annotate msi_qualitycontrol.xml @ 10:3eee933c27cf draft

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/msi_qualitycontrol commit 37da74ed68228b16efbdbde776e7c38cc06eb5d5

<tool id="mass_spectrometry_imaging_qc" name="MSI Qualitycontrol" version="1.10.0.2">
    <description>
        mass spectrometry imaging QC
    </description>
    <requirements>
        <requirement type="package" version="1.10.0">bioconductor-cardinal</requirement>
        <requirement type="package" version="2.2.1">r-ggplot2</requirement>
        <requirement type="package" version="1.1_2">r-rcolorbrewer</requirement>
        <requirement type="package" version="2.2.1">r-gridextra</requirement>
        <requirement type="package" version="2.23_15">r-kernsmooth</requirement>
        <requirement type="package" version="0.5.0">r-scales</requirement>
    </requirements>
    <command detect_errors="exit_code">
    <![CDATA[
        #if $infile.ext == 'imzml'
            ln -s '${infile.extra_files_path}/imzml' infile.imzML &&
            ln -s '${infile.extra_files_path}/ibd' infile.ibd &&
        #elif $infile.ext == 'analyze75'
            ln -s '${infile.extra_files_path}/hdr' infile.hdr &&
            ln -s '${infile.extra_files_path}/img' infile.img &&
            ln -s '${infile.extra_files_path}/t2m' infile.t2m &&
        #else
            ln -s '$infile' infile.RData &&
        #end if
        cat '${cardinal_qualitycontrol_script}' &&
        Rscript '${cardinal_qualitycontrol_script}'
    ]]>
    </command>
    <configfiles>
        <configfile name="cardinal_qualitycontrol_script"><![CDATA[

################################# load libraries and read file #################

library(Cardinal)
library(ggplot2)
library(RColorBrewer)
library(gridExtra)
library(KernSmooth)
library(scales)

#if $infile.ext == 'imzml'
    msidata <- readImzML('infile', mass.accuracy=$accuracy, units.accuracy = "$units")
#elif $infile.ext == 'analyze75'
    msidata = readAnalyze('infile')
#else
    load('infile.RData')
#end if

## create full matrix to make processed imzML files compatible with segmentation
iData(msidata) <- iData(msidata)[] 

###################################### file properties in numbers ######################

## Number of features (m/z)
maxfeatures = length(features(msidata))
## Range m/z
minmz = round(min(mz(msidata)), digits=2)
maxmz = round(max(mz(msidata)), digits=2)
## Number of spectra (pixels)
pixelcount = length(pixels(msidata))
## Range x coordinates
minimumx = min(coord(msidata)[,1])
maximumx = max(coord(msidata)[,1])
## Range y coordinates
minimumy = min(coord(msidata)[,2])
maximumy = max(coord(msidata)[,2])
## Range of intensities
minint = round(min(spectra(msidata)[]), digits=2)
maxint = round(max(spectra(msidata)[]), digits=2)
medint = round(median(spectra(msidata)[]), digits=2)
## Number of intensities > 0
npeaks= sum(spectra(msidata)[]>0)
## Spectra multiplied with m/z (potential number of peaks)
numpeaks = ncol(spectra(msidata)[])*nrow(spectra(msidata)[])
## Percentage of intensities > 0
percpeaks = round(npeaks/numpeaks*100, digits=2)
## Number of empty TICs
TICs = colSums(spectra(msidata)[]) 
NumemptyTIC = sum(TICs == 0)
## Median TIC
medTIC = round(median(TICs), digits=2)
## Median peaks per spectrum
medpeaks = median(colSums(spectra(msidata)[]>0))
print(cor(TICs,colSums(spectra(msidata)[]>0), method="pearson"))

## Processing informations
processinginfo = processingData(msidata)
centroidedinfo = processinginfo@centroided

## if TRUE write processinginfo if FALSE write FALSE

## normalization
if (length(processinginfo@normalization) == 0) {
  normalizationinfo='FALSE'
} else {
  normalizationinfo=processinginfo@normalization
}
## smoothing
if (length(processinginfo@smoothing) == 0) {
  smoothinginfo='FALSE'
} else {
  smoothinginfo=processinginfo@smoothing
}
## baseline
if (length(processinginfo@baselineReduction) == 0) {
  baselinereductioninfo='FALSE'
} else {
  baselinereductioninfo=processinginfo@baselineReduction
}
## peak picking
if (length(processinginfo@peakPicking) == 0) {
  peakpickinginfo='FALSE'
} else {
  peakpickinginfo=processinginfo@peakPicking
}

############## Read and filter tabular file with m/z ###########################

### reading peptide file: 

#if $peptide_file:

    input_list = read.delim("$peptide_file", header = FALSE, na.strings=c("","NA"), stringsAsFactors = FALSE)
    if (ncol(input_list) == 1)
        {input_list = cbind(input_list, input_list)} ## if there is just one column dublicate it to have a names column

    ### calculate how many input peptide m/z are valid:

    inputpeptides = input_list[input_list[,1]>minmz & input_list[,1]<maxmz,]
    number_peptides_in = length(input_list[,1])
    number_peptides_valid = length(inputpeptides[,1])

#else

    inputpeptides = as.data.frame(matrix(, nrow = 0, ncol = 2))
    number_peptides_in = 0
    number_peptides_valid = 0

#end if

colnames(inputpeptides) = c("m/z", "name")

### reading calibrant file: 

#if $calibrant_file:

    calibrant_list = read.delim("$calibrant_file", header = FALSE, na.strings=c("","NA"), stringsAsFactors = FALSE)
    if (ncol(calibrant_list) == 1)
        {calibrant_list = cbind(calibrant_list, calibrant_list)} ## if there is just one column dublicate it to have a names column

    ### calculate how many input calibrant m/z are valid: 

    inputcalibrants = calibrant_list[calibrant_list[,1]>minmz & calibrant_list[,1]<maxmz,]
    number_calibrants_in = length(calibrant_list[,1])
    number_calibrants_valid = length(inputcalibrants[,1])

#else

    inputcalibrants = as.data.frame(matrix(, nrow = 0, ncol = 2))
    number_calibrants_in = 0
    number_calibrants_valid = 0

#end if

colnames(inputcalibrants) = c("m/z", "name")

