comparison maldi_quant_preprocessing.xml @ 4:82b1de5c142b draft default tip

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/MALDIquant commit f1e1cd260ef2884d0ba12e2b614df3c72d0934dc

3:aa81463e21ea

<tool id="maldi_quant_preprocessing" name="MALDIquant preprocessing" version="@VERSION@.3">
    <description>
        Preprocessing of mass-spectrometry imaging data
    </description>
    <macros>
        <import>maldi_macros.xml</import>

            cp '${infile.extra_files_path}/img' infile.img &&
            cp '${infile.extra_files_path}/t2m' infile.t2m &&
            du infile.hdr &&
            du infile.img &&
            du -s -B1 infile.hdr &&
        #else
            ln -s $infile infile.RData &&
        #end if
        Rscript "${maldi_quant_preprocessing}" &&

        mkdir $outfile_imzml.files_path &&
        mv ./out.imzMl "${os.path.join($outfile_imzml.files_path, 'imzml')}" | true &&

        coordinates_info = cbind(coordinates(maldi_data)[,1:2], c(1:length(maldi_data)))
    #elif $infile.ext == 'analyze75'
        ## Import analyze7.5 file
        maldi_data = importAnalyze( 'infile.hdr' )
        coordinates_info = cbind(coordinates(maldi_data)[,1:2], c(1:length(maldi_data)))
    #else
        loadRData <- function(fileName){
        ##loads an RData file, and returns it
        load(fileName)
        get(ls()[ls() != "fileName"])
        }
        msidata = loadRData('infile.RData')
        ## save coordinates
        cardinal_coordinates = as.matrix(Cardinal::coord(msidata)[,1:2])
        ## save mz values
        cardinal_mzs = Cardinal::mz(msidata)
        ## create MALDIquant MassSpectrum object, order of pixels in iData is same as in coord(msidata):
        maldi_data = list()
        for(number_spectra in 1:ncol(msidata)){
        maldi_data[[number_spectra]] = MALDIquant::createMassSpectrum(mass = cardinal_mzs, intensity = iData(msidata)[,number_spectra])
        }
    #end if

#end if

## Quality control plots during preprocessing

            ## only if there are empty spectra to remove

            if (length(findEmptyMassObjects(maldi_data))>0)

                {
                    #if $infile.ext == 'rdata'
                        cardinal_coordinates = cardinal_coordinates[-findEmptyMassObjects(maldi_data),,drop=FALSE] ## remove coordinates of empty spectra for Cardinal RData input
                    #end if

                    maldi_data = removeEmptyMassObjects(maldi_data)
            }
        #end if

        ## QC plot

dev.off()

## export imzML file
if (length(maldi_data)>0){
    #if $infile.ext == 'rdata'
        MALDIquantForeign::exportImzMl(maldi_data, file="out.imzMl", processed=$export_processed, coordinates=cardinal_coordinates)
    #else
        MALDIquantForeign::exportImzMl(maldi_data, file="out.imzMl", processed=$export_processed)
    #end if

}else{"All spectra are empty, outputfiles will be empty,too."}

    ]]>
        </configfile>
    </configfiles>
    <inputs>
        <param name="infile" type="data" format="imzml,rdata,analyze75" label="MSI data" help="Input file as imzML (composite upload), or Cardinal MSImageSet saved as RData (regular upload). The file must be in profile mode, not centroided."/>
        <conditional name="restriction_conditional">
            <param name="restriction" type="select" label="Use only spectra of interest" help="This option only works for imzML files">
                <option value="no_restriction" selected="True">No, calculate on entire file</option>
                <option value="restrict">Yes, restrict to spectra of interest</option>
            </param>

                    </param>

                    <param name="snr" type="integer" value="2" label="Signal-to-noise-ratio"/>
                    <param name="allow_nomatch" type="boolean" label="Allow no matches" help="Don't throw an error when less than 2 reference m/z were found in a spectrum" truevalue="TRUE" falsevalue="FALSE"/>
                    <param name="empty_nomatch" type="boolean" label="Empty no matches" help="If TRUE the intensity values of MassSpectrum or MassPeaks objects with missing (NA) warping functions are set to zero" truevalue="TRUE" falsevalue="FALSE"/>
                    <param name="remove_empty" type="boolean" label="Remove empty spectra" truevalue="TRUE" falsevalue="FALSE" help="For Cardinal RData files this step can only be performed if pixel annotations were provided"/>

