feat(protein-prospector): Add TMT converter for protein prospector

DESCRIPTION

@@ -31,6 +31,7 @@ Suggests:
     knitr,
     rmarkdown
 Collate: 
+    'clean_ProteinProspector.R'
     'clean_Metamorpheus.R'
     'clean_DIANN.R'
     'clean_Philosopher.R'
@@ -53,6 +54,7 @@ Collate:
     'converters_OpenSWATHtoMSstatsFormat.R'
     'converters_PDtoMSstatsFormat.R'
     'converters_ProgenesistoMSstatsFormat.R'
+    'converters_ProteinProspectortoMSstatsTMTFormat.R'
     'converters_SkylinetoMSstatsFormat.R'
     'converters_SpectronauttoMSstatsFormat.R'
     'utils_MSstatsConvert.R'

NAMESPACE

@@ -18,6 +18,7 @@ export(OpenMStoMSstatsFormat)
 export(OpenSWATHtoMSstatsFormat)
 export(PDtoMSstatsFormat)
 export(ProgenesistoMSstatsFormat)
+export(ProteinProspectortoMSstatsTMTFormat)
 export(SkylinetoMSstatsFormat)
 export(SpectronauttoMSstatsFormat)
 export(getDataType)

R/MSstatsConvert_core_functions.R

@@ -67,6 +67,10 @@ setClass("MSstatsFragPipeFiles", contains = "MSstatsInputFiles")
 #' @rdname MSstatsInputFiles
 #' @keywords internal
 setClass("MSstatsMetamorpheusFiles", contains = "MSstatsInputFiles")
+#' MSstatsProteinProspectorFiles: class for ProteinProspector files.
+#' @rdname MSstatsInputFiles
+#' @keywords internal
+setClass("MSstatsProteinProspectorFiles", contains = "MSstatsInputFiles")
 
 
 #' Get one of files contained in an instance of `MSstatsInputFiles` class.
@@ -282,6 +286,13 @@ setMethod("MSstatsClean", signature = "MSstatsDIANNFiles",
 #' @return data.table
 setMethod("MSstatsClean", signature = "MSstatsMetamorpheusFiles", 
           .cleanRawMetamorpheus)
+#' Clean Protein Prospector files
+#' @include clean_ProteinProspector.R
+#' @rdname MSstatsClean
+#' @inheritParams .cleanRawProteinProspector
+#' @return data.table
+setMethod("MSstatsClean", signature = "MSstatsProteinProspectorFiles", 
+          .cleanRawProteinProspector)
 
 
 #' Preprocess outputs from MS signal processing tools for analysis with MSstats

R/clean_ProteinProspector.R

@@ -0,0 +1,38 @@
+#' Clean raw Protein Prospector data
+#' @param msstats_object object that inherits from MSstatsInputFiles class.
+#' @return data.table
+#' @keywords internal
+#' @noRd
+.cleanRawProteinProspector = function(msstats_object) {
+    PSM = PeptideSequence = PrecursorCharge = NULL
+    protein_prospector_input = getInputFile(msstats_object, "input")
+    protein_prospector_input = 
+        data.table::as.data.table(protein_prospector_input)
+    channels = .getChannelColumns(
+        colnames(protein_prospector_input), "Int")
+    req_cols = c('AccX', 'z', 'DBPeptide', 'Fraction', channels)
+    protein_prospector_input = protein_prospector_input[, req_cols, with = FALSE]
+    data.table::setnames(
+        protein_prospector_input, 
+        c("AccX", "DBPeptide", "z", "Fraction"),
+        c("ProteinName", "PeptideSequence", "PrecursorCharge", "Run"), 
+        skip_absent = TRUE)
+    protein_prospector_input[, PSM := paste(PeptideSequence, PrecursorCharge, 
+                            1:nrow(protein_prospector_input), sep = "_")]
+
+    protein_prospector_input = melt(protein_prospector_input, 
+                                    measure.vars = channels, 
+                                    id.vars = setdiff(
+                                        colnames(protein_prospector_input), 
+                                        channels
+                                    ),
+                                    variable.name = "Channel", 
+                                    value.name = "Intensity"
+                                )
+    protein_prospector_input$Channel = .standardizeColnames(
+        protein_prospector_input$Channel
+    )
+
+    .logSuccess("ProteinProspector", "clean")
+    protein_prospector_input
+}