### bind inputcalibrants and inputpeptides together, to make m/z heatmaps on both

inputs_all = rbind(inputcalibrants[,1:2], inputpeptides[,1:2])
inputmasses = inputs_all[,1]
inputnames = inputs_all[,2]

######################################## PDF #############################################
##########################################################################################
##########################################################################################

pdf("qualitycontrol.pdf", fonts = "Times", pointsize = 12)
plot(0,type='n',axes=FALSE,ann=FALSE)

## if no filename is given, name of file in Galaxy history is used

#if not $filename:
    #set $filename = $infile.display_name
#end if

title(main=paste("$filename"))

################# I) file properties in numbers ################################
################################################################################
print("properties in numbers")

properties = c("Number of m/z features",
               "Range of m/z values",
               "Number of pixels", 
               "Range of x coordinates", 
               "Range of y coordinates",
               "Range of intensities", 
               "Median of intensities",
               "Intensities > 0",
               "Number of zero TICs",
               "Median TIC", 
               "Median # peaks per spectrum",
               "Normalization", 
               "Smoothing",
               "Baseline reduction",
               "Peak picking",
               "Centroided", 
               paste0("# peptides in \n", "$peptide_file.display_name"), 
               paste0("# calibrants in \n", "$calibrant_file.display_name"))

values = c(paste0(maxfeatures), 
           paste0(minmz, " - ", maxmz), 
           paste0(pixelcount), 
           paste0(minimumx, " - ", maximumx),  
           paste0(minimumy, " - ", maximumy), 
           paste0(minint, " - ", maxint), 
           paste0(medint),
           paste0(percpeaks, " %"), 
           paste0(NumemptyTIC), 
           paste0(medTIC),
           paste0(medpeaks),
           paste0(normalizationinfo),
           paste0(smoothinginfo),
           paste0(baselinereductioninfo),
           paste0(peakpickinginfo),
           paste0(centroidedinfo), 
           paste0(number_peptides_valid, " / " , number_peptides_in),
           paste0(number_calibrants_valid, " / ", number_calibrants_in))

property_df = data.frame(properties, values)

grid.table(property_df, rows= NULL)

####################### II) images in x-y grid ###############################
##############################################################################
print("x-y images")

if (npeaks > 0){
    ## function for density plots
    plot_colorByDensity = function(x1,x2,
                                   ylim=c(min(x2),max(x2)),
                                   xlim=c(min(x1),max(x1)),
                                   xlab="",ylab="",main=""){
      df = data.frame(x1,x2)
      x = densCols(x1,x2, colramp=colorRampPalette(c("black", "white")))
      df\$dens = col2rgb(x)[1,] + 1L
      cols = colorRampPalette(c("#000099", "#00FEFF", "#45FE4F","#FCFF00", "#FF9400", "#FF3100"))(256)
      df\$col = cols[df\$dens]
      plot(x2~x1, data=df[order(df\$dens),], ylim=ylim,xlim=xlim,pch=20,col=col,
           cex=1,xlab=xlab,ylab=ylab,las=1, main=main)}

    abline_vector= -100000 ## will be filled for samples in case data is combined

    ## start list for optional spectrum values output
    spectrum_list = list()
    list_count = 1

    ################### 0) overview for combined data ###########################

    ### only for previously combined data, same plot as in combine QC pdf

    if (!is.null(levels(msidata\$combined_sample))){
        number_combined = length(levels(msidata\$combined_sample))

        ## the more combined_samples a file has the smaller will be the legend
        if (number_combined<20){
            legend_size = 10
            cex_boxplot = 1
        }else if (number_combined>20 && number_combined<40){
            legend_size = 9
            cex_boxplot = 0.8
        }else if (number_combined>40 && number_combined<60){
            legend_size = 8
            cex_boxplot = 0.6
        }else if (number_combined>60 && number_combined<100){
            legend_size = 7
            cex_boxplot = 0.5
        }else{
            legend_size = 6
            cex_boxplot = 0.3
        }

        position_df = cbind(coord(msidata)[,1:2], msidata\$combined_sample)
        colnames(position_df)[3] = "sample_name"

        combine_plot = ggplot(position_df, aes(x=x, y=y, fill=sample_name))+
               geom_tile() +
               coord_fixed()+
               ggtitle("Spatial orientation of combined data")+
               theme_bw()+
               theme(plot.title = element_text(hjust = 0.5))+
               theme(text=element_text(family="ArialMT", face="bold", size=12))+
               theme(legend.position="bottom",legend.direction="vertical")+
               theme(legend.key.size = unit(0.2, "line"), legend.text = element_text(size = legend_size))+
               guides(fill=guide_legend(ncol=5,byrow=TRUE))
        coord_labels = aggregate(cbind(x,y)~sample_name, data=position_df, mean)
        coord_labels\$file_number = gsub( "_.*$", "", coord_labels\$sample_name)
        for(file_count in 1:nrow(coord_labels))
            {combine_plot = combine_plot + annotate("text",x=coord_labels[file_count,"x"],
            y=coord_labels[file_count,"y"],label=toString(coord_labels[file_count,4]))}

        print(combine_plot)

        ### find max pixelnumber per subsample to later draw ablines 
        pixel_name_df = data.frame(pixels(msidata), msidata\$combined_sample)
        colnames(pixel_name_df) = c("pixel_number", "pixel_name")
        last_pixel = aggregate(pixel_number~pixel_name, data = pixel_name_df, max)
        pixel_vector = last_pixel[,2]
        abline_vector = pixel_vector[1:number_combined-1]
        print(abline_vector)
    }

    ################### 1) Pixel order image ###################################

    pixelnumber = 1:pixelcount
    pixelxyarray=cbind(coord(msidata)[,1:2],pixelnumber)

    print(ggplot(pixelxyarray, aes(x=x, y=y, fill=pixelnumber))+
     geom_tile() + coord_fixed()+
     ggtitle("Pixel order") + theme_bw()+
     theme(plot.title = element_text(hjust = 0.5))+
     theme(text=element_text(family="ArialMT", face="bold", size=12))+
     scale_fill_gradientn(colours = c("blue", "purple" , "red","orange"), 
       space = "Lab", na.value = "black", name = "Pixel number"))

    ################ 2) Number of calibrants per spectrum ######################

    pixelmatrix = matrix(ncol=ncol(msidata), nrow=0)
    inputcalibrantmasses = inputcalibrants[,1]

