annotate mqppep_anova.xml @ 0:dbff53e6f75f draft

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/mqppep commit 3a7b3609d6e514c9e8f980ecb684960c6b2252fe

<tool
  id="mqppep_anova"
  name="MaxQuant Phosphopeptide ANOVA"
  version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@"
  profile="21.05"
  >
    <description>Runs ANOVA and KSEA for phosphopeptides.</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <edam_topics>
        <edam_topic>topic_0121</edam_topic><!-- proteomics -->
        <edam_topic>topic_3520</edam_topic><!-- proteomics experiment-->
    </edam_topics>
    <edam_operations>
        <edam_operation>operation_0276</edam_operation><!-- Analyse a network of protein interactions. -->
        <edam_operation>operation_0531</edam_operation><!-- Heat map generation -->
        <edam_operation>operation_2938</edam_operation><!-- Dendrogram generation -->
        <edam_operation>operation_2938</edam_operation><!-- Imputation -->
        <edam_operation>operation_3435</edam_operation><!-- Standardisation and normalisation -->
        <edam_operation>operation_3501</edam_operation><!-- Enrichment analysis -->
        <edam_operation>operation_3658</edam_operation><!-- Statistical inference -->
    </edam_operations>
    <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[
      cp '$__tool_directory__/mqppep_anova_script.Rmd' . &&
      cp '$__tool_directory__/mqppep_anova.R'          . &&
      Rscript mqppep_anova.R
        --inputFile '$input_file'
        --alphaFile '$alpha_file'
        --preproc_sqlite '$preproc_sqlite'
        --firstDataColumn $intensity_column_regex_f
        --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'
        --ksea_sqlite '$ksea_sqlite'
        --ksea_cutoff_threshold '$ksea_cutoff_threshold'
        --ksea_cutoff_statistic 'FDR'
        --reportFile '$report_file'
        --anova_ksea_metadata '$anova_ksea_metadata'
    ]]></command>
    <configfiles>
      <configfile name="sample_names_regex_f">
        $sample_names_regex
      </configfile>
      <configfile name="sample_grouping_regex_f">
        $sample_grouping_regex
      </configfile>
      <configfile name="intensity_column_regex_f">
        $intensity_column_regex
      </configfile>
    </configfiles>
    <inputs>
        <param name="input_file" type="data" format="tabular" label="Filtered Phosphopeptide Intensities"
               help="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="ANOVA alpha cutoff level"
               help="ANOVA alpha cutoff values for significance testing: tabular data having one column and no header"
        />
        <param name="preproc_sqlite" type="data" format="sqlite" label="preproc_sqlite dataset from mqppep_preproc"
               help="'preproc_sqlite' dataset produced by 'MaxQuant Phosphopeptide Preprocessing' tool"
                />
        <param name="intensity_column_regex" type="text" value="^Intensity[^_]"
               label="Intensity-column pattern"
               help="Pattern matching columns that have peptide intensity data (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="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="Percentile center of random values; range [1,99]"
                />
                <param name="sdPercentile" type="float" value="1.0"
                       label="Percentile std. dev. for random values"
                       help="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="Pattern extracting sample-names from names of columns that have peptide intensity data (PERL-compatible regular expression)"
               label="Sample-extraction pattern">
          <sanitizer>
            <valid initial="string.printable">
              <remove value="&apos;"/>
            </valid>
          </sanitizer>
        </param>
        <param name="sample_grouping_regex" type="text" value="\d+"
               help="Pattern extracting sample-group from the sample-names that are extracted by 'Sample-extraction pattern' (PERL-compatible regular expression)"
               label="Group-extraction pattern">
          <sanitizer>
            <valid initial="string.printable">
              <remove value="&apos;"/>
            </valid>
          </sanitizer>
        </param>
        <param name="ksea_cutoff_threshold" type="float" value="0.05"
               label="KSEA threshold level"
               help="Maximum FDR to be used to score a kinase enrichment as significant"
        />
    </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="anova_ksea_metadata" format="tabular" label="${input_file.name}.${imputation.imputation_method}-anova_ksea_metadata" ></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>
        <data name="ksea_sqlite" format="sqlite" label="${input_file.name}..${imputation.imputation_method}-imputed_ksea_sqlite">
        </data>
    </outputs>
    <tests>
        <test>
            <param name="input_file" ftype="tabular" value="test_input_for_anova.tabular"/>
            <param name="preproc_sqlite" ftype="sqlite" value="test_input_for_anova.sqlite"/>
            <param name="alpha_file" ftype="tabular" value="alpha_levels.tabular"/>
            <param name="intensity_column_regex" value="^Intensity[^_]"/>
            <param name="imputation_method" value="median"/>
            <param name="sample_names_regex" value="\.\d+[A-Z]$"/>
            <param name="sample_grouping_regex" value="\d+"/>
            <output name="imputed_data_file">
                <assert_contents>
                    <has_text text="Phosphopeptide" />
                    <has_text text="AAAITDMADLEELSRLpSPLPPGpSPGSAAR" />
                    <!--                                               missing missing observd missing observd observd  -->
                    <has_text_matching expression="pSQKQEEENPAEETGEEK.*8765300.8765300.8765300.8765300.2355900.14706000" />

