view ipapy2_MS2_annotation.xml @ 0:6a23970e8093 draft default tip

planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/ipapy2 commit 64b61ff2823b4f54868c0ab7a4c0dc49eaf2979a

<tool id="ipapy2_MS2_annotation" name="ipaPy2 MS2 annotation" version="@TOOL_VERSION@+galaxy0" profile="@PROFILE@">
    <description>annotate features from MS2 using a supplied MS2 database</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    
    <expand macro="requirements"/>

    <command detect_errors="exit_code"><![CDATA[
        #set $computed_ppmthr = float($ppm) * 2
         python3  '${__tool_directory__}/ipapy2_MS2_annotation.py'
        --input_dataset_mapped_isotope_patterns '${mapped_isotope_patterns}' '${mapped_isotope_patterns.ext}'
        --input_dataset_MS2 '${MS2_fragmentation_data}' '${MS2_fragmentation_data.ext}'
        --input_dataset_adducts '${all_adducts}' '${all_adducts.ext}'
        --input_dataset_MS2_DB '${MS2_DB}' '${MS2_DB.ext}'
        --ppm ${ppm}
        --ratiosd ${ratiosd}
        #if $ppmunk
            --ppmunk ${ppmunk}
        #else
            --ppmunk ${ppm}
        #end if
            --ratiounk ${ratiounk}
        #if $ppmthr
            --ppmthr ${ppmthr}
        #else
            --ppmthr ${computed_ppmthr}
        #end if
        --pRTNone ${pRTNone}
        --pRTout ${pRTout}
        --mzdCS ${mzdCS}
        --ppmCS ${ppmCS}
        --CSunk ${CSunk}
        --evfilt ${evfilt}
        --output_dataset '${MS2_annotations}' '${MS2_annotations.ext}'
        --ncores \${GALAXY_SLOTS:-1}
    ]]></command>

    <inputs>
        <param label="Mapped isotope patterns" name="mapped_isotope_patterns" type="data" format="csv,tsv,tabular,parquet" help="A dataset containing the MS1 data. Ideally obtained from map_isotope_patterns" />
        <param label="MS2 fragmentation data" name="MS2_fragmentation_data" type="data" format="csv,tsv,tabular,parquet" help="A dataset containing the MS2 data. (If a csv file fails kindly use a tsv file.)" />
        <param label="all possible adducts table" name="all_adducts" type="data" format="csv,tsv,tabular,parquet" help="A dataset containing the information on all the possible adducts given the database." />
        <param label="MS2 Database" name="MS2_DB" type="data" format="csv,tsv,tabular,parquet" help="A dataset containing the database containing the MS2 information." />
        <expand macro="ppm"/>
        <section name="unknown" title="unknown settings">
            <expand macro="ms_unknown"/>
            <param name="CSunk" type="float" value="0.7">
                <label>cosine similarity for unknown</label>
                <help>cosine similarity score associated with the 'unknown' annotation. Default 0.7.</help>
            </param>
        </section>

        <section name="optional_settings" title="optional settings">
            <expand macro="ms_options"/>
            <param name="mzdCS" type="integer" value="0" label="MS2 mz threshold">
                <help>maximum mz difference allowed when computing cosine similarity scores. 
                If one wants to use this parameter instead of ppmCS, this must be set to 0. Default 0.</help>
            </param>
            <param name="ppmCS" type="integer" value="10" label="maximum ppm for cosine similarity scores">
                <help>maximum ppm allowed when computing cosine similarity scores. 
                If one wants to use this parameter instead of mzdCS, this must be set to 0. Default 10.</help>
            </param>
            <param name="evfilt" type="select" label="same collision energy">
                <help>If true, only spectrum acquired with the same collision energy are considered. Default value False.</help>
                <option value="False">False</option>
                <option value="True">True</option>
            </param>
        </section>
    </inputs>

    <outputs>
        <data label="${tool.name} on ${on_string}" name="MS2_annotations"  format_source="mapped_isotope_patterns"/>
    </outputs>

    <tests>
        <test>
            <param name="mapped_isotope_patterns" value="mapped_isotope_patterns.csv"/>
            <param name="MS2_fragmentation_data" value="MS2_fragmentation_data.tsv"/>
            <param name="all_adducts" value="all_adducts.csv"/>
            <param name="MS2_DB" value="MS2_DB.csv"/>
            <param name="ppm" value="3"/>
            <output name="MS2_annotations">
                <assert_contents>
                    <has_n_columns n="13" sep=","/>
                    <has_n_lines n="158" delta="5" />
                </assert_contents>
            </output>
        </test>
    </tests>

    <help><![CDATA[

.. _ipapy2_ms2_annotation:

==========================
ipaPy2 MS2 Annotation Tool
==========================

**Tool Description**

This tool performs annotation of features in your dataset using MS2 fragmentation data and a supplied MS2 database. It integrates MS1 and MS2 information to provide high-confidence annotations, leveraging prior and posterior probabilities based on mass, retention time (RT), known chemical knowledge, and isotope patterns.

How it works
------------

- **Prior probabilities** are calculated using only the mass information.
- **Posterior probabilities** incorporate mass, RT, prior knowledge, and isotope patterns for more accurate annotation.
- The tool matches features in your data to entries in the MS2 database, considering user-defined tolerances for mass (ppm), retention time, and cosine similarity thresholds for spectral matching.

Inputs
------

1. **Mapped isotope patterns**  
   Dataset containing MS1 data, ideally obtained from the ``map_isotope_patterns`` tool.

2. **MS2 fragmentation data**  
   Dataset with MS2 spectra. If a CSV file fails, try using a TSV file.

3. **All possible adducts table**  
   Table listing all possible adducts for the database.

4. **MS2 Database**  
   Reference database containing MS2 information for annotation.

5. **Parameters**  
   - **ppm**: Mass tolerance in parts per million for matching.
   - **Cosine similarity thresholds**:  
   - ``mzdCS``: Maximum m/z difference for cosine similarity (set to 0 to use ``ppmCS``).
   - ``ppmCS``: Maximum ppm for cosine similarity (set to 0 to use ``mzdCS``).
   - **evfilt**: If set to True, only spectra acquired with the same collision energy are considered.
   - **Unknown settings**: Parameters for handling unknowns, such as cosine similarity threshold for unknown annotations.

Outputs
-------

- **MS2_annotations**  
  Annotated dataset with additional columns describing the best-matching database entries, probabilities, and spectral similarity scores.

Example
-------

Suppose you have mapped isotope patterns, MS2 fragmentation data, a list of all adducts, and an MS2 database. You can use this tool to annotate your features as follows:

.. code-block::

    mapped_isotope_patterns.csv
    MS2_fragmentation_data.tsv
    all_adducts.csv
    MS2_DB.csv

Set the desired tolerances (e.g., ``ppm = 3``) and run the tool. The output will be a table with annotations for each feature.

Notes
-----

- For best results, ensure your input files are correctly formatted and contain the required columns.
- If you encounter issues with CSV files, try converting them to TSV format.
- The tool is designed to be flexible and can handle various input formats (CSV, TSV, Parquet, Tabular).

References
----------

- For more details on the annotation algorithm and scoring, refer to the ipaPy2 documentation or associated publications.

    ]]></help>

    <expand macro="citations"/>
</tool>