    ### find m/z range (ppm) for each calibrant and extract intensity matrix for this range
    plusminusvalues = rep($plusminus_ppm/1000000, length(inputcalibrantmasses))*inputcalibrantmasses

    if (length(inputcalibrantmasses) != 0){
        for (calibrantnr in 1:length(inputcalibrantmasses)){
            calibrantmz = inputcalibrantmasses[calibrantnr]
            calibrantfeaturemin = features(msidata, mz=calibrantmz-plusminusvalues[calibrantnr])
            calibrantfeaturemax = features(msidata, mz=calibrantmz+plusminusvalues[calibrantnr])

            ## in case m/z range includes only 1 m/z: 
            if (calibrantfeaturemin == calibrantfeaturemax){
                calibrantintensity = spectra(msidata)[calibrantfeaturemin,] 
            }else{
                ## if m/z range includes more than 1 m/z take sum of intensities
                calibrantintensity = colSums(spectra(msidata)[calibrantfeaturemin:calibrantfeaturemax,])
            }
            ## for each pixel add sum of intensity in the given m/z range
            pixelmatrix = rbind(pixelmatrix, calibrantintensity)
        }

        countvector= as.factor(colSums(pixelmatrix>0))
        countdf= cbind(coord(msidata)[,1:2], countvector)
        mycolours = c("black","grey", "darkblue", "blue", "green" , "red", "yellow", "magenta", "olivedrab1", "lightseagreen")

        print(ggplot(countdf, aes(x=x, y=y, fill=countvector))+
          geom_tile() + coord_fixed() +
          ggtitle("Number of calibrants per pixel") +
          theme_bw() +
          theme(plot.title = element_text(hjust = 0.5))+
          theme(text=element_text(family="ArialMT", face="bold", size=12))+
          scale_fill_manual(values = mycolours[1:length(countvector)], 
                                na.value = "black", name = "# calibrants"))

        ## append list for optional spectrum values output
        colnames(countdf)[3] = "Number of Calibrants"
        spectrum_list[[list_count]] = countdf
        list_count = list_count+1

    }else{print("2) The inputcalibrant m/z were not provided or outside the m/z range")}

    ########################## 3) fold change image ###########################

    #if $calibrantratio:
        #for $foldchanges in $calibrantratio:
            mass1 = $foldchanges.mass1
            mass2 = $foldchanges.mass2
            distance = $foldchanges.distance

            ### if user did not write a label use input m/z as label
            #if not str($foldchanges.filenameratioplot).strip():
                #set $label = "Fold change %s Da / %s Da" % ($foldchanges.mass1, $foldchanges.mass2)
            #else:
                #set $label = $foldchanges.filenameratioplot
            #end if

            ### filter msidata for given m/z range (for both input m/z)
            filtered_data1 = msidata[mz(msidata) >= mass1-distance & mz(msidata) <= mass1+distance,]
            filtered_data2 = msidata[mz(msidata) >= mass2-distance & mz(msidata) <= mass2+distance,]

            ### find m/z in the two given ranges with the highest mean intensity
            ### this two m/z will be used to calculate the fold change (red line in plot)
            maxmassrow1 = rowMeans(spectra(filtered_data1))
            maxmass1 = mz(filtered_data1)[which.max(maxmassrow1)]
            maxmassrow2 = rowMeans(spectra(filtered_data2))
            maxmass2 = mz(filtered_data2)[which.max(maxmassrow2)]

            ### plot legend: chosen value in blue, distance in blue, max m/z in red
            ### m/z range for each plot (fixed range of 5 Da)
            ### xlim does not work because it does not adjust for the max. intensities within the range
            mzdown1 = features(msidata, mz = mass1-2)
            mzup1 = features(msidata, mz = mass1+3)
            mzdown2 = features(msidata, mz = mass2-2)
            mzup2 = features(msidata, mz = mass2+3)

            ### plot for first m/z 
            par(mfrow=c(2,1), oma=c(0,0,2,0))
            plot(msidata[mzdown1:mzup1,], pixel = 1:pixelcount, main=paste0("average spectrum ", mass1, " Da"))
            abline(v=c(mass1-distance, mass1, mass1+distance), col="blue",lty=c(3,6,3))
            abline(v=maxmass1, col="red", lty=5)

            ### plot for second m/z 
            plot(msidata[mzdown2:mzup2,], pixel = 1:pixelcount, main= paste0("average spectrum ", mass2, " Da"))
            abline(v=c(mass2-distance, mass2, mass2+distance), col="blue", lty=c(3,6,3))
            abline(v=maxmass2, col="red", lty=5)
            title("Control of fold change plot", outer=TRUE)

            ### filter spectra for max m/z to have two vectors, which can be divided
            ### plot spatial distribution of fold change
            ### only possible when there are intensities > 0 in both given m/z ranges

            if (length(maxmass1)>0&length(maxmass2)>0){
                mass1vector = spectra(msidata)[features(msidata, mz = maxmass1),]
                mass2vector = spectra(msidata)[features(msidata, mz = maxmass2),]
                foldchange= log2(mass1vector/mass2vector)
                fcmatrix = cbind(foldchange, coord(msidata)[,1:2])

                print(ggplot(fcmatrix, aes(x=x, y=y, fill=foldchange), colour=colo)+
                 geom_tile() + coord_fixed()+
                 ggtitle("$label")+
                 theme_bw()+
                 theme(plot.title = element_text(hjust = 0.5))+
                 theme(text=element_text(family="ArialMT", face="bold", size=12))+
                 scale_fill_gradientn(colours = c("blue", "purple" , "red","orange")
                                        ,space = "Lab", na.value = "black", name ="FC"))
            }else{
                plot(0,type='n',axes=FALSE,ann=FALSE)
                title(main=paste("At least one m/z range did not contain any intensity value > 0,\n therefore no foldchange plot could be drawn"))}

        #end for
    #end if

    #################### 4) m/z heatmaps #######################################

    par(mfrow=c(1,1), mar=c(5.1, 4.1, 4.1, 2.1), mgp=c(3, 1, 0), las=0)
    if (length(inputmasses) != 0){
        for (mass in 1:length(inputmasses)){
            image(msidata, mz=inputmasses[mass], plusminus=$plusminus_dalton, 
            main= paste0(inputnames[mass], " (", round(inputmasses[mass], digits = 2)," ± ", $plusminus_dalton, " Da)"),
            contrast.enhance = "histogram", ylim= c(maximumy+0.2*maximumy,minimumy-0.2*minimumy))
        }
    } else {print("4) The input peptide and calibrant m/z were not provided or outside the m/z range")}

