comparison msi_qualitycontrol.xml @ 8:52ef77866de8 draft

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/msi_qualitycontrol commit 1c808d60243bb1eeda0cd26cb4b0a17ab05de2c0

7:b86a66dd1a16

<tool id="mass_spectrometry_imaging_qc" name="MSI Qualitycontrol" version="1.7.0.5">
    <description>
        mass spectrometry imaging QC
    </description>
    <requirements>
        <requirement type="package" version="1.7.0">bioconductor-cardinal</requirement>
        <requirement type="package" version="2.2.1">r-ggplot2</requirement>
        <requirement type="package" version="1.1_2">r-rcolorbrewer</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 '$infile' infile.RData &&
        #end if
        cat '${cardinal_qualitycontrol_script}' &&
        Rscript '${cardinal_qualitycontrol_script}'

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

  peakpickinginfo='FALSE'
} else {
  peakpickinginfo=processinginfo@peakPicking
}

### Read tabular file with peptide masses for plots and heatmap images: 

#if $peptide_file:

    input_list = read.delim("$peptide_file", header = FALSE, na.strings=c("","NA"), stringsAsFactors = FALSE)
        if (ncol(input_list) == 1)

        ### calculate how many input calibrant masses are valid: 
        inputcalibrants = calibrant_list[calibrant_list[,1]>minmz & calibrant_list[,1]<maxmz,]
        number_calibrants_in = length(calibrant_list[,1])
        number_calibrants_valid = length(inputcalibrants[,1])
#else
    ###inputcalibrants = data.frame(0,0)

    inputcalibrants = as.data.frame(matrix(, nrow = 0, ncol = 2))

    number_calibrants_in = 0
    number_calibrants_valid = 0
#end if

colnames(inputcalibrants) = c("mz", "name")

    if (length(inputmasses) != 0)
    {   for (mass in 1:length(inputmasses))
        {
          image(msidata, mz=inputmasses[mass], plusminus=$plusminus_dalton, 
          main= paste0(inputnames[mass], " (", round(inputmasses[mass], digits = 2)," ± ", $plusminus_dalton, " Da)"),
                contrast.enhance = "histogram", ylim=c(maximumy+2, 0))
        }
    } else {print("3) The inputpeptide masses were not provided or outside the mass range")}


    ## 4) Number of peaks per pixel - image

    ## 7) pca image for two components
    pca = PCA(msidata, ncomp=2) 
    par(mfrow = c(2,1))
    plot(pca, col=c("black", "darkgrey"), main="PCA for two components")
    image(pca, col=c("black", "white"),ylim=c(maximumy+2, 0),  strip=FALSE)


    ############################# III) properties over acquisition (spectra index)##########
    ##############################################################################

    </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="filename" type="text" value="" optional="true" label="Title" help="will appear in the quality report. If nothing given it will take the dataset name."/>
        <param name="peptide_file" type="data" optional="true" format="tabular" label="Text file with peptidemasses and names"
            help="first column peptide m/z, second column peptide name, tab separated file"/>
        <param name="calibrant_file" type="data" optional="true" format="tabular"
            label="Internal calibrants"
            help="Used for plot number of calibrant per spectrum and for zoomed in mass spectra"/>
        <param name="plusminus_dalton" value="0.25" type="text" label="Mass range" help="plusminus mass window in Dalton"/>
        <repeat name="calibrantratio" title="Plot fold change of two masses for each spectrum" min="0" max="10">
            <param name="mass1" value="1111" type="float" label="Mass 1" help="First mass in Dalton"/>
            <param name="mass2" value="2222" type="float" label="Mass 2" help="Second mass in Dalton"/>
            <param name="distance" value="0.25" type="float" label="Distance in Dalton" help="Distance in Da used to find peak maximum from input masses in both directions"/>
            <param name="filenameratioplot" type="text" optional="true" label="Title" help="Optional title for fold change plot."/>

        <test>
            <param name="infile" value="" ftype="imzml">
                <composite_data value="Example_Continuous.imzML" />
                <composite_data value="Example_Continuous.ibd" />
            </param>
            <param name="peptide_file" value="inputpeptides.csv" ftype="csv"/>
            <param name="calibrant_file" ftype="txt" value="inputcalibrantfile1.txt"/>
            <param name="plusminus_dalton" value="0.25"/>
            <param name="filename" value="Testfile_imzml"/>
            <repeat name="calibrantratio">
                <param name="mass1" value="111"/>
                <param name="mass2" value="222"/>
                <param name="distance" value="0.25"/>
                <param name="filenameratioplot" value = "Ratio of mass1 (111) / mass2 (222)"/>
            </repeat>
            <output name="plots" file="Testfile_qualitycontrol_imzml.pdf" compare="sim_size" delta="20000"/>
        </test>

