update utility functions and website

Author: Carol-seven

DESCRIPTION

@@ -29,6 +29,7 @@ Imports:
     limma,
     mice,
     multiUS,
+    openxlsx,
     pcaMethods,
     pheatmap,
     pls,

NAMESPACE

@@ -9,7 +9,6 @@ export(analyze.wilcox)
 export(dataMissing)
 export(filterNA)
 export(filterOutIn)
-export(filterProtein)
 export(impute.knn)
 export(impute.knn_seq)
 export(impute.knn_trunc)
@@ -60,6 +59,7 @@ importFrom(limma,normalizeQuantiles)
 importFrom(mice,complete)
 importFrom(mice,mice)
 importFrom(multiUS,seqKNNimp)
+importFrom(openxlsx,write.xlsx)
 importFrom(pcaMethods,completeObs)
 importFrom(pcaMethods,pca)
 importFrom(psych,describeBy)

R/globals.R

@@ -7,13 +7,15 @@ utils::globalVariables(c(
   "value", # <dataMissing>
   "PG.Quantity", # <preProcessFiltering>
   "PG.NrOfStrippedSequencesIdentified", # <preProcessFiltering>
-  "PG.ProteinNames", # <preProcessFiltering>
-  "PG.ProteinAccessions", # <preProcessFiltering>
+  "PG.ProteinName", # <preProcessFiltering>
+  "PG.ProteinAccession", # <preProcessFiltering>
+  "PG.ProteinNames", # <preprocessing>
+  "PG.ProteinAccessions", # <preprocessing>
   "value", # <preprocessing>
   "PG.Genes", # <preprocessing>
-  "PG.ProteinAccessions", # <preprocessing>
+  "PG.ProteinAccession", # <preprocessing>
   "PG.ProteinDescriptions", # <preprocessing>
-  "PG.ProteinNames", # <preprocessing>
+  "PG.ProteinName", # <preprocessing>
   "R.Condition", # <preprocessing>
   "R.Replicate", # <preprocessing>
   "PG.Quantity", # <preprocessing>
@@ -32,34 +34,31 @@ utils::globalVariables(c(
   "name", # <visualize.heatmap>
   "value", # <visualize.heatmap>
   "Regulation", # <visualize.ma>
-  "Variable", # <visualize.ma>
   "A", # <visualize.ma>
   "M", # <visualize.ma>
-  "label", # <visualize.ma>
+  "Label", # <visualize.ma>
   "R.Condition", # <visualize.rank>
   "R.Replicate", # <visualize.rank>
-  "Name", # <visualize.rank>
   "Abundance", # <visualize.rank>
   "Rank", # <visualize.rank>
-  "Proteins", # <visualize.rank>
+  "Type", # <visualize.rank>
   "Label", # <visualize.rank>
   "Variable", # <visualize.test>
   "name", # <visualize.test>
   "value", # <visualize.test>
   "Comparison", # <visualize.test>
   "binwidth", # <visualize.test>
   "Significant", # <visualize.volcano>
-  "Variable", # <visualize.volcano>
   "difference", # <visualize.volcano>
-  "p.value", # <visualize.volcano>
-  "label", # <visualize.volcano>
+  "p-value", # <visualize.volcano>
+  "Label", # <visualize.volcano>
   "Dim.1", # <visualize.loading>
   "Dim.2", # <visualize.loading>
   "Name", # <visualize.loading>
   "xcircle", # <visualize.loading>
   "ycircle", # <visualize.loading>
   "Score", # <visualize.vip>
-  "Variable", # <visualize.vip>
+  ":=", # <visualize.vip>
   "Group", # <visualize.vip>
   "Abundance", # <visualize.vip>
   NULL

