annotate Marea/marea.xml @ 9:7c76e8e319c2 draft

fix cluster file and help section

<tool id="MaREA" name="Metabolic Enrichment Analysis" version="1.0.0">
    <description>for Galaxy</description>
    <macros>
        <import>marea_macros.xml</import>
    </macros>
    <requirements>
        <requirement type="package" version="0.23.0">pandas</requirement>
        <requirement type="package" version="1.1.0">scipy</requirement>
        <requirement type="package" version="0.10.1">cobra</requirement>
        <requirement type="package" version="4.2.1">lxml</requirement>
        <requirement type="package" version="0.8.1">svglib</requirement>
        <requirement type="package" version="3.4.0">reportlab</requirement>
    </requirements>
    <command detect_errors="exit_code">
        <![CDATA[
      	python $__tool_directory__/marea.py
        --rules_selector $cond_rule.rules_selector
        #if $cond_rule.rules_selector == 'Custom':
            --custom ${cond_rule.Custom_rules}
            --yes_no ${cond_rule.cond_map.yes_no}
            #if $cond_rule.cond_map.yes_no == 'yes':
                --custom_map $cond_rule.cond_map.Custom_map
            #end if
        #end if
      	--none $None
      	--pValue $pValue
      	--fChange $fChange
      	--tool_dir $__tool_directory__
      	--option $cond.type_selector
        --out_log $log
        #if $cond.type_selector == 'datasets':
            --input_datas
            #for $data in $cond.input_Datasets:
                ${data.input}
            #end for
            --names
            #for $data in $cond.input_Datasets:
                ${data.input_name}
            #end for
        #elif $cond.type_selector == 'dataset_class':
            --input_data ${input_data}
            --input_class ${input_class}
        #end if
        ]]>
    </command>

    <inputs>
        <conditional name="cond_rule">
            <expand macro="options"/>
            <when value="HMRcore">
            </when>
            <when value="Recon">
            </when>
            <when value="Custom">
                <param name="Custom_rules" type="data" format="tabular, csv, tsv, xml" label="Custom rules" />
                <conditional name="cond_map">
                    <param name="yes_no" type="select" label="Custom map? (optional)">
                        <option value="no" selected="true">no</option>
                        <option value="yes">yes</option>
                    </param>
                    <when value="yes">
                        <param name="Custom_map" argument="--custom_map" type="data" format="xml, svg" label="custom-map.svg"/>
                    </when>
                    <when value="no">
                    </when>
                </conditional>
            </when>
        </conditional>
        <conditional name="cond">
            <param name="type_selector" argument="--option" type="select" label="Input format:">
                <option value="datasets" selected="true">RNAseq of group 1 + RNAseq of group 2 + ... + RNAseq of group N</option>
                <option value="dataset_class">RNAseq of all samples + sample group specification</option>
            </param>
            <when value="datasets">
                <repeat name="input_Datasets" title="RNAseq" min="2">
                    <param name="input" argument="--input_datas" type="data" format="tabular, csv, tsv" label="add dataset" />	
                    <param name="input_name" argument="--names" type="text" label="Dataset's name:" value="Dataset" help="Defalut: Dataset" />
                </repeat>
            </when>
            <when value="dataset_class">
                <param name="input_data" argument="--input_data" type="data" format="tabular, csv, tsv" label="RNAseq of all samples" />
                <param name="input_class" argument="--input_class" type="data" format="tabular, csv, tsv" label="Sample group specification" />
            </when>
        </conditional>
        <param name="None" argument="--none" type="boolean" truevalue="true" falsevalue="false" checked="true" label="(A and NaN) solved as (A)?" /> 
        <param name="pValue" argument="--pValue" type="float" size="20" value="0.05" max="1" min="0" label="P-value threshold:" help="min value 0" />
        <param name="fChange" argument="--fChange" type="float" size="20" value="1.5" min="1" label="Fold-Change threshold:" help="min value 1" />
    </inputs>

