annotate cloning_similation.xml @ 0:3a3b0f7cb5c2 draft

planemo upload for repository https://github.com/Edinburgh-Genome-Foundry/DnaCauldron/tree/master commit 3401816c949b538bd9c67e61cbe92badff6a4007-dirty

<tool id="cloning_simulation" name="Cloning Simulation" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.09">
    <description>A cloning simulator for synthetic biology</description>
    <macros>
        <token name="@VERSION_SUFFIX@">0</token>
        <token name="@TOOL_VERSION@">0.1.0</token>
    </macros>
    <requirements>
        <requirement type="package" version="0.1.11">flametree</requirement>
        <requirement type="package" version="1.85"> biopython </requirement>
        <requirement type="package" version="0.1.10">proglog</requirement>
        <requirement type="package" version="2.2.3">pandas</requirement>
        <requirement type="package" version="2.0.12">dnacauldron</requirement>
        <requirement type="package" version="0.3.9">pdf-reports</requirement>
        <requirement type="package" version="0.1.8">sequenticon</requirement>
        <requirement type="package" version="3.1.5">dna_features_viewer</requirement>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[
        #set genbank_file_paths = ','.join([str(f) for f in $genbank_files])
        #set file_name_mapping = ",".join(["%s:%s" % (file.file_name, file.name) for file in $genbank_files])
        #set domesticated_input_paths = ','.join([str(f) for f in $domesticated_input])
        #set file_name_mapping_dom = ",".join(["%s:%s" % (file.file_name, file.name) for file in $domesticated_input])
        #if $domesticated_input_paths != '' and $genbank_file_paths == ''
            #set genbank_file_paths = ','.join([str(f) for f in $domesticated_input])
            #set file_name_mapping = ",".join(["%s:%s" % (file.file_name, file.name) for file in $domesticated_input])
            #set domesticated_input_paths = ''
            #set file_name_mapping_dom = ''
        #end if
        mkdir 'outdir_zip' && mkdir 'outdir_gb' &&
        cp '$assembly_csv' 'assembly_csv.csv' &&
        python '$__tool_directory__/cloning_simulation.py'
            --parts_files '$genbank_file_paths'
            --domesticated_seq '$domesticated_input_paths'
            --assembly_csv 'assembly_csv.csv'
            --assembly_plan_name '$assembly_plan_name'
            --file_name_mapping '$file_name_mapping'
            --file_name_mapping_dom '$file_name_mapping_dom'
            --use_file_names_as_id '$adv.use_file_names_as_ids'
            --outdir_simulation 'outdir_zip'
            --outdir_gb 'outdir_gb'
            --output_simulation 'output_zip.zip'
            --enzyme '$adv.enzyme'
            --topology '$topology' &&
        cp 'output_zip.zip' '$output_zip'
    ]]></command>
    <inputs>
        <param name="genbank_files" type="data_collection" collection_type="list" format="genbank,fasta" label="GenBank and/or Fasta File(s)" optional="True"/>
        <param name="assembly_csv" type="data" format="csv" label="Assemby csv"/>
        <param name="domesticated_input" type="data_collection" collection_type="list" format="genbank" label="Domesticated GenBank" optional="True"/>
        <param name="assembly_plan_name" type="select" label="Assembly Calss" help="select the assambly class">
            <option value="Type2sRestrictionAssembly" selected="True">GoldenGate_assembly</option>
            <option value="GibsonAssembly">Gibson_assembly</option>
            <option value="BASICAssembly">BASIC_assembly</option>
            <option value="BioBrickStandardAssembly">biobrick_assembly</option>
            <option value="LigaseCyclingReactionAssembly">lcr_assembly</option>
        </param>
        <param name="topology" type="select" label="Assambly Topology" help="select circular or linear topology">
            <option value="linear">linear</option>
            <option value="circular" selected="True">circular</option>
        </param>
        <section name="adv" title="Advanced Options" expanded="false">
            <param name="enzyme" type="text" label="Enzyme" value="auto" optional="True"/>
            <param name="use_file_names_as_ids" type="boolean" checked="True" label="Use File Names As Sequence IDs" />
        </section>
    </inputs>   
    <outputs>
        <data format="zip" name="output_zip" label="simulation results (zip)"/>
        <collection name="construct_gb" type="list" label="simulation results (gb)">
                <discover_datasets pattern="(?P&lt;name&gt;.*).gb" format="genbank" directory="outdir_gb" />
        </collection>
    </outputs>
    <tests>
        <!--test type2s_assembly class-->
        <test> 
            <param name="genbank_files">
                <collection type="list">
                    <element name="part_A" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_A.gb" />
                    <element name="part_B" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_B.gb" />
                    <element name="part_C" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_C.gb" />
                    <element name="part_D" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_D.gb" />
                    <element name="part_E" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_E.gb" />
                    <element name="part_F" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_F.gb" />
                    <element name="part_G" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_G.gb" />
