comparison optdoe.xml @ 2:593e0f787172 draft

planemo upload commit f40274f6b9f6a15eb4022aab21286d4c96cd8475-dirty

1:c3f32929a4b7

<tool id="optdoe" name="Design of Experiment" version="@TOOL_VERSION@" profile="19.09">
    <description>An optimal design of experiments (DoE) base package for synthetic biology</description>
    <macros>
        <token name="@TOOL_VERSION@">2.0.2</token>
    </macros>
    <requirements>
        <requirement type="package" version="@TOOL_VERSION@">doebase</requirement>
    </requirements>

            #end if
            #if $adv.ref_parts_file
                --ref_parts_file '$adv.ref_parts_file'
            #end if
            --libsize '$adv.libsize'
            --get_sequences '$adv.get_sequences'
            --backtranslate '$adv.backtranslate'
            --codon_table '$adv.codon_table'
            '$genes_file'
            '$constructs'
    ]]></command>
    <inputs>
        <param name="genes_file" type="data" format="csv" label="Genes" />
        <section name="adv" title="Advanced Options" expanded="false">
            <param name="genes_sbol_file" type="data" format="xml" optional="true" label="Optimised Genes" />
            <param name="ref_parts_file" type="data" format="csv" value="None" optional="true" label="Ref Parts (default: E. coli compliant)"/>
            <param name="libsize" type="integer" value="32" min="32" label="Maximal library size" />
            <param name="get_sequences" type="boolean" checked="true" label="Get sequences" />
            <param name="backtranslate" type="boolean" checked="true" label="Back translate" />
            <param name="codon_table" type="select" label="Codon Table">
                <option value="Eecoli.cut">Escherichia coli K12</option>
                <option value="Ehuman.cut">Homo sapiens</option>
                <option value="Eacica.cut">Acinetobacter calcoaceticus</option>
                <option value="Eagrtu.cut">Agrobacterium tumefaciens str C58</option>
                <option value="Eanasp.cut">Anabaena sp</option>

        <!-- test 1: check if identical outputs are produced with default parameters  -->
            <param name="genes_file" value="genes_lycopene.csv" />
            <output name="constructs" >
                <assert_contents>
                    <is_valid_xml />
                    <has_size value="451293" delta="100" />
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[

.. math:: D_{eff} = \frac{1}{n}\abs{X^{T}X}^{\frac{1}{p}}

|

Where n is the number of experimental runs or library size, p is the number of independent variables, and X is the model matrix, i.e., a row for each experimental run and a column for each term in the model. The library size n can be selected and should be above a minimal threshold depending on the number of combinatorial complexity of the library. 
The experimental design can be evaluated through the provided diagnostics for D-efficiency, power analysis, and relative prediction variance, allowing the optimal selection of library size. 
The resulting design is provided as an SBOL collection containing the definition of each DNA component and the combinatorial library of constructs.

.. image:: https://raw.githubusercontent.com/brsynth/synbiocad-galaxy-wrappers/master/OptDoE/img/image3.png
	:width: 80 %
	:align: center

	:width: 80 %
	:align: center

|

Above are examples of two constructs generated through optimal combinatorial design and represented using SBOL Visual in SynBioHub. 
Note: if advanced parameter "input_parts" is left empty, the following parts are used:


    +---------+------------+--------------------------------------------------+
    | Name    | Type       | SynBioHub                                        |

Input
-----

Required:

* **genes_file**\ : (string) Genes File (csv).

Advanced options:

* **genes_sbol_file**\ : (string) SBOL file containing optimised versions of the genes (RBS, etc)
* **ref_parts_file**\ : (string) CSV with the genetic parts. Default (if left empty) is the above table. To generate a new compatible CSV file, please use the "OptDoE Parts Reference Generator" tool
* **libsize**\ : (integer, default: 32) Maximal library size 
* **get_sequences**\ : (boolean, default: True)
* **backtranslate**\ : (boolean, default: True)
* **codon_table**\ : (text, default: Eecoli.cut) Codon Usage Table. See `codon_table <https://www.ebi.ac.uk/seqdb/confluence/display/JDSAT/EMBOSS+backtranseq+Help+and+Documentation#EMBOSSbacktranseqHelpandDocumentation-WebServices>`_ for more codons.

Output
------

* **constructs**\ : (string) Path to the output SBOL file

Project Link
------------

* `Original Project <https://github.com/pablocarb/doebase>`_

Authors
-------

* **Pablo Carbonell**

License
-------

`MIT <https://raw.githubusercontent.com/pablocarb/appoptdes/master/LICENSE>`_

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

* Joan Hérisson
* Thomas Duigou
    ]]></help>
</tool>

2:593e0f787172

<tool id="optdoe" name="Design of Experiment" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.09">
    <description>An optimal design of experiments (DoE) base package for synthetic biology</description>
    <macros>
        <token name="@VERSION_SUFFIX@">0</token>
        <token name="@TOOL_VERSION@">2.0.2</token>
    </macros>
    <requirements>
        <requirement type="package" version="@TOOL_VERSION@">doebase</requirement>
    </requirements>

