view msi_filtering.xml @ 0:f17d3f1a065f draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/msi_filtering commit 3363c40790b0d64a085f980980f4289165eed27f

<tool id="mass_spectrometry_imaging_filtering" name="MSI filtering" version="1.7.0">
    <description>tool for filtering mass spectrometry imaging data</description>
    <requirements>
        <requirement type="package" version="1.7.0">bioconductor-cardinal</requirement>
        <requirement type="package" version="2.2.1">r-gridextra</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_subsetting}' &&
        echo ${MSI_subsetting} &&
        Rscript '${MSI_subsetting}'

    ]]>
    </command>
    <configfiles>
        <configfile name="MSI_subsetting"><![CDATA[


################################# load libraries and read file #########################


library(Cardinal)
library(gridExtra)

## 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

###################################### inputfile properties in numbers ######################

#if $outputs.outputs_select == "quality_control"
    ## 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])
    ## 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)
    ## median TIC
    medint = round(median(TICs), digits=2)
    ## Store features for QC plot
    featuresinfile = mz(msidata)
#end if


###################################### filtering of pixels ######################
#if $inputpixels:
    input_list = read.delim("$inputpixels", header = FALSE, 
            na.strings=c("","NA", "#NUM!", "#ZAHL!"), stringsAsFactors = FALSE)
    validpixels = input_list[,$pixel_column] %in% names(pixels(msidata))

            if (validpixels != 0)
        {
            pixelsofinterest = pixels(msidata)[names(pixels(msidata)) %in% input_list[validpixels,$pixel_column]]
            msidata = msidata[,pixelsofinterest]
            numberpixels = length(input_list[,$pixel_column])
        }else {
            numberpixels = 0
        }


#else
    input_list = data.frame(0, 0)
    validpixels=0
    numberpixels = 0
#end if



###################################### filtering of features ######################

#if $inputfeatures:
    input_features = read.delim("$inputfeatures", header = FALSE,
                 na.strings=c("","NA", "#NUM!", "#ZAHL!"), stringsAsFactors = FALSE)
    validfeatures = input_features[,$feature_column] %in% names(features(msidata)) 

            if (validfeatures != 0)
        {
            featuresofinterest = features(msidata)[names(features(msidata)) %in% input_features[validfeatures,$feature_column]]
            msidata = msidata[featuresofinterest,]
            numberfeatures = length(input_features[,$feature_column])
        } else {
            numberfeatures = 0
        }


#else
    input_features = data.frame(0, 0)
    validfeatures = 0
    numberfeatures = 0
#end if






# save msidata as Rfile
save(msidata, file="$msidata_filtered")

###################################### outputfile properties in numbers ######################

#if $outputs.outputs_select == "quality_control"

## Number of features (mz)
maxfeatures2 = length(features(msidata))
## Range mz
minmz2 = round(min(mz(msidata)), digits=2)
maxmz2 = round(max(mz(msidata)), digits=2)
## Number of spectra (pixels)
pixelcount2 = length(pixels(msidata))
## Range x coordinates
minimumx2 = min(coord(msidata)[,1])
maximumx2 = max(coord(msidata)[,1])
## Range y coordinates
minimumy2 = min(coord(msidata)[,2])
maximumy2 = max(coord(msidata)[,2])
## Number of intensities > 0
npeaks2= sum(spectra(msidata)[]>0)
## Spectra multiplied with mz (potential number of peaks)
numpeaks2 = ncol(spectra(msidata)[])*nrow(spectra(msidata)[])
## Percentage of intensities > 0
percpeaks2 = round(npeaks2/numpeaks2*100, digits=2)
## Number of empty TICs
TICs2 = colSums(spectra(msidata)[]) 
NumemptyTIC2 = sum(TICs2 == 0)
## median TIC
medint2 = round(median(TICs2), digits=2)


properties = c("Number of mz features",
               "Range of mz values [Da]",
               "Number of pixels", 
               "Range of x coordinates", 
               "Range of y coordinates",
               "Intensities > 0",
               "Median TIC per pixel",
               "Number of zero TICs", 
               paste0("# pixels in ", "$inputpixels.display_name"), 
               paste0("# mz in ", "$inputfeatures.display_name"))

before = c(paste0(maxfeatures), 
           paste0(minmz, " - ", maxmz), 
           paste0(pixelcount), 
           paste0(minimumx, " - ", maximumx),  
           paste0(minimumy, " - ", maximumy), 
           paste0(percpeaks, " %"), 
           paste0(medint),
           paste0(NumemptyTIC), 
           paste0("input pixels: ", numberpixels),
           paste0("input mz: ", numberfeatures))

filtered = c(paste0(maxfeatures2), 
           paste0(minmz2, " - ", maxmz2), 
           paste0(pixelcount2), 
           paste0(minimumx2, " - ", maximumx2),  
           paste0(minimumy2, " - ", maximumy2), 
           paste0(percpeaks2, " %"), 
           paste0(medint2),
           paste0(NumemptyTIC2), 
           paste0("valid pixels: ", sum(validpixels)),
           paste0("valid mz: ", sum(validfeatures)))


property_df = data.frame(properties, before, filtered)



######################################## PDF QC #############################################


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

    title(main=paste0("Qualitycontrol of filtering tool for file: \n\n", "$infile.display_name"))


    grid.table(property_df, rows= NULL)


    ### heatmap image as visual pixel control


    image(msidata, mz=$outputs.inputmz, plusminus = $outputs.plusminus_dalton, contrast.enhance = "none", 
          main= paste0($outputs.inputmz," ± ", $outputs.plusminus_dalton, " Da"), ylim = c(maximumy2+0.2*maximumy2,minimumy2-0.2*minimumy2))

