add classification

jpfeuffer · Jul 2, 2018 · dd64735 · dd64735
1 parent 9622d81
commit dd64735
Show file tree

Hide file tree

Showing 12 changed files with 1,200 additions and 1,040 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,8 +1,8 @@
 Package: MSstats
 Title: Protein Significance Analysis in DDA, SRM and DIA for Label-free
         or Label-based Proteomics Experiments
-Version: 3.13.3
-Date: 2018-06-01
+Version: 3.13.4
+Date: 2018-07-02
 Description: A set of tools for statistical relative protein significance analysis in DDA, SRM and DIA experiments.
 Authors@R: c(
   person("Meena","Choi", , "[email protected]", c("aut", "cre")),

diff --git a/R/DIAUmpiretoMSstatsFormat.R b/R/DIAUmpiretoMSstatsFormat.R
@@ -29,11 +29,22 @@ DIAUmpiretoMSstatsFormat <- function(raw.frag, raw.pep, raw.pro,
 
     if (is.null(annotation)) {
         stop('** Please prepare \'annotation\' as one of input.')
+    } else {
+        ## check annotation
+        required.annotation <- c('Condition', 'BioReplicate', 'Run')
+
+        if (!all(required.annotation %in% colnames(annotation))) {
+
+            missedAnnotation <- which(!(required.annotation %in% colnames(annotation)))
+
+            stop(paste("**", toString(required.annotation[missedAnnotation]), 
+                       "is not provided in Annotation. Please check the annotation file."))
+        } else {
+            ### annotation.txt : Condition, BioReplicate, Run, 
+            annot <- annotation
+        }
     }
 
-    ### annotation.txt : Raw.file, Condition, BioReplicate, Run, (IsotopeLabelType)
-    annot <- annotation
-
     ########################
     ## 1.  get selected frag from DIA-Umpire
     ########################

diff --git a/R/MaxQtoMSstatsFormat.R b/R/MaxQtoMSstatsFormat.R
@@ -38,6 +38,17 @@ MaxQtoMSstatsFormat <- function(evidence,
 	## annotation.txt : Raw.file, Condition, BioReplicate, Run, (IsotopeLabelType)
 	annot <- annotation
 
+	## check annotation
+	required.annotation <- c('Raw.file', 'Condition', 'BioReplicate', 'Run', 'IsotopeLabelType')
+
+	if (!all(required.annotation %in% colnames(annot))) {
+
+	    missedAnnotation <- which(!(required.annotation %in% colnames(annot)))
+
+	    stop(paste("**", toString(required.annotation[missedAnnotation]), 
+	               "is not provided in Annotation. Please check the annotation file."))
+	}
+
 	################################################
 	## 1.1 remove contaminant, reverse proteinID 
 	## Contaminant, Reverse column in evidence

diff --git a/R/OpenMStoMSstatsFormat.R b/R/OpenMStoMSstatsFormat.R
@@ -50,7 +50,19 @@ OpenMStoMSstatsFormat <- function(input,
     if (is.null(annotation)) {
         annotinfo <- unique(input[, c("Run", "Condition", 'BioReplicate')])	
     } else {
-        annotinfo <- annotation
+
+        ## check annotation
+        required.annotation <- c('Condition', 'BioReplicate', 'Run')
+
+        if (!all(required.annotation %in% colnames(annotation))) {
+
+            missedAnnotation <- which(!(required.annotation %in% colnames(annotation)))
+
+            stop(paste("**", toString(required.annotation[missedAnnotation]), 
+                       "is not provided in Annotation. Please check the annotation file."))
+        } else {
+            annotinfo <- annotation
+        }
     }
 
     ##############################

diff --git a/R/OpenSWATHtoMSstatsFormat.R b/R/OpenSWATHtoMSstatsFormat.R
@@ -23,7 +23,19 @@ OpenSWATHtoMSstatsFormat <- function(input,
     if (is.null(annotation)) {
         stop('** Please prepare \'annotation\' as one of input.')
     } else {
-        annotinfo <- annotation
+
+        ## check annotation
+        required.annotation <- c('Condition', 'BioReplicate', 'Run')
+
+        if (!all(required.annotation %in% colnames(annotation))) {
+
+            missedAnnotation <- which(!(required.annotation %in% colnames(annotation)))
+
+            stop(paste("**", toString(required.annotation[missedAnnotation]), 
+                       "is not provided in Annotation. Please check the annotation file."))
+        } else {
+            annotinfo <- annotation
+        }
     }
 
     ## Check correct option or input

diff --git a/R/PDtoMSstatsFormat.R b/R/PDtoMSstatsFormat.R
@@ -16,6 +16,18 @@ PDtoMSstatsFormat <- function(input,
                               which.proteinid = 'Protein.Group.Accessions',
                               which.sequence = 'Sequence'){
 
+    ## check annotation
+    required.annotation <- c('Condition', 'BioReplicate', 'Run')
+
+    if (!all(required.annotation %in% colnames(annotation))) {
+
+        missedAnnotation <- which(!(required.annotation %in% colnames(annotation)))
+
+        stop(paste("**", toString(required.annotation[missedAnnotation]), 
+                   "is not provided in Annotation. Please check the annotation file.",
+                   "'Run' will be matched with 'Spectrum.File' "))
+    }
+
     ################################################
     ## 0.1. which intensity : Precursor.Area vs. Intensity vs Area
     ################################################
@@ -244,7 +256,38 @@ PDtoMSstatsFormat <- function(input,
     rm(input.final)
 
     ##############################
-    ##  6. remove features which has 1 or 2 measurements across runs
+    ## 6. remove featuares with all na or zero
+    ## some rows have all zero values across all MS runs. They should be removed.
+    ##############################
+
+    input$fea <- paste(input$PeptideModifiedSequence,
+                       input$PrecursorCharge,
+                       input$FragmentIon,
+                       input$ProductCharge,
+                       sep="_")
+
+    inputtmp <- input[!is.na(input$Intensity) & input$Intensity > 1, ]
+
+    count <- inputtmp %>% group_by(fea) %>% summarise(length=length(Intensity))
+
+    ## get feature with all NA or zeros
+    getfea <- count[count$length > 0, 'fea']
+
+    if (nrow(getfea) > 0) {
+
+        nfea.remove <- length(unique(input$fea))-nrow(getfea)
+        input <- input[which(input$fea %in% getfea$fea), ]
+
+        message(paste0('** ', nfea.remove, ' features have all NAs or zero intensity values and are removed.'))
+
+    }
+
+    rm(inputtmp)
+    input <- input[, -which(colnames(input) %in% c('fea'))]
+
+
+    ##############################
+    ##  7. remove features which has 1 or 2 measurements across runs
     ##############################
     if (fewMeasurements=="remove") {
 
@@ -265,7 +308,7 @@ PDtoMSstatsFormat <- function(input,
     }
 
     ##############################
-    ##  7. remove proteins with only one peptide and charge per protein
+    ##  8. remove proteins with only one peptide and charge per protein
     ##############################
 
 	if (removeProtein_with1Peptide) {