comparison msi_qualitycontrol.xml @ 13:88e12d270e35 draft

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/msi_qualitycontrol commit 8087490eb4dcaf4ead0f03eae4126780d21e5503

12:c43a7821c030

<tool id="mass_spectrometry_imaging_qc" name="MSI Qualitycontrol" version="1.10.0.3">
    <description>
        mass spectrometry imaging QC
    </description>
    <requirements>
        <requirement type="package" version="1.10.0">bioconductor-cardinal</requirement>

#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

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

####################### II) x-y images #######################################
##############################################################################
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)),

    ## filter for m/z window of each calibrant and calculate if sum of peak intensities > 0
    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)) > 0){

            ## intensity of all m/z > 0
            intensity_sum = colSums(spectra(filtered_data)) > 0
        }else if(nrow(filtered_data) == 1 & sum(spectra(filtered_data)) > 0){

            ## intensity of only m/z > 0
            intensity_sum = spectra(filtered_data) > 0
        }else{
            intensity_sum = rep(FALSE, ncol(filtered_data))}

        ## for each pixel add sum of intensity in the given m/z range
        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))
        countdf= cbind(coord(msidata)[,1:2], countvector) ## add pixel coordinates to counts
        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() +

            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

                 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 #######################################

    } 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")+

    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]

    ## append list for optional tabular output with spectrum values
    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))

    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)) ## for each m/z average intensity is calculated
                maxvalue = mz(filtered_data)[which.max(maxmassrow)] ### m/z with highest average 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

            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)

            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

        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>

        </conditional>
        <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="plusminus_ppm" value="50" type="float" label="ppm range" 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."/>

                <param name="units" value="ppm"/>
            </conditional>
            <param name="calibrant_file" value="inputcalibrantfile1.txt"/>
            <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)"/>

                <composite_data value="Analyze75.img"/>
                <composite_data value="Analyze75.t2m"/>
            </param>
            <param name="calibrant_file" value="inputcalibrantfile2.txt"/>
            <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="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="calibrant_file" value="inputcalibrantfile2.txt"/>
            <param name="filename" value="Testfile_rdata"/>
            <output name="plots" file="QC_empty_spectra.pdf" compare="sim_size" delta="20000"/>
        </test>
    </tests>
    <help>
        <![CDATA[

13:88e12d270e35

<tool id="mass_spectrometry_imaging_qc" name="MSI Qualitycontrol" version="1.10.0.4">
    <description>
        mass spectrometry imaging QC
    </description>
    <requirements>
        <requirement type="package" version="1.10.0">bioconductor-cardinal</requirement>

#end if

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

## remove duplicated coordinates
print(paste0(sum(duplicated(coord(msidata))), " duplicated coordinates were removed"))
msidata <- msidata[,!duplicated(coord(msidata))]

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

## Number of features (m/z)
maxfeatures = length(features(msidata))
## Range m/z

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)[], na.rm=TRUE), digits=2)
maxint = round(max(spectra(msidata)[], na.rm=TRUE), digits=2)
medint = round(median(spectra(msidata)[], na.rm=TRUE), digits=2)
## Number of intensities > 0
npeaks= sum(spectra(msidata)[]>0, na.rm=TRUE)
## 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)[], na.rm=TRUE) 
NumemptyTIC = sum(TICs == 0)
## Median TIC
medTIC = round(median(TICs), digits=2)
## Median peaks per spectrum
medpeaks = median(colSums(spectra(msidata)[]>0, na.rm=TRUE), na.rm=TRUE)
print(cor(TICs,colSums(spectra(msidata)[]>0), method="pearson"))

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

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

## only do plots for file with intensity peaks
if (npeaks > 0){
    ## function for density plots
    plot_colorByDensity = function(x1,x2,
                                   ylim=c(min(x2),max(x2)),
                                   xlim=c(min(x1),max(x1)),

    ## filter for m/z window of each calibrant and calculate if sum of peak intensities > 0
    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))}

        ## for each pixel add sum of intensity in the given m/z range
        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 = 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() +

            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), na.rm=TRUE)
            maxmass1 = mz(filtered_data1)[which.max(maxmassrow1)]
            maxmassrow2 = rowMeans(spectra(filtered_data2), na.rm=TRUE)
            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

