comparison msi_combine.xml @ 5:ff91e78b5c5c draft

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

4:d05bd881af3d

<tool id="mass_spectrometry_imaging_combine" name="MSI combine" version="1.10.0.2">
    <description>
        combine several mass spectrometry imaging datasets into one
    </description>
    <requirements>
        <requirement type="package" version="1.10.0">bioconductor-cardinal</requirement>

############## reading files and changing pixel coordinates ###################

#for $i, $infile in enumerate($infiles):

    #if $infile.ext == 'imzml'
        msidata_$i <- readImzML('infile_${i}', mass.accuracy=$accuracy, units.accuracy = "$units")
    #elif $infile.ext == 'analyze75'
        msidata_$i <- readAnalyze('infile_${i}')
    #else
        msidata_$i = loadRData('infile_${i}.RData')
    #end if

        sampleNames(msidata_$i) = "msidata" ## same name necessary to combine data in one single coordinate system

    ################### preparation xy shifts ##########################

    #if str( $combine_conditional.combine_method ) == 'xy_shifts':

        coord(msidata_$i)\$x = coord(msidata_$i)\$x + input_list[$i+1,$combine_conditional.column_x] ## shifts x coordinates according to tabular file
        coord(msidata_$i)\$y = coord(msidata_$i)\$y + input_list[$i+1,$combine_conditional.column_y] ## shifts y coordinates according to tabular file
        pixel_vector = append(pixel_vector, rep(paste($i+1, input_list[$i+1,$combine_conditional.column_names], sep="_"),times=ncol(msidata_$i))) ## stores file name for each pixel

        pixelcoords_$i = cbind(coord(msidata_$i)[,1:2], rep($i+1,ncol(msidata_$i)))
        #silent $pixelcoords.append('pixelcoords_'+str($i))
        colnames(pixelcoords_$i)[3] = "file_number"

    ################### preparation automatic combination ##########################

    #elif str( $combine_conditional.combine_method ) == 'automatic_combine':
        names_vector = character()
        #set escaped_element_identifier = re.sub('[^\w\-\s\[/]]', '_', str($infile.element_identifier)) ## use name of inputfile from Galaxy
        if (sum(spectra(msidata_$i))>0) ## use only valid files
        {
            if (is.null(levels(msidata_$i\$combined_sample))) ### if the file was not combined before use input file name, otherwise keep combined_sample name which was assigned before
            {
            names_vector = append(names_vector, rep(paste($i+1, "$escaped_element_identifier", sep="_"),ncol(msidata_$i)))
            msidata_$i\$combined_sample = as.factor(names_vector)

    ## store files to combine them later and for each file check if it is valid

    #silent $msidata.append('msidata_'+str($i))
    valid_dataset = append(valid_dataset, 
         (ncol(msidata_$i)>0 & nrow(msidata_$i)>0 & sum(spectra(msidata_$i))>0))

#end for


###################### automatic combination ###################################

           ggtitle("Spatial orientation of combined data")+
           theme_bw()+
           theme(text=element_text(family="ArialMT", face="bold", size=15))+
           theme(legend.position="bottom",legend.direction="vertical")+
           guides(fill=guide_legend(ncol=4,byrow=TRUE))
    coord_labels = aggregate(cbind(x,y)~sample_name, data=position_df, mean)
    coord_labels\$file_number = gsub( "_.*$", "", coord_labels\$sample_name)
    for(file_count in 1:nrow(coord_labels))
    {combine_plot = combine_plot + annotate("text",x=coord_labels[file_count,"x"],
    y=coord_labels[file_count,"y"],label=toString(coord_labels[file_count,4]))}
    print(combine_plot)

    print("xy_shifts")

    #if str($combine_conditional.combination_true) == "yes_combi":
        print("combination with xy shifts")

        msidata_combined = do.call(combine, list(#echo ','.join($msidata)#))
        sample_names = as.factor(pixel_vector) ## the sample names are assigned to each pixel
        msidata_combined\$combined_sample = sample_names ## sample names are stored in $combined_sample slot

        ## save as (.RData)

        msidata = msidata_combined
        save(msidata, file="$msidata_combined")

    #else:
        print("no combination, only testing xy shifts")

        position_df = do.call(rbind, list(#echo ','.join($pixelcoords)#))
        position_df\$sample_name = as.factor(pixel_vector)