R/converters_ProteinProspectortoMSstatsTMTFormat.R

@@ -0,0 +1,59 @@
+#' Generate MSstatsTMT required input format from Protein Prospector output
+#' 
+#' @inheritParams .sharedParametersAmongConverters
+#' @param input Input txt peptide report file from Protein Prospector with 
+#' "Keep Replicates", "Mods in Peptide", and "Protein Mods" options selected.
+#' @param annotation data frame which contains column Run, Fraction, 
+#' TechRepMixture, Mixture, Channel, BioReplicate, Condition. 
+#' 
+#' @return data.frame of class "MSstatsTMT"
+#' 
+#' @export
+#' 
+#' @examples
+#' input = system.file("tinytest/raw_data/ProteinProspector/Prospector_TotalTMT.txt",
+#'     package = "MSstatsConvert")
+#' input = data.table::fread(input)
+#' annot = system.file("tinytest/raw_data/ProteinProspector/Annotation.csv",
+#'                                 package = "MSstatsConvert")
+#' annot = data.table::fread(annot)
+#' output <- ProteinProspectortoMSstatsTMTFormat(input, annot)
+#' head(output)
+#' 
+ProteinProspectortoMSstatsTMTFormat = function(
+        input, annotation, useUniquePeptide = TRUE, removeFewMeasurements = TRUE,
+        removeProtein_with1Feature = FALSE, summaryforMultipleRows = sum,
+        use_log_file = TRUE, append = FALSE, verbose = TRUE, 
+        log_file_path = NULL
+) {
+    MSstatsConvert::MSstatsLogsSettings(use_log_file, append, verbose, 
+                                        log_file_path, 
+                                        base = "MSstatsTMT_converter_log_")
+
+    input = MSstatsConvert::MSstatsImport(list(input = input), 
+                                          "MSstatsTMT", "ProteinProspector")
+    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)
+        )
+    input = MSstatsConvert::MSstatsBalancedDesign(input, feature_columns,
+                                                  fix_missing = "zero_to_na")
+    data.table::setnames(input, "PrecursorCharge", "Charge", skip_absent = TRUE)
+
+    msg_final = paste("** Finished preprocessing. The dataset is ready",
+                      "to be processed by the proteinSummarization function.")
+    getOption("MSstatsLog")("INFO", msg_final)
+    getOption("MSstatsMsg")("INFO", msg_final)
+    getOption("MSstatsLog")("INFO", "\n")
+    input
+}

