comparison quality_report.xml @ 15:23d0394b5908 draft

"planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/cardinal commit c8d3adac445b4e08e2724e22d7201bfc38bbf40f"

14:5a35e3a8d013

<tool id="cardinal_quality_report" name="MSI Qualitycontrol" version="@VERSION@.1">
    <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="3.3.2">r-ggplot2</requirement>
        <requirement type="package" version="1.1_2">r-rcolorbrewer</requirement>
        <requirement type="package" version="2.23_17">r-kernsmooth</requirement>
        <requirement type="package" version="1.1.1">r-scales</requirement>
        <requirement type="package" version="1.0.12">r-pheatmap</requirement>
    </expand>
    <command detect_errors="exit_code">
    <![CDATA[

        #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)

        rm(TICcoordarray)
        gc()

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

    median_int = pixelApply(msidata, median, na.rm=TRUE)

    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))+
     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 = "median\nintensity"))

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

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

    max_int = pixelApply(msidata, max, na.rm=TRUE)

    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))+
     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 = "max\nintensity"))

    ## remove median_coordarray to clean up RAM space
        rm(max_coordarray)
        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() +
    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)))

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


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

    #if $do_pca:

    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)

    if (!is.null(unique(msidata\$annotation))){
        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 contribution of annotation groups

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

        df_9 = data.frame(peaksperpixel, msidata\$annotation)
        colnames(df_9) = c("Npeaks", "annotation")
 
        hist_9 = ggplot(df_9, aes(x=Npeaks, fill=annotation)) +
        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 = 8))+
        theme(legend.position="bottom",legend.direction="vertical")+
        labs(title="Number of peaks per spectrum and annotation group", 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))

    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")

    ########################## 12) Number of peaks per m/z #####################

    peakspermz = rowSums(spectra(msidata) > 0, na.rm=TRUE)

    par(mfrow = c(2,1), mar=c(5,6,4,4.5))
    ## 12a) 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)

    ## 12b) 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") 

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

    ## Sum of all intensities for each m/z (like TIC, but for m/z instead of pixel)
    mzTIC = featureApply(msidata, sum, na.rm=TRUE) ## calculate intensity sum for each m/z

    par(mfrow = c(2,1), mar=c(5,6,4,2))
    ## 13a) 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)

    ## 13b) histogram
    hist(mzTIC, main="", xlab = "", las=1, ylab="")
    title(main="Sum of intensities per m/z", line=2, ylab="")
    title(xlab = "sum of intensities per m/z")
    title(ylab = "Frequency", line=4)
    abline(v=median(mzTIC[mzTIC>0]), col="blue")

    ################################## V) intensity plots ########################
    ############################################################################
    print("intensity plots")
    ########################## 14) Intensity distribution ######################

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

    ## 14a) Median intensity over spectra
    medianint_spectra = pixelApply(msidata, 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(unique(msidata\$annotation))){
        abline(v=abline_vector, lty = 3)}

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


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

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

    ############################################################################
    print("Mass spectra and m/z accuracy")

    ############################ 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 = round(nrow(msidata_no_NA)/3,0)

    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", col="black"))
    print(plot(msidata_no_NA[1:third_mz_range,], layout=FALSE, run="infile", strip=FALSE, main="Zoomed average spectrum", col="black"))
    print(plot(msidata_no_NA[third_mz_range:(2*third_mz_range),], layout=FALSE, run="infile", strip=FALSE, main="Zoomed average spectrum", col="black"))
    print(plot(msidata_no_NA[(2*third_mz_range):nrow(msidata_no_NA),], layout=FALSE, run="infile", strip=FALSE, main="Zoomed average spectrum", col="black"))

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

    if (!is.null(unique(msidata\$annotation))){
        ## print legend only for less than 10 samples
        if (length(unique(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(unique(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, col="black"))


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

    count = 1
    differencevector = numeric()

        rm(msidata_no_NA)
        gc()

    ######### 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])

        theme(plot.title = element_text(hjust = 0.5, size=14))+theme(text=element_text(family="ArialMT", face="bold", size=14))+
        geom_text(aes(label=differencevector2), vjust=-0.3, size=5.5, col="blue")+
        theme(axis.text.x = element_text(angle = 90, hjust = 1, size=14))

        print(diff_plot2)

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

        par(mfrow = c(1,1))
        count = 1

             if (!is.null(unique(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)]

                 theme_bw() +
                 theme(plot.title = element_text(hjust = 0.5))+
                 theme(text=element_text(family="ArialMT", face="bold", size=12))+
                 scale_fill_gradient2(low = "navy", mid = "grey", high = "red", midpoint = 0 ,space = "Lab", na.value = "black", name = "ppm\nerror"))}


