[WIP] Feature/cleanup and refactor

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: MetFamily
 Type: Package
 Title: MetFamily: Discovering Regulated Metabolite Families in Untargeted Metabolomics Studies
-Version: 0.99.2
+Version: 0.99.3
 Date: 2024-03-02
 Author: c( person("Hendrik", "Treutler, role = c("aut"), email = "hendrik.treutler@ipb-halle.de"),
            person("Khabat", "Vahabi, role = c("aut"), email = "khabat.vahabi@ipb-halle.de"),
@@ -27,31 +27,40 @@ Depends:
     searchable, 
     tools,
     stringr,
-    xcms,
     mzR,
     matrixStats,
     plotrix,
     slam,
-    plotly,
-    egg
+    plotly
+Imports:
+    egg,
+    graphics,
+    grDevices,
+    methods,
+    stats,
+    utils
 Remotes: decisionpatterns/searchable
 Suggests:
     knitr,
     testthat
 VignetteBuilder: knitr
 Maintainer: Hendrik Treutler<hendrik.treutler@ipb-halle.de>
-Description: We present a novel approach for the untargeted discovery of metabolite families offering a bird's eye view of metabolic regulation in comparative metabolomics. We implemented the presented methodology in the easy-to-use web application MetFamily to enable the analysis of comprehensive metabolomics studies for all researchers worldwide.
-License: GPL (>= 2)
+Description: We present a novel approach for the untargeted discovery 
+  of metabolite families offering a bird's eye view of metabolic regulation 
+  in comparative metabolomics. We implemented the presented methodology 
+  in the easy-to-use web application MetFamily to enable the analysis 
+  of comprehensive metabolomics studies for all researchers worldwide.
+License: GPL (>= 2) + file LICENSE
 biocViews: Software, Visualization
 Collate:
     'Annotation.R'
     'Classifiers.R'
     'runMetFamily.R'
-    'R_packages.R'
     'FragmentMatrixFunctions.R'
     'DataProcessing.R'
     'Analysis.R'
     'TreeAlgorithms.R'
     'Plots.R'
+    'R_packages.R'
 RoxygenNote: 7.2.3
 Encoding: UTF-8

Dockerfile

@@ -1,7 +1,7 @@
 #FROM sneumann/metfamily-base:latest
-#FROM sneumann/metfamily-base:4.3.2
+FROM sneumann/metfamily-base:4.3.2
 #FROM sneumann/metfamily-base:4.0.5
-FROM sneumann/metfamily-base:3.6.3
+#FROM sneumann/metfamily-base:3.6.3
 
 MAINTAINER Steffen Neumann <sneumann@ipb-halle.de>
 

NAMESPACE

@@ -1,3 +1,28 @@
-#export(startMetFamily)
+# Generated by roxyXXXgen2: do not edit by hand
+
+## Hardcoded:
 exportPattern("^[^\\.]")
 import(egg)
+importFrom("grDevices", "as.raster", "rainbow", "rgb")
+importFrom("methods", "as")
+importFrom("graphics", "axis", "mtext", "par", "plot.new",
+           "plot.window", "points", "rasterImage", "rect", "segments",
+           "title")
+importFrom("methods", "as", "is")
+importFrom("stats", "as.dendrogram", "cor", "dendrapply", "dist",
+           "hclust", "is.leaf", "median", "na.omit", "predict", "sd")
+importFrom("utils", "flush.console", "read.table")
+
+
+## From roxygen:
+export(calcPlotDendrogram_plotly)
+export(calcPlotHeatmapLegend)
+export(castListEntries)
+export(data.numericmatrix)
+export(metaboliteFamilyVersusClass)
+export(mzClustGeneric)
+export(processMS1data)
+export(readClusterDataFromProjectFile)
+export(readProjectData)
+export(runMetFamily)
+importFrom(grDevices,colorRampPalette)

NEWS

@@ -1,6 +1,13 @@
 CHANGES IN VERSION 0.99.2
 -------------------------
 
+BUG FIXES
+
+    o Now producing correct PCA on R-4.0.0+ by using a custom data.matrix() function with old R-3.6.3 behaviour
+
+CHANGES IN VERSION 0.99.2
+-------------------------
+
 NEW FEATURES
 
     o More and better colors available for plotting (thanks @khabatv)