    <outputs>
        <data format="txt" name="log" label="Log" />
        <collection name="map_svg" type="list" label="Graphical results (.svg)">
            <filter>(cond_rule['rules_selector'] == 'HMRcore') or ((cond_rule['rules_selector'] == 'Custom') and (cond_rule['cond_map']['yes_no'] == 'yes'))</filter>
            <discover_datasets pattern="__name_and_ext__" directory="map_svg" />
        </collection>
        <collection name="map_pdf" type="list" label="Graphical results (.pdf)">
            <filter>(cond_rule['rules_selector'] == 'HMRcore') or ((cond_rule['rules_selector'] == 'Custom') and (cond_rule['cond_map']['yes_no'] == 'yes'))</filter>
            <discover_datasets pattern="__name_and_ext__" directory="map_pdf" />
        </collection>
        <collection name="table_out" type="list" label="Tabular results">
            <discover_datasets pattern="__name_and_ext__" directory="table_out" />
        </collection>
    </outputs>
    <tests>
        <test>
            <param name="pValue" value="0.56"/>
            <output name="log" file="log.txt"/>
        </test>
    </tests>
    <help>
<![CDATA[

What it does
-------------

This tool analyzes RNA-seq dataset(s) as described in Graudenzi et al."`MaREA`_: Metabolic feature extraction, enrichment and visualization of RNAseq data" bioRxiv (2018): 248724.

Accepted files are: 
    - option 1) two or more RNA-seq datasets, each referring to samples in a given condition/class. The user can specify a label for each class (as e.g. "*classA*" and "*classB*");
    - option 2) one RNA dataset and one class-file specifying the class/condition each sample belongs to.

Optional files:
    - custom GPR (Gene-Protein-Reaction) rules. Two accepted formats:

	* (Cobra Toolbox and CobraPy compliant) xml of metabolic model;
	* .csv file specifyig for each reaction ID (column 1) the corresponding GPR rule (column 2).
    - custom svg map. Graphical elements must have the same IDs of reactions. See HmrCore svg map for an example.

The tool generates:
    1) a tab-separated file: reporting fold-change and p-values of reaction activity scores (RASs) between a pair of conditions/classes;
    2) a metabolic map file (downlodable as .svg): visualizing up- and down-regulated reactions between a pair of conditions/classes;
    3) a log file (.txt).

RNA-seq datasets format: tab-separated text files, reporting the expression level (e.g., TPM, RPKM, ...) of each gene (row) for a given sample (column). Header: sample ID.

Class-file format: each row of the class-file reports the sample ID (column1) and the label of the class/condition the sample belongs to (column 2).

To calculate P-Values and Fold-Changes and to generate maps, comparisons are performed for each possible pair of classes.

Output files will be named as classA_vs_classB. Reactions will conventionally be reported as up-regulated (down-regulated) if they are significantly more (less) active in class having label "classA".


Example input
-------------

**"Custom Rules"** option:

Custom Rules Dastaset:

@CUSTOM_RULES_EXEMPLE@

**"RNAseq of group 1 + RNAseq of group 2 + ... + RNAseq of group N"** option:

RNA-seq Dataset 1:						

@DATASET_EXEMPLE1@

RNA-seq Dataset 2:

@DATASET_EXEMPLE2@

**"RNAseq of all samples + sample group specification"** option:

RNA-seq Dataset:

@DATASET_EXEMPLE1@

Class-file:

+------------+------------+   
| Patient_ID |    class   |   
+============+============+   
| TCGAAA3529 |     MSI    |   
+------------+------------+    
| TCGAA62671 |     MSS    |    
+------------+------------+    
| TCGAA62672 |     MSI    |   
+------------+------------+

|

.. class:: infomark

**TIP**: If your data is not TAB delimited, use `Convert delimiters to TAB`_.

.. class:: infomark

**TIP**: If your dataset is not split into classes, use `MaREA cluster analysis`_.

@REFERENCE@

.. _MaREA: https://www.biorxiv.org/content/early/2018/01/16/248724
.. _Convert delimiters to TAB: https://usegalaxy.org/?tool_id=Convert+characters1&version=1.0.0&__identifer=6t22teyofhj
.. _MaREA cluster analysis: http://link del tool di cluster.org

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