annotate macros.xml @ 0:cfd2e19f00a9 draft

planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/recetox-xmsannotator commit 1ab1a1dabfcebe11720de1411927a7438c1b64c1

<macros>
<token name="@TOOL_VERSION@">0.10.0</token>

<xml name="requirements">
    <requirements>
        <requirement type="package" version="@TOOL_VERSION@">r-recetox-xmsannotator</requirement>
    </requirements>
</xml>

<xml name="creator">
    <creator>
        <person
            givenName="Jiří"
            familyName="Novotný"
            url="https://github.com/xtracko"
            identifier="0000-0001-5449-3523" />
        <person
            givenName="Martin"
            familyName="Čech"
            url="https://github.com/martenson"
            identifier="0000-0002-9318-1781" />
        <person
            givenName="Matej"
            familyName="Troják"
            url="https://github.com/xtrojak"
            identifier="0000-0003-0841-2707" />
        <organization
            url="https://www.recetox.muni.cz/"
            email="[e-mail]"
            name="RECETOX MUNI" />
    </creator>
</xml>

<xml name="inputs">
    <param name="metadata_table" type="data" format="parquet,csv">
        <label>Metadata table</label>
        <help><![CDATA[
            Peak metadata table*.
        ]]></help>
    </param>
    <param name="intensity_table" type="data" format="parquet,csv">
        <label>Intensity table</label>
        <help><![CDATA[
            Table with intensities** for features (rows) across samples (columns).
        ]]></help>
    </param>
    <param name="compound_table" type="data" format="parquet,csv">
        <label>Compound database</label>
        <help><![CDATA[
            Database of compounds according to which the annotation is performed.
            The database is required to contain the fields <em>compound_id</em>, <em>monoisotopic_mass</em>, and <em>molecular_formula</em>.
        ]]></help>
    </param>
    <param name="adduct_table" type="data" format="parquet,csv" optional="true">
        <label>Adduct database</label>
        <help><![CDATA[
            Database of adduct which is combined with the database of compound to form a molecule-adduct pairs.
            The database is required to contain <em>adduct</em>, <em>charge</em>, <em>mass</em>, and <em>n_molecules</em>.
        ]]></help>
    </param>
    <param name="adduct_weights" type="data" format="parquet,csv" optional="true">
        <label>Adduct weights</label>
        <help>
            A weight-by-adduct table.
        </help>
    </param>
</xml>

<xml name="outputs">
    <data name="output_file" format="parquet">
        <change_format>
            <when input="metadata_table.ext" value="csv" format="csv" />
        </change_format>
    </data>
</xml>

<xml name="tolerance">
    <param name="mass_tolerance_ppm" type="integer" min="0" value="5">
        <label>Mass tolerance [ppm]</label>
        <help>Mass tolerance in ppm for database matching.</help>
    </param>
    <yield/>
</xml>

<token name="@HELP@">
Description
===========

Annotate the peak intensity table (e.g. from an apLCMS run) with compounds from the compounds database
using advanced methods.

The annotation process generates all possible compound-adduct pairs and matches those pairs to the measured
peaks. A compound-adduct pair is pronounced as a match to a certain peak when the difference of their masses are
withing some tolerance.

Then, a score and a confidence level is assigned to each match based on peak correlation
clustering, metabolite pathway associations, adducts expectations, and isotope conformations.

Input tables description
------------------------

(*) Metadata table
~~~~~~~~~~~~~~~~~~

The output from recetox-aplcms tool. 
The `npeaks` column denotes the number of peaks which have been grouped into this feature. 
The columns with the sample names indicate whether this feature is present in the sample.
Only id, mz, and rt columns are required to be present.

+-------+--------------+--------------+---------------+----------------+---------------+---------------+-----------+------------------------+------------------------+------------------------+
|  id   | mz           |  mzmin       |  mzmax        |  rt            |  rtmin        |  rtmax        |   npeaks  |  21_qc_no_dil_milliq   |  29_qc_no_dil_milliq   |  8_qc_no_dil_milliq    |
+=======+==============+==============+===============+================+===============+===============+===========+========================+========================+========================+
|  1    | 70.03707021  |  70.037066   |  70.0370750   |  294.1038014   |  294.0634942  |  294.149985   |   3       |  1                     |  1                     |  1                     |
+-------+--------------+--------------+---------------+----------------+---------------+---------------+-----------+------------------------+------------------------+------------------------+
|  2    | 70.06505677  |  70.065045   |  70.0650676   |  141.9560055   |  140.5762528  |  143.335758   |   2       |  1                     |  0                     |  1                     |
+-------+--------------+--------------+---------------+----------------+---------------+---------------+-----------+------------------------+------------------------+------------------------+
|  57   | 78.04643252  |  78.046429   |  78.0464325   |  294.0063397   |  293.9406777  |  294.072001   |   2       |  1                     |  1                     |  0                     |
+-------+--------------+--------------+---------------+----------------+---------------+---------------+-----------+------------------------+------------------------+------------------------+
|  ...  | ...          |   ...        |  ...          |  ...           |  ...          |  ...          |   ...     |  ...                   |  ...                   |  ...                   |
+-------+--------------+--------------+---------------+----------------+---------------+---------------+-----------+------------------------+------------------------+------------------------+

(**) Intensity table
~~~~~~~~~~~~~~~~~~~~

The output from recetox-aplcms tool.
This table contains the peak area for aligned features in all samples.

+-------+------------------------+------------------------+------------------------+
|  id   |  21_qc_no_dil_milliq   |  29_qc_no_dil_milliq   |  8_qc_no_dil_milliq    |
+=======+========================+========================+========================+
|  1    |  13187487.20482895     |  7957395.699119729     |  11700594.397257797    |
+-------+------------------------+------------------------+------------------------+
|  2    |  2075168.6398983458    |  0                     |  2574362.159289044     |
+-------+------------------------+------------------------+------------------------+
|  57   |  2934524.4406785755    |  1333044.5065971944    |  0                     |
+-------+------------------------+------------------------+------------------------+
|  ...  |  ...                   |  ...                   |  ...                   |
+-------+------------------------+------------------------+------------------------+
</token>

<xml name="citations">
    <citation type="doi">10.1021/acs.analchem.6b01214</citation>
</xml>
</macros>