                    <conditional name="reference_for_alignment">
                        <param name="align_ref" type="select" label="Reference" help="If given, samples will be aligned to reference, use internal calibrants to perform m/z calibration">
                            <option value="no_reference" selected="True">no reference</option>
                            <option value="yes_reference">reference from tabular file</option>

                <param name="smooth_method" value="SavitzkyGolay"/>
                <param name="method" value="Basline"/>
                <param name="baseline_method" value ="TopHat"/>
            </conditional>
            <output name="outfile_imzml" ftype="imzml" file="preprocessing1.imzml.txt" lines_diff="4">
                <extra_files type="file" file="outfile1.imzml" name="imzml" lines_diff="6"/>
                <extra_files type="file" file="outfile1.ibd" name="ibd" compare="sim_size"/>
            </output>
            <output name="plots" file="Preprocessing1_QC.pdf" compare="sim_size"/>
        </test>
        <test>
            <param name="infile" value="msidata_1.RData" ftype="rdata"/>
            <conditional name="methods_conditional">
                <param name="method" value="Align"/>
                <param name="warping_method" value="lowess"/>
                <param name="halfWindowSize" value="5"/>
                <param name="tolerance" value="0.001"/>
                <param name="allow_nomatch" value="TRUE"/>
                <param name="remove_empty" value="TRUE"/>
                <param name="empty_nomatch" value="TRUE"/>
                <conditional name="reference_for_alignment">
                    <param name="align_ref" value="yes_reference"/>
                    <param name="reference_file" value="inputpeptides.tabular" ftype="tabular"/>
                </conditional>
            </conditional>
            <output name="outfile_imzml" ftype="imzml" file="preprocessing2.imzml.txt" lines_diff="4">
                <extra_files type="file" file="outfile2.imzml" name="imzml" lines_diff="6"/>
                <extra_files type="file" file="outfile2.ibd" name="ibd" compare="sim_size"/>
            </output>
            <output name="plots" file="Preprocessing2_QC.pdf" compare="sim_size"/>
        </test>
        <test>
            <param name="infile" value="" ftype="imzml">
                <composite_data value="Example_Continuous.imzML"/>
                <composite_data value="Example_Continuous.ibd"/>

            <conditional name="methods_conditional">
                <param name="method" value="Calibrate"/>
                <param name="calibrate_method" value="median"/>
            </conditional>
            <output name="outfile_imzml" ftype="imzml" file="preprocessing3.imzml.txt" lines_diff="4">
                <extra_files type="file" file="outfile3.imzml" name="imzml" lines_diff="6"/>
                <extra_files type="file" file="outfile3.ibd" name="ibd" compare="sim_size"/>
            </output>
            <output name="plots" file="Preprocessing3_QC.pdf" compare="sim_size"/>
        </test>
    </tests>

**Input data**

- MSI data: 2 types of input data can be used:

    - imzml file (upload imzml and ibd file via the "composite" function) `Introduction to the imzml format <https://ms-imaging.org/wp/imzml/>`_
    - Cardinal "MSImageSet" data saved as .RData

- Optional: Tabular file with pixel coordinates to restrict reading of imzML files to coordinates of interest. Tabular files with any header name or no header at all are supported. 

    ::

4:82b1de5c142b

<tool id="maldi_quant_preprocessing" name="MALDIquant preprocessing" version="@VERSION@.0">
    <description>
        Preprocessing of mass-spectrometry imaging data
    </description>
    <macros>
        <import>maldi_macros.xml</import>

            cp '${infile.extra_files_path}/img' infile.img &&
            cp '${infile.extra_files_path}/t2m' infile.t2m &&
            du infile.hdr &&
            du infile.img &&
            du -s -B1 infile.hdr &&
        #end if
        Rscript "${maldi_quant_preprocessing}" &&

        mkdir $outfile_imzml.files_path &&
        mv ./out.imzMl "${os.path.join($outfile_imzml.files_path, 'imzml')}" | true &&

        coordinates_info = cbind(coordinates(maldi_data)[,1:2], c(1:length(maldi_data)))
    #elif $infile.ext == 'analyze75'
        ## Import analyze7.5 file
        maldi_data = importAnalyze( 'infile.hdr' )
        coordinates_info = cbind(coordinates(maldi_data)[,1:2], c(1:length(maldi_data)))
    #end if