    ### control features which are left

    par(mfrow = c(2,1))
    plot(featuresinfile, ylab = "m/z in Dalton", xlab = "feature index")
    plot(mz(msidata), ylab = "m/z in Dalton", xlab = "feature index")


    dev.off()

#end if

######################################## intensity matrix ##################################

#if $output_matrix:

if (length(features(msidata))> 0 & length(pixels(msidata)) > 0)
{

    spectramatrix = spectra(msidata)
    rownames(spectramatrix) = mz(msidata)
    newmatrix = rbind(pixels(msidata), 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="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)"/>
        <param name="inputpixels" type="data" optional="true" format="tabular" label="pixels for filtering of MSI data"
            help="tabular file with pixels of interest in the form x = 1, y = 1"/>
        <param name="pixel_column" data_ref="inputpixels" optional="true" label="Column with pixels" type="data_column" />
        <param name="inputfeatures" type="data" optional="true" format="tabular" label="features for filtering of MSI data"
            help="tabular file with masses of interest in the form mz = 800.05"/>
        <param name="feature_column" data_ref="inputfeatures" optional="true" label="Column with features" type="data_column" />

        <conditional name="outputs">
           <param name="outputs_select" type="select" label="Quality control output">
               <option value="quality_control" selected="True">yes</option>
               <option value="no_quality_control" >no</option>
           </param>
           <when value="quality_control">
              <param name="inputmz" type="float" value="1296.7" label="Mass for which a heatmap image will be drawn" help="Use a mass which is still present in all pixels to control if the pixel filtering went well"/>
              <param name="plusminus_dalton" value="0.25" type="float" label="mass range for mz value" help="plusminus mass window in Dalton"/>
           </when>
         </conditional>
         <param name="output_matrix" type="boolean" display="radio" label="Intensity matrix output"/>
    </inputs>
    <outputs>
        <data format="rdata" name="msidata_filtered" label="${tool.name} on $infile.display_name"/>
        <data format="pdf" name="filtering_qc" from_work_dir="filtertool_QC.pdf" label = "QC ${tool.name} on $infile.display_name">
            <filter>outputs["outputs_select"] == "quality_control"</filter>
        </data>
        <data format="tabular" name="matrixasoutput" label="matrix ${tool.name} on $infile.display_name">
            <filter>output_matrix</filter>
        </data>
    </outputs>

    <tests>
        <test expect_num_outputs="2">
            <param name="infile" value="" ftype="imzml">
                <composite_data value="Example_Continuous.imzML"/>
                <composite_data value="Example_Continuous.ibd"/>
            </param>
            <param name="inputpixels" ftype="tabular" value = "inputpixels.tabular"/>
            <param name="pixel_column" value="1"/>
            <param name="inputfeatures" ftype="tabular" value = "inputfeatures.tabular"/>
            <param name="feature_column" value="2"/>

            <conditional name="outputs">
                <param name="outputs_select" value="quality_control"/>
                    <param name="inputmz" value="328.9"/>
                    <param name="plusminus_dalton" value="0.25"/>
            </conditional>
            <output name="filtering_qc" file="imzml_filtered.pdf" compare="sim_size" delta="20000"/>
            <output name="msidata_filtered" file="imzml_filtered.RData" compare="sim_size" />
        </test>
        <test expect_num_outputs="3">
           <param name="infile" value="" ftype="analyze75">
                <composite_data value="Analyze75.hdr"/>
                <composite_data value="Analyze75.img"/>
                <composite_data value="Analyze75.t2m"/>
            </param>
            <param name="inputpixels" ftype="tabular" value = "inputpixels2.tabular"/>
            <param name="pixel_column" value="1"/>
            <param name="inputfeatures" ftype="tabular" value = "featuresofinterest2.tabular"/>
            <param name="feature_column" value="1"/>
            <conditional name="outputs">
                <param name="outputs_select" value="quality_control"/>
                    <param name="inputmz" value="702"/>
                    <param name="plusminus_dalton" value="0.25"/>
            </conditional>
            <param name="output_matrix" value="True"/>
            <output name="filtering_qc" file="analyze_filtered.pdf" compare="sim_size" delta="20000"/>
            <output name="msidata_filtered" file="analyze_filtered.RData" compare="sim_size" />
            <output name="matrixasoutput" file="analyze_matrix.tabular"/>
        </test>
        <test expect_num_outputs="1">
           <param name="infile" value="" ftype="analyze75">
                <composite_data value="Analyze75.hdr"/>
                <composite_data value="Analyze75.img"/>
                <composite_data value="Analyze75.t2m"/>
            </param>
            <conditional name="outputs">
                <param name="outputs_select" value="no_quality_control"/>
            </conditional>
            <output name="msidata_filtered" file="analyze_originaloutput.RData" compare="sim_size" />
        </test>
        <test expect_num_outputs="2">
            <param name="infile" value="preprocessing_results1.RData" ftype="rdata"/>
            <conditional name="outputs">
                <param name="outputs_select" value="no_quality_control"/>
            </conditional>
            <param name="output_matrix" value="True"/>
            <output name="matrixasoutput" file="rdata_matrix.tabular"/>
        </test>
    </tests>
    <help>
        <![CDATA[

This tool can filter three types of mass-spectrometry imaging files (see below) for pixels and features of interest. This can be used to keep only pixels in a regions of interest.
For filtering at least one valid pixel/feature is needed otherwise no filtering will be performed.

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 is a subsetted Cardinal "MSImageSet" with the variable name "msidata" saved as .RData. 
        ]]>
    </help>
    <citations>
        <citation type="doi">10.1093/bioinformatics/btv146</citation>
    </citations>
</tool>