        <test>
            <param name="infile" value="" ftype="analyze75">
                <composite_data value="Analyze75.hdr"/>
                <composite_data value="Analyze75.img"/>
                <composite_data value="Analyze75.t2m"/>
            </param>
            <param name="peptide_file" value="inputpeptides.txt" ftype="txt"/>
            <param name="calibrant_file" ftype="txt" value="inputcalibrantfile2.txt"/>
            <param name="plusminus_dalton" value="0.5"/>
            <param name="filename" value="Testfile_analyze75"/>
            <output name="plots" file="Testfile_qualitycontrol_analyze75.pdf" compare="sim_size" delta="20000"/>
        </test>

        <test>
            <param name="infile" value="preprocessing_results1.RData" ftype="rdata"/>
            <param name="plusminus_dalton" value="0.1"/>
            <param name="filename" value="Testfile_rdata"/>
            <output name="plots" file="Testfile_qualitycontrol_rdata.pdf" compare="sim_size" delta="20000"/>
        </test>
        <test>
            <param name="infile" value="LM8_file16.rdata" ftype="rdata"/>
            <param name="peptide_file" value="inputpeptides.txt" ftype="txt"/>
            <param name="calibrant_file" ftype="txt" value="inputcalibrantfile2.txt"/>
            <param name="plusminus_dalton" value="0.1"/>
            <param name="filename" value="Testfile_rdata"/>
            <output name="plots" file="LM8_file16output.pdf" compare="sim_size" delta="20000"/>
        </test>
    </tests>
    <help>
        <![CDATA[
Quality control for maldi imaging mass spectrometry data. The output of this tool contains key values and plots of the imaging data as pdf. 
For additional beautiful heatmap images use the MSI ion images tool and to plot more mass spectra use the MSI massspectra tool. 

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)



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

8:52ef77866de8

<tool id="mass_spectrometry_imaging_qc" name="MSI Qualitycontrol" version="1.10.0.0">
    <description>
        mass spectrometry imaging QC
    </description>
    <requirements>
        <requirement type="package" version="1.10.0">bioconductor-cardinal</requirement>
        <requirement type="package" version="2.2.1">r-ggplot2</requirement>
        <requirement type="package" version="1.1_2">r-rcolorbrewer</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 $infile.ext == 'imzml'
            ln -s '${infile.extra_files_path}/imzml' infile.imzML &&
            ln -s '${infile.extra_files_path}/ibd' infile.ibd &&
        #elif $infile.ext == 'analyze75'
            ln -s '${infile.extra_files_path}/hdr' infile.hdr &&
            ln -s '${infile.extra_files_path}/img' infile.img &&
            ln -s '${infile.extra_files_path}/t2m' infile.t2m &&
        #else
            ln -s '$infile' infile.RData &&
        #end if
        cat '${cardinal_qualitycontrol_script}' &&
        Rscript '${cardinal_qualitycontrol_script}'

library(KernSmooth)

## Read MALDI Imaging dataset

#if $infile.ext == 'imzml'
    msidata = readImzML('infile')
#elif $infile.ext == 'analyze75'
    msidata = readAnalyze('infile')
#else
    load('infile.RData')
#end if

  peakpickinginfo='FALSE'
} else {
  peakpickinginfo=processinginfo@peakPicking
}

### Read tabular file with masses for plots and heatmap images: 

#if $peptide_file:

    input_list = read.delim("$peptide_file", header = FALSE, na.strings=c("","NA"), stringsAsFactors = FALSE)
        if (ncol(input_list) == 1)

        ### calculate how many input calibrant masses are valid: 
        inputcalibrants = calibrant_list[calibrant_list[,1]>minmz & calibrant_list[,1]<maxmz,]
        number_calibrants_in = length(calibrant_list[,1])
        number_calibrants_valid = length(inputcalibrants[,1])
#else

    inputcalibrants = as.data.frame(matrix(, nrow = 0, ncol = 2))
    number_calibrants_in = 0
    number_calibrants_valid = 0
#end if

colnames(inputcalibrants) = c("mz", "name")

    if (length(inputmasses) != 0)
    {   for (mass in 1:length(inputmasses))
        {
          image(msidata, mz=inputmasses[mass], plusminus=$plusminus_dalton, 
          main= paste0(inputnames[mass], " (", round(inputmasses[mass], digits = 2)," ± ", $plusminus_dalton, " Da)"),
                contrast.enhance = "histogram", ylim= c(maximumy+0.2*maximumy,minimumy-0.2*minimumy))
        }
    } else {print("3) The inputpeptide masses were not provided or outside the mass range")}


