, please refer to <http://unlicense.org>

NAMESPACE

+exportPattern("^[[:alpha:]]+")

R/run_quality_control.R

+#' @title Executes a quality control of a given micro-array dataset.
+#' @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).
+#'
+#' 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 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 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.
+#' @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 <- function(dataset_name,
+                                raw_data_dir,
+                                output_data_dir,
+                                compressed       = TRUE,
+                                phenotype_groups = c(),
+                                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, "/")
+
+  # 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."))
+  }
+
+  # 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)
+  batch <- affy::ReadAffy(filenames = raw_file_list, compress = compressed, verbose = verbose)
+  Biobase::phenoData(batch) <- pheno_data
+
+  # 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."))
+  }
+
+  # We run the quality control itself.
+  arrayQualityMetrics::arrayQualityMetrics(expressionset   = batch,
+                                           outdir          = data_output_dir,
+                                           force           = TRUE,
+                                           do.logtransform = TRUE,
+                                           intgroup        = phenotype_groups)
+
+  # We clean up and log information.
+  rm(data_output_dir, batch)
+  if (verbose == TRUE) {
+    message(paste0("[", Sys.time(), "][", dataset_name, "] QC analysis performed."))
+  }
+}