                 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 > 0,\n therefore no foldchange plot could be drawn"))}

        #end for
    #end if

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

    } 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, na.rm=TRUE)
    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")+

    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", 
      limits=c(min(highestmz_matrix\$highestmzinDa), max(highestmz_matrix\$highestmzinDa)))+
    theme(text=element_text(family="ArialMT", face="bold", size=12)))

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

    ## 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 = FALSE, col.names=TRUE, sep = "\t")
    #end if

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

    #if $do_pca:

    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))

    #end if

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

    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)) ## for each m/z average intensity is calculated
                maxvalue = mz(filtered_data)[which.max(maxmassrow)] ### m/z with highest average 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

            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(3,5,3))
            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(3,5,3))
            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(3,5,3))
            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(3,5,3))
            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)

            count=count+1
        }

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

        ### 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)){
                plot(0,type='n',axes=FALSE,ann=FALSE)
                title(main=paste("plot 17: no peaks in the chosen region, repeat with higher ppm range")) ## here klammer weggenommen...
        }else{

        diff_plot1=ggplot(data=diff_df, aes(x=calibrant_names, y=differencevector)) + geom_bar(stat="identity", fill = "darkgray") + theme_minimal() +
        labs(title="Average m/z error (max. average intensity vs. theor. calibrant m/z)", x="calibrants", y = "Average m/z error in ppm")+
        theme(plot.title = element_text(hjust = 0.5, size=14))+theme(text=element_text(family="ArialMT", face="bold", size=16))+
        geom_text(aes(label=differencevector), vjust=-0.3, size=5.5, col="blue") +
        theme(axis.text.x = element_text(angle = 90, hjust = 1, size=16))

        print(diff_plot1)
        }

    ######### 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_plot2=ggplot(data=diff_df, aes(x=calibrant_names, y=differencevector2)) + geom_bar(stat="identity", fill = "darkgray") + theme_minimal() +
        labs(title="Average m/z error (closest measured m/z vs. theor. calibrant m/z)", x="calibrants", y = "Average m/z error in ppm")+
        theme(plot.title = element_text(hjust = 0.5, size=16))+theme(text=element_text(family="ArialMT", face="bold", size=16))+
        geom_text(aes(label=differencevector2), vjust=-0.3, size=5.5, col="blue")+
        theme(axis.text.x = element_text(angle = 90, hjust = 1, size=16))

        print(diff_plot2)


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

    par(mfrow = c(1,1))
    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

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

        if (sum(is.na(ppm_df)) == ncol(ppm_df)*nrow(ppm_df)){
                plot(0,type='n',axes=FALSE,ann=FALSE)
            title(main=paste("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("plot 16+17+18+19) The inputcalibrant m/z were not provided or outside the m/z range")}
}else{
    print("inputfile has no intensities > 0")
}
    dev.off()



    ]]></configfile>
    </configfiles>

        </conditional>
        <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="plusminus_ppm" value="50" type="float" label="ppm range" help="Will be added in both directions to input calibrant m/z"/>
        <param name="do_pca" type="boolean" display="radio" label="PCA with 2 components"/>
        <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."/>

                <param name="units" value="ppm"/>
            </conditional>
            <param name="calibrant_file" value="inputcalibrantfile1.txt"/>
            <param name="plusminus_ppm" value="100"/>
            <param name="filename" value="Testfile_imzml"/>
            <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="0.25"/>
                <param name="filenameratioplot" value = "Ratio of mass1 (328.9) / mass2 (398.8)"/>

                <composite_data value="Analyze75.img"/>
                <composite_data value="Analyze75.t2m"/>
            </param>
            <param name="calibrant_file" value="inputcalibrantfile2.txt"/>
            <param name="filename" value="Testfile_analyze75"/>
            <param name="do_pca" value="True"/>
            <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="filename" value="Testfile_rdata"/>
            <param name="do_pca" value="True"/>
            <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="calibrant_file" value="inputcalibrantfile2.txt"/>
            <param name="filename" value="Testfile_rdata"/>
            <param name="do_pca" value="False"/>
            <output name="plots" file="QC_empty_spectra.pdf" compare="sim_size" delta="20000"/>
        </test>
    </tests>
    <help>
        <![CDATA[