    #end if

    ## create PDF to show all pixels in PDF as QC

           coord_fixed()+
           ggtitle("Spatial orientation of combined data")+
           theme_bw()+
           theme(text=element_text(family="ArialMT", face="bold", size=15))+
           theme(legend.position="bottom",legend.direction="vertical")+
           theme(legend.key.size = unit(0.2, "line"), legend.text = element_text(size = 6))+
           guides(fill=guide_legend(ncol=5,byrow=TRUE))
    coord_labels = aggregate(cbind(x,y)~sample_name, data=position_df, mean)
    coord_labels\$file_number = gsub( "_.*$", "", coord_labels\$sample_name)
    for(file_count in 1:nrow(coord_labels))
    {combine_plot = combine_plot + annotate("text",x=coord_labels[file_count,"x"],

####################### optional matrix output #################################

#if $output_matrix:

    if (length(features(msidata_combined))> 0 & length(pixels(msidata_combined)) > 0)
    {
        spectramatrix = spectra(msidata_combined)
        rownames(spectramatrix) = mz(msidata_combined)
        newmatrix = rbind(pixels(msidata_combined), spectramatrix)
        write.table(newmatrix[2:nrow(newmatrix),], file="$matrixasoutput", quote = FALSE, row.names = TRUE, col.names=NA, sep = "\t")
    }else{
        print("file has no features or pixels left")
    }
#end if

    ]]></configfile>
    </configfiles>
    <inputs>
        <param name="infiles" type="data" multiple="true" format="imzml,rdata,analyze75"
            label="MSI data as imzml, analyze7.5 or Cardinal MSImageSet saved as RData"
            help="load imzml and ibd file by uploading composite datatype imzml"/>
        <param name="accuracy" type="float" value="50" label="Only for processed imzML files: enter mass accuracy to which the m/z values will be binned" help="This should be set to the native accuracy of the mass spectrometer, if known"/>
        <param name="units" display="radio" type="select" label="Only for processed imzML files: unit of the mass accuracy" help="either m/z or ppm">
            <option value="mz" >mz</option>
            <option value="ppm" selected="True" >ppm</option>
        </param>
        <conditional name="combine_conditional">
            <param name="combine_method" type="select" label="Select the way you want to combine multiple files" help="More detailed help can be found in the help section at the bottom">
                <option value="automatic_combine" selected="True" >automatic combination</option>
                <option value="xy_shifts">xy shifts by hand</option>
            </param>

                <param name="coordinates_file" type="data" format="tabular" label="datasetnames, X and y values to shift data before combining"
            help="Tabular file with three columns: 1 for the filename, 1 for the x-coordinate shift and 1 for the y-coordinate shift"/>
                <param name="column_x" data_ref="coordinates_file" label="Column with values for shift in x direction" type="data_column"/>
                <param name="column_y" data_ref="coordinates_file" label="Column with values for shift in y direction" type="data_column"/>
                <param name="column_names" data_ref="coordinates_file" label="Column with dataset names" type="data_column"/>
                <param name="combination_true" type="boolean" display="radio" truevalue="yes_combi" falsevalue="no_combi" label="Combine datasets" help = "Combination only works if x and y-shifts lead to unique pixel positions. If this is unknown use the No option to get an idea about the pixel overlap"/>
            </when>
        </conditional>
    <param name="output_matrix" type="boolean" display="radio" label="Intensity matrix output"/>
    </inputs>
    <outputs>

Options: 

- "automatic combination": files are automatically arranged in a grid, subfiles are named according to input file name
- "xy shifts by hand": each file can be moved in x and y direction according to the users need (define one tabular file in the order in which the files are loaded in the history (bottom to top) and define for each file the x and y coordinates shifts in separate columns and the file name in a third column). To test if the pixels are correctly shifted use "combine datasets: No".


Output: 

- imzML file containing multiple subfiles
- pdf that shows the pixel positions of the combined files

5:ff91e78b5c5c

<tool id="mass_spectrometry_imaging_combine" name="MSI combine" version="1.10.0.3">
    <description>
        combine several mass spectrometry imaging datasets into one
    </description>
    <requirements>
        <requirement type="package" version="1.10.0">bioconductor-cardinal</requirement>

############## reading files and changing pixel coordinates ###################

#for $i, $infile in enumerate($infiles):

#if $infile.ext == 'imzml'
    #if str($processed_cond.processed_file) == "processed":
        msidata_$i <- readImzML('infile_${i}', mass.accuracy=$processed_cond.accuracy, units.accuracy = "$processed_cond.units")
    #else
        msidata <- readImzML('infile')
    #end if
#elif $infile.ext == 'analyze75'
        msidata_$i <- readAnalyze('infile_${i}')
#else
        msidata_$i = loadRData('infile_${i}.RData')
#end if


        sampleNames(msidata_$i) = "msidata" ## same name necessary to combine data in one single coordinate system