    #################### 5) Number of peaks per pixel - image ##################

    ## here every intensity value > 0 counts as pixel
    peaksperpixel = colSums(spectra(msidata)[]> 0)
    peakscoordarray=cbind(coord(msidata)[,1:2], peaksperpixel)

    print(ggplot(peakscoordarray, aes(x=x, y=y, fill=peaksperpixel), colour=colo)+
     geom_tile() + coord_fixed() +
     ggtitle("Number of peaks per spectrum")+
     theme_bw() +
     theme(plot.title = element_text(hjust = 0.5))+
     theme(text=element_text(family="ArialMT", face="bold", size=12))+
     scale_fill_gradientn(colours = c("blue", "purple" , "red","orange") 
                            ,space = "Lab", na.value = "black", name = "# peaks"))

    ## append list for optional spectrum values output
    colnames(peakscoordarray)[3] = "Number of Peaks"
    spectrum_list[[list_count]] = peakscoordarray
    list_count = list_count+1

    ############################### 6) TIC image ###############################

    TICcoordarray=cbind(coord(msidata)[,1:2], TICs)
    colo = colorRampPalette(
    c("blue", "cyan", "green", "yellow","red"))
    print(ggplot(TICcoordarray, aes(x=x, y=y, fill=TICs), colour=colo)+
     geom_tile() + coord_fixed() +
     ggtitle("Total Ion Chromatogram")+
     theme_bw() +
     theme(plot.title = element_text(hjust = 0.5))+
     theme(text=element_text(family="ArialMT", face="bold", size=12))+
     scale_fill_gradientn(colours = c("blue", "purple" , "red","orange") 
                            ,space = "Lab", na.value = "black", name = "TIC"))

    ## append list for optional spectrum values output
    colnames(TICcoordarray)[3] = "TIC per spectrum"
    spectrum_list[[list_count]] = TICcoordarray
    list_count = list_count+1

    ############################### 7) Most abundant m/z image #################

    highestmz = apply(spectra(msidata)[],2,which.max) 
    highestmz_matrix = cbind(coord(msidata)[,1:2],mz(msidata)[highestmz])
    colnames(highestmz_matrix)[3] = "highestmzinDa"

    print(ggplot(highestmz_matrix, aes(x=x, y=y, fill=highestmzinDa))+
    geom_tile() + coord_fixed() +
    ggtitle("Most abundant m/z in each spectrum")+
    theme_bw() +
    theme(plot.title = element_text(hjust = 0.5))+
    scale_fill_gradientn(colours = c("blue", "purple" , "red","orange"), space = "Lab", na.value = "black", name = "m/z", 
      labels = as.character(pretty(highestmz_matrix\$highestmzinDa)[c(1,3,5,7)]),
      breaks = pretty(highestmz_matrix\$highestmzinDa)[c(1,3,5,7)], limits=c(min(highestmz_matrix\$highestmzinDa), max(highestmz_matrix\$highestmzinDa)))+
    theme(text=element_text(family="ArialMT", face="bold", size=12)))

    ## which m/z are highest
    highestmz_peptides = names(sort(table(round(highestmz_matrix\$highestmzinDa, digits=0)), decreasing=TRUE)[1])
    highestmz_pixel = which(round(highestmz_matrix\$highestmzinDa, digits=0) == highestmz_peptides)[1]

    secondhighestmz = names(sort(table(round(highestmz_matrix\$highestmzinDa, digits=0)), decreasing=TRUE)[2]) 
    secondhighestmz_pixel = which(round(highestmz_matrix\$highestmzinDa, digits=0) == secondhighestmz)[1]

    print(head(sort(table(round(highestmz_matrix\$highestmzinDa, digits=0)), decreasing=TRUE)))

    ## append list for optional spectrum values output
    colnames(highestmz_matrix)[3] = "Most abundant m/z"
    spectrum_list[[list_count]] = highestmz_matrix

    ########################## 8) pca image for two components #################

    pca = PCA(msidata, ncomp=2) 
    par(mfrow = c(2,1))
    plot(pca, col=c("black", "darkgrey"), main="PCA for two components")
    image(pca, col=c("black", "white"), strip=FALSE, ylim= c(maximumy+0.2*maximumy,minimumy-0.2*minimumy))

    ################## III) properties over spectra index ##########
    ##############################################################################
    print("properties over pixels")
    par(mfrow = c(2,1), mar=c(5,6,4,2))

    ########################## 9) number of peaks per spectrum #################
    ## 9a) scatterplot
    plot_colorByDensity(pixels(msidata), peaksperpixel, ylab = "", xlab = "", main="Number of peaks per spectrum")
    title(xlab="Spectra index", line=3)
    title(ylab="Number of peaks", line=4)
    abline(v=abline_vector, lty = 3)

    ## 9b) histogram

    hist(peaksperpixel, main="", las=1, xlab = "Number of peaks per spectrum", ylab="") 
    title(main="Number of peaks per spectrum", line=2)
    title(ylab="Frequency = # spectra", line=4)
    abline(v=median(peaksperpixel), col="blue")

    ## 9c) additional histogram to show subsample contributions
    ## only when samples were combined before (combined_sample)
    if (!is.null(levels(msidata\$combined_sample))){

        df_9 = data.frame(peaksperpixel, msidata\$combined_sample)
        colnames(df_9) = c("Npeaks", "sample_name")

        hist_9 = ggplot(df_9, aes(x=Npeaks, fill=sample_name)) +
        geom_histogram()+ theme_bw()+
        theme(text=element_text(family="ArialMT", face="bold", size=12))+
        theme(plot.title = element_text(hjust = 0.5))+
        theme(legend.key.size = unit(0.2, "line"), legend.text = element_text(size = legend_size))+
        theme(legend.position="bottom",legend.direction="vertical")+
        labs(title="Number of peaks per spectrum and sample", x="Number of peaks per spectrum", y = "Frequency = # spectra") +
        guides(fill=guide_legend(ncol=5,byrow=TRUE))+
        geom_vline(xintercept = median(peaksperpixel), size = 1, colour = "black",linetype = "dashed")
        print(hist_9)}