    }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")
}

        </conditional>
        <expand macro="pdf_filename"/>
        <expand macro="reading_2_column_mz_tabular" optional="true"/>
        <param name="plusminus_ppm" value="200" type="float" label="ppm range" help="Will be added in both directions to input calibrant m/z"/>
        <param name="do_pca" type="boolean" 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="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.">

                <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>
            <expand macro="infile_analyze75"/>
            <conditional name="tabular_annotation">
                <param name="load_annotation" value="no_annotation"/>
            </conditional>
            <param name="filename" value="Testfile_analyze75"/>
            <param name="do_pca" value="True"/>
            <output name="QC_report" file="QC_analyze75.pdf" compare="sim_size"/>
        </test>

        <test>
            <param name="infile" value="3_files_combined.RData" ftype="rdata"/>
            <conditional name="tabular_annotation">
                <param name="load_annotation" value="yes_annotation"/>
                <param name="annotation_file" value="annotations_rdata.tabular"/>

            <param name="name_column" value="2"/>
            <param name="filename" value="Testfile_rdata"/>
            <param name="do_pca" value="False"/>
            <output name="QC_report" file="QC_empty_spectra.pdf" compare="sim_size"/>
        </test>
    </tests>
    <help>
        <![CDATA[
@CARDINAL_DESCRIPTION@

15:23d0394b5908

<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="3.3.5">r-ggplot2</requirement>
        <requirement type="package" version="1.1_2">r-rcolorbrewer</requirement>
        <requirement type="package" version="2.23_20">r-kernsmooth</requirement>
        <requirement type="package" version="1.1.1">r-scales</requirement>
        <requirement type="package" version="1.0.12">r-pheatmap</requirement>
    </expand>
    <command detect_errors="exit_code">
    <![CDATA[

        #end for
    #end if

    #################### 4) m/z heatmaps #######################################
   
    #if $report_depth:
       
		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")}
		
    #end if

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

    ## here every intensity value > 0 counts as peak
    peaksperpixel = colSums(spectra(msidata)> 0, na.rm=TRUE)

        rm(TICcoordarray)
        gc()

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

    #if $report_depth:
    
		median_int = pixelApply(msidata, median, na.rm=TRUE)

		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))+
		 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 = "median\nintensity"))

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

		############################### 6c) max int image ###############################
		
		max_int = pixelApply(msidata, max, na.rm=TRUE)

		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))+
		 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 = "max\nintensity"))

		## remove median_coordarray to clean up RAM space
		    rm(max_coordarray)
		    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() +
		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)))

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

    #end if

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

    #if $do_pca:

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

    ########################## 9) number of peaks per spectrum #################
    ## 9a) scatterplot
    
    #if $report_depth:

		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)

		if (!is.null(unique(msidata\$annotation))){
		    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 contribution of annotation groups

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

		    df_9 = data.frame(peaksperpixel, msidata\$annotation)
		    colnames(df_9) = c("Npeaks", "annotation")
	 
		    hist_9 = ggplot(df_9, aes(x=Npeaks, fill=annotation)) +
		    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 = 8))+
		    theme(legend.position="bottom",legend.direction="vertical")+
		    labs(title="Number of peaks per spectrum and annotation group", 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)}
        
    #end if

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

    ## 10a)density scatterplot
    par(mfrow = c(2,1), mar=c(5,6,4,2))

    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")

    ########################## 12) Number of peaks per m/z #####################

    #if $report_depth:
        
		peakspermz = rowSums(spectra(msidata) > 0, na.rm=TRUE)

		par(mfrow = c(2,1), mar=c(5,6,4,4.5))
		## 12a) 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)

		## 12b) 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") 

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

		## Sum of all intensities for each m/z (like TIC, but for m/z instead of pixel)
		mzTIC = featureApply(msidata, sum, na.rm=TRUE) ## calculate intensity sum for each m/z

		par(mfrow = c(2,1), mar=c(5,6,4,2))
		## 13a) 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)

		## 13b) histogram
		hist(mzTIC, main="", xlab = "", las=1, ylab="")
		title(main="Sum of intensities per m/z", line=2, ylab="")
		title(xlab = "sum of intensities per m/z")
		title(ylab = "Frequency", line=4)
		abline(v=median(mzTIC[mzTIC>0]), col="blue")

		################################## V) intensity plots ########################
		############################################################################
		print("intensity plots")
		########################## 14) Intensity distribution ######################

