view mqppep_anova.xml @ 13:b41a077af3aa draft

"planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 040e4945da00a279cb60daae799fce9489f99c50"

<tool id="mqppep_anova" name="MaxQuant Phosphopeptide ANOVA" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" python_template_version="3.5">
    <description>Perform ANOVA on merged and filtered data from phospho-peptide enrichment/MaxQuant pipeline</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <!--
      The weird invocation used here is because knitr and install_tinytex
      both need access to a writeable directory, but most directories in a
      biocontainer are read-only, so this builds a pseudo-home under /tmp
    -->
    <command detect_errors="exit_code"><![CDATA[
      export OLD_PWD=\$(dirname \$(pwd));
      export HOME=/tmp\${OLD_PWD};
      mkdir -p \$HOME/bin;
      mkdir -p \$HOME/tmp;
      export TEMP=\$HOME/tmp;
      export TMPDIR=\$TEMP;
      cd \$TEMP;
      cp '$__tool_directory__/mqppep_anova_script.Rmd' . || exit 0;
      cp '$__tool_directory__/mqppep_anova.R' . || exit 0;
      \${CONDA_PREFIX}/bin/Rscript \$TEMP/mqppep_anova.R
        --inputFile '$input_file'
        --alphaFile '$alpha_file'
        --firstDataColumn $first_data_column
        --imputationMethod $imputation.imputation_method
        #if $imputation.imputation_method == "random"
          --meanPercentile '$imputation.meanPercentile'
          --sdPercentile   '$imputation.sdPercentile'
        #end if
        --regexSampleNames $sample_names_regex_f
        --regexSampleGrouping $sample_grouping_regex_f
        --imputedDataFile $imputed_data_file
        --imputedQNLTDataFile '$imp_qn_lt_file'
        --reportFile '$report_file';
      export RESULT=\$?;
      cd \${OLD_PWD};
      rm -rf \$HOME;
      exit \${RESULT}
    ]]></command>
    <configfiles>
      <configfile name="sample_names_regex_f">
        $sample_names_regex
      </configfile>
      <configfile name="sample_grouping_regex_f">
        $sample_grouping_regex
      </configfile>
    </configfiles>
    <inputs>
        <param name="input_file" type="data" format="tabular" label="Filtered Phosphopeptide Intensities"
               help="[input_file] Phosphopeptide intensities filtered for minimal quality.  First column label 'Phosphopeptide'; sample-intensities must begin in column 10 and must have column labels to match argument [sample_names_regex]"
        />
        <param name="alpha_file" type="data" format="tabular" label="alpha cutoff level"
               help="[alpha_file] List of alpha cutoff values for significance testing; text file having one column and no header"
        />
        <param name="first_data_column" type="text" value="Intensity"
               label="First data column"
               help="[first_data_column] First column having intensity values (integer or PERL-compatible regular expression matching column label)"
        />
        <!-- imputation_method <- c("group-median","median","mean","random")[1] -->
        <conditional name="imputation">
            <param name="imputation_method" type="select" label="Imputation Method"
                   help="[imputation_method] Impute missing values by (1) using median for each sample-group; (2) using median across all samples; (3) using mean across all samples; or (4) using randomly generated values having same std. dev. as across all samples (with mean specified by [meanPercentile])"
            >
                <option value="random" selected="true">random</option>
                <option value="group-median">group-median</option>
                <option value="median">median</option>
                <option value="mean">mean</option>
            </param>
            <when value="group-median" />
            <when value="median" />
            <when value="mean" />
            <when value="random">
                <param name="meanPercentile" type="integer" value="1" min="1" max="99"
                       label="Mean percentile for random values"
                       help="[meanPercentile] Percentile center of random values; range [1,99]"
                />
                <param name="sdPercentile" type="float" value="0.2"
                       label="Percentile std. dev. for random values"
                       help="[sdPercentile] Standard deviation adjustment-factor for random values; real number.  (1.0 means SD equal to the SD for the entire data set.)"
                />
            </when>
        </conditional>
        <param name="sample_names_regex" type="text" value="\.\d+[A-Z]$"
               help="[sample_names_regex] PERL-compatible regular expression extracting sample-names from the the name of a spectrum file (without extension)"
               label="Sample-extraction regex">
          <sanitizer>
            <valid initial="string.printable">
              <remove value="&apos;"/>
            </valid>
          </sanitizer>
        </param>
        <param name="sample_grouping_regex" type="text" value="\d+"
               help="[sample_grouping_regex] PERL-compatible regular expression extracting sample-group from each sample-name (i.e., extracted by previous regex pattern)"
               label="Group-extraction regex">
          <sanitizer>
            <valid initial="string.printable">
              <remove value="&apos;"/>
            </valid>
          </sanitizer>
        </param>
    </inputs>
    <outputs>
        <data name="imputed_data_file" format="tabular" label="${input_file.name}.${imputation.imputation_method}-imputed_intensities" ></data>
        <data name="imp_qn_lt_file" format="tabular" label="${input_file.name}.${imputation.imputation_method}-imputed_QN_LT_intensities" ></data>
        <!--
        <data name="report_file" format="html" label="${input_file.name}.${imputation.imputation_method}-imputed_report (download/unzip to view)" ></data>
        -->
        <data name="report_file" format="pdf" label="${input_file.name}.${imputation.imputation_method}-imputed_report" ></data>
    </outputs>
    <tests>
        <test>
            <param name="input_file" ftype="tabular" value="test_input_for_anova.tabular"/>
            <param name="alpha_file" ftype="tabular" value="alpha_levels.tabular"/>
            <param name="first_data_column" value="10"/>
            <param name="imputation_method" value="group-median"/>
            <param name="sample_names_regex" value="\.\d+[A-Z]$"/>
            <param name="sample_grouping_regex" value="\d+"/>
            <output name="imp_qn_lt_file">
                <assert_contents>
                    <has_text text="Phosphopeptide" />
                    <has_text text="AAAITDMADLEELSRLpSPLPPGpSPGSAAR" />
                    <has_text text="7.935878" />
                    <has_text text="pSQKQEEENPAEETGEEK" />
                </assert_contents>
            </output>
        </test>
        <test>
            <param name="input_file" ftype="tabular" value="test_input_for_anova.tabular"/>
            <param name="alpha_file" ftype="tabular" value="alpha_levels.tabular"/>
            <param name="first_data_column" value="10"/>
            <param name="imputation_method" value="random"/>
            <param name="meanPercentile" value="1" />
            <param name="sdPercentile" value="0.2" />
            <param name="sample_names_regex" value="\.\d+[A-Z]$"/>
            <param name="sample_grouping_regex" value="\d+"/>
            <output name="imp_qn_lt_file">
                <assert_contents>
                    <has_text text="Phosphopeptide" />
                    <has_text text="AAAITDMADLEELSRLpSPLPPGpSPGSAAR" />
                    <has_text text="8.392287" />
                    <has_text text="pSQKQEEENPAEETGEEK" />
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[
===========================================
Phopsphoproteomic Enrichment Pipeline ANOVA
===========================================

