In bihealth/metaquac: Metabolomics Targeted Quality Control

Import

Import of r params$kit data of measurement type r params$measurement_type.

Data files to import:

# Data files
pander::pander(params$data_files)

# Measurement Type
meas_type <- params$measurement_type

# Import data (TODO: import batches)
generic_data <- import_generic_table_set(
  filenames = params$data_files[[1]],
  index_first_compound = params$generic_index_first_compound,
  zero2na = params$zero2na
)

CONTINUE <- exists("generic_data")

# Set "Batch" if data set contains multi batches, else NULL
# Also, make sure it is a factor (so it won't misbehave if just numbers)
# TODO: move to restructuring section (for Biocrates as well)
if (!COLUMN_BATCH %in% names(generic_data)) {
  generic_data[[COLUMN_BATCH]] <- "Batch1"
}
if (length(unique(generic_data$Batch)) > 1) {
  BATCH <- COLUMN_BATCH
  MULTIBATCH <- TRUE
  generic_data[[COLUMN_BATCH]] <- factor(generic_data[[COLUMN_BATCH]])
} else {
  BATCH <- NULL
}

# Add batch to sample name
# TODO: move to restructuring section (for Biocrates as well)
if (!is.null(BATCH)) {
  generic_data$Sample.Name <- 
    paste0(generic_data$Sample.Name, "_", generic_data$Batch)
}

# Set available data types
assign("CONCENTRATION", params$generic_data_types["CONCENTRATION"], ENV) # Unit added on import
assign("INTENSITY", params$generic_data_types["INTENSITY"], ENV)
assign("AREA", params$generic_data_types["AREA"], ENV)
assign("ISTD_INTENSITY", params$generic_data_types["ISTD_INTENSITY"], ENV)
assign("ISTD_AREA", params$generic_data_types["ISTD_AREA"], ENV)
DATA_TYPES <- params$generic_data_types[params$generic_data_types %in% names(generic_data)]
assign("DATA_TYPES", DATA_TYPES, ENV)

# Set sample types
# TODO: create and check parameter for sample types
assign("SAMPLE_TYPE_REFERENCE_QC", "Reference QC", ENV)

# Check if a proper dataset is available
REQUIRED_METAQUAC_COLUMNS <- c(make.names(c(
  "Sample Type",
  "Sample Identification",
  # "Well Position",
  "Compound",
  "MetIDQ_Status",
  # "Class",
  "Sequence Position",
  "Sample Name"
  # "Batch"
)), DATA_TYPES)

CONTINUE <- all(REQUIRED_METAQUAC_COLUMNS %in% names(generic_data)) && !nrow(generic_data) < 1

message("Error: Data import failed, further processing canceled!")
if (exists("generic_data")){
  print(generic_data)
}

# TODO: apply a more generic name to the dataset running through MeTaQuaC
biocrates <- generic_data

bihealth/metaquac documentation built on Aug. 7, 2021, 8:40 a.m.