inst/tinytest/raw_data/ProteinProspector/Annotation.csv

@@ -0,0 +1,73 @@
+Run,Fraction,TechRepMixture,Channel,Condition,Mixture,BioReplicate
+Z20180606-01_FTMSms2hcd,1,1,Int 126,Young,Mixture1,S1
+Z20180606-02_FTMSms2hcd,2,1,Int 126,Young,Mixture1,S1
+Z20180606-03_FTMSms2hcd,3,1,Int 126,Young,Mixture1,S1
+Z20180606-04_FTMSms2hcd,4,1,Int 126,Young,Mixture1,S1
+Z20180606-05_FTMSms2hcd,5,1,Int 126,Young,Mixture1,S1
+Z20180606-06_FTMSms2hcd,6,1,Int 126,Young,Mixture1,S1
+Z20180606-07_FTMSms2hcd,7,1,Int 126,Young,Mixture1,S1
+Z20180606-08_FTMSms2hcd,8,1,Int 126,Young,Mixture1,S1
+Z20180606-09_FTMSms2hcd,9,1,Int 126,Young,Mixture1,S1
+Z20180606-10_FTMSms2hcd,10,1,Int 126,Young,Mixture1,S1
+Z20180606-11_FTMSms2hcd,11,1,Int 126,Young,Mixture1,S1
+Z20180606-12_FTMSms2hcd,12,1,Int 126,Young,Mixture1,S1
+Z20180606-01_FTMSms2hcd,1,1,Int 127,Young,Mixture1,S2
+Z20180606-02_FTMSms2hcd,2,1,Int 127,Young,Mixture1,S2
+Z20180606-03_FTMSms2hcd,3,1,Int 127,Young,Mixture1,S2
+Z20180606-04_FTMSms2hcd,4,1,Int 127,Young,Mixture1,S2
+Z20180606-05_FTMSms2hcd,5,1,Int 127,Young,Mixture1,S2
+Z20180606-06_FTMSms2hcd,6,1,Int 127,Young,Mixture1,S2
+Z20180606-07_FTMSms2hcd,7,1,Int 127,Young,Mixture1,S2
+Z20180606-08_FTMSms2hcd,8,1,Int 127,Young,Mixture1,S2
+Z20180606-09_FTMSms2hcd,9,1,Int 127,Young,Mixture1,S2
+Z20180606-10_FTMSms2hcd,10,1,Int 127,Young,Mixture1,S2
+Z20180606-11_FTMSms2hcd,11,1,Int 127,Young,Mixture1,S2
+Z20180606-12_FTMSms2hcd,12,1,Int 127,Young,Mixture1,S2
+Z20180606-01_FTMSms2hcd,1,1,Int 128,Young,Mixture1,S3
+Z20180606-02_FTMSms2hcd,2,1,Int 128,Young,Mixture1,S3
+Z20180606-03_FTMSms2hcd,3,1,Int 128,Young,Mixture1,S3
+Z20180606-04_FTMSms2hcd,4,1,Int 128,Young,Mixture1,S3
+Z20180606-05_FTMSms2hcd,5,1,Int 128,Young,Mixture1,S3
+Z20180606-06_FTMSms2hcd,6,1,Int 128,Young,Mixture1,S3
+Z20180606-07_FTMSms2hcd,7,1,Int 128,Young,Mixture1,S3
+Z20180606-08_FTMSms2hcd,8,1,Int 128,Young,Mixture1,S3
+Z20180606-09_FTMSms2hcd,9,1,Int 128,Young,Mixture1,S3
+Z20180606-10_FTMSms2hcd,10,1,Int 128,Young,Mixture1,S3
+Z20180606-11_FTMSms2hcd,11,1,Int 128,Young,Mixture1,S3
+Z20180606-12_FTMSms2hcd,12,1,Int 128,Young,Mixture1,S3
+Z20180606-01_FTMSms2hcd,1,1,Int 129,Aged,Mixture1,S4
+Z20180606-02_FTMSms2hcd,2,1,Int 129,Aged,Mixture1,S4
+Z20180606-03_FTMSms2hcd,3,1,Int 129,Aged,Mixture1,S4
+Z20180606-04_FTMSms2hcd,4,1,Int 129,Aged,Mixture1,S4
+Z20180606-05_FTMSms2hcd,5,1,Int 129,Aged,Mixture1,S4
+Z20180606-06_FTMSms2hcd,6,1,Int 129,Aged,Mixture1,S4
+Z20180606-07_FTMSms2hcd,7,1,Int 129,Aged,Mixture1,S4
+Z20180606-08_FTMSms2hcd,8,1,Int 129,Aged,Mixture1,S4
+Z20180606-09_FTMSms2hcd,9,1,Int 129,Aged,Mixture1,S4
+Z20180606-10_FTMSms2hcd,10,1,Int 129,Aged,Mixture1,S4
+Z20180606-11_FTMSms2hcd,11,1,Int 129,Aged,Mixture1,S4
+Z20180606-12_FTMSms2hcd,12,1,Int 129,Aged,Mixture1,S4
+Z20180606-01_FTMSms2hcd,1,1,Int 130,Aged,Mixture1,S5
+Z20180606-02_FTMSms2hcd,2,1,Int 130,Aged,Mixture1,S5
+Z20180606-03_FTMSms2hcd,3,1,Int 130,Aged,Mixture1,S5
+Z20180606-04_FTMSms2hcd,4,1,Int 130,Aged,Mixture1,S5
+Z20180606-05_FTMSms2hcd,5,1,Int 130,Aged,Mixture1,S5
+Z20180606-06_FTMSms2hcd,6,1,Int 130,Aged,Mixture1,S5
+Z20180606-07_FTMSms2hcd,7,1,Int 130,Aged,Mixture1,S5
+Z20180606-08_FTMSms2hcd,8,1,Int 130,Aged,Mixture1,S5
+Z20180606-09_FTMSms2hcd,9,1,Int 130,Aged,Mixture1,S5
+Z20180606-10_FTMSms2hcd,10,1,Int 130,Aged,Mixture1,S5
+Z20180606-11_FTMSms2hcd,11,1,Int 130,Aged,Mixture1,S5
+Z20180606-12_FTMSms2hcd,12,1,Int 130,Aged,Mixture1,S5
+Z20180606-01_FTMSms2hcd,1,1,Int 131,Aged,Mixture1,S6
+Z20180606-02_FTMSms2hcd,2,1,Int 131,Aged,Mixture1,S6
+Z20180606-03_FTMSms2hcd,3,1,Int 131,Aged,Mixture1,S6
+Z20180606-04_FTMSms2hcd,4,1,Int 131,Aged,Mixture1,S6
+Z20180606-05_FTMSms2hcd,5,1,Int 131,Aged,Mixture1,S6
+Z20180606-06_FTMSms2hcd,6,1,Int 131,Aged,Mixture1,S6
+Z20180606-07_FTMSms2hcd,7,1,Int 131,Aged,Mixture1,S6
+Z20180606-08_FTMSms2hcd,8,1,Int 131,Aged,Mixture1,S6
+Z20180606-09_FTMSms2hcd,9,1,Int 131,Aged,Mixture1,S6
+Z20180606-10_FTMSms2hcd,10,1,Int 131,Aged,Mixture1,S6
+Z20180606-11_FTMSms2hcd,11,1,Int 131,Aged,Mixture1,S6
+Z20180606-12_FTMSms2hcd,12,1,Int 131,Aged,Mixture1,S6