                    <element name="part_H" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_H.gb" />
                    <element name="part_I" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_I.gb" />
                    <element name="part_J" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_J.gb" />
                    <element name="part_K" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_K.gb" />
                    <element name="part_L" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_L.gb" />
                </collection>
            </param>
            <param name="assembly_csv" value="2-step_golden_gate_parts/2-step-golden_gate_plan.csv" />
            <param name='assembly_plan_name' value='Type2sRestrictionAssembly' />
            <param name="topology" value="circular"/>
            <param name="adv|use_file_names_as_ids" value="True" />
            <output name="output_zip" ftype='zip'>
                <assert_contents>
                    <has_archive_member path=".*" n="62"/>
                    <has_archive_member path="assambly_simulation/assembly_plan_graph.pdf">
                        <has_size min="5"/>
                    </has_archive_member>
                </assert_contents>
            </output>
            <output_collection name="construct_gb" type="list" count="4">
                <element name="construct_1">
                    <assert_contents>
                     <has_n_lines min="20" />
                    </assert_contents>
                </element>
                <element name="construct_2">
                    <assert_contents>
                     <has_n_lines min="20" />
                    </assert_contents>
                </element>
                <element name="construct_3">
                    <assert_contents>
                     <has_n_lines min="20" />
                    </assert_contents>
                </element>
                 <element name="construct_4">
                    <assert_contents>
                     <has_n_lines min="20" />
                    </assert_contents>
                </element>
            </output_collection>
        </test>
        <!--test gibson_assembly class-->
        <test> 
            <param name="genbank_files">
                <collection type="list">
                    <element name="gibson_sequences" value="Gibson_assembly_dataset/gibson_sequences.fa" />
                </collection>
            </param>
            <param name="assembly_csv" value="Gibson_assembly_dataset/gibson_assembly.csv" />
            <param name='assembly_plan_name' value='GibsonAssembly' />
            <param name="topology" value="circular"/>
            <param name="adv|use_file_names_as_ids" value="True" />
            <output name="output_zip" ftype='zip'>
                <assert_contents>
                    <has_archive_member path=".*" n="78"/>
                    <has_archive_member path="assambly_simulation/Report.pdf">
                        <has_size min="5"/>
                    </has_archive_member>
                </assert_contents>
            </output>
            <output_collection name="construct_gb" type="list" count="3">
                <element name="construct_1">
                    <assert_contents>
                     <has_n_lines min="20" />
                    </assert_contents>
                </element>
                <element name="construct_2">
                    <assert_contents>
                     <has_n_lines min="20" />
                    </assert_contents>
                </element>
                <element name="construct_3">
                    <assert_contents>
                     <has_n_lines min="20" />
                    </assert_contents>
                </element>
            </output_collection>
        </test>
        <!--test lcr_assembly class-->
        <test> 
            <param name="genbank_files">
                <collection type="list">
                    <element name="RFP_GFP_plasmid_BOs" value="lcr_assembly_dataset/RFP_GFP_plasmid_BOs.fa" />
                    <element name="RFP_GFP_plasmid_parts" value="lcr_assembly_dataset/RFP_GFP_plasmid_parts.fa" />
                </collection>
            </param>
            <param name="assembly_csv" value="lcr_assembly_dataset/assembly_plan.csv" />
            <param name='assembly_plan_name' value='LigaseCyclingReactionAssembly' />
            <param name="topology" value="circular"/>
            <param name="adv|use_file_names_as_ids" value="True" />
            <output name="output_zip" ftype='zip'>
                <assert_contents>
                    <has_archive_member path=".*" n="68"/>
                    <has_archive_member path="assambly_simulation/Report.pdf">
                        <has_size min="5"/>
                    </has_archive_member>
                </assert_contents>
            </output>
            <output_collection name="construct_gb" type="list" count="0">
            </output_collection>
        </test>
        <!--test BASIC_assembly class-->
        <test> 
            <param name="genbank_files">
                <collection type="list">
                    <element name="GFP" value="BASIC_assembly_dataset/GFP.gb" />
                    <element name="p15A_kan" value="BASIC_assembly_dataset/p15A_kan.gb" />
                    <element name="promoter" value="BASIC_assembly_dataset/promoter.gb" />
                    <element name="RFP" value="BASIC_assembly_dataset/RFP.gb" />
