update pullProteinPath

R/pullProteinPath.R

@@ -21,22 +21,52 @@
 #' @description
 #' Summarize the steps performed on the data for one protein.
 #' 
-#' @param proteinName A string identifying the protein of interest.
+#' @param listName A character vector identifying the proteins of interest.
+#' 
+#' @param regexName A character vector specifying the proteins for regular expression
+#' pattern matching.
 #' 
 #' @param dataSetList A list of data frames, the order dictates the order of presentation.
 #' 
-#' @details \code{proteinName} must match the labels in the data sets exactly.
+#' @param proteinInformation The name of the .csv file containing protein information data
+#' (including the path to the file, if needed). This file is automatically generated by
+#' the function \code{\link[msDiaLogue]{preprocessing}}.
 #' 
 #' @returns A 2d dataframe, with the protein data at each step present in the \code{dataSetList}.
 #' 
 #' @autoglobal
 #' 
 #' @export
 
-pullProteinPath <- function(proteinName, dataSetList) {
+pullProteinPath <- function(listName = NULL, regexName = NULL, dataSetList,
+                            proteinInformation = "preprocess_protein_information.csv") {
+
+  allnames <- colnames(dataSetList[[1]])[!colnames(dataSetList[[1]]) %in% c("R.Condition", "R.Replicate")]
+
+  ## only list filter if listName is present
+  if (!is.null(listName)) {
+    listName <- allnames[which(allnames %in% listName)]
+  }
+
+  ## only regex filter if regexName is present
+  if (!is.null(regexName)) {
+    regexName <- grep(paste(regexName, collapse = "|"), allnames, value = TRUE)
+  }
+
+  ## combine protein names from list and regex filters
+  unionName <- union(listName, regexName)
+
+  proteinPath <- do.call(rbind, lapply(unionName, function(name) {
+    cbind(dataSetList[[1]][c("R.Condition", "R.Replicate")],
+          Protein = name,
+          sapply(dataSetList, function(data) data[[name]]))
+  }))
 
-  proteinPath <- cbind(dataSetList[[1]][c("R.Condition", "R.Replicate")],
-                       sapply(dataSetList, function(mat) mat[[proteinName]]))
+  if (!is.null(proteinInformation)) {
+    proteinInformation <- read.csv(proteinInformation)
+    proteinPath <- merge(proteinPath, proteinInformation,
+                         by.x = "Protein", by.y = "PG.ProteinNames", sort = FALSE)
+  }
 
   ## return the path of data for this protein
   return(proteinPath)