    ################### preparation xy shifts ##########################

    #if str( $combine_conditional.combine_method ) == 'xy_shifts':

        coord(msidata_$i)\$x = coord(msidata_$i)\$x + input_list[$i+1,$combine_conditional.column_x] ## shifts x coordinates according to tabular file
        coord(msidata_$i)\$y = coord(msidata_$i)\$y + input_list[$i+1,$combine_conditional.column_y] ## shifts y coordinates according to tabular file
        pixel_vector = append(pixel_vector, rep(paste($i+1, input_list[$i+1,$combine_conditional.column_names], sep="_"),times=ncol(msidata_$i))) ## stores file name for each pixel
        msidata_$i\$combined_sample = rep(paste($i+1, input_list[$i+1,$combine_conditional.column_names], sep="_"),times=ncol(msidata_$i))
        pixelcoords_$i = cbind(coord(msidata_$i)[,1:2], rep($i+1,ncol(msidata_$i)))
        #silent $pixelcoords.append('pixelcoords_'+str($i))
        colnames(pixelcoords_$i)[3] = "file_number"

    ################### preparation automatic combination ##########################

    #elif str( $combine_conditional.combine_method ) == 'automatic_combine':
        names_vector = character()
        #set escaped_element_identifier = re.sub('[^\w\-\s\[/]]', '_', str($infile.element_identifier)) ## use name of inputfile from Galaxy
        if (sum(spectra(msidata_$i)[],na.rm=TRUE)>0) ## use only valid files
        {
            if (is.null(levels(msidata_$i\$combined_sample))) ### if the file was not combined before use input file name, otherwise keep combined_sample name which was assigned before
            {
            names_vector = append(names_vector, rep(paste($i+1, "$escaped_element_identifier", sep="_"),ncol(msidata_$i)))
            msidata_$i\$combined_sample = as.factor(names_vector)

    ## store files to combine them later and for each file check if it is valid

    #silent $msidata.append('msidata_'+str($i))
    valid_dataset = append(valid_dataset, 
         (ncol(msidata_$i)>0 & nrow(msidata_$i)>0 & sum(spectra(msidata_$i)[], na.rm=TRUE)>0))

#end for


###################### automatic combination ###################################

           ggtitle("Spatial orientation of combined data")+
           theme_bw()+
           theme(text=element_text(family="ArialMT", face="bold", size=15))+
           theme(legend.position="bottom",legend.direction="vertical")+
           guides(fill=guide_legend(ncol=4,byrow=TRUE))
    coord_labels = aggregate(cbind(x,y)~sample_name, data=position_df, mean, na.rm=TRUE, na.action="na.pass")
    coord_labels\$file_number = gsub( "_.*$", "", coord_labels\$sample_name)
    for(file_count in 1:nrow(coord_labels))
    {combine_plot = combine_plot + annotate("text",x=coord_labels[file_count,"x"],
    y=coord_labels[file_count,"y"],label=toString(coord_labels[file_count,4]))}
    print(combine_plot)

    print("xy_shifts")

    #if str($combine_conditional.combination_true) == "yes_combi":
        print("combination with xy shifts")

        ## find duplicated coordinates
        all_coordinates = do.call(rbind, list(#echo ','.join($pixelcoords)#))
        duplicated_coordinates= duplicated(all_coordinates[,1:2])| duplicated(all_coordinates[,1:2], fromLast=TRUE)
print(paste0("Number of removed duplicated coordinates: ", sum(duplicated_coordinates)/2))
        unique_coordinates = all_coordinates[!duplicated_coordinates,]

        ## remove duplicated coordinates
        datasetlist = list()
        count = 1
        for (usable_dataset in list(#echo ','.join($msidata)#)){
            pixelsofinterest = pixels(usable_dataset)[names(pixels(usable_dataset)) %in% rownames(unique_coordinates)]
            filtered_dataset = usable_dataset[,pixelsofinterest]
            if (ncol(filtered_dataset) > 0 ){
                datasetlist[[count]] = filtered_dataset}
            count = count +1}

        msidata_combined = do.call(combine, datasetlist)

        ## save as (.RData)

        msidata = msidata_combined
        save(msidata, file="$msidata_combined")