**Input files**

``input_file``
  Phosphopeptides annotated with SwissProt and phosphosite metadata (in tabular format).
  This is the output from the "Phopsphoproteomic Enrichment Pipeline Merge and Filter"
  (``mqppep_mrgflt``) tool.

``alpha_file``
  List of alpha cutoff values for significance testing; text file having one column and no header.  For example:

::

  0.2
  0.1
  0.05

**Input parameters**

``first_data_column``
  First column of ``input_file`` having intensity values (integer or PERL-compatible regular expression matching column label). Default: **Intensity**

``imputation_method``
  Impute missing values by:

    1. using median for each sample-group;
    2. using median across all samples;
    3. using mean across all samples; or
    4. using randomly generated values where:

      - ``meanPercentile`` specifies the percentile among non-missing values to be used as mean of random values, and
      - ``sdPercentile`` specifies the factor to be mulitplied by the standard deviation among the non-missing values (across all samples) to determine the standard deviation of random values.

``sample_names_regex``
  PERL-compatible regular expression extracting the sample-name from the the name of a column of instensities (from ``input_file``) for one sample.

    - For example, ``"\.\d+[A-Z]$"`` applied to ``Intensity.splunge.10A`` would produce ``.10A``
    - Note that *this is case sensitive* by default.

``sample_grouping_regex``
  PERL-compatible regular expression extracting the sample-grouping from the sample-name that was extracted with ``sample_names_regex`` from a column of intensites (from ``input_file``).

    - For example, ``"\d+$"`` applied to ``.10A`` would produce ``10``
    - Note that *this is case sensitive* by default.


**Outputs**

``imputed_intensities``
  Phosphopeptide MS intensities where missing values have been **imputed** by the chosen method, in tabular format.

``imputed_QN_LT_intensities``
  Phosphopeptide MS intensities where missing values have been **imputed** by the chosen method, quantile-normalized (**QN**), and log10-transformed (**LT**), in tabular format.

``report_file``
  Summary report for normalization, imputation, and **ANOVA**, in PDF format.

**Authors**

``Larry C. Cheng``
  (`ORCiD 0000-0002-6922-6433 <https://orcid.org/0000-0002-6922-6433>`_) wrote the original script.

``Arthur C. Eschenlauer``
  (`ORCiD 0000-0002-2882-0508 <https://orcid.org/0000-0002-2882-0508>`_) adapted the script to run in Galaxy.

===================================
PERL-compatible regular expressions
===================================

Note that the PERL-compatible regular expressions accepted by this tool are documented at http://rdrr.io/r/base/regex.html

    ]]></help>
    <citations>
        <!-- Cheng_2018 "Phosphopeptide Enrichment ..." PMID: 30124664 -->
        <citation type="doi">10.3791/57996</citation>
    </citations>
</tool>