    ########################## 10) TIC per spectrum ###########################

    ## 10a)density scatterplot
    par(mfrow = c(2,1), mar=c(5,6,4,2))
    plot_colorByDensity(pixels(msidata), TICs,  ylab = "", xlab = "", main="TIC per spectrum")
    title(xlab="Spectra index", line=3)
    title(ylab = "Total ion chromatogram intensity", line=4)
    abline(v=abline_vector, lty = 3)

    ## 10b) histogram
    hist(log(TICs), main="", las=1, xlab = "log(TIC per spectrum)", ylab="")
    title(main= "TIC per spectrum", line=2)
    title(ylab="Frequency = # spectra", line=4)
    abline(v=median(log(TICs[TICs>0])), col="blue")    

    ## 10c) additional histogram to show subsample contributions
    ## only when samples were combined before (combined_sample)
    if (!is.null(levels(msidata\$combined_sample))){
        df_10 = data.frame(log(TICs), msidata\$combined_sample)
        colnames(df_10) = c("TICs", "sample_name")

        hist_10 = ggplot(df_10, aes(x=TICs, fill=sample_name)) +
        geom_histogram()+ theme_bw()+
        theme(text=element_text(family="ArialMT", face="bold", size=12))+
        theme(plot.title = element_text(hjust = 0.5))+
        theme(legend.position="bottom",legend.direction="vertical")+
        theme(legend.key.size = unit(0.2, "line"), legend.text = element_text(size = legend_size))+
        labs(title="TIC per spectrum and sample", x="log(TIC per spectrum)", y = "Frequency = # spectra") +
        guides(fill=guide_legend(ncol=5,byrow=TRUE))+
        geom_vline(xintercept = median(log(TICs[TICs>0])), size = 1, colour = "black",linetype = "dashed")
        print(hist_10)}

    ################################## IV) changes over m/z ####################
    ############################################################################
    print("changes over m/z")
    ########################## 11) Number of peaks per m/z #####################

    peakspermz = rowSums(spectra(msidata)[] > 0 )

    par(mfrow = c(2,1), mar=c(5,6,4,4.5))
    ## 11a) scatterplot
    plot_colorByDensity(mz(msidata),peakspermz, main= "Number of peaks per m/z", ylab ="")
    title(xlab="m/z", line=2.5)
    title(ylab = "Number of peaks", line=4)
    axis(4, at=pretty(peakspermz),labels=as.character(round((pretty(peakspermz)/pixelcount*100), digits=1)), las=1)
    mtext("Coverage of spectra [%]", 4, line=3, adj=1)

    ## 11b) histogram
    hist(peakspermz, main="", las=1, ylab="", xlab="")
    title(ylab = "Frequency", line=4)
    title(main="Number of peaks per m/z", xlab = "Number of peaks per m/z", line=2)
    abline(v=median(peakspermz), col="blue") 

    ########################## 12) Sum of intensities per m/z ##################

    ## Sum of all intensities for each m/z (like TIC, but for m/z instead of pixel)
    mzTIC = rowSums(spectra(msidata)[]) ## calculate intensity sum for each m/z

    par(mfrow = c(2,1), mar=c(5,6,4,2))
    ## 12a) scatterplot
    plot_colorByDensity(mz(msidata),mzTIC,  main= "Sum of intensities per m/z", ylab ="")
    title(xlab="m/z", line=2.5)
    title(ylab="Intensity sum", line=4)

    ## 12b) histogram
    hist(log(mzTIC), main="", xlab = "", las=1, ylab="")
    title(main="Sum of intensities per m/z", line=2, ylab="")
    title(xlab = "log (sum of intensities per m/z)")
    title(ylab = "Frequency", line=4)
    abline(v=median(log(mzTIC[mzTIC>0])), col="blue")

    ################################## V) general plots ########################
    ############################################################################
    print("general plots")
    ########################## 13) Intensity distribution ######################

    par(mfrow = c(2,1), mar=c(5,6,4,2))

    ## 13a) Median intensity over spectra
    medianint_spectra = apply(spectra(msidata), 2, median)
    plot(medianint_spectra, main="Median intensity per spectrum",las=1, xlab="Spectra index", ylab="")
    title(ylab="Median spectrum intensity", line=4)
    abline(v=abline_vector, lty = 3)

    ## 13b) histogram: 
    hist(log2(spectra(msidata)[]), main="", xlab = "", ylab="", las=1)
    title(main="Log2-transformed intensities", line=2)
    title(xlab="log2 intensities")
    title(ylab="Frequency", line=4)
    abline(v=median(log2(spectra(msidata)[(spectra(msidata)>0)])), col="blue")

    ## 13c) histogram to show subsample contribution
    ## only for previously combined samples
    if (!is.null(levels(msidata\$combined_sample))){

    df_13 = data.frame(matrix(,ncol=2, nrow=0))
    for (subsample in levels(msidata\$combined_sample)){
        log2_int_subsample = log2(spectra(msidata)[,msidata\$combined_sample==subsample])
        df_subsample = data.frame(as.numeric(log2_int_subsample))
        df_subsample\$sample_name = subsample
        df_13 = rbind(df_13, df_subsample)}
    df_13\$sample_name = as.factor(df_13\$sample_name)
    colnames(df_13) = c("logint", "sample_name")

    hist_13 = ggplot(df_13, aes(x=logint, fill=sample_name)) +
    geom_histogram()+ theme_bw()+
    theme(text=element_text(family="ArialMT", face="bold", size=12))+
    labs(title="Log2-transformed intensities per sample", x="log2 intensities", y = "Frequency") +
    theme(plot.title = element_text(hjust = 0.5))+
    theme(legend.position="bottom",legend.direction="vertical")+
    theme(legend.key.size = unit(0.2, "line"), legend.text = element_text(size = legend_size))+
    guides(fill=guide_legend(ncol=5,byrow=TRUE))+
    geom_vline(xintercept = median(log2(spectra(msidata)[(spectra(msidata)>0)])), size = 1, colour = "black",linetype = "dashed")
    print(hist_13)