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

		## 14a) Median intensity over spectra
		medianint_spectra = pixelApply(msidata, 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(unique(msidata\$annotation))){
		    abline(v=abline_vector, lty = 3)}

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

    #end if

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

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

    ############################################################################
    print("Mass spectra and m/z accuracy")

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

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

		## find three equal m/z ranges for the average mass spectra plots: 
		third_mz_range = round(nrow(msidata_no_NA)/3,0)

		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", col="black"))
		print(plot(msidata_no_NA[1:third_mz_range,], layout=FALSE, run="infile", strip=FALSE, main="Zoomed average spectrum", col="black"))
		print(plot(msidata_no_NA[third_mz_range:(2*third_mz_range),], layout=FALSE, run="infile", strip=FALSE, main="Zoomed average spectrum", col="black"))
		print(plot(msidata_no_NA[(2*third_mz_range):nrow(msidata_no_NA),], layout=FALSE, run="infile", strip=FALSE, main="Zoomed average spectrum", col="black"))

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

		if (!is.null(unique(msidata\$annotation))){
		    ## print legend only for less than 10 samples
		    if (length(unique(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(unique(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, col="black"))

    #end if

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

    count = 1
    differencevector = numeric()

        rm(msidata_no_NA)
        gc()

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

    #if $report_depth:
    
        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])

        theme(plot.title = element_text(hjust = 0.5, size=14))+theme(text=element_text(family="ArialMT", face="bold", size=14))+
        geom_text(aes(label=differencevector2), vjust=-0.3, size=5.5, col="blue")+
        theme(axis.text.x = element_text(angle = 90, hjust = 1, size=14))

        print(diff_plot2)
        
    #end if

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

        par(mfrow = c(1,1))
        count = 1

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

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

    #if $report_depth:
            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)]

                 theme_bw() +
                 theme(plot.title = element_text(hjust = 0.5))+
                 theme(text=element_text(family="ArialMT", face="bold", size=12))+
                 scale_fill_gradient2(low = "navy", mid = "grey", high = "red", midpoint = 0 ,space = "Lab", na.value = "black", name = "ppm\nerror"))}

    #end if

    }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")
}

        </conditional>
        <expand macro="pdf_filename"/>
        <expand macro="reading_2_column_mz_tabular" optional="true"/>
        <param name="plusminus_ppm" value="200" type="float" label="ppm range" help="Will be added in both directions to input calibrant m/z"/>
        <param name="do_pca" type="boolean" label="PCA with 2 components"/>
        <param name="report_depth" type="boolean" label="Generate full QC report" truevalue="TRUE" falsevalue="FALSE" checked="True" help="No: does not generate all plots but only the most informatives"/>
        <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="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.">

                <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>
            <expand macro="infile_analyze75"/>
            <conditional name="tabular_annotation">
                <param name="load_annotation" value="no_annotation"/>
            </conditional>
            <param name="filename" value="Testfile_analyze75"/>
            <param name="do_pca" value="True"/>
            <output name="QC_report" file="QC_analyze75.pdf" compare="sim_size"/>
        </test>
        <test>
            <param name="infile" value="3_files_combined.RData" ftype="rdata"/>
            <conditional name="tabular_annotation">
                <param name="load_annotation" value="yes_annotation"/>
                <param name="annotation_file" value="annotations_rdata.tabular"/>

            <param name="name_column" value="2"/>
            <param name="filename" value="Testfile_rdata"/>
            <param name="do_pca" value="False"/>
            <output name="QC_report" file="QC_empty_spectra.pdf" compare="sim_size"/>
        </test>
        <test>
            <param name="infile" value="" ftype="imzml">
                <composite_data value="Example_Processed.imzML"/>
                <composite_data value="Example_Processed.ibd"/>
            </param>
            <conditional name="processed_cond">
                <param name="processed_file" value="processed"/>
                <param name="accuracy" value="200"/>
                <param name="units" value="ppm"/>
            </conditional>
            <conditional name="tabular_annotation">
                <param name="load_annotation" value="no_annotation"/>
            </conditional>
            <param name="calibrant_file" value="inputcalibrantfile1.tabular" ftype="tabular"/>
            <param name="mz_column" value="1"/>
            <param name="name_column" value="1"/>
            <param name="report_depth" value="False"/>
            <output name="QC_report" file="QC_imzml_shortreport.pdf" compare="sim_size"/>
        </test>  
    </tests>
    <help>
        <![CDATA[
@CARDINAL_DESCRIPTION@