annotate msi_spectra_plots.xml @ 0:c93ae3463b30 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/msi_spectra_plot commit 6d271de132f364b1e16b0222ad2d6e315586f0dd

<tool id="mass_spectrometry_imaging_mzplots" name="MSI massspectra" version="1.7.0">
    <description>
        mass spectrometry imaging mass spectra plots
    </description>
    <requirements>
        <requirement type="package" version="1.7.0">bioconductor-cardinal</requirement>
        <requirement type="package" version="2.2.1">r-gridextra</requirement>
        <requirement type="package" version="2.23-15">r-kernsmooth</requirement>
    </requirements>
    <command detect_errors="exit_code">
    <![CDATA[
        #if $infile.ext == 'imzml'
            cp '${infile.extra_files_path}/imzml' infile.imzML &&
            cp '${infile.extra_files_path}/ibd' infile.ibd &&
        #elif $infile.ext == 'analyze75'
            cp '${infile.extra_files_path}/hdr' infile.hdr &&
            cp '${infile.extra_files_path}/img' infile.img &&
            cp '${infile.extra_files_path}/t2m' infile.t2m &&
        #else
            ln -s $infile infile.RData &&
        #end if
        cat '${MSI_mzplots}' &&
        Rscript '${MSI_mzplots}'
    ]]>
    </command>
    <configfiles>
        <configfile name="MSI_mzplots"><![CDATA[
################################# load libraries and read file #########################

library(Cardinal)
library(gridExtra)
library(KernSmooth)

## Read MALDI Imaging dataset

#if $infile.ext == 'imzml'
    msidata <- readMSIData('infile.imzML')
#elif $infile.ext == 'analyze75'
    msidata <- readMSIData('infile.hdr')
#else
    load('infile.RData')
#end if

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

## Number of features (mz)
maxfeatures = length(features(msidata))
## Range mz
minmz = round(min(mz(msidata)), digits=2)
maxmz = round(max(mz(msidata)), digits=2)
## Number of spectra (pixels)
pixelcount = length(pixels(msidata))
## Range x coordinates
minimumx = min(coord(msidata)[,1])
maximumx = max(coord(msidata)[,1])
## Range y coordinates
minimumy = min(coord(msidata)[,2])
maximumy = max(coord(msidata)[,2])
## Range of intensities
minint = round(min(spectra(msidata)[]), digits=2)
maxint = round(max(spectra(msidata)[]), digits=2)
medint = round(median(spectra(msidata)[]), digits=2)
## Number of intensities > 0
npeaks= sum(spectra(msidata)[]>0)
## Spectra multiplied with mz (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)

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

## if TRUE write processinginfo if no write FALSE

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

properties = c("Number of mz features",
               "Range of mz values [Da]",
               "Number of pixels", 
               "Range of x coordinates", 
               "Range of y coordinates",
               "Range of intensities", 
               "Median of intensities",
               "Intensities > 0",
               "Number of zero TICs",
               "Preprocessing", 
               "Normalization", 
               "Smoothing",
               "Baseline reduction",
               "Peak picking",
               "Centroided")

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

property_df = data.frame(properties, values)


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


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

title(main=paste0("Plotted mass spectra for file: \n\n", "$infile.display_name"))


############################# I) numbers ####################################
#############################################################################
grid.table(property_df, rows= NULL)

counting = 2

    outputmatrix = matrix(mz(msidata), ncol=1, byrow=TRUE)
    colnames(outputmatrix) = "m/z"

if (npeaks > 0)
{
    pixeldf = data.frame(matrix(ncol = 2, nrow=0))

    #for $chosenpixel in $repeatpixel: 


        ### is x and y which was put in to define pixel valid coordinates? 
        pixelisvalid = as.character($chosenpixel.inputx %in% coord(msidata)\$x & $chosenpixel.inputy %in% coord(msidata)\$y)
        pixelname = paste0("x=", $chosenpixel.inputx,", ", "y=", $chosenpixel.inputy) 
        pixeldf = rbind(pixeldf, cbind(pixelname, pixelisvalid))


############################# II) control image #############################
#############################################################################


    if (pixelisvalid == "TRUE")
    {


        image(msidata, mz=$chosenpixel.inputmz, 
              ylim = c(maximumy+(0.2*maximumy),minimumy-1),colorkey=FALSE, plusminus = $chosenpixel.plusminusinDalton, contrast.enhance = "histogram", 
              main= paste0("x= ",$chosenpixel.inputx, ", y= ", $chosenpixel.inputy))

        abline(v=$chosenpixel.inputx, col ="$chosenpixel.inputcolour", lty="$chosenpixel.inputtype", lwd=$chosenpixel.inputwidth)
        abline(h=$chosenpixel.inputy, col ="$chosenpixel.inputcolour", lty="$chosenpixel.inputtype", lwd=$chosenpixel.inputwidth)


