comparison msstats.xml @ 1:3e2606fa85bf draft

"planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/msstats commit fa543ac667f63409bfb2e28fd6c711e74d828a79"

0:80b40b9ab835

<tool id="msstats" name="MSstats" version="@VERSION@.0" python_template_version="3.5">
    <description>statistical relative protein significance analysis in DDA, SRM and DIA Mass Spectrometry</description>
    <macros>
        <token name="@VERSION@">3.20.1</token>
        <xml name="useUniquePeptide">
            <param name="useUniquePeptide" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" label="remove peptides that are assigned for more than one proteins" help="We assume to use unique peptide for each protein"/>

    <requirements>
        <requirement type="package" version="@VERSION@">bioconductor-msstats</requirement>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[
        cat '$msstats_script' > '$r_script' &&
        cat '$msstats_script' &&
        Rscript '$msstats_script'
        && cat msstats*.log > $log
    ]]></command>
    <configfiles>
        <configfile name="msstats_script"><![CDATA[
library('MSstats', warn.conflicts = F, quietly = T, verbose = F)

  #if 'model_qc' in $group.select_outputs
write.table(comparisons\$ModelQC, "ModelQC.tsv", sep = "\t", quote = F, row.names = F, dec = ".")
  #end if

## TODO: transform fittedmodel to table 
##class(DDA2009.comparisons$fittedmodel) # list, probably good to output this somehow

## Visualizations:

  #if 'qqplot' in $group.select_outputs
\# normal quantile-quantile plots
modelBasedQCPlots(data=comparisons, type="QQPlots",

    <inputs>
        <conditional name="input">
            <param name="input_src" type="select" label="input source">
                <option value="MSstats">MStats 10 column format</option>
                <option value="MaxQuant">MaxQuant</option>
                <option value="OpenMS">OpenMS</option>
                <option value="OpenSWATH">OpenSWATH</option>
            </param>
            <when value="MSstats">
                <param name="msstats_input" type="data" format="tabular,csv" label="MSstats 10-column input"/>
            </when>

                    <param name="removeMpeptides" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" label="Remove the peptides including 'M' sequence"/>
                    <param name="removeOxidationMpeptides" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" label="Remove the peptides including Oxidized 'M' sequence"/>
                    <expand macro="removeProtein_with1Peptide"/>
                </section>
            </when>
            <when value="OpenMS">
                <param name="evidence" type="data" format="tabular,csv" label="OpenSWATH_input"/>
                <param name="annotation" type="data" format="tabular,csv" label="OpenSWATH_annotation"/>
                <section name="input_options" title="MaxQtoMSstatsFormat Options" expanded="false">
                    <expand macro="useUniquePeptide"/>
                    <expand macro="summaryforMultipleRows"/>
                    <expand macro="fewMeasurements"/>
                    <expand macro="removeProtein_with1Peptide"/>
                </section>
            </when>
            <when value="OpenSWATH">
                <param name="evidence" type="data" format="tabular,csv" label="OpenSWATH_input"/>
                <param name="annotation" type="data" format="tabular,csv" label="OpenSWATH_annotation"/>
                <section name="input_options" title="OpenSWATHtoMSstatsFormat Options" expanded="false">
                    <param name="filter_with_mscore" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" label="Remove the peptides including 'M' sequence"/>

        <data name="r_script" format="txt" label="MSstats Rscript">
            <filter>'r_script' in selected_outputs</filter>
        </data>
        <data name="processed_data" format="tabular" label="MSstats ProcessedData" from_work_dir="ProcessedData.tsv">
            <filter>'processed_data' in selected_outputs</filter>
        </data>
        <data name="runlevel_data" format="tabular" label="MSstats RunlevelData" from_work_dir="RunlevelData.tsv">
            <filter>'runlevel_data' in selected_outputs</filter>
        </data>
        <data name="qcplot" format="pdf" label="MSstats QCPlot.pdf" from_work_dir="MSStats_only_QCPlot.pdf">
            <filter>'qcplot' in selected_outputs</filter>
        </data>
        <data name="profile_plot" format="pdf" label="MSstats ProfilePlot.pdf" from_work_dir="MSStats_only_ProfilePlot.pdf">

