view geo_query/Get_Datasets.xml @ 6:6d0c31137c89 draft

Uploaded
author proteomisc
date Thu, 30 Nov 2023 09:56:30 +0000
parents 7c3585c4241a
children 3eccdf500662
line wrap: on
line source

<tool id="Get_Datasets" name="Query GEO Database" version="2.0">
    <description> Query Gene Expression Omnibus (GEO) Database using an accession code. </description> 
    <macros>
        <import>citations.xml</import>
    </macros>   
    <requirements>
        <requirement type="package" >r-base</requirement>
        <requirement type="package" >r-batch</requirement>
        <requirement type="package" >bioconductor-geoquery</requirement>
        <requirement type="package" >libiconv</requirement>
    </requirements>
    <stdio>
        <exit_code range="1" level="fatal" description="Wrong accession code" />
        <exit_code range="2" level="fatal" description="Network trouble, try again or check your GeoCode" />
        <exit_code range="3" level="fatal" description="GeoCode with no raw data, choose another code or retry" />
    </stdio>
    <command>
    <![CDATA[
    Rscript '$__tool_directory__/GetDatasets.R' GeoCode $GeoCode;
    sh '$__tool_directory__/datatypetweek.sh' 
    
    ]]>
    </command> 
    <inputs>
    <param name="GeoCode"  type="text" value="GSE4632" label="GEO accession code" help="Gene Expression Omnibus (GEO) accession code">
        <sanitizer>
            <valid initial="string.printable,string.digits">
            </valid>
        </sanitizer>
    </param>
    </inputs>
    <outputs>
    <data format="" name="Raw files" >
            <discover_datasets pattern="(?P&lt;name&gt;.+)\.(gpr|GPR)(\.gz)?"  directory="CEL" visible="true"  ext="gpr" assign_primary_output="false"/>
            <discover_datasets pattern="(?P&lt;name&gt;.+)\.(cel|CEL)(\.gz)?"  directory="CEL" visible="true"   ext="cel" assign_primary_output="false" />
            <discover_datasets pattern="(?P&lt;name&gt;.+)\.(gal|GAL)(\.gz)?"  directory="CEL" visible="true"  ext="gal" assign_primary_output="false" />
            <discover_datasets pattern="(?P&lt;name&gt;.+)\.(txt|TXT)(\.gz)?"  directory="CEL" visible="true"   ext="txt" assign_primary_output="false" />
    </data>
    </outputs>
    <tests>
    <test>
        <param name="GeoCode" value="GSE4632" />
        <output name="Raw files">
            <discovered_dataset designation="GSM103772_1" ftype="gpr" file="GSM103772_1.gpr.gz" compare="sim_size"/>
        </output>
    </test>
    </tests>
    <help>
		
.. class:: infomark

**Authors**  T.Bensellak, B.Ettetuani. 

---------------------------------------------------

==================================================================
Query Gene Expression Omnibus (GEO) Database.
==================================================================

-----------
Description
-----------

This tool is used for querying Gene Expression Omnibus Database.

**GEO accession code**

GEO Accession code 

-----------------
Workflow position
-----------------

**Upstream tools**

+------------------------+------------------+--------+-----------+
| Name                   | output file      |format  | parameter |
+========================+==================+========+===========+
| NA                     |  NA              | NA     | NA	 |			
+------------------------+------------------+--------+-----------+


**Downstream tools**

+----------------------------------------------------------------+------------------------------------------------+--------------+
| Name                                                           | Output file                                    | Format       |
+================================================================+================================================+==============+
| Make design and read dataset                                   | Project information and design file            | RData,Tabular|
+----------------------------------------------------------------+------------------------------------------------+--------------+

-----------
Input files
-----------

+---------------------------+------------+
| Parameter : num + label   |   Format   |
+===========================+============+
| GEO accession code        |   String   |
+---------------------------+------------+

------------
Output files
------------

**Set of raw samples**

------------------------------
General schema of the workflow
------------------------------

.. image:: workflow.png 
          :height: 800 
          :width: 700

    </help>
    <expand macro="R_citation">
    </expand>
</tool>