R/Analysis.R

@@ -1,7 +1,7 @@
 
 #########################################################################################
 ## constants
-filterData <- function(dataList, groups, sampleSet, filterBySamples, filter_average, filter_lfc, filterList_ms2_masses, filter_ms2_ppm, filter_ms1_masses, filter_ms1_ppm, includeIgnoredPrecursors, progress = FALSE){
+filterData <- function(dataList, grouXXXps, sampleSet, filterBySamples, filter_average, filter_lfc, filterList_ms2_masses, filter_ms2_ppm, filter_ms1_masses, filter_ms1_ppm, includeIgnoredPrecursors, progress = FALSE){
   ##########################################
   ## filter
   filter <- rep(x = TRUE, times = dataList$numberOfPrecursors)
@@ -10,9 +10,9 @@ filterData <- function(dataList, groups, sampleSet, filterBySamples, filter_aver
   if(!is.null(filter_average)){
     #print("this is entering the line 11")
     #if(filterBySamples){
-    #  filter <- filter & apply(X = as.data.frame(dataList$dataFrameMeasurements[, sapply(X = as.vector(groups), FUN = dataList$dataMeanColumnNameFunctionFromName)]), MARGIN = 1, FUN = mean) >= filter_average
+    #  filter <- filter & apply(X = as.data.frame(dataList$dataFrameMeasurements[, sapply(X = as.vector(grouXXXps), FUN = dataList$dataMeanColumnNameFunctionFromName)]), MARGIN = 1, FUN = mean) >= filter_average
     #} else {
-      filter <- filter & apply(X = as.data.frame(dataList$dataFrameMeasurements[, sapply(X = as.vector(groups), FUN = dataList$dataMeanColumnNameFunctionFromName)]), MARGIN = 1, FUN = mean) >= filter_average
+      filter <- filter & apply(X = as.data.frame(dataList$dataFrameMeasurements[, sapply(X = as.vector(grouXXXps), FUN = dataList$dataMeanColumnNameFunctionFromName)]), MARGIN = 1, FUN = mean) >= filter_average
       #print(filter)
       #print(names(filter)[unname(filter)])
     #}
@@ -21,11 +21,11 @@ filterData <- function(dataList, groups, sampleSet, filterBySamples, filter_aver
   ## filter_lfc
   if(!is.null(filter_lfc)){
     if(filter_lfc != 0){
-      if(length(groups) != 2){  stop("The number of groups for LFC is not equal to two!") }
+      if(length(grouXXXps) != 2){  stop("The number of grouXXXps for LFC is not equal to two!") }
       if(filter_lfc > 0)
-        filter <- filter & dataList$dataFrameMeasurements[, dataList$lfcColumnNameFunctionFromName(groups[[1]], groups[[2]])] >= filter_lfc
+        filter <- filter & dataList$dataFrameMeasurements[, dataList$lfcColumnNameFunctionFromName(grouXXXps[[1]], grouXXXps[[2]])] >= filter_lfc
       else
-        filter <- filter & dataList$dataFrameMeasurements[, dataList$lfcColumnNameFunctionFromName(groups[[1]], groups[[2]])] <= filter_lfc
+        filter <- filter & dataList$dataFrameMeasurements[, dataList$lfcColumnNameFunctionFromName(grouXXXps[[1]], grouXXXps[[2]])] <= filter_lfc
     }
   }
 
@@ -80,16 +80,16 @@ filterData <- function(dataList, groups, sampleSet, filterBySamples, filter_aver
   resultObj$filter <- filter
   resultObj$numberOfPrecursors <- dataList$numberOfPrecursors
   resultObj$numberOfPrecursorsFiltered <- length(filter)
-  if(is.null(groups)){
-    resultObj$groups    <- list()
+  if(is.null(grouXXXps)){
+    resultObj$grouXXXps    <- list()
     resultObj$sampleSet <- list()
     resultObj$filterBySamples <- NA
   } else {
-    resultObj$groups    <- groups
+    resultObj$grouXXXps    <- grouXXXps
     resultObj$sampleSet <- sampleSet
     resultObj$filterBySamples <- filterBySamples
   }
-  #resultObj$groups                   <- ifelse(test = is.null(groups),                   yes = NA, no = groups)
+  #resultObj$grouXXXps                   <- ifelse(test = is.null(grouXXXps),                   yes = NA, no = grouXXXps)
   resultObj$filter_average           <- ifelse(test = is.null(filter_average),           yes = 0, no = filter_average)
   resultObj$filter_lfc               <- ifelse(test = is.null(filter_lfc),               yes = 0, no = filter_lfc)
   if(is.null(filterList_ms2_masses)){
@@ -974,7 +974,7 @@ performPca <- function(dataList, dataFrame2, ms1AnalysisMethod){
   #.. ..$ : chr [1:5] "Dim.1" "Dim.2" "Dim.3" "Dim.4" ...
   #$ variance: num [1:18] 35.96 21.67 11.66 8.15 4.56 ...
   #
-  ## artificial data two groups
+  ## artificial data two grouXXXps
   #$ scores  : num [1:2, 1] 0 0
   #..- attr(*, "dimnames")=List of 2
   #.. ..$ : chr [1:2] "A_1" "B_2"
@@ -1054,7 +1054,7 @@ calculatePCA <- function(dataList, filterObj, ms1AnalysisMethod, scaling, logTra
   if(filterObj$filterBySamples){
     dataFrame <- dataList$dataFrameMeasurements[filterObj$filter, filterObj$sampleSet]
   } else {
-    dataFrame <- dataList$dataFrameMeasurements[filterObj$filter, dataList$dataColumnsNameFunctionFromGroupNames(groups = filterObj$groups, sampleNamesToExclude = dataList$excludedSamples(dataList$groupSampleDataFrame))]
+    dataFrame <- dataList$dataFrameMeasurements[filterObj$filter, dataList$dataColumnsNameFunctionFromGroupNames(grouXXXps = filterObj$grouXXXps, sampleNamesToExclude = dataList$excludedSamples(dataList$groupSampleDataFrame))]
   }
   dataFrame <- t(dataFrame)
 

R/Annotation.R

@@ -822,6 +822,24 @@ evaluatePutativeMetaboliteFamiliesOfPrecursorSet_old <- function(dataList, precu
   return(printPutativeMetaboliteFamilies)
 }
 
+
+
+#' Title
+#'
+#' @param dataList 
+#' @param precursorSet 
+#' @param classToSpectra_class 
+#' @param properties_class 
+#' @param classifierClass 
+#' @param mappingSpectraToClassDf 
+#' @param addClassifierConsensusSpectrum 
+#'
+#' @return
+#' @export
+#' @importFrom grDevices colorRampPalette
+#' 
+#'
+#' @examples
 metaboliteFamilyVersusClass <- function(dataList, precursorSet, classToSpectra_class, properties_class, classifierClass, mappingSpectraToClassDf, addClassifierConsensusSpectrum){
   returnObj <- getSpectrumStatistics(dataList = dataList, precursorSet = precursorSet)
   masses_spec <- returnObj$fragmentMasses