                </assert_contents>
            </output>
            <output name="imp_qn_lt_file">
                <assert_contents>
                    <has_text text="Phosphopeptide" />
                    <has_text text="AAAITDMADLEELSRLpSPLPPGpSPGSAAR" />
                    <!--                                               missing   missing   observed  missing   observed  observed  -->
                    <has_text_matching expression="pSQKQEEENPAEETGEEK.*6.962256.*6.908828.*6.814580.*6.865411.*6.908828.*7.088909" />

                    <has_text text="pSQKQEEENPAEETGEEK" />
                </assert_contents>
            </output>
        </test>
        <test>
            <param name="input_file" ftype="tabular" value="test_input_for_anova.tabular"/>
            <param name="preproc_sqlite" ftype="sqlite" value="test_input_for_anova.sqlite"/>
            <param name="alpha_file" ftype="tabular" value="alpha_levels.tabular"/>
            <param name="intensity_column_regex" value="^Intensity[^_]"/>
            <param name="imputation_method" value="mean"/>
            <param name="sample_names_regex" value="\.\d+[A-Z]$"/>
            <param name="sample_grouping_regex" value="\d+"/>
            <output name="imputed_data_file">
                <assert_contents>
                    <has_text text="Phosphopeptide" />
                    <has_text text="AAAITDMADLEELSRLpSPLPPGpSPGSAAR" />
                    <!--                                               missing missing observd missing observd observd  -->
                    <has_text_matching expression="pSQKQEEENPAEETGEEK.*6721601.6721601.8765300.6721601.2355900.14706000" />

                </assert_contents>
            </output>
            <output name="imp_qn_lt_file">
                <assert_contents>
                    <has_text text="Phosphopeptide" />
                    <has_text text="AAAITDMADLEELSRLpSPLPPGpSPGSAAR" />
                    <!--                                               missing   missing   observed  missing   observed  observed  -->
                    <has_text_matching expression="pSQKQEEENPAEETGEEK.*6.839850.*6.797424.*6.797424.*6.797424.*6.896609.*7.092451" />
                </assert_contents>
            </output>
        </test>
        <test>
            <param name="input_file" ftype="tabular" value="test_input_for_anova.tabular"/>
            <param name="preproc_sqlite" ftype="sqlite" value="test_input_for_anova.sqlite"/>
            <param name="alpha_file" ftype="tabular" value="alpha_levels.tabular"/>
            <param name="intensity_column_regex" value="^Intensity[^_]"/>
            <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="imputed_data_file">
                <assert_contents>
                    <has_text text="Phosphopeptide" />
                    <has_text text="AAAITDMADLEELSRLpSPLPPGpSPGSAAR" />
                    <!--                                               missing missing observd missing observd observd  -->
                    <has_text_matching expression="pSQKQEEENPAEETGEEK.*8765300.8765300.8765300.5886074.2355900.14706000" />

