comparison quality_report.xml @ 8:bb9500286fe4 draft

"planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/cardinal commit f986c51abe33c7f622d429a3c4a79ee24b33c1f3"

7:74b61bf5bc4b

<tool id="cardinal_quality_report" name="MSI Qualitycontrol" version="@VERSION@.4">
    <description>
        mass spectrometry imaging QC
    </description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements">
        <requirement type="package" version="1.1_2">r-rcolorbrewer</requirement>
        <requirement type="package" version="2.3">r-gridextra</requirement>
        <requirement type="package" version="3.0">r-ggplot2</requirement>
        <requirement type="package" version="2.23_15">r-kernsmooth</requirement>
        <requirement type="package" version="1.0.0">r-scales</requirement>
        <requirement type="package" version="1.0.10"> r-pheatmap</requirement>
    </expand>
    <command detect_errors="exit_code">
    <![CDATA[
        @INPUT_LINKING@
        cat '${cardinal_qualitycontrol_script}' &&

library(gridExtra)
library(KernSmooth)
library(scales)
library(pheatmap)


@READING_MSIDATA_INRAM@

## remove duplicated coordinates
msidata <- msidata[,!duplicated(coord(msidata))]

## optional annotation from tabular file to obtain pixel groups (otherwise all pixels are considered to be one sample)

    annotation_input = input_tabular[,c($tabular_annotation.column_x, $tabular_annotation.column_y, $tabular_annotation.column_names)]
    annotation_name = colnames(annotation_input)[3] ##extract header for annotations to later export tabular with same name
    colnames(annotation_input) = c("x", "y", "annotation") ## rename annotations header to default name "annotation"

    ## merge with coordinate information of msidata
    msidata_coordinates = cbind(coord(msidata)[,1:2], c(1:ncol(msidata)))
    colnames(msidata_coordinates)[3] = "pixel_index"
    merged_annotation = merge(msidata_coordinates, annotation_input, by=c("x", "y"), all.x=TRUE)
    merged_annotation[is.na(merged_annotation)] = "NA"
    merged_annotation = merged_annotation[order(merged_annotation\$pixel_index),]
    msidata\$annotation = as.factor(merged_annotation[,4])

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

## only do plots for file with intensity peaks

if (npeaks > 0){

    ## function for density plots

    if (!is.null(levels(msidata\$annotation))){

        number_combined = length(levels(msidata\$annotation))

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

        combine_plot = ggplot(position_df, aes(x=x, y=y, fill=annotation))+
               geom_tile() +
               coord_fixed()+
               ggtitle("Spatial orientation of pixel annotations")+

    }

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

    pixelnumber = 1:pixelcount
    pixelxyarray=cbind(coord(msidata)[,1:2],pixelnumber)
    gg_title = "Pixel order"
    
    print(ggplot(pixelxyarray, aes(x=x, y=y, fill=pixelnumber))+
     geom_tile() + coord_fixed()+
     ggtitle(gg_title) + theme_bw()+

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

            filtered_data = msidata[mz(msidata) >= inputcalibrantmasses[mass]-plusminusvalues[mass] & mz(msidata) <= inputcalibrantmasses[mass]+plusminusvalues[mass],]

            if (nrow(filtered_data) > 1 & sum(spectra(filtered_data),na.rm=TRUE) > 0){

                ## intensity of all m/z > 0
                intensity_sum = colSums(spectra(filtered_data), na.rm=TRUE) > 0

            }else if(nrow(filtered_data) == 1 & sum(spectra(filtered_data), na.rm=TRUE) > 0){

                ## intensity of only m/z > 0
                intensity_sum = spectra(filtered_data) > 0 

            }else{

                intensity_sum = rep(FALSE, ncol(filtered_data))}

            pixelmatrix = rbind(pixelmatrix, intensity_sum)
        }

        ## for each pixel count TRUE (each calibrant m/z range with intensity > 0 is TRUE)
        countvector= as.factor(colSums(pixelmatrix, na.rm=TRUE))
        countdf= cbind(coord(msidata)[,1:2], countvector) ## add pixel coordinates to counts
        mycolours = brewer.pal(9, "Set1")

        print(ggplot(countdf, aes(x=x, y=y, fill=countvector))+
          geom_tile() + coord_fixed() +
          ggtitle(paste0("Number of calibrants per pixel (±",$plusminus_ppm, " ppm)")) +

            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-distance1, mass1, mass1+distance1), col="blue",lty=c(3,6,3))

            ### plot for second m/z 
            plot(msidata[mzdown2:mzup2,], pixel = 1:pixelcount, main= paste0("Average spectrum ", mass2, " Da"))
            abline(v=c(mass2-distance2, mass2, mass2+distance2), col="blue", lty=c(3,6,3))
            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