#end if

## Quality control plots during preprocessing

            ## only if there are empty spectra to remove

            if (length(findEmptyMassObjects(maldi_data))>0)

                {
                    maldi_data = removeEmptyMassObjects(maldi_data)
            }
        #end if

        ## QC plot

dev.off()

## export imzML file
if (length(maldi_data)>0){
        MALDIquantForeign::exportImzMl(maldi_data, file="out.imzMl", processed=$export_processed)

}else{"All spectra are empty, outputfiles will be empty,too."}

    ]]>
        </configfile>
    </configfiles>
    <inputs>
        <param name="infile" type="data" format="imzml,analyze75" label="MSI data" help="Input file as imzML (composite upload). The file must be in profile mode, not centroided."/>
        <conditional name="restriction_conditional">
            <param name="restriction" type="select" label="Use only spectra of interest" help="This option only works for imzML files">
                <option value="no_restriction" selected="True">No, calculate on entire file</option>
                <option value="restrict">Yes, restrict to spectra of interest</option>
            </param>

                    </param>

                    <param name="snr" type="integer" value="2" label="Signal-to-noise-ratio"/>
                    <param name="allow_nomatch" type="boolean" label="Allow no matches" help="Don't throw an error when less than 2 reference m/z were found in a spectrum" truevalue="TRUE" falsevalue="FALSE"/>
                    <param name="empty_nomatch" type="boolean" label="Empty no matches" help="If TRUE the intensity values of MassSpectrum or MassPeaks objects with missing (NA) warping functions are set to zero" truevalue="TRUE" falsevalue="FALSE"/>
                    <param name="remove_empty" type="boolean" label="Remove empty spectra" truevalue="TRUE" falsevalue="FALSE"/>

                    <conditional name="reference_for_alignment">
                        <param name="align_ref" type="select" label="Reference" help="If given, samples will be aligned to reference, use internal calibrants to perform m/z calibration">
                            <option value="no_reference" selected="True">no reference</option>
                            <option value="yes_reference">reference from tabular file</option>

                <param name="smooth_method" value="SavitzkyGolay"/>
                <param name="method" value="Basline"/>
                <param name="baseline_method" value ="TopHat"/>
            </conditional>
            <output name="outfile_imzml" ftype="imzml" file="preprocessing1.imzml.txt" lines_diff="4">
                <extra_files type="file" file="outfile1.imzml" name="imzml" lines_diff="8"/>
                <extra_files type="file" file="outfile1.ibd" name="ibd" compare="sim_size"/>
            </output>
            <output name="plots" file="Preprocessing1_QC.pdf" compare="sim_size"/>
        </test>
        <test>
            <param name="infile" value="" ftype="imzml">
                <composite_data value="Example_Continuous.imzML"/>
                <composite_data value="Example_Continuous.ibd"/>

            <conditional name="methods_conditional">
                <param name="method" value="Calibrate"/>
                <param name="calibrate_method" value="median"/>
            </conditional>
            <output name="outfile_imzml" ftype="imzml" file="preprocessing3.imzml.txt" lines_diff="4">
                <extra_files type="file" file="outfile3.imzml" name="imzml" lines_diff="8"/>
                <extra_files type="file" file="outfile3.ibd" name="ibd" compare="sim_size"/>
            </output>
            <output name="plots" file="Preprocessing3_QC.pdf" compare="sim_size"/>
        </test>
    </tests>

**Input data**

- MSI data: 2 types of input data can be used:

    - imzml file (upload imzml and ibd file via the "composite" function) `Introduction to the imzml format <https://ms-imaging.org/imzml/>`_

- Optional: Tabular file with pixel coordinates to restrict reading of imzML files to coordinates of interest. Tabular files with any header name or no header at all are supported. 

    ::