                </assert_contents>
            </output>
            <output name="imp_qn_lt_file">
                <assert_contents>
                    <has_text text="Phosphopeptide" />
                    <has_text text="AAAITDMADLEELSRLpSPLPPGpSPGSAAR" />
                    <!--                                               missing   missing   observed  missing   observed  observed  -->
                    <has_text_matching expression="pSQKQEEENPAEETGEEK.*6.946112.*6.888985.*6.792137.*6.792137.*6.888985.*7.089555" />
                </assert_contents>
            </output>
        </test>
        <test>
            <param name="input_file" ftype="tabular" value="test_input_for_anova.tabular"/>
            <param name="preproc_sqlite" ftype="sqlite" value="test_input_for_anova.sqlite"/>
            <param name="alpha_file" ftype="tabular" value="alpha_levels.tabular"/>
            <param name="intensity_column_regex" value="^Intensity[^_]"/>
            <param name="imputation_method" value="random"/>
            <param name="meanPercentile" value="1" />
            <param name="sdPercentile" value="1.0" />
            <param name="sample_names_regex" value="\.\d+[A-Z]$"/>
            <param name="sample_grouping_regex" value="\d+"/>
            <output name="imputed_data_file">
                <assert_contents>
                    <has_text text="Phosphopeptide" />
                    <has_text text="AAAITDMADLEELSRLpSPLPPGpSPGSAAR" />
                    <!--                           observd  observd  observd  -->
                    <has_text_matching expression="pSQKQEEENPAEETGEEK.*8765300.*2355900.*4706000" />

                </assert_contents>
            </output>
            <output name="imp_qn_lt_file">
                <assert_contents>
                    <has_text text="Phosphopeptide" />
                    <has_text text="AAAITDMADLEELSRLpSPLPPGpSPGSAAR" />
                    <has_text text="5.409549" /> <!-- log-transformed value for pTYVDPFTpYEDPNQAVR .1B -->
                    <has_text text="6.464714" /> <!-- log-transformed value for pSQKQEEENPAEETGEEK .2A -->
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[
====================================================
Phopsphoproteomic Enrichment Pipeline ANOVA and KSEA
====================================================

**Input files**

``Filtered Phosphopeptide Intensities``
  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.

``ANOVA alpha cutoff level``
  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**

``Intensity-column pattern``
  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. ``group-median`` - use median for each sample-group;
    2. ``mean`` - use mean across all samples; or
    3. ``median`` - use median across all samples;
    4. ``random`` - use randomly generated values where:

      - ``Mean percentile for random values`` specifies the percentile among non-missing values to be used as mean of random values, and
      - ``Percentile std. dev. for random values`` specifies the factor to be multiplied by the standard deviation among the non-missing values (across all samples) to determine the standard deviation of random values.

``Sample-extraction pattern``
  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.

``Group-extraction pattern``
  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.

``KSEA threshold level``
  Specifies minimum FDR at which a kinase will be considered to be enriched; the default choice of 0.05 is arbitrary.

**Outputs**

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

``imputed_QN_LT_intensities (input_file.imputation_method-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 (input_file.imputation_method-imputed_report)``
  Summary report for normalization, imputation, and **ANOVA**, in PDF format.

``anova_ksea_metadata (input_file.imputation_method-imputed_anova_ksea_metadata)``
  Phosphopeptide metadata including ANOVA significance and KSEA enrichments.

``ksea_sqlite (input_file.imputation_method-imputed_ksea_sqlite)``
  SQLite database for ad-hoc report creation.

**Algorithm**

The KSEA algorithm used here is as in the KSEAapp package as reported in [Wiredja 2017].
The code is adapted from "Danica D. Wiredja (2017). KSEAapp: Kinase-Substrate Enrichment Analysis. R package version 0.99.0." to work with output from the "MaxQuant Phosphopeptide Preprocessing" Galaxy tool.

**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>
        <!-- Wiredja_2017 "The KSEA App ..." PMID: 28655153 -->
        <citation type="doi">10.1093/bioinformatics/btx415</citation>
    </citations>
</tool>