            ## calculate mean intensity for each m/z over the ppm range; then calculate log2 foldchange
            mass1vector = colMeans(spectra(filtered_data1), na.rm =TRUE)
            mass2vector = colMeans(spectra(filtered_data2), na.rm = TRUE)
            foldchange= log2(mass1vector/mass2vector)
            fcmatrix = cbind(foldchange, coord(msidata)[,1:2])

            print(ggplot(fcmatrix, aes(x=x, y=y, fill=foldchange))+
             geom_tile() + coord_fixed()+
             ggtitle("$label")+
             theme_bw()+

        #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(inputcalibrants[,1]) != 0){
        for (mass in 1:length(inputcalibrants[,1])){


            image(msidata, mz=inputcalibrants[,1][mass], plusminus=plusminusvalues[mass], 
            main= paste0(inputcalibrants[,2][mass], ": ", round(inputcalibrants[,1][mass], digits = 2)," (±",$plusminus_ppm, " ppm)"),
            contrast.enhance = "histogram", ylim= c(maximumy+0.2*maximumy,minimumy-1))
        }
    } 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 peak
    peaksperpixel = colSums(spectra(msidata)> 0, na.rm=TRUE)
    peakscoordarray=cbind(coord(msidata)[,1:2], peaksperpixel)

    print(ggplot(peakscoordarray, aes(x=x, y=y, fill=peaksperpixel))+
     geom_tile() + coord_fixed() +
     ggtitle("Number of peaks per spectrum")+
     theme_bw() +

        gc()


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

    TICcoordarray=cbind(coord(msidata)[,1:2], TICs)

    print(ggplot(TICcoordarray, aes(x=x, y=y, fill=TICs))+
     geom_tile() + coord_fixed() +
     ggtitle("Total Ion Current")+
     theme_bw() +

        rm(TICcoordarray)
        gc()

    ############################### 6b) median int image ###############################

    median_int = apply(spectra(msidata),2,median) 
    median_coordarray=cbind(coord(msidata)[,1:2], median_int)

    print(ggplot(median_coordarray, aes(x=x, y=y, fill=median_int))+
     geom_tile() + coord_fixed() +
     ggtitle("Median intensity per spectrum")+
     theme_bw() +
     theme(plot.title = element_text(hjust = 0.5))+

        rm(median_coordarray)
        gc()

    ############################### 6c) max int image ###############################

    max_int = apply(spectra(msidata),2,max) 
    max_coordarray=cbind(coord(msidata)[,1:2], max_int)

    print(ggplot(max_coordarray, aes(x=x, y=y, fill=max_int))+
     geom_tile() + coord_fixed() +
     ggtitle("Maximum intensity per spectrum")+
     theme_bw() +
     theme(plot.title = element_text(hjust = 0.5))+

        gc()

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

    ## for each spectrum find the row (m/z) with the highest intensity
    highestmz = apply(spectra(msidata),2,which.max)
    ## in case for some spectra max returns integer(0), highestmz is a list and integer(0) have to be replaced with NA and unlisted
    if (class(highestmz) == "list"){
        ##find zero-length values
        zero_entry <- !(sapply(highestmz, length))
        ### replace these values with NA
        highestmz[zero_entry] <- NA
        ### unlist list to get a vector
        highestmz = unlist(highestmz)}

    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() +

        set.seed(1)
        pca = PCA(msidata, ncomp=2)

        ## plot overview image and plot and PC1 and 2 images
        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-1))

        for (PCs in 1:2){
            print(image(pca, column = c(paste0("PC",PCs)) , strip=FALSE, superpose = FALSE, main=paste0("PC", PCs), col.regions = risk.colors(100), ylim=c(maximumy+2, minimumy-2)))}

    ## remove pca to clean up RAM space
        rm(pca)
        gc()

    #end if

    ########################## 14) Intensity distribution ######################

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

    ## 14a) Median intensity over spectra

    medianint_spectra = apply(spectra(msidata), 2, median, na.rm=TRUE)
    plot(medianint_spectra, main="Median intensity per spectrum",las=1, xlab="Spectra index", ylab="")
    title(ylab="Median spectrum intensity", line=4)
    if (!is.null(levels(msidata\$annotation))){
        abline(v=abline_vector, lty = 3)}

    ## 14b) histogram: 
    hist(spectra(msidata), main="", xlab = "", ylab="", las=1)
    title(main="Intensity histogram", line=2)
    title(xlab="intensities")
    title(ylab="Frequency", line=4)
    abline(v=median(spectra(msidata)[(spectra(msidata)>0)], na.rm=TRUE), col="blue")


