Merge pull request #81 from NorStorz/feature/qfeature

Feature/qfeature

.Rbuildignore

@@ -0,0 +1,2 @@
+^.*\.Rproj$
+^\.Rproj\.user$

MetFamily.Rproj

@@ -0,0 +1,17 @@
+Version: 1.0
+
+RestoreWorkspace: Default
+SaveWorkspace: Default
+AlwaysSaveHistory: Default
+
+EnableCodeIndexing: Yes
+UseSpacesForTab: Yes
+NumSpacesForTab: 2
+Encoding: UTF-8
+
+RnwWeave: Sweave
+LaTeX: pdfLaTeX
+
+BuildType: Package
+PackageUseDevtools: Yes
+PackageInstallArgs: --no-multiarch --with-keep.source

R/FragmentMatrixFunctions.R

@@ -1585,6 +1585,10 @@ convertToProjectFile2 <- function(filePeakMatrixQF,
   metaboliteFamilies <- metaboliteFamilies[orderMS1features]
   furtherProperties <- lapply(X = furtherProperties, FUN = function(props){props[orderMS1features]})
 
+  #TODO: resolve ?
+  #temporary fix
+  #filePeakMatrix <- NULL
+
   if(!is.null(filePeakMatrix)){
     ## allHits: dataFrame$"Average Mz" --> precursorMz; allHits indexes the spectraList
     diffAll <- abs(outer(X = precursorMz, Y = dataFrame$"Average Mz", FUN = function(x, y){abs(x-y)}))

R/parsePeakAbundanceMatrixQF.R

@@ -11,6 +11,7 @@
 #' @export
 #'
 #' @examples
+
 parsePeakAbundanceMatrixQF <- function(qfeatures, 
                                      doPrecursorDeisotoping, 
                                      mzDeviationInPPM_precursorDeisotoping, 
@@ -19,33 +20,36 @@ parsePeakAbundanceMatrixQF <- function(qfeatures,
                                      progress=FALSE)
 {
   ## read file
-
   if(!is.na(progress)) {
     if(progress) {
       incProgress(amount = 0.1, detail = paste("Parsing MS1 file content...", sep = ""))
     } else {
       print(paste("Parsing MS1 file content...", sep = ""))
     } 
   }
+
+
+
 
   cols_to_exclude <- c("Reference RT","Reference m/z","Comment",
                        "Manually modified for quantification",
                        "Total score","RT similarity","Average","Stdev") 
 
   cols_to_keep <- which(!colnames(rowData(qfeatures))[[1]] %in% cols_to_exclude)
-
+ 
   dataFrame <- cbind(rowData(qfeatures)[[1]][,cols_to_keep] ,assay(qfeatures))
-
-  ncol(rowData(qfeatures)[[1]]) 
+  #workaround for avoiding change in colnames during coercion
+  cnames <- colnames(dataFrame)
+  dataFrame <- as.data.frame(dataFrame)
+  colnames(dataFrame) <- cnames
+  oldFormat <- ncol(colData(qfeatures))==3
+  numRowDataCols <- ncol(rowData(qfeatures)[[1]])
+  dataColumnStartEndIndeces <- c(numRowDataCols+1,ncol(dataFrame))
   numberOfPrecursors <- nrow(dataFrame)
   numberOfPrecursorsPrior <- numberOfPrecursors 
-
 
-
-  if(nrow(colData(qfeatures))>0){
-
-    dataColumnStartEndIndeces <- 1
-    numberOfDataColumns   <- nrow(colData(qfeatures))
+  if(ncol(assay(qfeatures))>0){
+    numberOfDataColumns   <- ncol(assay(qfeatures))
     sampleClass           <- colData(qfeatures)$Class
     sampleType            <- colData(qfeatures)$Type
     sampleInjectionOrder  <- colData(qfeatures)$"Injection order"
@@ -74,7 +78,7 @@ parsePeakAbundanceMatrixQF <- function(qfeatures,
 
     ## replace -1 by 0
     if(numberOfDataColumns > 0) {
-      for(colIdx in dataColumnStartEndIndeces[[1]]:dataColumnStartEndIndeces[[2]]){
+      for(colIdx in (numRowDataCols+1):ncol(dataFrame)){
         dataFrame[ , colIdx] <- gsub(x = gsub(x = dataFrame[ , colIdx], pattern = "\\.", replacement = ""), pattern = ",", replacement = ".")
       }
     }
@@ -97,13 +101,13 @@ parsePeakAbundanceMatrixQF <- function(qfeatures,
 