R/pullProteinPath.R

@@ -26,71 +26,60 @@
 #' @param regexName A character vector specifying the proteins for regular expression
 #' pattern matching.
 #' 
-#' @param by A character string specifying the information to which the \code{listName}
-#' and/or \code{regexName} are applied, with allowable options:
+#' @param by A character string (default = "PG.ProteinName" for Spectronaut, default =
+#' "AccessionNumber" for Scaffold) specifying the information to which \code{listName}
+#' and/or \code{regexName} are applied. Allowable options include:
 #' \itemize{
-#' \item For Spectronaut: "PG.Genes", "PG.ProteinAccessions", "PG.ProteinDescriptions",
-#' and "PG.ProteinNames".
+#' \item For Spectronaut: "PG.Genes", "PG.ProteinAccession", "PG.ProteinDescriptions", and
+#' "PG.ProteinName".
 #' \item For Scaffold: "ProteinDescriptions", "AccessionNumber", and "AlternateID".
 #' }
 #' 
 #' @param dataSetList A list of data frames, the order dictates the order of presentation.
 #' 
-#' @param proteinInformation The name of the .csv file containing protein information data
-#' (including the path to the file, if needed). The file should include the following
-#' columns:
-#' \itemize{
-#' \item For Spectronaut: "PG.Genes", "PG.ProteinAccessions", "PG.ProteinDescriptions",
-#' and "PG.ProteinNames".
-#' \item For Scaffold: "ProteinDescriptions", "AccessionNumber", and "AlternateID".
-#' }
-#' This file is automatically generated by the function
-#' \code{\link[msDiaLogue]{preprocessing}} or
-#' \code{\link[msDiaLogue]{preprocessing_scaffold}}.
-#' 
 #' @return
 #' A 2d dataframe, with the protein data at each step present in the \code{dataSetList}.
 #' 
 #' @export
 
-pullProteinPath <- function(listName = NULL, regexName = NULL, dataSetList,
-                            by = "PG.ProteinNames",
-                            proteinInformation = "preprocess_protein_information.csv") {
+pullProteinPath <- function(listName = NULL, regexName = NULL, dataSetList, by = NULL) {
 
-  proteinInformation <- read.csv(proteinInformation)
+  information <- read.csv("preprocess_protein_information.csv", check.names = FALSE)
+  scaffoldCheck <- any(colnames(information) == "Visible?")
+  IDcol <- ifelse(scaffoldCheck, "AccessionNumber", "PG.ProteinName")
 
-  allName <- proteinInformation[[by]]
+  if (is.null(by)) {
+    by <- IDcol
+  }
 
   ## only list filter if listName is present
   if (length(listName) != 0) {
-    listIndex <- which(allName %in% listName)
+    listIndex <- which(information[[by]] %in% listName)
   } else {
     listIndex <- NULL
   }
 
   ## only regex filter if regexName is present
   if (length(regexName) != 0) {
-    regexIndex <- grep(paste(regexName, collapse = "|"), allName, value = FALSE)
+    regexIndex <- grep(paste(regexName, collapse = "|"), information[[by]], value = FALSE)
   } else {
     regexIndex <- NULL
   }
 
   ## combine protein names from list and regex filters
   unionIndex <- union(listIndex, regexIndex)
-  
-  keyid <- ifelse(startsWith(by, "PG."), "PG.ProteinNames", "AccessionNumber")
-  unionName <- proteinInformation[unionIndex, keyid]
+  unionName <- information[unionIndex, IDcol]
 
   proteinPath <- do.call(rbind, lapply(unionName, function(name) {
     cbind(dataSetList[[1]][c("R.Condition", "R.Replicate")],
           name,
           sapply(dataSetList, function(data) data[[name]] %||% NA))
   }))
 
-  colnames(proteinPath)[colnames(proteinPath) == "name"] <- keyid
+  colnames(proteinPath)[colnames(proteinPath) == "name"] <- by
 
-  result <- merge(proteinInformation[unionIndex,], proteinPath,
-                  by = keyid, sort = TRUE)
+  result <- merge(information[unionIndex,], proteinPath,
+                  by = by, sort = TRUE)
 
   return(result)
 }

R/zzz.R

@@ -3,6 +3,7 @@
 #' @import ggrepel
 #' @import tibble
 #' @import tidyr
+#' @importFrom openxlsx write.xlsx
 #' @importFrom Rdpack reprompt
 #' @importFrom stats as.formula cor density integrate median model.matrix na.omit p.adjust
 #' @importFrom stats pnorm prcomp sd setNames t.test wilcox.test var

_pkgdown.yml

@@ -32,7 +32,6 @@ reference:
   contents:
   - filterNA
   - filterOutIn
-  - filterProtein
 - title: Normalization
   contents:
   - normalize