    ## 14c) histogram to show contribution of annotation groups

    if (!is.null(levels(msidata\$annotation))){

        ## 14e) Heatmap of pearson correlation on mean intensities between annotation groups

        corr_matrix = mean_matrix
        corr_matrix[corr_matrix == 0] <- NA
        colnames(corr_matrix) = levels(msidata\$annotation)
        ## pearson correlation is only possible if there are at least 2 groups
        if (length(colnames)>1)
        {
            corr_matrix = cor(corr_matrix, method= "pearson",use="complete.obs")

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

    ## replace any NA with 0, otherwise plot function will not work at all
    msidata_no_NA = msidata
    spectra(msidata_no_NA)[is.na(spectra(msidata_no_NA))] = 0

    ## find three equal m/z ranges for the average mass spectra plots: 
    third_mz_range = nrow(msidata_no_NA)/3

    par(mfrow = c(2, 2), cex.axis=1, cex.lab=1, mar=c(5.1,4.1,4.1,2.1))
    plot(msidata_no_NA, pixel = 1:ncol(msidata_no_NA), main= "Average spectrum")
    plot(msidata_no_NA[1:third_mz_range,], pixel = 1:ncol(msidata_no_NA), main= "Zoomed average spectrum")
    plot(msidata_no_NA[third_mz_range:(2*third_mz_range),], pixel = 1:ncol(msidata_no_NA), main= "Zoomed average spectrum")
    plot(msidata_no_NA[(2*third_mz_range):nrow(msidata_no_NA),], pixel = 1:ncol(msidata_no_NA), main= "Zoomed average spectrum")

    ## plot one average mass spectrum for each pixel annotation group

    if (!is.null(levels(msidata\$annotation))){
        ## print legend only for less than 10 samples
        if (length(levels(msidata\$annotation)) < 10){
            key_legend = TRUE
        }else{key_legend = FALSE}
        par(mfrow = c(1,1), cex.axis=1, cex.lab=1, mar=c(5.1,4.1,4.1,2.1))
        plot(msidata, pixel=1:ncol(msidata), pixel.groups=msidata\$annotation, key=key_legend, col=hue_pal()(length(levels(msidata\$annotation))),superpose=TRUE, main="Average mass spectra for annotation groups")
    }

    ## plot 4 random mass spectra
    ## find four random pixel to plot their spectra in the following plots:
    pixel1 = sample(pixelnumber,1)
    pixel2 = sample(pixelnumber,1)
    pixel3 = sample(pixelnumber,1)
    pixel4 = sample(pixelnumber,1)

    par(mfrow = c(2, 2), cex.axis=1, cex.lab=1, mar=c(5.1,4.1,4.1,2.1))
    plot(msidata_no_NA, pixel = pixel1, main=paste0("Spectrum at ", rownames(coord(msidata_no_NA)[pixel1,1:2])))
    plot(msidata_no_NA, pixel = pixel2, main=paste0("Spectrum at ", rownames(coord(msidata_no_NA)[pixel2,1:2])))
    plot(msidata_no_NA, pixel = pixel3, main= paste0("Spectrum at ", rownames(coord(msidata_no_NA)[pixel3,1:2])))
    plot(msidata_no_NA, pixel = pixel4, main= paste0("Spectrum at ", rownames(coord(msidata_no_NA)[pixel4,1:2])))

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

    count = 1
    differencevector = numeric()

            ### define the plot window with xmin und xmax
            minmasspixel1 = features(msidata_no_NA, mz=inputcalibrantmasses[mass]-0.5)
            maxmasspixel1 = features(msidata_no_NA, mz=inputcalibrantmasses[mass]+1.5)
            minmasspixel2 = features(msidata_no_NA, mz=inputcalibrantmasses[mass]-0.25)
            maxmasspixel2 = features(msidata_no_NA, mz=inputcalibrantmasses[mass]+0.5)
            minmasspixel3 = features(msidata_no_NA, mz=inputcalibrantmasses[mass]-3)
            maxmasspixel3 = features(msidata_no_NA, 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_no_NA[mz(msidata_no_NA) >= inputcalibrantmasses[mass]-plusminusvalues[mass] & mz(msidata_no_NA) <= inputcalibrantmasses[mass]+plusminusvalues[mass],]

            mzdifference2 = mzvalue - inputcalibrantmasses[mass] 
            ppmdifference2 = mzdifference2/inputcalibrantmasses[mass]*1000000 
            differencevector2[mass] = round(ppmdifference2, digits=2)