        ##################### III) plot full mass spectrum ##########################
        #############################################################################

        plot(msidata, coord=list(x=$chosenpixel.inputx, y=$chosenpixel.inputy))



            ##################### IV) plot zoom-in mass spectrum ##########################
            #############################################################################

        #if $chosenpixel.zoomedplot:
            #for $token in $chosenpixel.zoomedplot:

                minmasspixel = features(msidata, mz=$token.xlimmin)
                maxmasspixel = features(msidata, mz=$token.xlimmax)

                plot(msidata[minmasspixel:maxmasspixel,], coord=list(x=$chosenpixel.inputx, y=$chosenpixel.inputy), 
                     xlim= c($token.xlimmin,$token.xlimmax))

            #end for
        #end if

        ##################### V) Output with mz and intensities #####################
        #############################################################################


        ### for each repeat a new intensity column for the new pixel is added
        outputmatrix = cbind(outputmatrix, spectra(msidata)[,pixels(msidata, coord=list(x=$chosenpixel.inputx, y=$chosenpixel.inputy))])
        colnames(outputmatrix)[counting] = paste0("x= ",$chosenpixel.inputx, ", y= ", $chosenpixel.inputy, " intensity")
        counting = counting+1

    }else{
        print("These pixel coordinates did not correspond to a real pixel")}

#end for

    colnames(pixeldf) = c("pixel coordinates", "coordinates were found in this file")
    plot(0,type='n',axes=FALSE,ann=FALSE)
    title(main=paste0("Overview of chosen pixel for file:\n", "$infile.display_name"))
    grid.table(pixeldf, rows= NULL)

    dev.off()

        write.table(outputmatrix, file="$tabularmatrix", quote = FALSE, row.names = FALSE, col.names=TRUE, sep = "\t")
}else{
    print("Inputfile has no intensities > 0")
    dev.off()
}
    ]]></configfile>
    </configfiles>
    <inputs>
        <param name="infile" type="data" format="imzml,rdata,analyze75" label="Inputfile as imzML, Analyze7.5 or Cardinal MSImageSet saved as RData"
            help="Upload composite datatype imzml (ibd+imzML) or analyze75 (hdr+img+t2m) or regular upload .RData (Cardinal MSImageSet)"/>
        <repeat name="repeatpixel" title="Plot mass spectra for pixel of interest" min="1" max="20">
            <param name="inputx" type="integer" value="" label="x-coordinate of pixel of interest" help="x-value of the pixel of interest"/>
            <param name="inputy" type="integer" value="" label="y-coordinate of pixel of interest" help="y-value of the pixel of interest"/>
            <param name="inputmz" type="float" value="1296.7" label="Next parameters are to control heatmap image which will be plotted, here mz in Dalton" help="mz will be displayed as heatmap and the pixel of interest will be visualized by the intersection of two lines"/>
            <param name="plusminusinDalton" value="0.25" type="float" label="mass range for this mz value" help="plusminus mass window in Dalton"/>
            <param name="inputcolour" type="select" label="select the colour for the lines at x and y position">
                <option value="white" selected="True">white</option>
                <option value="black">black</option>
                <option value="grey">grey</option>
                <option value="blue">blue</option>
                <option value="red">red</option>
                <option value="green">green</option>
            </param>
            <param name="inputtype" type="select" label="select the line type for the lines at x and y position">
                <option value="solid" selected="True">solid</option>
                <option value="dashed">dashed</option>
                <option value="dotted">dotted</option>
                <option value="longdash">longdash</option>
            </param>
            <param name="inputwidth" type="integer" value="2" label="select the width of the lines at x and y position"/>
            <repeat name="zoomedplot" title="Zoomed in plots with mz min and mz max to define the plot window" min="0" max="50">
                <param name="xlimmin" type="integer" value="" label="lower boundary in Dalton for plotting window" help="minimum mz for zoomed in window"/>
                <param name="xlimmax" type="integer" value="" label="upper boundary in Dalton for plotting window" help="maximum mz for zoomed in window"/>
            </repeat>
        </repeat>
    </inputs>
    <outputs>
        <data format="pdf" name="plots" from_work_dir="mzplots.pdf" label = "${tool.name} on $infile.display_name"/>
        <data format="tabular" name="tabularmatrix" label="${tool.name} on $infile.display_name" />
    </outputs>
    <tests>
        <test>
            <param name="infile" value="" ftype="imzml">
                <composite_data value="Example_Continuous.imzML"/>
                <composite_data value="Example_Continuous.ibd"/>
            </param>
            <repeat name="repeatpixel">
                <param name="plusminusinDalton" value="0.25"/>
                <param name="inputx" value="3"/>
                <param name="inputy" value="3"/>
                <repeat name="zoomedplot">
                    <param name="xlimmin" value="550"/>
                    <param name="xlimmax" value="555"/>
                </repeat>
                <repeat name="zoomedplot">
                    <param name="xlimmin" value="750"/>
                    <param name="xlimmax" value="800"/>
                </repeat>
                <repeat name="zoomedplot">
                    <param name="xlimmin" value="400"/>
                    <param name="xlimmax" value="420"/>
                </repeat>
            </repeat>
            <repeat name="repeatpixel">
                <param name="plusminusinDalton" value="0.25"/>
                <param name="inputx" value="2"/>
                <param name="inputy" value="2"/>
            </repeat>
            <repeat name="repeatpixel">
                <param name="plusminusinDalton" value="0.25"/>
                <param name="inputx" value="1"/>
                <param name="inputy" value="1"/>
            </repeat>
            <output name="plots" file="Plot_imzml.pdf" compare="sim_size" delta="20000"/>
            <output name="tabularmatrix" file="Matrix_imzml.txt"/>
        </test>