    #else:
        print("no combination, only testing xy shifts")

        position_df = do.call(rbind, list(#echo ','.join($pixelcoords)#))
        position_df\$sample_name = as.factor(pixel_vector)

print(paste0("Number of duplicated coordinates: ", sum(duplicated(position_df[,1:2]))))

    #end if

    ## create PDF to show all pixels in PDF as QC

           coord_fixed()+
           ggtitle("Spatial orientation of combined data")+
           theme_bw()+
           theme(text=element_text(family="ArialMT", face="bold", size=15))+
           theme(legend.position="bottom",legend.direction="vertical")+
           guides(fill=guide_legend(ncol=5,byrow=TRUE))
    coord_labels = aggregate(cbind(x,y)~sample_name, data=position_df, mean)
    coord_labels\$file_number = gsub( "_.*$", "", coord_labels\$sample_name)
    for(file_count in 1:nrow(coord_labels))
    {combine_plot = combine_plot + annotate("text",x=coord_labels[file_count,"x"],

####################### optional matrix output #################################

#if $output_matrix:

    if (length(features(msidata))> 0 & length(pixels(msidata)) > 0){
        spectramatrix = spectra(msidata)[]
        spectramatrix = cbind(mz(msidata),spectramatrix)
        newmatrix = rbind(c("mz | spectra", names(pixels(msidata))), spectramatrix)
        write.table(newmatrix, file="$matrixasoutput", quote = FALSE, row.names = FALSE, col.names=FALSE, sep = "\t")
    }else{
        print("file has no features or pixels left")
    }

#end if

    ]]></configfile>
    </configfiles>
    <inputs>
        <param name="infiles" type="data" multiple="true" format="imzml,rdata,analyze75"
            label="MSI data as imzml, analyze7.5 or Cardinal MSImageSet saved as RData"
            help="load imzml and ibd file by uploading composite datatype imzml"/>
        <conditional name="processed_cond">
            <param name="processed_file" type="select" label="Is the input file a processed imzML file ">
                <option value="no_processed" selected="True">not a processed imzML</option>
                <option value="processed">processed imzML</option>
            </param>
            <when value="no_processed"/>
            <when value="processed">
                <param name="accuracy" type="float" value="50" label="Mass accuracy to which the m/z values will be binned" help="This should be set to the native accuracy of the mass spectrometer, if known"/>
                <param name="units" display="radio" type="select" label="Unit of the mass accuracy" help="either m/z or ppm">
                    <option value="mz" >mz</option>
                    <option value="ppm" selected="True" >ppm</option>
                </param>
            </when>
        </conditional>
        <conditional name="combine_conditional">
            <param name="combine_method" type="select" label="Select the way you want to combine multiple files" help="More detailed help can be found in the help section at the bottom">
                <option value="automatic_combine" selected="True" >automatic combination</option>
                <option value="xy_shifts">xy shifts by hand</option>
            </param>

                <param name="coordinates_file" type="data" format="tabular" label="datasetnames, X and y values to shift data before combining"
            help="Tabular file with three columns: 1 for the filename, 1 for the x-coordinate shift and 1 for the y-coordinate shift"/>
                <param name="column_x" data_ref="coordinates_file" label="Column with values for shift in x direction" type="data_column"/>
                <param name="column_y" data_ref="coordinates_file" label="Column with values for shift in y direction" type="data_column"/>
                <param name="column_names" data_ref="coordinates_file" label="Column with dataset names" type="data_column"/>
                <param name="combination_true" type="boolean" display="radio" truevalue="yes_combi" falsevalue="no_combi" label="Combine datasets" help = "If there are duplicated pixels they will be deleted. If it is not clear if there are duplicated pixels, select No to get an idea about the pixel overlap"/>
            </when>
        </conditional>
    <param name="output_matrix" type="boolean" display="radio" label="Intensity matrix output"/>
    </inputs>
    <outputs>

Options: 

- "automatic combination": files are automatically arranged in a grid, subfiles are named according to input file name
- "xy shifts by hand": each file can be moved in x and y direction according to the users need (define one tabular file in the order in which the files are loaded in the history (bottom to top) and define for each file the x and y coordinates shifts in separate columns and the file name in a third column). To test if the pixels are correctly shifted use "combine datasets: No".
Combine datasets: Yes - Combines all datasets and removes all duplicated pixels (same x and y coordinates).

Output: 

- imzML file containing multiple subfiles
- pdf that shows the pixel positions of the combined files