Add initial support for reading Spectronaut log files

NAMESPACE

@@ -63,6 +63,7 @@ export(readDIANNInfo)
 export(readFragPipeInfo)
 export(readMaxQuantXML)
 export(readProteomeDiscovererInfo)
+export(readSpectronautSetup)
 export(runDIANNAnalysis)
 export(runFragPipeAnalysis)
 export(runMaxQuantAnalysis)

NEWS.md

@@ -6,6 +6,7 @@
 * Update DIA-NN example data
 * Expand input data paths in run*Analysis() functions
 * Add support for importing Spectronaut PG pivot files
+* Add initial support for reading Spectronaut setup.txt files
 
 # einprot 0.9.3
 

R/readSpectronautSetup.R

@@ -0,0 +1,55 @@
+#' Extract information from Spectronaut setup file
+#'
+#' Read \code{Spectronaut} setup.txt file and extract information about the
+#' run.
+#'
+#' @param spectronautSetupFile Character scalar, the path to a
+#'     \code{Spectronaut} setup file. Can be \code{NULL} (in this case, an
+#'     empty list is returned).
+#'
+#' @author Charlotte Soneson
+#' @export
+#'
+#' @returns A list with extracted information about the Spectronaut run.
+#'
+readSpectronautSetup <- function(spectronautSetupFile) {
+    .assertScalar(x = spectronautSetupFile, type = "character",
+                  allowNULL = TRUE)
+
+    if (is.null(spectronautSetupFile)) {
+        return(list())
+    } else {
+        if (!file.exists(spectronautSetupFile)) {
+            stop(spectronautSetupFile, " doesn't exist.")
+        }
+
+        ## Read file and extract settings and setup part
+        sf <- readLines(spectronautSetupFile)
+        settings <- sf[seq(which(sf == "[BEGIN-SETTINGS]") + 1,
+                           which(sf == "[END-SETTINGS]") - 1)]
+        setup <- sf[seq(which(sf == "[BEGIN-SETUP]") + 1,
+                        which(sf == "[END-SETUP]") - 1)]
+
+        ## Version
+        sp_version <- grep("^Spectronaut ", sf, value = TRUE)[1]
+
+        ## Raw files
+        sp_raw_files <- paste(sub("Run: ", "", grep("^Run: ", setup,
+                                                    value = TRUE)),
+                              collapse = ", ")
+
+        ## Protein databases
+        sp_fasta_files <- unique(sub(".*Original File: ", "",
+                                     grep("Original File: ", setup,
+                                          value = TRUE)))
+        sp_fasta_files <- paste(sp_fasta_files, collapse = ", ")
+
+        L <- list(
+            "Spectronaut version" = sp_version,
+            "Setup file" = spectronautSetupFile,
+            "Raw files" = sp_raw_files,
+            "Databases" = sp_fasta_files
+        )
+        return(L[!vapply(L, is.null, TRUE)])
+    }
+}

R/runSpectronautAnalysis.R

@@ -16,7 +16,7 @@
 #' @param outLevel Character string indicating the desired output level.
 #'     Currently only \code{"pg"} is supported.
 #' @param spectronautLogFile Character string pointing to the Spectronaut
-#'     log file. File paths will be expressed in canonical form (using
+#'     setup.txt log file. File paths will be expressed in canonical form (using
 #'     \code{normalizePath()}) before they are processed.
 #' @param iColPattern Character scalar defining a regular expression to
 #'     identify sample columns (only used if \code{spectronautFileType} is

inst/extdata/process_basic_template.Rmd

@@ -149,9 +149,9 @@ if (expType == "MaxQuant") {
                   "Analysis level" = outLevel), dia)
     tb <- dia[names(dia) != "DIA-NN command"]
 } else if (expType == "Spectronaut") {
-    tb <- list("Spectronaut file" = spectronautFile,
-               "Spectronaut log file" = spectronautLogFile,
-               "Analysis level" = outLevel)
+    tb <- readSpectronautSetup(spectronautSetupFile = spectronautLogFile)
+    tb <- c(list("Spectronaut file" = spectronautFile,
+                 "Analysis level" = outLevel), tb)
 } else {
     stop("Unknown 'expType'")
 }