            ## plotting of 4 spectra in one page
            par(mfrow = c(2, 2), oma=c(0,0,2,0))
            ## average plot
            plot(msidata_no_NA[minmasspixel1:maxmasspixel1,], pixel = 1:length(pixelnumber), main= "Average spectrum")
            abline(v=c(inputcalibrantmasses[mass] -plusminusvalues[count], inputcalibrantmasses[mass] ,inputcalibrantmasses[mass] +plusminusvalues[count]), col="blue", lty=c(3,5,3))
            abline(v=c(maxvalue), col="red", lty=2)
            abline(v=c(mzvalue), col="green2", lty=4)
            ## average plot including points per data point
            plot(msidata_no_NA[minmasspixel1:maxmasspixel1,], pixel = 1:length(pixelnumber), main="Average spectrum with data points")
            points(mz(msidata_no_NA[minmasspixel1:maxmasspixel1,]), rowMeans(spectra(msidata_no_NA)[minmasspixel1:maxmasspixel1,,drop=FALSE]), col="blue", pch=20)
            ## plot of third average plot
            plot(msidata_no_NA[minmasspixel2:maxmasspixel2,], pixel = 1:length(pixelnumber), main= "Average spectrum")
            abline(v=c(inputcalibrantmasses[mass] -plusminusvalues[count], inputcalibrantmasses[mass] ,inputcalibrantmasses[mass] +plusminusvalues[count]), col="blue", lty=c(3,5,3))
            abline(v=c(maxvalue), col="red", lty=2)
            abline(v=c(mzvalue), col="green2", lty=4)
            ## plot of fourth average plot
            plot(msidata_no_NA[minmasspixel3:maxmasspixel3,], pixel = 1:length(pixelnumber), main= "Average spectrum")
            abline(v=c(inputcalibrantmasses[mass] -plusminusvalues[count], inputcalibrantmasses[mass] ,inputcalibrantmasses[mass] +plusminusvalues[count]), col="blue", lty=c(3,5,3))
            abline(v=c(maxvalue), col="red", lty=2)
            abline(v=c(mzvalue), col="green2", lty=4)
            title(paste0("theor. m/z: ", round(inputcalibrants[count,1], digits=4)), 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)

            if (!is.null(levels(msidata\$annotation))){
                if (number_combined < 10){
                    key_zoomed = TRUE
                }else{key_zoomed = FALSE}
                par(mfrow = c(1, 1))
                plot(msidata_no_NA[minmasspixel1:maxmasspixel1,], pixel=1:ncol(msidata_no_NA),main="Average spectrum per annotation group",
                pixel.groups=msidata\$annotation, 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
        }

             if (!is.null(levels(msidata\$annotation))){
                abline(v=abline_vector, lty = 3)}}

            ### make x-y-images for mz accuracy

            ppm_dataframe = cbind(coord(msidata)[,1:2], ppm_df)

            for (each_cal in 1:ncol(ppm_df)){
                tmp_ppm = ppm_dataframe[,c(1,2,each_cal+2)]
                tmp_ppm[,3] = as.numeric(tmp_ppm[,3])
                colnames(tmp_ppm) = c("x","y", "ppm_each_cal")

            <param name="distance" value="200" type="float" label="ppm range" help="Will be added in both directions to input calibrant m/z and intensities will be averaged in this range."/>
            <param name="filenameratioplot" type="text" optional="true" label="Title" help="Optional title for fold change plot.">
                <sanitizer invalid_char="">
                    <valid initial="string.ascii_letters,string.digits">
                        <add value="_" />
                    </valid>
                </sanitizer>
            </param>
        </repeat>
    </inputs>

            <param name="do_pca" value="True"/>
            <repeat name="calibrantratio">
                <param name="mass1" value="328.9"/>
                <param name="mass2" value="398.8"/>
                <param name="distance" value="500"/>
                <param name="filenameratioplot" value = "Ratio of mass1 (328.9) / mass2 (398.8)"/>
            </repeat>
            <output name="QC_report" file="QC_imzml.pdf" compare="sim_size"/>
        </test>

        <test>

        ]]>
    </help>
    <expand macro="citations"/>
</tool>

8:bb9500286fe4

<tool id="cardinal_quality_report" name="MSI Qualitycontrol" version="@VERSION@.0">
    <description>
        mass spectrometry imaging QC
    </description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements">
        <requirement type="package" version="2.3">r-gridextra</requirement>
        <requirement type="package" version="3.2.1">r-ggplot2</requirement>
        <requirement type="package" version="1.1_2">r-rcolorbrewer</requirement>
        <requirement type="package" version="2.23_16">r-kernsmooth</requirement>
        <requirement type="package" version="1.1.0">r-scales</requirement>
        <requirement type="package" version="1.0.12"> r-pheatmap</requirement>
    </expand>
    <command detect_errors="exit_code">
    <![CDATA[
        @INPUT_LINKING@
        cat '${cardinal_qualitycontrol_script}' &&

library(gridExtra)
library(KernSmooth)
library(scales)
library(pheatmap)