        <test>
            <param name="infile" value="" ftype="analyze75">
                <composite_data value="Analyze75.hdr"/>
                <composite_data value="Analyze75.img"/>
                <composite_data value="Analyze75.t2m"/>
            </param>
            <repeat name="repeatpixel">
                <param name="plusminusinDalton" value="0.25"/>
                <param name="inputx" value="5"/>
                <param name="inputy" value="2"/>
                <repeat name="zoomedplot">
                    <param name="xlimmin" value="840"/>
                    <param name="xlimmax" value="850"/>
                </repeat>
            </repeat>
            <repeat name="repeatpixel">
                <param name="plusminusinDalton" value="0.25"/>
                <param name="inputx" value="2"/>
                <param name="inputy" value="2"/>
            </repeat>
            <output name="plots" file="Plot_analyze75.pdf" compare="sim_size" delta="20000"/>
            <output name="tabularmatrix" file="Matrix_analyze75.txt"/>
        </test>

        <test>
            <param name="infile" value="preprocessing_results1.RData" ftype="rdata"/>
            <repeat name="repeatpixel">
                <param name="plusminusinDalton" value="0.25"/>
                <param name="inputx" value="2"/>
                <param name="inputy" value="2"/>
                <repeat name="zoomedplot">
                     <param name="xlimmin" value="222"/>
                     <param name="xlimmax" value="244"/>
                 </repeat>
            </repeat>
            <output name="plots" file="Plot_rdata.pdf" compare="sim_size" delta="20000"/>
            <output name="tabularmatrix" file="Matrix_rdata.txt"/>
        </test>
        <test>
            <param name="infile" value="LM8_file16.rdata" ftype="rdata"/>
            <param name="plusminusinDalton" value="0.1"/>
            <param name="inputx" value="1"/>
            <param name="inputy" value="1"/>
            <repeat name="repeatpixel">
                <param name="plusminusinDalton" value="0.25"/>
                <param name="inputx" value="2"/>
                <param name="inputy" value="2"/>
               <repeat name="zoomedplot">
                    <param name="xlimmin" value="1000"/>
                    <param name="xlimmax" value="1050"/>
                </repeat>
            </repeat>
            <output name="plots" file="Plot_LM8_file16.pdf" compare="sim_size" delta="20000"/>
            <output name="tabularmatrix" file="Matrix_LM8.txt"/>
        </test>
    </tests>
    <help><![CDATA[

Returns a full mass-spectrum plot and peaklist output with masses and intensities for the chosen pixel. Input needs the x and the y coordinates of the pixel of interest. 
Additionally zoom into mass-spectra plots is possible by providing the minimum and maximum mz value to define the limits of the plot.  
To have a visual control that the right pixel was chosen, a heatmap of a mass in Dalton which can be specified will be plotted and two intersecting lines will show where the chosen pixel is located in the ion image. 

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

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

The output of this tool contains a heatmap of the mass of interest with two lines intersecting at the pixel of interest. Then the full mass-spectrum plot is obtained and if chosen also several zoomed in mass spectra. A peaklist with masses and intensities for this pixel is exported as tabular file. 

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