view dimet_abundance_plot.xml @ 3:422207876644 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/DIMet commit 0e7c185547d51ec3fc8ff2d87ac7e2b6d9ae0b0f

<tool id="dimet_@EXECUTABLE@" name="dimet @TOOL_LABEL@" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="20.05">
    <description>
        Figures of metabolites total abundance as barplots (by DIMet)
    </description>
    <macros>
        <token name="@TOOL_LABEL@">abundance plot</token>
        <token name="@EXECUTABLE@">abundance_plot</token>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <command detect_errors="exit_code"><![CDATA[
    @INIT_CONFIG@
    @INIT_ABUNDANCE_PLOT@
    @INIT_ABUNDANCE_PLOT_CONDITIONS@
    @INIT_TIMEPOINTS@
    @INIT_ENRICHMENT_METABOLITES@
    HYDRA_FULL_ERROR=1 python -m dimet
        -cp '$__new_file_path__/config'
        '++hydra.run.dir=abundance_plot'
        '++figure_path=figures'
        '++table_path=tables'
        '++analysis={
            metabolites:${metabolites},
            dataset:{
                _target_:dimet.data.DatasetConfig,
                name: "Galaxy DIMet run"
            },
            method:{
                _target_: dimet.method.AbundancePlotConfig,
                label: abundance_plot,
                name: "Generate abundance plots",
                barcolor: timepoint,
                axisx: condition,
                axisx_labeltilt: '${output_options.axisx_labeltilt}',
                height_each_subfig: '${output_options.height_each_subfig}',
                palette:${output_options.palette},
                as_grid:${output_options.as_grid},
                x_text_modify_as:null,
                do_stripplot:${output_options.do_stripplot},
                figure_format:${output_options.figure_format}
            },
            label: abundance_plot,
            width_each_subfig: '${output_options.width_each_subfig}'
        }'
        '++analysis.dataset.label='
        '++analysis.timepoints=${timepoints}'
        '++analysis.dataset.subfolder='
        '++analysis.dataset.conditions=${conditions}'
        #if $metadata_path:
             '++analysis.dataset.metadata=metadata'
        #end if
        #if $abundance_file:
            '++analysis.dataset.abundances=abundance'
        #end if
    @REMOVE_CONFIG@
    ]]></command>
    <inputs>
        <expand macro="input_parameters_abundance"/>
        <expand macro="plot_abundance_factor_list"/>
        <expand macro="timepoint"/>
        <expand macro="compartments_abundance"/>
        <expand macro="abundance_metabolites_list"/>
        <section name="output_options" title="Output options">
            <expand macro="palette"/>
            <param name="figure_format" type="select" value="pdf" display="radio" label="Select output figure format" help="Please enter at max 1 format">
                <option value="pdf">Pdf</option>
                <option value="svg">Svg</option>
            </param>
            <param name="axisx_labeltilt" type="integer" min="0" max="180" value="70" label="X axis label tilt"
                   help="Default value is 70."/>
            <param name="width_each_subfig" type="float" min="1.0" max="15.0" value="3.0" label="width of subfig plots"
                   help="Default value is 3."/>
            <param name="height_each_subfig" type="float" min="1.0" max="15.0" value="5.5" label="height of subfig plots"
                   help="Default value is 5.5"/>
            <param name="as_grid" type="boolean" value="false" label="plot as grid"
                   help="Default value is false."/>
            <param name="do_stripplot" type="boolean" value="false" label="add strip plot on abundance bar"
                   help="Default value is false."/>

        </section>
    </inputs>
    <outputs>
        <collection name="report" type="list">
            <discover_datasets pattern="__designation_and_ext__" directory="figures"/>
        </collection>
    </outputs>
    <tests>
        <test>
            <param name="abundance_file" ftype="tabular" value="AbundanceCorrected.csv"/>
            <param name="metadata_path" ftype="tabular" value="example1_metadata.csv"/>
            <repeat name="plot_abundance_factor_list">
                <param name="condition" value="sgLDHA"/>
            </repeat>
            <param name="timepoint" value='T0,T24'/>
            <param name="compartments" value='endo'/>
            <param name="metabolites_list" value="Fru1P"/>
            <section name="output_options">
                <param name="axisx_labeltilt" value="70"/>
                <param name="palette" value="pastel"/>
                <param name="width_each_subfig" value="3.0"/>
                <param name="height_each_subfig" value="5.5"/>
                <param name="as_grid" value="false"/>
                <param name="do_stripplot" value="false"/>
                <param name="figure_format" value="svg"/>
            </section>
            <output_collection name="report" type="list" count="2">
                <element file="bars_endo_Fru1P-total_abundance.svg" name="bars_endo_Fru1P-total_abundance" ftype="svg" compare="sim_size" delta="100"/>
                <element file="legend.svg" name="legend" ftype="svg" compare="sim_size" delta="100"/>
            </output_collection>
        </test>
    </tests>
    <help><![CDATA[

This module is part of DIMet: Differential analysis of Isotope-labeled targeted Metabolomics data (https://pypi.org/project/DIMet/).