            #end if
            #if $adv.ref_parts_file
                --ref_parts_file '$adv.ref_parts_file'
            #end if
            --libsize '$adv.libsize'
            $adv.get_sequences
            $adv.backtranslate
            --codon_table '$adv.codon_table'
            '$genes_file'
            '$constructs'
    ]]></command>
    <inputs>
        <param name="genes_file" type="data" format="csv" label="Genes" help="CSV file with header: Name,Type,Part,Step. Provided by the tool Selenzyme"/>
        <section name="adv" title="Advanced Options" expanded="false">
            <param name="genes_sbol_file" type="data" format="xml" optional="true" label="Optimised Genes" help="SBOL file with genes associated with different RBS. Provided by the tool PartsGenie"/>
            <param argument="--ref_parts_file" type="data" format="csv" value="None" optional="true" label="Ref Parts (default: E. coli compliant)" help="Provide fixed parts"/>
            <param argument="--libsize" type="integer" value="32" min="32" label="Maximal library size" help="Maximal number of contructs in the output"/>
            <param argument="--get_sequences" type="boolean" truevalue="--get_sequences true" falsevalue="--get_sequences false" checked="true" label="Get sequences" help="Grab the sequence for each part of the SBOL output"/>
            <param argument="--backtranslate" type="boolean" truevalue="--backtranslate true" falsevalue="--backtranslate false" checked="true" label="Back translate" help="Translate the protein sequence given by its Uniprot ID to a DNA sequence"/>
            <param argument="--codon_table" type="select" label="Codon Table">
                <option value="Eecoli.cut">Escherichia coli K12</option>
                <option value="Ehuman.cut">Homo sapiens</option>
                <option value="Eacica.cut">Acinetobacter calcoaceticus</option>
                <option value="Eagrtu.cut">Agrobacterium tumefaciens str C58</option>
                <option value="Eanasp.cut">Anabaena sp</option>

        <!-- test 1: check if identical outputs are produced with default parameters  -->
            <param name="genes_file" value="genes_lycopene.csv" />
            <output name="constructs" >
                <assert_contents>
                    <is_valid_xml />
                    <has_text text='rdf:RDF xmlns:owl="http://www.w3.org/2002/07/owl#" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:rdfs="http://www.w3.org/2000/01/rdf-schema#" xmlns:xsd="http://www.w3.org/2001/XMLSchema#" xmlns:dcterms="http://purl.org/dc/terms/" xmlns:prov="http://www.w3.org/ns/prov#" xmlns:sbol="http://sbols.org/v2#" xmlns:xsd1="http://www.w3.org/2001/XMLSchema#dateTime/" xmlns:om="http://www.ontology-of-units-of-measure.org/resource/om-2/" xmlns:synbiohub="http://synbiohub.org#" xmlns:sbh="http://wiki.synbiohub.org/wiki/Terms/synbiohub#" xmlns:sybio="http://www.sybio.ncl.ac.uk#" xmlns:ncbi="http://www.ncbi.nlm.nih.gov#" xmlns:igem="http://wiki.synbiohub.org/wiki/Terms/igem#" xmlns:genbank="http://www.ncbi.nlm.nih.gov/genbank#" xmlns:gbconv="http://sbols.org/genBankConversion#" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:obo="http://purl.obolibrary.org/obo/"'/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[

.. math:: D_{eff} = \frac{1}{n}\abs{X^{T}X}^{\frac{1}{p}}

|

Where n is the number of experimental runs or library size, p is the number of independent variables, and X is the model matrix, i.e., a row for each experimental run and a column for each term in the model. The library size n can be selected and should be above a minimal threshold depending on the number of combinatorial complexity of the library.
The experimental design can be evaluated through the provided diagnostics for D-efficiency, power analysis, and relative prediction variance, allowing the optimal selection of library size.
The resulting design is provided as an SBOL collection containing the definition of each DNA component and the combinatorial library of constructs.

.. image:: https://raw.githubusercontent.com/brsynth/synbiocad-galaxy-wrappers/master/OptDoE/img/image3.png
	:width: 80 %
	:align: center

	:width: 80 %
	:align: center

|

Above are examples of two constructs generated through optimal combinatorial design and represented using SBOL Visual in SynBioHub.
Note: if advanced parameter "input_parts" is left empty, the following parts are used:


    +---------+------------+--------------------------------------------------+
    | Name    | Type       | SynBioHub                                        |

Input
-----

Required:

* **Genes**\ : Output of Selenzyme. The CSV file contains four columnds: Name,Type,Part,Step. The column "Name" contains the Uniprot ID found by Selenzyme. The column "Type" represents the type of the "Part", a *gene*. The column "Part" has the same information as the column "Name". The column "Step" contains the order of the position in the pathway of the gene.

Advanced options:

* **Optimised Genes**\ : SBOL file containing optimized versions of the genes associated with different RBS. Output of the PartsGenie tool.
* **Ref Parts**\ : CSV with the genetic parts. Default (if left empty) is the above table. To generate a new compatible CSV file, please use the "OptDoE Parts Reference Generator" tool
* **Maximal library size**\ : (integer, default: 32) Maximal number of constructs in the SBOL output. 
* **Get sequences**\ : (boolean, default: True) Grab the sequence for each part of the SBOL output.
* **Back translate**\ : (boolean, default: True) Translate the protein sequence given by its Uniprot ID to a DNA sequence.
* **Codon Table**\ : (text, default: Eecoli.cut) Codon Usage Table. See `codon_table <https://www.ebi.ac.uk/seqdb/confluence/display/JDSAT/EMBOSS+backtranseq+Help+and+Documentation#EMBOSSbacktranseqHelpandDocumentation-WebServices>`_ for more codons.

Output
------

* **Constructs**\ : Output SBOL file. It contains some combinations of constructs according to the algorithm described above.

Project Link
------------

* `Original Project <https://github.com/pablocarb/doebase>`_

License
-------

`MIT <https://raw.githubusercontent.com/pablocarb/appoptdes/master/LICENSE>`_

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

* Joan Hérisson
* Thomas Duigou
    ]]></help>
    <creator>
        <person givenName="Pablo" familyName="Carbonell" email="[e-mail]" identifier="https://orcid.org/0000-0002-0993-5625" />
    </creator>
</tool>