working on addIdentificationData-MSnExp,mzRident - see issue #232

lgatto · Jul 27, 2017 · 597ffea · 597ffea
1 parent 7795968
commit 597ffea
Show file tree

Hide file tree

Showing 2 changed files with 45 additions and 19 deletions.
diff --git a/R/methods-MSnExp.R b/R/methods-MSnExp.R
@@ -265,24 +265,46 @@ setMethod("removeReporters", "MSnExp",
 setMethod("addIdentificationData", c("MSnExp", "character"),
           function(object, id,
                    fcol = c("spectrum.file", "acquisition.number"),
-                   icol = c("spectrumFile", "acquisitionnum"),
+                   icol = c("spectrumID", "acquisitionNum"), 
+                   acc = "DatabaseAccess",
+                   desc = "DatabaseDescription",
+                   pepseq = "sequence",
                    verbose = isMSnbaseVerbose()) {
-              addIdentificationData(object, id = mzID(id, verbose = verbose),
-                                    fcol = fcol, icol = icol)
+              addIdentificationData(object, id = mzR::openIDfile(id),
+                                    fcol = fcol, icol = icol,
+                                    acc, desc, pepseq)
+          })
+
+setMethod("addIdentificationData", c("MSnExp", "mzRident"),
+          function(object, id,
+                   fcol = c("spectrum.file", "acquisition.number"),
+                   icol = c("spectrumID", "acquisitionNum"),
+                   acc = "DatabaseAccess",
+                   desc = "DatabaseDescription",
+                   pepseq = "sequence",
+                   ...) {
+              ## prepare id
+              addIdentificationData(object, id,
+                                    fcol = fcol, icol = icol,
+                                    acc, desc, pepseq)
           })
 
 setMethod("addIdentificationData", c("MSnExp", "mzIDClasses"),
           function(object, id,
                    fcol = c("spectrum.file", "acquisition.number"),
-                   icol = c("spectrumFile", "acquisitionnum"), ...) {
+                   icol = c("spectrumFile", "acquisitionnum"),
+                   acc = "accession",
+                   desc = "description",
+                   pepseq = "pepseq",
+                   ...) {
               addIdentificationData(object, id = flatten(id),
-                                    fcol = fcol, icol = icol)
+                                    fcol = fcol, icol = icol,
+                                    acc, desc, pepseq)
           })
 
 setMethod("addIdentificationData", c("MSnExp", "data.frame"),
-          function(object, id,
-                   fcol = c("spectrum.file", "acquisition.number"),
-                   icol = c("spectrumFile", "acquisitionnum"), ...) {
+          function(object, id, fcol, icol, acc, desc, pepseq,
+                   ...) {
               ## we temporaly add the spectrum.file/acquisition.number information
               ## to our fData data.frame because
               ## utils.mergeSpectraAndIdentificationData needs this information
@@ -297,7 +319,10 @@ setMethod("addIdentificationData", c("MSnExp", "data.frame"),
 
               fd <- utils.mergeSpectraAndIdentificationData(fd, id,
                                                             fcol = fcol,
-                                                            icol = icol)
+                                                            icol = icol,
+                                                            acc = acc,
+                                                            desc = desc,
+                                                            pepseq = pepseq)
 
               ## after adding the identification data we remove the
               ## temporary data to avoid duplication and problems in quantify

diff --git a/R/utils.R b/R/utils.R
@@ -765,7 +765,8 @@ utils.leftJoin <- function(x, y, by, by.x=by, by.y=by,
 # @noRd
 utils.mergeSpectraAndIdentificationData <- function(featureData, id,
                                                     fcol = c("file", "acquisition.number"),
-                                                    icol = c("file", "acquisitionnum")) {
+                                                    icol = c("file", "acquisitionnum"),
+                                                    acc, desc, pepseq) {
     ## mzR::acquisitionNum (stored in fData()[, "acquisition.number"] and
     ## mzID::acquisitionnum should be identical
     if (!all(fcol %in% colnames(featureData))) {
@@ -789,8 +790,8 @@ utils.mergeSpectraAndIdentificationData <- function(featureData, id,
     id <- id[o, ]
 
     ## use flat version of accession/description if multiple ones are available
-    id$accession <- ave(id$accession, id[, icol], FUN=utils.vec2ssv)
-    id$description <- ave(id$description, id[, icol], FUN=utils.vec2ssv)
+    id[, acc] <- ave(id[, acc], id[, icol], FUN=utils.vec2ssv)
+    id[, desc] <- ave(id[, desc], id[, icol], FUN=utils.vec2ssv)
 
     ## remove duplicated entries
     id <- id[!duplicated(id[, icol]), ]
@@ -802,23 +803,23 @@ utils.mergeSpectraAndIdentificationData <- function(featureData, id,
     )
 
     ## number of members in the protein group
-    featureData$nprot <- sapply(utils.ssv2list(featureData$accession),
+    featureData$nprot <- sapply(utils.ssv2list(featureData[, acc]),
                                 function(x) {
                                     n <- length(x)
                                     if (n == 1 && is.na(x)) return(NA)
                                     n
                                 })
     ## number of peptides observed for each protein
-    featureData$npep.prot <- as.integer(ave(featureData$accession,
-                                            featureData$pepseq,
+    featureData$npep.prot <- as.integer(ave(featureData[, acc],
+                                            featureData[, pepseq],
                                             FUN = length))
     ## number of PSMs observed for each protein
-    featureData$npsm.prot <- as.integer(ave(featureData$accession,
-                                            featureData$accession,
+    featureData$npsm.prot <- as.integer(ave(featureData[, acc],
+                                            featureData[, acc],
                                             FUN = length))
     ## number of PSMs observed for each protein
-    featureData$npsm.pep <- as.integer(ave(featureData$pepseq,
-                                           featureData$pepseq,
+    featureData$npsm.pep <- as.integer(ave(featureData[, pepseq],
+                                           featureData[, pepseq],
                                            FUN = length))
     return(featureData)
 }