annotate diffacto.xml @ 0:3cc7ce0822a1 draft default tip

"planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/diffacto commit 507bb20a2c246bb0a1a0c7dae1555a851730e4a6"

<tool id="diffacto" name="Diffacto" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" python_template_version="3.5">
    <description>Comparative Protein Abundance from Covariation of Peptide Abundances</description>
    <macros>
        <token name="@TOOL_VERSION@">1.0.6</token>
        <token name="@VERSION_SUFFIX@">0</token>
    </macros>
    <requirements>
        <requirement type="package" version="@TOOL_VERSION@">diffacto</requirement>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[
        tr '\t' ',' < '$input' > input.csv &&
        diffacto
        -i input.csv
        #if $db
            -db '$db'
        #end if
        #if $samples
            -samples '$samples'
        #end if
        -reference '$reference'
        #if $normalize
            -normalize $normalize
        #end if
        #if $farms_mu
            -farms_mu $farms_mu
        #end if
        #if $farms_alpha
            -farms_alpha $farms_alpha
        #end if
        -min_samples $min_samples
        -impute_threshold $impute_threshold
        -cutoff_weight $cutoff_weight
        $use_unique
        #if $scale == 'log2'
            -log2 True
        #else
            -log2 False
        #end if
        $fast
        -out '$output'
        #if $mcfdr
            -mc_out '$mc_out'
        #end if
        #if $loadings
            -loadings_out '$loadings_out'
        #end if
    ]]></command>
    <inputs>
        <param name="input" argument="-i" type="data" format="tabular,csv" label="Peptides abundances">
            <help><![CDATA[
                Peptides abundances in tabular or csv format. 
                <ul>
                <li>The first row is column headers and should contain the sample name for each sample column. </li>
                <li>The first column should contain unique peptide sequences. </li>
                <li><i>Optionally, the second column may be ProteinID assignments, else the <b>Protein database</b> input is required.</i></li>
                <li>Each remaining column is a sample column with numeric abundance values.</li>
                <li>Missing values should be empty instead of zeros.</li>
                </ul>
            ]]></help>
        </param>
        <param argument="-db" type="data" format="fasta" label="Protein database" optional="true"
               help="Required if the Peptide abundances input does not have Protein IDs in the second column"/> 
        <param argument="-samples" type="data" format="tabular" label="Sample Groups" optional="true">
            <help><![CDATA[
               <i>Optional: By default, each Sample column in Peptide abundances is treated as a singleton group.</i> 
               <br>
               Groups the samples from the Peptides abundance input for comparison.
               Each sample column from Peptides abundance input should be on a line with 2 columns:
               <ol> 
               <li>Sample name for header line of the Peptides abundance input.</li>
               <li>Group Name assignemnt for the sample</li>
               </ol>
            ]]></help>
        </param>
        <param argument="-reference" type="text" value="" label="Reference sample groups" optional="true">
            <help><![CDATA[
            <i>Optional: By default, Diffacto uses the average of all samples/groups as the reference.</i> 
            <br>
            Names of sample groups <i>(separated by semicolon)</i> treated as the comparison reference.
            <ul>
            <li>If a Sample Groups input was used, the reference names should be Group names from column 2.</li>
            <li>Otherwise, the reference names should be Sample names from the Peptides abundance column header line.</li>
	    </ul>
            ]]></help>
        </param>
        <param name="scale" argument="-log2" type="select" label="Peptides abundance scale">
            <option value="linear">linear</option>
            <option value="log2">log2</option>
        </param>
        <param argument="-normalize" type="select" label="Sample-wise normalization" optional="true">
            <option value="average">average</option>
            <option value="median">median</option>
            <option value="GMM">GMM</option>
        </param>
        <param argument="-farms_mu" type="float" value="0.1" min="0.0" max="1.0" optional="true" label="Hyperparameter mu"
            help="Hyperparameter mu (default: 0.1)"/>
        <param argument="-farms_alpha" type="float" value="0.1" min="0.0" max="1.0" optional="true" label="Hyperparameter alpha"
            help="Hyperparameter weight of prior probability (default: 0.1)"/>
        <param argument="-min_samples" type="integer" value="1" min="1" label="Minimum samples for peptide"
            help="Minimum number of samples peptides needed to be quantified in"/>
        <param argument="-impute_threshold" type="float" value="0.99" min="0.1" max="1.0" label="Minimum fraction of missing values in the group"
            help="Impute missing values if missing fraction is larger than the threshold."/>
        <param argument="-cutoff_weight" type="float" value="0.5" min="0." max="1.0" label="Peptide cutoff weight"
            help="Peptides weighted lower than the cutoff will be excluded."/>
        <param argument="-use_unique" type="boolean" truevalue="-use_unique True" falsevalue="" checked="false" label="Use unique peptides only"/>
        <param argument="-fast" type="boolean" truevalue="-fast True" falsevalue="" checked="false" label="Allow early termination in EM calculation when noise is sufficiently small."/>
        <param name="mcfdr" argument="-mc_out" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Perform Monte Carlo FDR simulation"/>
        <param name="loadings" argument="-loadings_out" type="boolean" truevalue="True" falsevalue="False" checked="false" label="Output Protein Peptide loadings file"/>
    </inputs>
    <outputs>
        <data name="output" format="tabular" label="${tool.name} on ${on_string}: Protein Abundance">
            <actions>
                <action name="comment_lines" type="metadata" default="1" />
                <action name="column_names" type="metadata" default="Protein,N.Pept,Q.Pept,S/N,P(PECA)" />
            </actions>
        </data>
        <data name="mc_out" format="tabular" label="${tool.name} on ${on_string}: MC FDR">
            <filter>mcfdr == True</filter>
            <actions>
                <action name="comment_lines" type="metadata" default="1" />
                <action name="column_names" type="metadata" default="Protein,P(MC),MCFDR" />
            </actions>
        </data>
        <data name="loadings_out" format="tabular" label="${tool.name} on ${on_string}: Protein Peptide loading">
            <filter>loadings == True</filter>
            <actions>
                <action name="comment_lines" type="metadata" default="1" />
                <action name="column_names" type="metadata" default="Protein,Peptide,Loading" />
            </actions>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="input" ftype="csv" value="HBY20Mix.peptides.csv"/>
            <param name="db" ftype="fasta" value="UP000002311_559292.fasta"/>
            <param name="samples" ftype="tabular" value="HBY20Mix.samples.lst"/>
            <output name="output">
               <assert_contents>
                    <has_text text="P19097" />
                </assert_contents>
            </output>
        </test>
        <test>
            <param name="input" ftype="tabular" value="HBY20Mix.peptides.tsv"/>
            <param name="db" ftype="fasta" value="UP000002311_559292.fasta"/>
            <param name="samples" ftype="tabular" value="HBY20Mix.samples.lst"/>
            <output name="output">
               <assert_contents>
                    <has_text text="P19097" />
                </assert_contents>
            </output>
        </test>