        <data name="quant_sample_matrix" format="tabular" label="MSstats SampleQuantificationMatrix.tsv" from_work_dir="SampleQuantificationMatrix.tsv">
            <filter>'quant_sample_matrix' in selected_outputs</filter>
        </data>
        <data name="quant_sample_long" format="tabular" label="MSstats SampleQuantificationLong.tsv" from_work_dir="SampleQuantificationLong.tsv">
            <filter>'quant_sample_long' in selected_outputs</filter>
        </data>
        <data name="quant_group_matrix" format="tabular" label="MSstats GroupQuantificationMatrix.tsv" from_work_dir="GroupQuantificationMatrix.tsv">
            <filter>'quant_group_matrix' in selected_outputs</filter>
        </data>
        <data name="quant_group_long" format="tabular" label="MSstats GroupQuantificationLong.tsv" from_work_dir="GroupQuantificationLong.tsv">
            <filter>'quant_group_long' in selected_outputs</filter>
        </data>
        <data name="comparison_result" format="tabular" label="MSstats ComparisonResult.tsv" from_work_dir="ComparisonResult.tsv">
            <filter> group['group_comparison'] == 'yes' and 'comparison_result' in group['select_outputs']</filter>
        </data>
        <data name="fittedmodel" format="txt" label="MSstats ComparisonFittedModel.txt" from_work_dir="ComparisonFittedModel.txt">
            <filter> group['group_comparison'] == 'yes' and 'fittedmodel' in group['select_outputs']</filter>
        </data>
        <data name="model_qc" format="tabular" label="MSstats ModelQC.tsv" from_work_dir="ModelQC.tsv">
            <filter> group['group_comparison'] == 'yes' and 'model_qc' in group['select_outputs']</filter>
        </data>
        <data name="qqplot" format="pdf" label="MSstats ModelQQ.pdf" from_work_dir="MSStats_group_QQPlot.pdf">
            <filter> group['group_comparison'] == 'yes' and 'qqplot' in group['select_outputs']</filter>
        </data>
        <data name="residualplot" format="pdf" label="MSstats ResidualPlot.pdf" from_work_dir="MSStats_group_ResidualPlot.pdf">

            <filter> group['group_comparison'] == 'yes' and 'heatmap' in group['select_outputs']</filter>
        </data>
        <data name="comparisonplot" format="pdf" label="MSstats ComparisonPlot.pdf" from_work_dir="MSStats_group_ComparisonPlot.pdf">
            <filter> group['group_comparison'] == 'yes' and 'comparisonplot' in group['select_outputs']</filter>
        </data>
<!--
Tabular file (from groupcomparison): "fittedmodel"
-->
    </outputs>
    <tests>

        <test>
            <conditional name="input">

            </output>
            <output name="condition_plot" file="condition_plot.pdf" compare="sim_size"/>                     
            <output name="qqplot" file="qq_plot.pdf" compare="sim_size"/>                     
        </test>
        
        
                          

        <!--
        <test>
            <conditional name="input">
                <param name="input_src" value="OpenMS"/>
                <param name="evidence" ftype="tabular" value=""/>

1:3e2606fa85bf

<tool id="msstats" name="MSstats" version="@VERSION@.0">
    <description>statistical relative protein significance analysis in DDA, SRM and DIA Mass Spectrometry</description>
    <macros>
        <token name="@VERSION@">3.20.1</token>
        <xml name="useUniquePeptide">
            <param name="useUniquePeptide" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" label="remove peptides that are assigned for more than one proteins" help="We assume to use unique peptide for each protein"/>

