Add option to use MS1Quantity for quantifications for Spectronaut (#117)

Author: tonywu1999

R/clean_Spectronaut.R

@@ -1,8 +1,6 @@
 #' Clean raw Spectronaut output.
 #' @param msstats_object an object of class `MSstatsSpectronautFiles`.
-#' @param intensity chr, specifies which column will be used for Intensity.
-#' @param calculateAnomalyScores logical, whether to calculate anomaly scores
-#' @param anomalyModelFeatures character vector, specifies which columns will be used for anomaly detection model. Can be NULL if calculateAnomalyScores=FALSE.
+#' @inheritParams SpectronauttoMSstatsFormat
 #' @return `data.table`
 #' @keywords internal
 .cleanRawSpectronaut = function(msstats_object, intensity,
@@ -20,10 +18,17 @@
                                     colnames(spec_input))
   exclude_col = .findAvailable(c("FExcludedFromQuantification"), 
                                colnames(spec_input))
+  intensity_column_mapping = c(
+      "PeakArea" = "FPeakArea",
+      "NormalizedPeakArea" = "FNormalizedPeakArea",
+      "MS1Quantity" = "FGMS1Quantity"
+  )
+  intensity = match.arg(intensity, names(intensity_column_mapping))
+  intensity_column = intensity_column_mapping[[intensity]]
   cols = c("PGProteinGroups", "EGModifiedSequence", "FGCharge", "FFrgIon", 
            f_charge_col, "RFileName", "RCondition", "RReplicate", 
            "EGQvalue", pg_qval_col, interference_col, exclude_col,
-           paste0("F", intensity))
+           intensity_column)
   if (calculateAnomalyScores){
     cols = c(cols, anomalyModelFeatures)
   }
@@ -32,7 +37,7 @@
   data.table::setnames(
     spec_input, 
     c("PGProteinGroups", "EGModifiedSequence", "FGCharge", "FFrgIon",
-      f_charge_col, "RFileName", paste0("F", intensity), 
+      f_charge_col, "RFileName", intensity_column, 
       "RCondition", "RReplicate"),
     c("ProteinName", "PeptideSequence", "PrecursorCharge", "FragmentIon",
       "ProductCharge", "Run", "Intensity", "Condition", "BioReplicate"), 

R/converters_SpectronauttoMSstatsFormat.R

@@ -2,7 +2,8 @@
 #' 
 #' @param input name of Spectronaut output, which is long-format. ProteinName, PeptideSequence, PrecursorCharge, FragmentIon, ProductCharge, IsotopeLabelType, Condition, BioReplicate, Run, Intensity, F.ExcludedFromQuantification are required. Rows with F.ExcludedFromQuantification=True will be removed.
 #' @param annotation name of 'annotation.txt' data which includes Condition, BioReplicate, Run. If annotation is already complete in Spectronaut, use annotation=NULL (default). It will use the annotation information from input.
-#' @param intensity 'PeakArea'(default) uses not normalized peak area. 'NormalizedPeakArea' uses peak area normalized by Spectronaut.
+#' @param intensity 'PeakArea'(default) uses not normalized MS2 peak area. 'NormalizedPeakArea' uses MS2 peak area normalized by Spectronaut.
+#' 'MS1Quantity' uses MS1 level quantification, which should be used if MS2 is unreliable.
 #' @param excludedFromQuantificationFilter Remove rows with F.ExcludedFromQuantification=TRUE Default is TRUE.
 #' @param filter_with_Qvalue FALSE(default) will not perform any filtering. TRUE will filter out the intensities that have greater than qvalue_cutoff in EG.Qvalue column. Those intensities will be replaced with zero and will be considered as censored missing values for imputation purpose.
 #' @param qvalue_cutoff Cutoff for EG.Qvalue. default is 0.01.
@@ -32,7 +33,8 @@
 #' head(spectronaut_imported)
 #' 
 SpectronauttoMSstatsFormat = function(
-        input, annotation = NULL, intensity = 'PeakArea', 
+        input, annotation = NULL, 
+        intensity = c('PeakArea', 'NormalizedPeakArea', 'MS1Quantity'),
         excludedFromQuantificationFilter = TRUE,
         filter_with_Qvalue = FALSE, qvalue_cutoff = 0.01, 
         useUniquePeptide = TRUE, removeFewMeasurements=TRUE,

R/utils_checks.R

@@ -152,11 +152,6 @@
         }
     }
 
-    # Intensity validation (if provided)
-    if (!is.null(config$intensity)) {
-        checkmate::assertString(config$intensity)
-    }
-    
     # Q-value filtering parameters
     checkmate::assertLogical(config$filter_with_Qvalue, len = 1)
     checkmate::assertNumber(config$qvalue_cutoff, lower = 0, upper = 1)

inst/tinytest/test_clean_Spectronaut.R

@@ -0,0 +1,16 @@
+# Test intensity parameter
+spectronaut_raw = system.file("tinytest/raw_data/Spectronaut/spectronaut_input.csv",
+                              package = "MSstatsConvert")
+spectronaut_raw = data.table::fread(spectronaut_raw)
+spectronaut_raw$FG.MS1Quantity = 100000
+msstats_input = MSstatsConvert::MSstatsImport(
+    list(input = spectronaut_raw), "MSstats", "Spectronaut")
+output = MSstatsConvert:::.cleanRawSpectronaut(msstats_input, intensity = 'MS1Quantity', 
+                                    calculateAnomalyScores = FALSE, 
+                                    anomalyModelFeatures = c())
+expect_true(all(output$Intensity == 100000))
+
+expect_error(MSstatsConvert:::.cleanRawSpectronaut(msstats_input, intensity = 'invalid', 
+                                                   calculateAnomalyScores = FALSE, 
+                                                   anomalyModelFeatures = c()), 
+             pattern = "'arg' should be one of .*PeakArea")