    ## 13d) boxplots to visualize in a different way the intensity distributions
    par(mfrow = c(1,1), cex.axis=1.3, cex.lab=1.3, mar=c(13.1,4.1,5.1,2.1))

    mean_matrix = matrix(,ncol=0, nrow = nrow(msidata))
    for (subsample in levels(msidata\$combined_sample)){
        mean_mz_sample = rowMeans(spectra(msidata)[,msidata\$combined_sample==subsample])
        mean_matrix = cbind(mean_matrix, mean_mz_sample)}

    boxplot(log2(mean_matrix), ylab = "log2 mean intensity per m/z", main="Mean intensities per m/z and sample", xaxt = "n")
    (axis(1, at = c(1:number_combined), labels=levels(msidata\$combined_sample), cex.axis=cex_boxplot, las=2))
    }

    ########################## 14) Histogram on m/z values #####################

    par(mfrow = c(1, 1), cex.axis=1, cex.lab=1, mar=c(5.1,4.1,4.1,2.1))
    hist(mz(msidata), xlab = "m/z", main="Histogram of m/z values")

    ############################ 15) Mass spectra ##############################

    par(mfrow = c(2, 2))
    pixels_for_plot = c(round(length(pixelnumber)/2, , digits=0), round(length(pixelnumber)/4, , digits=0), round(length(pixelnumber)/4*3, , digits=0))
    plot(msidata, pixel = 1:length(pixelnumber), main= "Average spectrum")
    plot(msidata, pixel = pixels_for_plot[1], main=paste0("Spectrum at ", rownames(coord(msidata)[pixels_for_plot[1],1:2])))
    plot(msidata, pixel = pixels_for_plot[2], main= paste0("Spectrum at ", rownames(coord(msidata)[pixels_for_plot[2],1:2])))
    plot(msidata, pixel = pixels_for_plot[3], main= paste0("Spectrum at ", rownames(coord(msidata)[pixels_for_plot[3],1:2])))

    #################### 16) Zoomed in mass spectra for calibrants##############

    count = 1
    differencevector = numeric()
    differencevector2 = vector()

    if (length(inputcalibrantmasses) != 0){

    ### calculate plusminus values in m/z for each calibrant, this is used for all following plots
    plusminusvalues = rep($plusminus_ppm/1000000, length(inputcalibrantmasses))*inputcalibrantmasses

        for (mass in 1:length(inputcalibrantmasses)){

            ### define the plot window with xmin und xmax
            minmasspixel = features(msidata, mz=inputcalibrantmasses[mass]-1)
            maxmasspixel = features(msidata, mz=inputcalibrantmasses[mass]+3)

            ### find m/z with the highest mean intensity in m/z range (red line in plot 16) and calculate ppm difference for plot 17
            filtered_data = msidata[mz(msidata) >= inputcalibrantmasses[mass]-plusminusvalues[mass] & mz(msidata) <= inputcalibrantmasses[mass]+plusminusvalues[mass],]
            if (nrow(filtered_data) > 0 & sum(spectra(filtered_data)) > 0){
                maxmassrow = rowMeans(spectra(filtered_data))
                maxvalue = mz(filtered_data)[which.max(maxmassrow)] ### m/z with highestaverage intensity in m/z range
                mzdifference = maxvalue - inputcalibrantmasses[mass] ### difference: theoretical value - closest m/z value
            ppmdifference = mzdifference/inputcalibrantmasses[mass]*1000000 ### calculate ppm for accuracy measurement
            }else{
                ppmdifference = NA
                maxvalue = NA}
            differencevector[mass] = round(ppmdifference, digits=2)

            ### find m/z closest to inputcalibrant and calculate ppm difference for plot 18
            mznumber = features(msidata, mz = inputcalibrantmasses[mass]) ### gives closest featurenumber which is closest to given m/z
            mzvalue = mz(msidata)[mznumber] ### gives the closest m/z
            mzdifference2 = mzvalue - inputcalibrantmasses[mass] 
            ppmdifference2 = mzdifference2/inputcalibrantmasses[mass]*1000000 
            differencevector2[mass] = round(ppmdifference2, digits=2)

            par(mfrow = c(2, 2), oma=c(0,0,2,0))
            plot(msidata[minmasspixel:maxmasspixel,], pixel = 1:length(pixelnumber), main= "average spectrum")
            abline(v=c(inputcalibrantmasses[mass] -plusminusvalues[count], inputcalibrantmasses[mass] ,inputcalibrantmasses[mass] +plusminusvalues[count]), col="blue", lty=c(3,1,3))
            abline(v=c(maxvalue), col="red", lty=2)
            abline(v=c(mzvalue), col="green2", lty=4)
            plot(msidata[minmasspixel:maxmasspixel,], pixel = pixels_for_plot[1], main=paste0("Spectrum at ", rownames(coord(msidata)[pixels_for_plot[1],1:2])))
            abline(v=c(inputcalibrantmasses[mass] -plusminusvalues[count], inputcalibrantmasses[mass] ,inputcalibrantmasses[mass] +plusminusvalues[count]), col="blue", lty=c(3,1,3))
            abline(v=c(maxvalue), col="red", lty=2)
            abline(v=c(mzvalue), col="green2", lty=4)
            plot(msidata[minmasspixel:maxmasspixel,], pixel = pixels_for_plot[2], main= paste0("Spectrum at ", rownames(coord(msidata)[pixels_for_plot[2],1:2])))
            abline(v=c(inputcalibrantmasses[mass] -plusminusvalues[count], inputcalibrantmasses[mass] ,inputcalibrantmasses[mass] +plusminusvalues[count]), col="blue", lty=c(3,1,3))
            abline(v=c(maxvalue), col="red", lty=2)
            abline(v=c(mzvalue), col="green2", lty=4)
            plot(msidata[minmasspixel:maxmasspixel,], pixel = pixels_for_plot[3], main= paste0("Spectrum at ", rownames(coord(msidata)[pixels_for_plot[3],1:2])))
            abline(v=c(inputcalibrantmasses[mass] -plusminusvalues[count], inputcalibrantmasses[mass] ,inputcalibrantmasses[mass] +plusminusvalues[count]), col="blue", lty=c(3,1,3))
            abline(v=c(maxvalue), col="red", lty=2)
            abline(v=c(mzvalue), col="green2", lty=4)
            title(paste0("theor. m/z: ", inputcalibrants[count,1]), col.main="blue", outer=TRUE, line=0, adj=0.074)
            title(paste0("most abundant m/z: ", round(maxvalue, digits=4)), col.main="red", outer=TRUE, line=0, adj=0.49)
            title(paste0("closest m/z: ", round(mzvalue, digits=4)), col.main="green2", outer=TRUE, line=0, adj=0.93)