@READING_MSIDATA@

## in case RData input is MSImageSet:
if (class(msidata) == "MSImageSet"){
    msidata = as(msidata, "MSImagingExperiment")
    run(msidata) = "infile"
    }
print(class(msidata))
## remove duplicated coordinates
msidata <- msidata[,!duplicated(coord(msidata))]

## optional annotation from tabular file to obtain pixel groups (otherwise all pixels are considered to be one sample)

    annotation_input = input_tabular[,c($tabular_annotation.column_x, $tabular_annotation.column_y, $tabular_annotation.column_names)]
    annotation_name = colnames(annotation_input)[3] ##extract header for annotations to later export tabular with same name
    colnames(annotation_input) = c("x", "y", "annotation") ## rename annotations header to default name "annotation"

    ## merge with coordinate information of msidata
    msidata_coordinates = data.frame(coord(msidata)\$x, coord(msidata)\$y, c(1:ncol(msidata)))
    colnames(msidata_coordinates) = c("x", "y", "pixel_index")
    merged_annotation = merge(msidata_coordinates, annotation_input, by=c("x", "y"), all.x=TRUE)
    merged_annotation[is.na(merged_annotation)] = "NA"
    merged_annotation = merged_annotation[order(merged_annotation\$pixel_index),]
    msidata\$annotation = as.factor(merged_annotation[,4])

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


## only do plots for file with intensity peaks

if (npeaks > 0){

    ## function for density plots

    if (!is.null(levels(msidata\$annotation))){

        number_combined = length(levels(msidata\$annotation))

        position_df = data.frame(coord(msidata)\$x, coord(msidata)\$y, msidata\$annotation)
        colnames(position_df) = c("x", "y","annotation")

        combine_plot = ggplot(position_df, aes(x=x, y=y, fill=annotation))+
               geom_tile() +
               coord_fixed()+
               ggtitle("Spatial orientation of pixel annotations")+

    }

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

    pixelnumber = 1:pixelcount
    pixelxyarray=data.frame(coord(msidata)\$x, coord(msidata)\$y,pixelnumber)
    colnames(pixelxyarray) = c("x", "y", "pixelnumber")
    gg_title = "Pixel order"
    
    print(ggplot(pixelxyarray, aes(x=x, y=y, fill=pixelnumber))+
     geom_tile() + coord_fixed()+
     ggtitle(gg_title) + theme_bw()+

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

            filtered_data = msidata[mz(msidata) >= inputcalibrantmasses[mass]-plusminusvalues[mass] & mz(msidata) <= inputcalibrantmasses[mass]+plusminusvalues[mass],]

           if (nrow(filtered_data) > 0 & sum(spectra(filtered_data),na.rm=TRUE) > 0){

                ## intensity of all m/z > 0
                intensity_sum = colSums(spectra(filtered_data), na.rm=TRUE) > 0

            ###}else if(nrow(filtered_data) == 1 & sum(spectra(filtered_data), na.rm=TRUE) > 0){

                ## intensity of only m/z > 0
                intensity_sum = colSums(spectra(filtered_data), na.rm=TRUE) > 0

            }else{

                intensity_sum = rep(FALSE, ncol(filtered_data))}

            pixelmatrix = rbind(pixelmatrix, intensity_sum)
        }

        ## for each pixel count TRUE (each calibrant m/z range with intensity > 0 is TRUE)
        countvector= as.factor(colSums(pixelmatrix, na.rm=TRUE))
        countdf= data.frame(coord(msidata)\$x, coord(msidata)\$y, countvector) ## add pixel coordinates to counts
        colnames(countdf) = c("x", "y", "countvector")
        mycolours = brewer.pal(9, "Set1")

        print(ggplot(countdf, aes(x=x, y=y, fill=countvector))+
          geom_tile() + coord_fixed() +
          ggtitle(paste0("Number of calibrants per pixel (±",$plusminus_ppm, " ppm)")) +

            mzup1 = features(msidata, mz = mass1+3)
            mzdown2 = features(msidata, mz = mass2-2)
            mzup2 = features(msidata, mz = mass2+3)

            ### plot for first m/z 
            par(oma=c(0,0,2,0))
            print(plot(msidata[mzdown1:mzup1,], run="infile", layout=c(2,1), strip=FALSE, main=paste0("Average spectrum ", mass1, " Da")))
            abline(v=c(mass1-distance1, mass1, mass1+distance1), col="blue",lty=c(3,6,3))

            ### plot for second m/z 
            print(plot(msidata[mzdown2:mzup2,], run="infile", layout=FALSE, strip=FALSE, main= paste0("Average spectrum ", mass2, " Da")))
            abline(v=c(mass2-distance2, mass2, mass2+distance2), col="blue", lty=c(3,6,3))
            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