    <requirements>
        <requirement type="package" version="@VERSION@">bioconductor-msstats</requirement>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[
        cat '$msstats_script' > '$r_script' &&
        Rscript '$msstats_script'
        && cat msstats*.log > '$log'
    ]]></command>
    <configfiles>
        <configfile name="msstats_script"><![CDATA[
library('MSstats', warn.conflicts = F, quietly = T, verbose = F)

  #if 'model_qc' in $group.select_outputs
write.table(comparisons\$ModelQC, "ModelQC.tsv", sep = "\t", quote = F, row.names = F, dec = ".")
  #end if

## Visualizations:

  #if 'qqplot' in $group.select_outputs
\# normal quantile-quantile plots
modelBasedQCPlots(data=comparisons, type="QQPlots",

    <inputs>
        <conditional name="input">
            <param name="input_src" type="select" label="input source">
                <option value="MSstats">MStats 10 column format</option>
                <option value="MaxQuant">MaxQuant</option>
                <!-- 
                <option value="OpenMS">OpenMS</option>
                -->
                <option value="OpenSWATH">OpenSWATH</option>
            </param>
            <when value="MSstats">
                <param name="msstats_input" type="data" format="tabular,csv" label="MSstats 10-column input"/>
            </when>

                    <param name="removeMpeptides" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" label="Remove the peptides including 'M' sequence"/>
                    <param name="removeOxidationMpeptides" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" label="Remove the peptides including Oxidized 'M' sequence"/>
                    <expand macro="removeProtein_with1Peptide"/>
                </section>
            </when>
            <!--
            <when value="OpenMS">
                <param name="evidence" type="data" format="tabular,csv" label="OpenSWATH_input"/>
                <param name="annotation" type="data" format="tabular,csv" label="OpenSWATH_annotation"/>
                <section name="input_options" title="MaxQtoMSstatsFormat Options" expanded="false">
                    <expand macro="useUniquePeptide"/>
                    <expand macro="summaryforMultipleRows"/>
                    <expand macro="fewMeasurements"/>
                    <expand macro="removeProtein_with1Peptide"/>
                </section>
            </when>
            -->
            <when value="OpenSWATH">
                <param name="evidence" type="data" format="tabular,csv" label="OpenSWATH_input"/>
                <param name="annotation" type="data" format="tabular,csv" label="OpenSWATH_annotation"/>
                <section name="input_options" title="OpenSWATHtoMSstatsFormat Options" expanded="false">
                    <param name="filter_with_mscore" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="true" label="Remove the peptides including 'M' sequence"/>

        <data name="r_script" format="txt" label="MSstats Rscript">
            <filter>'r_script' in selected_outputs</filter>
        </data>
        <data name="processed_data" format="tabular" label="MSstats ProcessedData" from_work_dir="ProcessedData.tsv">
            <filter>'processed_data' in selected_outputs</filter>
            <actions>
                <action name="column_names" type="metadata" default="PROTEIN,PEPTIDE,TRANSITION,FEATURE,LABEL,GROUP_ORIGINAL,SUBJECT_ORIGINAL,RUN,GROUP,SUBJECT,INTENSITY,SUBJECT_NESTED,ABUNDANCE,FRACTION,originalRUN,censored" />
            </actions>
        </data>
        <data name="runlevel_data" format="tabular" label="MSstats RunlevelData" from_work_dir="RunlevelData.tsv">
            <filter>'runlevel_data' in selected_outputs</filter>
            <actions>
               <action name="column_names" type="metadata" default="RUN,Protein,LogIntensities,NumMeasuredFeature,MissingPercentage,more50missing,NumImputedFeature,originalRUN,GROUP,GROUP_ORIGINAL,SUBJECT_ORIGINAL,SUBJECT_NESTED,SUBJECT" />
            </actions>
        </data>
        <data name="qcplot" format="pdf" label="MSstats QCPlot.pdf" from_work_dir="MSStats_only_QCPlot.pdf">
            <filter>'qcplot' in selected_outputs</filter>
        </data>
        <data name="profile_plot" format="pdf" label="MSstats ProfilePlot.pdf" from_work_dir="MSStats_only_ProfilePlot.pdf">