DIMet total abundances plot performs comparative bars for visualization of the total abundances of each metabolite across the different conditions present in your data and all/selected time points.  All (or selected) metabolites are processed automatically.

The figures in .pdf format are of publication quality, and as they are vectorial images you can open them and customize aesthetics with a professional image software such as Inkscape, Adobe Illustrator, Sketch,  CorelDRAW, etc.


    **Input data files**

For running DIMet @EXECUTABLE@ you need the following .csv files :

- The total **abundances** file, and

- The metadata file, a unique file with the description of the samples. This file is compulsory (see section **Metadata File Information**).


The total abundances file must be organized as a matrix:
- The first column must contain Metabolite IDs that are unique (not repeated) within the file.
- The rest of the columns correspond to the samples
- The rows correspond to the metabolites
- The values must be tab separated, with the first row containing the sample/column labels.



Example - Metabolites **abundances**:

    =============== ================== ================== ================== ================== ================== ==================
    ID              **MCF001089_TD01** **MCF001089_TD02** **MCF001089_TD03** **MCF001089_TD04** **MCF001089_TD05** **MCF001089_TD06**
    =============== ================== ================== ================== ================== ================== ==================
    2_3-PG          8698823.9926       10718737.7217      10724373.9         8536484.5          22060650           28898956
    2-OHGLu         36924336           424336             92060650           45165              84951950           965165051
    Glc6P           2310               2142               2683               1683               012532068          1252172
    Gly3P           399298             991656565          525195             6365231            89451625           4952651963
    IsoCit          0                  0                  0                  84915613           856236             954651610
    =============== ================== ================== ================== ================== ================== ==================


**Metadata File Information**

Provide a tab-separated file that has the names of the samples in the first column and one header row.
Column names must be exactly in this order:

   name_to_plot
   condition
   timepoint
   timenum
   compartment
   original_name


Example **Metadata File**:


    ==================== =============== ============= ============ ================ =================
    **name_to_plot**     **condition**   **timepoint** **timenum**  **compartment**   **original_name**
    -------------------- --------------- ------------- ------------ ---------------- -----------------
    Control_cell_T0-1    Control         T0            0            cell             MCF001089_TD01
    Control_cell_T0-2    Control         T0            0            cell             MCF001089_TD02
    Control_cell_T0-3    Control         T0            0            cell             MCF001089_TD03
    Tumoral_cell_T0-1    Tumoral         T0            0            cell             MCF001089_TD04
    Tumoral_cell_T0-2    Tumoral         T0            0            cell             MCF001089_TD05
    Tumoral_cell_T0-3    Tumoral         T0            0            cell             MCF001089_TD06
    Tumoral_cell_T24-1   Tumoral         T24           24           cell             MCF001089_TD07
    Tumoral_cell_T24-2   Tumoral         T24           24           cell             MCF001089_TD08
    Tumoral_cell_T24-3   Tumoral         T24           24           cell             MCF001090_TD01
    Control_med_T24-1    Control         T24           24           med              MCF001090_TD02
    Control_med_T24-2    Control         T24           24           med              MCF001090_TD03
    Tumoral_med_T24-1    Tumoral         T24           24           med              MCF001090_TD04
    Tumoral_med_T24-2    Tumoral         T24           24           med              MCF001090_TD05
    Control_med_T0-1     Control         T0            0            med              MCF001090_TD06
    Tumoral_med_T0-1     Tumoral         T0            0            med              MCF001090_TD07
    Tumoral_med_T0-2     Tumoral         T0            0            med              MCF001090_TD08
    ==================== =============== ============= ============ ================ =================


The column **original_name** must have the names of the samples as given in your data.

The column **name_to_plot** must have the names as you want them to be (or set identical to original_name if you prefer). To set names that
are meaningful is a better choice, as we will take them to display the results.

The column **timenum** must contain only the numeric part of the timepoint, for example 2,0, 10, 100 (this means, without letters ("T", "t", "s", "h" etc)
nor any other symbol). Make sure these time numbers are in the same units (but do not write the units here!).

The column **compartment** is an abbreviation, coined by you, for the compartments. This will be used for the results' files names: the longer the
compartments names are, the longer the output files' names! Please pick short and clear abbreviations to fill this column.


**Running the analysis**


You can precise how you want your analysis to be executed, with the parameters:

- **conditions** : the conditions present in your data, exactly in the ORDER you want them to appear both in the x axis and in the legend.

- **timepoints** : the selected (you can select all) time points, that will be shown in the x axis.

- **width_each_subfig** : the desired width (in inches) for the the individual metabolites' figures



There exist hints on use that will guide you, next to the parameters.


The output consists of bar-plot figures, one by each metabolite, and one legend .pdf file, common to all the produced figures.



**Available data for testing**

You can test our tool with the data from our manuscript https://zenodo.org/record/10579862 (the pertinent
files for you are located in the subfolders inside the data folder).
You can also use the minimal data examples from https://zenodo.org/record/10579891

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