            ## calculate mean intensity for each m/z over the ppm range; then calculate log2 foldchange
            mass1vector = colMeans(spectra(filtered_data1), na.rm =TRUE)
            mass2vector = colMeans(spectra(filtered_data2), na.rm = TRUE)
            foldchange= log2(mass1vector/mass2vector)
            fcmatrix = data.frame(coord(msidata)\$x, coord(msidata)\$y,foldchange)
            colnames(fcmatrix) = c("x", "y", "foldchange")

            print(ggplot(fcmatrix, aes(x=x, y=y, fill=foldchange))+
             geom_tile() + coord_fixed()+
             ggtitle("$label")+
             theme_bw()+

        #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(inputcalibrants[,1]) != 0){
        for (mass in 1:length(inputcalibrants[,1])){
            par(oma=c(0,0,0,1))## margin for image legend

           tryCatch(
                        {
                        print(image(msidata, mz=inputcalibrants[,1][mass], plusminus=plusminusvalues[mass], 
            main= paste0(inputcalibrants[,2][mass], ": ", round(inputcalibrants[,1][mass], digits = 2)," (±",$plusminus_ppm, " ppm)"),
            contrast.enhance = "histogram", strip=FALSE, ylim= c(maximumy,minimumy)))
                        },
                        error=function(cond) {
                        ## if there are not enough intensities in the mz range skip creating an image
                        print(paste0("Not enough intensities > 0 for m/z ", inputcalibrants[,1][mass]))
                        }
                    )    
        }
    } 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 peak
    peaksperpixel = colSums(spectra(msidata)> 0, na.rm=TRUE)
    peakscoordarray=data.frame(coord(msidata)\$x, coord(msidata)\$y, peaksperpixel)
    colnames(peakscoordarray) = c("x", "y", "peaksperpixel")

    print(ggplot(peakscoordarray, aes(x=x, y=y, fill=peaksperpixel))+
     geom_tile() + coord_fixed() +
     ggtitle("Number of peaks per spectrum")+
     theme_bw() +

        gc()


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

    TICcoordarray=data.frame(coord(msidata)\$x, coord(msidata)\$y, TICs)
    colnames(TICcoordarray) = c("x", "y", "peaksperpixel")

    print(ggplot(TICcoordarray, aes(x=x, y=y, fill=TICs))+
     geom_tile() + coord_fixed() +
     ggtitle("Total Ion Current")+
     theme_bw() +

        rm(TICcoordarray)
        gc()

    ############################### 6b) median int image ###############################

    median_int = pixelApply(msidata, median)

    median_coordarray=data.frame(coord(msidata)\$x, coord(msidata)\$y, median_int)
    colnames(median_coordarray) = c("x", "y", "median_int")
    print(ggplot(median_coordarray, aes(x=x, y=y, fill=median_int))+
     geom_tile() + coord_fixed() +
     ggtitle("Median intensity per spectrum")+
     theme_bw() +
     theme(plot.title = element_text(hjust = 0.5))+

        rm(median_coordarray)
        gc()

    ############################### 6c) max int image ###############################

    max_int = pixelApply(msidata, max)

    max_coordarray=data.frame(coord(msidata)\$x, coord(msidata)\$y, max_int)
    colnames(max_coordarray) = c("x", "y", "max_int")
    print(ggplot(max_coordarray, aes(x=x, y=y, fill=max_int))+
     geom_tile() + coord_fixed() +
     ggtitle("Maximum intensity per spectrum")+
     theme_bw() +
     theme(plot.title = element_text(hjust = 0.5))+

        gc()

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

    ## for each spectrum find the row (m/z) with the highest intensity
    highestmz = pixelApply(msidata, which.max)

    ## in case for some spectra max returns integer(0), highestmz is a list and integer(0) have to be replaced with NA and unlisted
    if (class(highestmz) == "list"){
        ##find zero-length values
        zero_entry <- !(sapply(highestmz, length))
        ### replace these values with NA
        highestmz[zero_entry] <- NA
        ### unlist list to get a vector
        highestmz = unlist(highestmz)}

    highestmz_matrix = data.frame(coord(msidata)\$x, coord(msidata)\$y,mz(msidata)[highestmz])
    colnames(highestmz_matrix) = c("x", "y", "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() +

        set.seed(1)
        pca = PCA(msidata, ncomp=2)

