feat(metamorpheus): Add converter from metamorpheus to core MSstats

NAMESPACE

@@ -23,6 +23,7 @@ export(MSstatsSummarize)
 export(MSstatsSummarizeSingleLinear)
 export(MSstatsSummarizeSingleTMP)
 export(MaxQtoMSstatsFormat)
+export(MetamorpheustoMSstatsFormat)
 export(OpenMStoMSstatsFormat)
 export(OpenSWATHtoMSstatsFormat)
 export(PDtoMSstatsFormat)

R/converters.R

@@ -860,3 +860,64 @@ FragPipetoMSstatsFormat = function(
     getOption("MSstatsLog")("INFO", "\n")
     input
 }
+
+
+#' Import Metamorpheus files
+#' 
+#' @param input name of Metamorpheus output file, which is tabular format. Use the AllQuantifiedPeaks.tsv file from the Metamorpheus output.
+#' @param annotation name of 'annotation.txt' data which includes Condition, BioReplicate. 
+#' @param ... additional parameters to `data.table::fread`.
+#' @inheritParams .documentFunction
+#' 
+#' @return data.frame in the MSstats required format.
+#' 
+#' @author Anthony Wu
+#' 
+#' @export
+#' 
+#' @examples 
+#' input = system.file("tinytest/raw_data/Metamorpheus/AllQuantifiedPeaks.tsv", 
+#'                                 package = "MSstatsConvert")
+#' input = data.table::fread(input)
+#' annot = system.file("tinytest/raw_data/Metamorpheus/Annotation.tsv", 
+#'                                 package = "MSstatsConvert")
+#' annot = data.table::fread(annot)
+#' metamorpheus_imported = MSstats:::MetamorpheustoMSstatsFormat(input, annotation = annot)
+#' head(metamorpheus_imported)
+#' 
+MetamorpheustoMSstatsFormat = function(
+        input, annotation = NULL, useUniquePeptide = TRUE, removeFewMeasurements = TRUE,
+        removeProtein_with1Feature = FALSE, summaryforMultipleRows = max,
+        use_log_file = TRUE, append = FALSE, verbose = TRUE, log_file_path = NULL,
+        ...
+) {
+    MSstatsConvert::MSstatsLogsSettings(use_log_file, append, verbose, 
+                                        log_file_path)
+
+    input = MSstatsConvert::MSstatsImport(list(input = input), 
+                                          "MSstats", "Metamorpheus", ...)
+    input = MSstatsConvert::MSstatsClean(input)
+    annotation = MSstatsConvert::MSstatsMakeAnnotation(input, annotation)
+
+    feature_columns = c("PeptideSequence", "PrecursorCharge")
+    input = MSstatsConvert::MSstatsPreprocess(
+        input, 
+        annotation, 
+        feature_columns,
+        remove_shared_peptides = useUniquePeptide,
+        remove_single_feature_proteins = removeProtein_with1Feature,
+        feature_cleaning = list(remove_features_with_few_measurements = removeFewMeasurements,
+                                summarize_multiple_psms = summaryforMultipleRows),
+        columns_to_fill = list("FragmentIon" = NA,
+                               "ProductCharge" = NA,
+                               "IsotopeLabelType" = "L"))
+    input = MSstatsConvert::MSstatsBalancedDesign(input, feature_columns,
+                                                  remove_few = removeFewMeasurements)
+
+    msg_final = paste("** Finished preprocessing. The dataset is ready",
+                      "to be processed by the dataProcess function.")
+    getOption("MSstatsLog")("INFO", msg_final)
+    getOption("MSstatsMsg")("INFO", msg_final)
+    getOption("MSstatsLog")("INFO", "\n")
+    return(input)
+}

inst/tinytest/test_converters.R

@@ -0,0 +1,24 @@
+# Test MetamorpheustoMSstatsFormat ---------------------------
+
+input_file_path = system.file("tinytest/raw_data/Metamorpheus/AllQuantifiedPeaks.tsv", package="MSstatsConvert")
+annotation_file_path = system.file("tinytest/raw_data/Metamorpheus/Annotation.tsv", package = "MSstatsConvert")
+input = data.table::fread(input_file_path)
+annotation = data.table::fread(annotation_file_path)
+output = MSstats:::MetamorpheustoMSstatsFormat(input, annotation = annotation)
+expect_equal(ncol(output), 11)
+expect_true(nrow(output) > 0)
+expected_column_names = c(
+    "Run",
+    "ProteinName",
+    "PeptideSequence",
+    "PrecursorCharge",
+    "Intensity",
+    "FragmentIon",
+    "ProductCharge",
+    "IsotopeLabelType",
+    "Condition",
+    "BioReplicate",
+    "Fraction"
+)
+missing_columns = setdiff(expected_column_names, colnames(output))
+expect_equal(length(missing_columns), 0)