            ### 16b) one large extra plot with different colours for different samples (for combined_sample only)

            if (!is.null(levels(msidata\$combined_sample))){
                if (number_combined < 10){
                    key_zoomed = TRUE
                }else{key_zoomed = FALSE}
                par(mfrow = c(1, 1))
                plot(msidata[minmasspixel:maxmasspixel,], pixel=1:ncol(msidata),main="average spectrum per sample",
                pixel.groups=msidata\$combined_sample, key=key_zoomed, col=hue_pal()(number_combined),superpose=TRUE)
                abline(v=c(inputcalibrantmasses[mass] -plusminusvalues[count], inputcalibrantmasses[mass] ,inputcalibrantmasses[mass] +plusminusvalues[count]), col="black", lty=c(3,1,3))
            count=count+1
            }
        }

    ######### 17) ppm difference input calibrant m/z and m/z with max intensity in given m/z range#########

        par(mfrow = c(1, 1))

        ### plot the ppm difference calculated above: theor. m/z value to highest m/z value: 

        calibrant_names = as.character(inputcalibrants[,2])
        diff_df = data.frame(differencevector, calibrant_names)

        if (sum(is.na(diff_df[,1])) == nrow(diff_df)){
            print("plot 17: no peaks in the chosen region, repeat with higher ppm range")
        }else{

        diff_plot=ggplot(data=diff_df, aes(x=calibrant_names, y=differencevector)) + geom_bar(stat="identity", fill = "darkgray") + theme_minimal() +
        labs(title="Difference m/z with max. average intensity vs. theor. calibrant m/z", x="calibrants", y = "Difference in ppm")+
        theme(plot.title = element_text(hjust = 0.5))+theme(text=element_text(family="ArialMT", face="bold", size=12))+
        geom_text(aes(label=differencevector), vjust=-0.3, size=3.5, col="blue")

        print(diff_plot)}

    ######### 18) ppm difference input calibrant m/z and closest m/z ###########

        ### plot the ppm difference calculated above theor. m/z value to closest m/z value: 

        differencevector2 = round(differencevector2, digits=2)
        calibrant_names = as.character(inputcalibrants[,2])
        diff_df = data.frame(differencevector2, calibrant_names)

        diff_plot=ggplot(data=diff_df, aes(x=calibrant_names, y=differencevector2)) + geom_bar(stat="identity", fill = "darkgray") + theme_minimal() +
        labs(title="Difference closest measured m/z vs. theor. calibrant m/z", x="calibrants", y = "Difference in ppm")+
        theme(plot.title = element_text(hjust = 0.5))+theme(text=element_text(family="ArialMT", face="bold", size=12))+
        geom_text(aes(label=differencevector2), vjust=-0.3, size=3.5, col="blue")

        print(diff_plot)

    #################### 19) ppm difference over pixels #####################

    mycolours = c("darkgrey", "darkblue", "blue", "green" , "red", "orange", "yellow", "magenta", "olivedrab1", "lightseagreen")
    count = 1
    ppm_df = as.data.frame(matrix(,ncol=0, nrow = ncol(msidata)))
    for (calibrant in inputcalibrantmasses){
        ### find m/z with the highest mean intensity in m/z range, if no m/z in the range, all ppm differences will be NA
        filtered_data = msidata[mz(msidata) >= calibrant-plusminusvalues[count] & mz(msidata) <= calibrant+plusminusvalues[count],]

        if (nrow(filtered_data) > 0){
            ### filtered for m/z range, now go through it pixel by pixel to find max peak in each spectrum
            ppm_vector = numeric()
            for (pixel_count in 1:ncol(filtered_data)){
                mz_max = mz(filtered_data)[which.max(spectra(filtered_data)[,pixel_count])]

                mzdiff = mz_max - calibrant
                ppmdiff = mzdiff/calibrant*1000000 

                ### if maximum intensity in m/z range was 0 set ppm diff to NA (not shown in plot)
                if (max(spectra(filtered_data)[,pixel_count]) == 0){
                ppmdiff = NA}
                ppm_vector[pixel_count] = ppmdiff}
        }else{ppm_vector = rep(NA, ncol(msidata))}

        ppm_df = cbind(ppm_df, ppm_vector)
        count=count+1}

        if (sum(is.na(ppm_df)) == ncol(ppm_df)*nrow(ppm_df)){
            print("plot 19: no peaks in the chosen region, repeat with higher ppm range")
        }else{

    ### plot ppm differences over pixels (spectra index)

    par(mar=c(4.1, 4.1, 4.1, 7.5))
    plot(0,0,type="n", ylim=c(min(ppm_df, na.rm=TRUE),max(ppm_df, na.rm=TRUE)), xlim = c(1,ncol(filtered_data)),xlab = "Spectra index", ylab = "m/z difference in ppm", main="Difference m/z with max. average intensity vs. theor. m/z\n(per spectrum)") 

    for (each_cal in 1:ncol(ppm_df)){
        lines(ppm_df[,each_cal], col=mycolours[each_cal], type="p")}
    legend("topright", inset=c(-0.25,0), xpd = TRUE, bty="n", legend=inputcalibrantmasses, col=mycolours[1:ncol(ppm_df)],lty=1)
    abline(v=abline_vector, lty = 3)}

    }else{print("16+17+18+19) The inputcalibrant m/z were not provided or outside the m/z range")}

dev.off()

}else{
    print("inputfile has no intensities > 0")
    dev.off()
}

## tabular output of spectra values

#if $pixel_output:
    print("pixel list")
    pixel_df = Reduce(function(...) merge(..., by=c("x", "y"), all=T), spectrum_list)
    write.table(pixel_df, file="$pixel_tabular_output", quote = FALSE, row.names = TRUE, col.names=NA, sep = "\t")
#end if