        ## plot overview image and plot and PC1 and 2 images
        print(plot(pca, col=c("black", "darkgrey"), main="PCA for two components", layout=c(2,1), strip=FALSE))
        print(image(pca, run="infile", col=c("black", "white"), strip=FALSE,  ylim= c(maximumy+0.2*maximumy,minimumy-1), layout=FALSE))

        par(oma=c(0,0,0,1))## margin for image legend
        print(image(pca, column = "PC1" , strip=FALSE, superpose = FALSE, main="PC1", col.regions = risk.colors(100), layout=c(2,1), ylim= c(maximumy+0.2*maximumy,minimumy-1)))
        print(image(pca, column = "PC2" , strip=FALSE, superpose = FALSE, main="PC2", col.regions = risk.colors(100), layout=FALSE,  ylim= c(maximumy+0.2*maximumy,minimumy-1)))
    ## remove pca to clean up RAM space
        rm(pca)
        gc()

    #end if

    ########################## 14) Intensity distribution ######################

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

    ## 14a) Median intensity over spectra
    medianint_spectra = apply(spectra(msidata), 2, median, na.rm=TRUE) 
    plot(medianint_spectra, main="Median intensity per spectrum",las=1, xlab="Spectra index", ylab="")
    title(ylab="Median spectrum intensity", line=4)
    if (!is.null(levels(msidata\$annotation))){
        abline(v=abline_vector, lty = 3)}

    ## 14b) histogram: 
    hist(as.matrix(spectra(msidata)), main="", xlab = "", ylab="", las=1)
    title(main="Intensity histogram", line=2)
    title(xlab="intensities")
    title(ylab="Frequency", line=4)
    abline(v=median(as.matrix(spectra(msidata))[(as.matrix(spectra(msidata))>0)], na.rm=TRUE), col="blue")


    ## 14c) histogram to show contribution of annotation groups

    if (!is.null(levels(msidata\$annotation))){

        ## 14e) Heatmap of pearson correlation on mean intensities between annotation groups

        corr_matrix = mean_matrix
        corr_matrix[corr_matrix == 0] <- NA
        colnames(corr_matrix) = levels(msidata\$annotation)

        ## pearson correlation is only possible if there are at least 2 groups
        if (length(colnames)>1)
        {
            corr_matrix = cor(corr_matrix, method= "pearson",use="complete.obs")

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

    ## replace any NA with 0, otherwise plot function will not work at all
    msidata_no_NA = msidata

    ## find three equal m/z ranges for the average mass spectra plots: 
    third_mz_range = nrow(msidata_no_NA)/3

    par(cex.axis=1, cex.lab=1, mar=c(5.1,4.1,4.1,2.1))
    print(plot(msidata_no_NA, run="infile", layout=c(2,2), strip=FALSE, main= "Average spectrum"))
    print(plot(msidata_no_NA[1:third_mz_range,], run="infile", layout=FALSE, strip=FALSE, main= "Zoomed average spectrum"))
    print(plot(msidata_no_NA[third_mz_range:(2*third_mz_range),], run="infile", layout=FALSE, strip=FALSE, main= "Zoomed average spectrum"))
    print(plot(msidata_no_NA[(2*third_mz_range):nrow(msidata_no_NA),], run="infile", layout=FALSE, strip=FALSE, main= "Zoomed average spectrum"))

    ## plot one average mass spectrum for each pixel annotation group

    if (!is.null(levels(msidata\$annotation))){
        ## print legend only for less than 10 samples
        if (length(levels(msidata\$annotation)) < 10){
            key_legend = TRUE
        }else{key_legend = FALSE}
        par(mfrow = c(1,1), cex.axis=1, cex.lab=1, mar=c(5.1,4.1,4.1,2.1))
        print(plot(msidata, run="infile", pixel.groups=msidata\$annotation, key=key_legend, col=hue_pal()(length(levels(msidata\$annotation))),superpose=TRUE, main="Average mass spectra for annotation groups"))
    }

    ## plot 4 random mass spectra
    ## find four random, not empty pixel to plot their spectra in the following plots:
    pixel_vector = sample(which(TICs != 0),4)

    par(mfrow = c(2, 2), cex.axis=1, cex.lab=1, mar=c(5.1,4.1,4.1,2.1))
    print(plot(msidata_no_NA, pixel = pixel_vector))


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

    count = 1
    differencevector = numeric()

            ### define the plot window with xmin und xmax
            minmasspixel1 = features(msidata_no_NA, mz=inputcalibrantmasses[mass]-0.5)
            maxmasspixel1 = features(msidata_no_NA, mz=inputcalibrantmasses[mass]+1.5)
            minmasspixel2 = features(msidata_no_NA, mz=inputcalibrantmasses[mass]-0.25)
            maxmasspixel2 = features(msidata_no_NA, mz=inputcalibrantmasses[mass]+0.5)
            minmasspixel3 = features(msidata_no_NA, mz=inputcalibrantmasses[mass]-1.5)
            maxmasspixel3 = features(msidata_no_NA, 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_no_NA[mz(msidata_no_NA) >= inputcalibrantmasses[mass]-plusminusvalues[mass] & mz(msidata_no_NA) <= inputcalibrantmasses[mass]+plusminusvalues[mass],]

            mzdifference2 = mzvalue - inputcalibrantmasses[mass] 
            ppmdifference2 = mzdifference2/inputcalibrantmasses[mass]*1000000 
            differencevector2[mass] = round(ppmdifference2, digits=2)