        <test>
            <param name="input" ftype="csv" value="iPRG.novo.pep.csv"/>
            <param name="samples" ftype="tabular" value="iPRG.samples.lst"/>
            <param name="min_samples" value="2"/>
            <output name="output">
               <assert_contents>
                    <has_text text="FAS2" />
                </assert_contents>
            </output>
        </test>
        <test>
            <param name="input" ftype="csv" value="iPRG.novo.pep.csv"/>
            <param name="samples" ftype="tabular" value="iPRG.samples.lst"/>
            <param name="min_samples" value="4"/>
            <param name="use_unique" value="True"/>
            <param name="mcfdr" value="True"/>
            <output name="output">
               <assert_contents>
                    <has_text text="FAS2" />
                </assert_contents>
            </output>
            <output name="mc_out">
               <assert_contents>
                    <has_text text="FAS2" />
                </assert_contents>
            </output>
        </test>

    </tests>
    <help><![CDATA[
**Diffacto**

Diffacto_ quantifies comparative protein abundance from the covariation of peptide abundances.

Diffacto_ applies factor analysis to extract the covariation of peptides' abundances. The method enables a weighted geometrical average summarization and automatic elimination of incoherent peptides, which may result from suboptimal digestion or being partially modified, and are not representative of the protein concentration.

**Inputs**

  - **Peptides abundances** *in tabular or csv format*

    - The first row is column headers and should contain the sample name for each sample column.
    - The first column should contain unique peptide sequences.
    - *Optionally, the second column may be Protein ID assignments, else the* **Protein database** *input is required.*
    - Each remaining column is a sample column with numeric abundance values.
    - Missing values should be empty instead of zeros.
    - Example: 

      ============ ========== ========= ========= ========= =========
      sequences    Protein    Sample1-A Sample1_B Sample2_A Sample2_B
      ============ ========== ========= ========= ========= =========
      AAATAAMTK    EF3A       127.35209 142.58217 135.89206 162.54500
      AAATTGEWDK   PDC1       100.35922 114.68676 922.60617 833.97955
      LPVLLADACCSR HSP72;PDC1 120.21570 194.99594 977.48321 219.23281
      AAEEAGVTDVK  FAS2       442.67501 457.52266 448.52837 424.15980
      ============ ========== ========= ========= ========= =========


  - **Protein database** *(optional)*

    - The Protein database in fasta format that has protein seqeunces containing the peptides.
    - Required if the **Peptides abundances** input does not have a second column containing Protein ID assignments


  - **Sample Groups** *(optional)*

    - First column has the sample name
    - Second column has the group name
    - Example:

      ========= ==
      Sample1-A S1
      Sample1_B S1
      Sample2_A S2
      Sample2_B S2
      ========= ==


**Outputs**

  - **Protein Abundance**

        ======= ====== ====== =================== =================== ================== ==================
        Protein N.Pept Q.Pept S/N                 P(PECA)	         S1                 S2
        ======= ====== ====== =================== =================== ================== ==================
        EF3A    2      2      -2.874362404756714  0.2608189432601452  463172795.59269696 489796576.81520355
        FAS2    6      4      -0.5901265476375578 0.8395809777778386  52093246.23323742  53280470.3811749
        PDC1    3      2      6.634988423694361   0.25491030879514676 203769831.79809052 174641994.14231393
        ======= ====== ====== =================== =================== ================== ==================

  - **FDR Estimate from Monte Carlo Simulation** *(optional)*

        =======  =================== ===================
        Protein  P(MC)               MCFDR            
        =======  =================== ===================
        EF3A     0.1419053964023984  0.5287482885321804
        FAS2     0.9867109634551495  0.9132662960822688
        PDC1     0.3338088445078459  0.5287482885321804
        =======  =================== ===================

  - **Protein Peptide Loadings** *(optional)*

        =======  ===========  ===================
        EF3A     AAATAAMTK    0.5287482885321804
        FAS2     AAEEAGVTDVK  0.9132662960822688
        PDC1     AAATTGEWDK   0.5287482885321804
        =======  ===========  ===================

.. _Diffacto: https://github.com/statisticalbiotechnology/diffacto

    ]]></help>
    <citations>
        <citation type="doi">10.1074/mcp.O117.067728</citation>
    </citations>
</tool>