        <data name="quant_sample_matrix" format="tabular" label="MSstats SampleQuantificationMatrix.tsv" from_work_dir="SampleQuantificationMatrix.tsv">
            <filter>'quant_sample_matrix' in selected_outputs</filter>
        </data>
        <data name="quant_sample_long" format="tabular" label="MSstats SampleQuantificationLong.tsv" from_work_dir="SampleQuantificationLong.tsv">
            <filter>'quant_sample_long' in selected_outputs</filter>
            <actions>
                <action name="column_names" type="metadata" default="Protein,Group_Subject,LogIntensity" />
            </actions>
        </data>
        <data name="quant_group_matrix" format="tabular" label="MSstats GroupQuantificationMatrix.tsv" from_work_dir="GroupQuantificationMatrix.tsv">
            <filter>'quant_group_matrix' in selected_outputs</filter>
        </data>
        <data name="quant_group_long" format="tabular" label="MSstats GroupQuantificationLong.tsv" from_work_dir="GroupQuantificationLong.tsv">
            <filter>'quant_group_long' in selected_outputs</filter>
            <actions>
                <action name="column_names" type="metadata" default="Protein,Group,LogIntensity" />
            </actions>
        </data>
        <data name="comparison_result" format="tabular" label="MSstats ComparisonResult.tsv" from_work_dir="ComparisonResult.tsv">
            <filter> group['group_comparison'] == 'yes' and 'comparison_result' in group['select_outputs']</filter>
            <actions>
                <action name="column_names" type="metadata" default="Protein,Label,log2FC,SE,Tvalue,DF,pvalue,adj.pvalue,issue,MissingPercentage,ImputationPercentage" />
            </actions>
        </data>
        <data name="fittedmodel" format="txt" label="MSstats ComparisonFittedModel.txt" from_work_dir="ComparisonFittedModel.txt">
            <filter> group['group_comparison'] == 'yes' and 'fittedmodel' in group['select_outputs']</filter>
        </data>
        <data name="model_qc" format="tabular" label="MSstats ModelQC.tsv" from_work_dir="ModelQC.tsv">
            <filter> group['group_comparison'] == 'yes' and 'model_qc' in group['select_outputs']</filter>
            <actions>
                <action name="column_names" type="metadata" default="RUN,PROTEIN,ABUNDANCE,NumMeasuredFeature,MissingPercentage,more50missing,NumImputedFeature,originalRUN,GROUP,GROUP_ORIGINAL,SUBJECT_ORIGINAL,SUBJECT_NESTED,SUBJECT,residuals,fitted" />
            </actions>
        </data>
        <data name="qqplot" format="pdf" label="MSstats ModelQQ.pdf" from_work_dir="MSStats_group_QQPlot.pdf">
            <filter> group['group_comparison'] == 'yes' and 'qqplot' in group['select_outputs']</filter>
        </data>
        <data name="residualplot" format="pdf" label="MSstats ResidualPlot.pdf" from_work_dir="MSStats_group_ResidualPlot.pdf">

            <filter> group['group_comparison'] == 'yes' and 'heatmap' in group['select_outputs']</filter>
        </data>
        <data name="comparisonplot" format="pdf" label="MSstats ComparisonPlot.pdf" from_work_dir="MSStats_group_ComparisonPlot.pdf">
            <filter> group['group_comparison'] == 'yes' and 'comparisonplot' in group['select_outputs']</filter>
        </data>
    </outputs>
    <tests>

        <test>
            <conditional name="input">

            </output>
            <output name="condition_plot" file="condition_plot.pdf" compare="sim_size"/>                     
            <output name="qqplot" file="qq_plot.pdf" compare="sim_size"/>                     
        </test>
        
        <!--
        <test>
            <conditional name="input">
                <param name="input_src" value="OpenMS"/>
                <param name="evidence" ftype="tabular" value=""/>