            ## plotting of 4 spectra in one page
            par(oma=c(0,0,2,0))
            ## average plot

            print(plot(msidata_no_NA[minmasspixel1:maxmasspixel1,], run="infile", layout=c(2,2), strip=FALSE, main= "Average spectrum"))
            abline(v=c(inputcalibrantmasses[mass] -plusminusvalues[count], inputcalibrantmasses[mass] ,inputcalibrantmasses[mass] +plusminusvalues[count]), col="blue", lty=c(3,5,3))
            abline(v=c(maxvalue), col="red", lty=2)
            abline(v=c(mzvalue), col="green2", lty=4)
            ## average plot including points per data point
            print(plot(msidata_no_NA[minmasspixel1:maxmasspixel1,], run="infile", layout=FALSE, strip=FALSE, main="Average spectrum with data points"))
            points(mz(msidata_no_NA[minmasspixel1:maxmasspixel1,]), rowMeans(spectra(msidata_no_NA)[minmasspixel1:maxmasspixel1,,drop=FALSE]), col="blue", pch=20)
            ## plot of third average plot
            print(plot(msidata_no_NA[minmasspixel2:maxmasspixel2,], run="infile", layout=FALSE, strip=FALSE, main= "Average spectrum"))
            abline(v=c(inputcalibrantmasses[mass] -plusminusvalues[count], inputcalibrantmasses[mass] ,inputcalibrantmasses[mass] +plusminusvalues[count]), col="blue", lty=c(3,5,3))
            abline(v=c(maxvalue), col="red", lty=2)
            abline(v=c(mzvalue), col="green2", lty=4)
            ## plot of fourth average plot
            print(plot(msidata_no_NA[minmasspixel3:maxmasspixel3,], run="infile", layout=FALSE, strip=FALSE, main= "Average spectrum"))
            abline(v=c(inputcalibrantmasses[mass] -plusminusvalues[count], inputcalibrantmasses[mass] ,inputcalibrantmasses[mass] +plusminusvalues[count]), col="blue", lty=c(3,5,3))
            abline(v=c(maxvalue), col="red", lty=2)
            abline(v=c(mzvalue), col="green2", lty=4)
            title(paste0("theor. m/z: ", round(inputcalibrants[count,1], digits=4)), 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)

            if (!is.null(levels(msidata\$annotation))){
                if (number_combined < 10){
                    key_zoomed = TRUE
                }else{key_zoomed = FALSE}
                par(mfrow = c(1, 1))
                print(plot(msidata_no_NA[minmasspixel1:maxmasspixel1,], run="infile", strip=FALSE,main="Average spectrum per annotation group",
                pixel.groups=msidata\$annotation, 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
        }

             if (!is.null(levels(msidata\$annotation))){
                abline(v=abline_vector, lty = 3)}}

            ### make x-y-images for mz accuracy

            ppm_dataframe = data.frame(coord(msidata)\$x, coord(msidata)\$y, ppm_df)
            colnames(ppm_dataframe) = c("x", "y", "ppm_df")

            for (each_cal in 1:ncol(ppm_df)){
                tmp_ppm = ppm_dataframe[,c(1,2,each_cal+2)]
                tmp_ppm[,3] = as.numeric(tmp_ppm[,3])
                colnames(tmp_ppm) = c("x","y", "ppm_each_cal")

            <param name="distance" value="200" type="float" label="ppm range" help="Will be added in both directions to input calibrant m/z and intensities will be averaged in this range."/>
            <param name="filenameratioplot" type="text" optional="true" label="Title" help="Optional title for fold change plot.">
                <sanitizer invalid_char="">
                    <valid initial="string.ascii_letters,string.digits">
                        <add value="_" />
                        <add value=" " />
                    </valid>
                </sanitizer>
            </param>
        </repeat>
    </inputs>

            <param name="do_pca" value="True"/>
            <repeat name="calibrantratio">
                <param name="mass1" value="328.9"/>
                <param name="mass2" value="398.8"/>
                <param name="distance" value="500"/>
                <param name="filenameratioplot" value = "Ratio of mz 328.9 and mz 398.8"/>
            </repeat>
            <output name="QC_report" file="QC_imzml.pdf" compare="sim_size"/>
        </test>

        <test>

        ]]>
    </help>
    <expand macro="citations"/>
</tool>