   ## replace -1 by 0
   if(numberOfDataColumns > 0){
-    for(colIdx in dataColumnStartEndIndeces[[1]]:dataColumnStartEndIndeces[[2]]){
+    for(colIdx in (numRowDataCols+1):ncol(dataFrame)){
       dataFrame[ , colIdx] <- as.numeric(dataFrame[ , colIdx])
       if(!is.na(sum(dataFrame[,colIdx] == -1)))
         dataFrame[(dataFrame[,colIdx] == -1),colIdx] <- 0
     }
   }
-
+  vals <- NULL
   ## deisotoping
   numberOfRemovedIsotopePeaks <- 0
   if(doPrecursorDeisotoping & !is.null(dataFrame$"Average Mz")){
@@ -114,7 +118,7 @@ parsePeakAbundanceMatrixQF <- function(qfeatures,
     precursorsToRemove <- vector(mode = "logical", length = numberOfPrecursors)
 
     if(numberOfDataColumns > 0){
-      intensities <- dataFrame[ , dataColumnStartEndIndeces[[1]]:dataColumnStartEndIndeces[[2]]]
+      intensities <- dataFrame[ , (numRowDataCols+1):ncol(dataFrame)]
       medians <- apply(X = as.matrix(intensities), MARGIN = 1, FUN = median)
     }
 
@@ -139,21 +143,23 @@ parsePeakAbundanceMatrixQF <- function(qfeatures,
       } else {
         validPrecursorsInIntensity <- TRUE
       }
-      
+
       if(any(validPrecursorsInRt & validPrecursorsInMz & validPrecursorsInIntensity))
         precursorsToRemove[[precursorIdx]] <- TRUE
-    }
 
+    }
+
     ## remove isotopes
     dataFrame <- dataFrame[!precursorsToRemove, ]
 
     numberOfRemovedIsotopePeaks <- sum(precursorsToRemove)
     numberOfPrecursors <- nrow(dataFrame)
   }
-  
+
   if(!is.na(progress))  if(progress)  incProgress(amount = 0, detail = paste("Boxing...", sep = "")) else print(paste("Boxing...", sep = ""))
   returnObj <- list()
   returnObj$dataFrame <- dataFrame
+  returnObj$vals <- vals
 
   ## meta
   returnObj$oldFormat <- oldFormat

R/readMSDial.R

@@ -69,12 +69,12 @@ readMSDial <- function(file, version){
     rownames(counts) <- ids
 
     # Ensure row names of colData match counts column names
-    colData <- DataFrame(t(colDataRaw[-nrow(colDataRaw), -1]))
+    colData <- data.frame(t(colDataRaw[-nrow(colDataRaw), -1]))
     rownames(colData) <- as.character(colDataRaw[nrow(colDataRaw), -1])
     colnames(colData) <- as.character(colDataRaw[-nrow(colDataRaw), 1])
 
     # Ensure row names of rowData match counts row names
-    rowData <- DataFrame(rowDataRaw[-1, ], row.names = ids)
+    rowData <- data.frame(rowDataRaw[-1, ], row.names = ids)
     colnames(rowData) <- as.character(rowDataRaw[1,])
 
     # Create SummarizedExperiment object

tests/testthat/test-readMSDial.R

@@ -7,13 +7,14 @@ test_that("exampledata", {
                                    maximumRtDifference=0.05,
                                    progress=FALSE)
 
+
   ## Test dimensions  
-  expect_equal(nrow(data$dataFrame1), 5403)
-  expect_equal(ncol(data$dataFrame1),   20)
+  expect_equal(nrow(data$dataFrame), 5403)
+  expect_equal(ncol(data$dataFrame),   20)
 
   ## Test some values
-  expect_true(all(summary(t(data$dataFrame1[1,c("TRI03", "TRI02", "TRI01", "LVS03", "LVS02", "LVS01")])) == c("Min.   : 236.0  ", "1st Qu.: 306.2  ", "Median : 357.5  ", "Mean   : 501.0  ", "3rd Qu.: 554.2  ", "Max.   :1146.0  ")))
-  expect_true(all(round(summary(data$dataFrame1[, "TRI01"])) == c(0,     809,    1537,    9818,    3207, 4407926)))
+  expect_true(all(summary(t(data$dataFrame[1,c("TRI03", "TRI02", "TRI01", "LVS03", "LVS02", "LVS01")])) == c("Min.   : 236.0  ", "1st Qu.: 306.2  ", "Median : 357.5  ", "Mean   : 501.0  ", "3rd Qu.: 554.2  ", "Max.   :1146.0  ")))
+  expect_true(all(round(summary(data$dataFrame[, "TRI01"])) == c(0,     809,    1537,    9818,    3207, 4407926)))
 })
 
 
@@ -37,3 +38,4 @@ test_that("Number of Rows and Columns are correct", {
 })
 
 
+