    ]]></configfile>
    </configfiles>
    <inputs>
        <param name="infile" type="data" format="imzml,rdata,analyze75" label="Inputfile as imzML, Analyze7.5 or Cardinal MSImageSet saved as RData"
            help="Upload composite datatype imzml (ibd+imzML) or analyze75 (hdr+img+t2m) or regular upload .RData (Cardinal MSImageSet)"/>
        <param name="accuracy" type="float" value="50" label="Only for processed imzML files: enter mass accuracy to which the m/z values will be binned" help="This should be set to the native accuracy of the mass spectrometer, if known"/>
        <param name="units" display="radio" type="select" label="Only for processed imzML files: unit of the mass accuracy" help="either m/z or ppm">
            <option value="mz" >mz</option>
            <option value="ppm" selected="True" >ppm</option>
        </param>
        <param name="filename" type="text" value="" optional="true" label="Title" help="will appear as header in the quality report, if nothing given input dataset name is used"/>
        <param name="calibrant_file" type="data" optional="true" format="tabular"
            label="File with internal calibrants" help="first column: m/z, second column: name (optional), tabular file"/>
        <param name="peptide_file" type="data" optional="true" format="tabular" label="File with m/z of interest"
            help="first column: m/z, second column: name (optional), tabular file"/>
        <param name="plusminus_dalton" value="0.25" type="float" label="M/z range for m/z heatmaps (x-y grid)" help="Will be added in both directions to input calibrants and peptide m/z"/>
        <param name="plusminus_ppm" value="50" type="float" label="Ppm range for accuracy and number of calibrants plots" help="Will be added in both directions to input calibrant m/z"/>
        <repeat name="calibrantratio" title="Plot fold change of two m/z" min="0" max="10">
            <param name="mass1" value="1111" type="float" label="M/z 1" help="First m/z"/>
            <param name="mass2" value="2222" type="float" label="M/z 2" help="Second m/z"/>
            <param name="distance" value="0.25" type="float" label="M/z range" help="Plusminus m/z window added to input m/z. In both m/z ranges the maximum intensity is used to calculate the fold change"/>
            <param name="filenameratioplot" type="text" optional="true" label="Title" help="Optional title for fold change plot."/>
        </repeat>
        <param name="pixel_output" type="boolean" display="radio" label="Tabular with spectra information" help="Values for each spectrum (pixel) in x-y grid images"/>
    </inputs>
    <outputs>
        <data format="pdf" name="plots" from_work_dir="qualitycontrol.pdf" label = "$infile.display_name QC_report"/>
        <data format="tabular" name="pixel_tabular_output" label="$infile.display_name spectra information">
            <filter>pixel_output</filter>
        </data>
    </outputs>
    <tests>
        <test expect_num_outputs="2">
            <param name="infile" value="" ftype="imzml">
                <composite_data value="Example_Processed.imzML"/>
                <composite_data value="Example_Processed.ibd"/>
            </param>
            <param name="accuracy" value="200"/>
            <param name="units" value="ppm"/>
            <param name="peptide_file" value="inputpeptides.txt"/>
            <param name="calibrant_file" value="inputcalibrantfile1.txt"/>
            <param name="plusminus_dalton" value="0.25"/>
            <param name="plusminus_ppm" value="100"/>
            <param name="filename" value="Testfile_imzml"/>
            <repeat name="calibrantratio">
                <param name="mass1" value="328.9"/>
                <param name="mass2" value="398.8"/>
                <param name="distance" value="0.25"/>
                <param name="filenameratioplot" value = "Ratio of mass1 (328.9) / mass2 (398.8)"/>
            </repeat>
            <param name="pixel_output" value="True"/>
            <output name="pixel_tabular_output" file="spectra_info_imzml.txt"/>
            <output name="plots" file="QC_imzml.pdf" compare="sim_size" delta="20000"/>
        </test>
        <test expect_num_outputs="1">
            <param name="infile" value="" ftype="analyze75">
                <composite_data value="Analyze75.hdr"/>
                <composite_data value="Analyze75.img"/>
                <composite_data value="Analyze75.t2m"/>
            </param>
            <param name="peptide_file" value="inputpeptides.txt"/>
            <param name="calibrant_file" value="inputcalibrantfile2.txt"/>
            <param name="plusminus_dalton" value="0.5"/>
            <param name="filename" value="Testfile_analyze75"/>
            <output name="plots" file="QC_analyze75.pdf" compare="sim_size" delta="20000"/>
        </test>
        <test expect_num_outputs="2">
            <param name="infile" value="123_combined.RData" ftype="rdata"/>
            <param name="plusminus_dalton" value="0.2"/>
            <param name="filename" value="Testfile_rdata"/>
            <param name="pixel_output" value="True"/>
            <output name="pixel_tabular_output" file="spectra_info_123_combi.txt"/>
            <output name="plots" file="QC_rdata.pdf" compare="sim_size" delta="20000"/>
        </test>
        <test expect_num_outputs="1">
            <param name="infile" value="empty_spectra.rdata" ftype="rdata"/>
            <param name="peptide_file" value="inputpeptides.txt"/>
            <param name="calibrant_file" value="inputcalibrantfile2.txt"/>
            <param name="plusminus_dalton" value="0.1"/>
            <param name="filename" value="Testfile_rdata"/>
            <output name="plots" file="QC_empty_spectra.pdf" compare="sim_size" delta="20000"/>
        </test>
    </tests>
    <help>
        <![CDATA[
Cardinal is an R package that implements statistical & computational tools for analyzing mass spectrometry imaging datasets. `More information on Cardinal <http://cardinalmsi.org//>`_

This tool uses some Cardinal functions to create a quality control report with descriptive plots for mass spectrometry imaging data. 

Input data: 3 types of input data can be used:

- imzml file (upload imzml and ibd file via the "composite" function) `Introduction to the imzml format <https://ms-imaging.org/wp/imzml/>`_
- Analyze7.5 (upload hdr, img and t2m file via the "composite" function)
- Cardinal "MSImageSet" data (with variable name "msidata", saved as .RData)

Options: 

- internal calibrants are used for m/z heatmaps (x-y grid), heatmap of number of calibrants per spectrum (x-y grid), zoomed in mass spectra, m/z accuracy
- m/z of interest are used to generate m/z heatmaps (x-y grid)
- optional fold change plot: draws a heatmap (x-y grid) for the fold change of two m/z (log2(intensity ratio))

Output: 

- quality control report as pdf with key numbers and descriptive plots describing the mass spectrometry imaging data
- optional spectra information as tabular file with numbers of calibrants (needs input calibrant file), numbers of peaks, TIC and most abundant m/z in each spectrum

Tip: 

- For additional m/z heatmaps use the MSI ion images tool and to plot more mass spectra use the MSI massspectra tool. 

        ]]>
    </help>
    <citations>
        <citation type="doi">10.1093/bioinformatics/btv146</citation>
    </citations>
</tool>