    ## 4) Number of peaks per pixel - image

    ## 7) pca image for two components
    pca = PCA(msidata, ncomp=2) 
    par(mfrow = c(2,1))
    plot(pca, col=c("black", "darkgrey"), main="PCA for two components")
    image(pca, col=c("black", "white"),ylim= c(maximumy+0.2*maximumy,minimumy-0.2*minimumy),  strip=FALSE)


    ############################# III) properties over acquisition (spectra index)##########
    ##############################################################################

    </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="filename" type="text" value="" optional="true" label="Title" help="will appear in the quality report. If nothing given it will take the dataset name."/>
        <param name="peptide_file" type="data" optional="true" format="tabular" label="Text file with masses and names"
            help="first column m/z, second column name, tab separated file"/>
        <param name="calibrant_file" type="data" optional="true" format="tabular"
            label="Internal calibrants and names"
            help="Used for plot number of calibrant per spectrum and for zoomed in mass spectra"/>
        <param name="plusminus_dalton" value="0.25" type="text" label="Mass range in Dalton" help="Plusminus mass window in Dalton for calibrant and peptide plots"/>
        <repeat name="calibrantratio" title="Plot fold change of two masses for each spectrum" min="0" max="10">
            <param name="mass1" value="1111" type="float" label="Mass 1" help="First mass in Dalton"/>
            <param name="mass2" value="2222" type="float" label="Mass 2" help="Second mass in Dalton"/>
            <param name="distance" value="0.25" type="float" label="Distance in Dalton" help="Distance in Da used to find peak maximum from input masses in both directions"/>
            <param name="filenameratioplot" type="text" optional="true" label="Title" help="Optional title for fold change plot."/>

        <test>
            <param name="infile" value="" ftype="imzml">
                <composite_data value="Example_Continuous.imzML" />
                <composite_data value="Example_Continuous.ibd" />
            </param>
            <param name="peptide_file" value="inputpeptides.txt"/>
            <param name="calibrant_file" value="inputcalibrantfile1.txt"/>
            <param name="plusminus_dalton" value="0.25"/>
            <param name="filename" value="Testfile_imzml"/>
            <repeat name="calibrantratio">
                <param name="mass1" value="111"/>
                <param name="mass2" value="222"/>
                <param name="distance" value="0.25"/>
                <param name="filenameratioplot" value = "Ratio of mass1 (111) / mass2 (222)"/>
            </repeat>
            <output name="plots" file="QC_imzml.pdf" compare="sim_size" delta="20000"/>
        </test>
        <test>
            <param name="infile" value="" ftype="analyze75">
                <composite_data value="Analyze75.hdr"/>
                <composite_data value="Analyze75.img"/>
                <composite_data value="Analyze75.t2m"/>
            </param>
            <param name="peptide_file" value="inputpeptides.txt"/>
            <param name="calibrant_file" value="inputcalibrantfile2.txt"/>
            <param name="plusminus_dalton" value="0.5"/>
            <param name="filename" value="Testfile_analyze75"/>
            <output name="plots" file="QC_analyze75.pdf" compare="sim_size" delta="20000"/>
        </test>
        <test>
            <param name="infile" value="preprocessed.RData" ftype="rdata"/>
            <param name="plusminus_dalton" value="0"/>
            <param name="filename" value="Testfile_rdata"/>
            <output name="plots" file="QC_rdata.pdf" compare="sim_size" delta="20000"/>
        </test>
        <test>
            <param name="infile" value="empty_spectra.rdata" ftype="rdata"/>
            <param name="peptide_file" value="inputpeptides.txt"/>
            <param name="calibrant_file" value="inputcalibrantfile2.txt"/>
            <param name="plusminus_dalton" value="0.1"/>
            <param name="filename" value="Testfile_rdata"/>
            <output name="plots" file="QC_empty_spectra.pdf" compare="sim_size" delta="20000"/>
        </test>
    </tests>
    <help>
        <![CDATA[
Cardinal is an R package that implements statistical & computational tools for analyzing mass spectrometry imaging datasets. `More information on Cardinal <http://cardinalmsi.org//>`_

This tool uses some Cardinal functions to create a quality control report with descriptive plots for mass-spectrometry imaging data. 

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

Options: 

- masses of interest as tabular file, used to generate heatmap images
- internal calibrants as tabular file, used for the following plots: Number of calibrant per spectrum, heatmap images, mass-spectrum plot zoomed in for calibrant region, ppm accuracy
- fold change plot: draws a heatmap of the fold change of two masses (log2(intensity ratio))

Output: 

- pdf with numbers and descriptive plots to check the quality of the mass-spectrometry imaging data

Tip: 

- For additional heatmap images use the MSI ion images tool and to plot more mass spectra use the MSI massspectra tool. 

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