                    <element name="oligos" value="BASIC_assembly_dataset/oligos.fa" />
                </collection>
            </param>
            <param name="assembly_csv" value="BASIC_assembly_dataset/basic_assembly.csv" />
            <param name='assembly_plan_name' value='BASICAssembly' />
            <param name="topology" value="circular"/>
            <param name="adv|use_file_names_as_ids" value="True" />
            <output name="output_zip" ftype='zip'>
                <assert_contents>
                    <has_archive_member path=".*" n="47"/>
                    <has_archive_member path="assambly_simulation/Report.pdf">
                        <has_size min="5"/>
                    </has_archive_member>
                </assert_contents>
            </output>
            <output_collection name="construct_gb" type="list" count="0">
            </output_collection>
        </test>
        <!--test biobrick_assembly class-->
        <test> 
            <param name="genbank_files">
                <collection type="list">
                    <element name="BBa_E0040_GFP" value="BioBrick_assembly_dataset/BBa_E0040_GFP.gb" />
                    <element name="BBa_J23119_prom" value="BioBrick_assembly_dataset/BBa_J23119_prom.gb" />
                    <element name="BBa_J23119_prom_flawed" value="BioBrick_assembly_dataset/BBa_J23119_prom_flawed.gb" />
                    <element name="BBa_J61048_term" value="BioBrick_assembly_dataset/BBa_J61048_term.gb" />
                    <element name="BBa_K611094_bar" value="BioBrick_assembly_dataset/BBa_K611094_bar.gb" />
                </collection>
            </param>
            <param name="assembly_csv" value="BioBrick_assembly_dataset/hierarchical_biobrick.csv" />
            <param name='assembly_plan_name' value='BioBrickStandardAssembly' />
            <param name="topology" value="circular"/>
            <param name="adv|use_file_names_as_ids" value="True" />
            <output name="output_zip" ftype='zip'>
                <assert_contents>
                    <has_archive_member path=".*" n="47"/>
                    <has_archive_member path="assambly_simulation/Report.pdf">
                        <has_size min="5"/>
                    </has_archive_member>
                </assert_contents>
            </output>
            <output_collection name="construct_gb" type="list" count="3">
                <element name="C1_prom_barcode">
                    <assert_contents>
                     <has_n_lines min="20" />
                    </assert_contents>
                </element>
                <element name="C2_gfp_term">
                    <assert_contents>
                     <has_n_lines min="20" />
                    </assert_contents>
                </element>
                <element name="C3_final">
                    <assert_contents>
                     <has_n_lines min="20" />
                    </assert_contents>
                </element>
            </output_collection>
        </test>
        <!--test type2s_assembly with domesticated files-->
        <test> 
            <param name="genbank_files">
                <collection type="list">
                    <element name="part_A" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_A.gb" />
                    <element name="part_B" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_B.gb" />
                    <element name="part_C" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_C.gb" />
                    <element name="part_D" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_D.gb" />
                    <element name="part_E" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_E.gb" />
                    <element name="part_F" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_F.gb" />
                    <element name="part_G" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_G.gb" />
                </collection>
            </param>
            <param name="assembly_csv" value="2-step_golden_gate_parts/2-step-golden_gate_plan.csv" />
            <param name='assembly_plan_name' value='Type2sRestrictionAssembly' />
            <param name="domesticated_input">
                <collection type="list">
                    <element name="part_H" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_H.gb" />
                    <element name="part_I" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_I.gb" />
                    <element name="part_J" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_J.gb" />
                    <element name="part_K" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_K.gb" />
                    <element name="part_L" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_L.gb" />
                </collection>
            </param>
            <param name="topology" value="circular"/>
            <param name="adv|use_file_names_as_ids" value="True" />
            <output name="output_zip" ftype='zip'>
                <assert_contents>
                    <has_archive_member path=".*" n="62"/>
                    <has_archive_member path="assambly_simulation/assembly_plan_graph.pdf">
                        <has_size min="5"/>
                    </has_archive_member>
                </assert_contents>
            </output>
            <output_collection name="construct_gb" type="list" count="4">
                <element name="construct_1">
                    <assert_contents>
                     <has_n_lines min="20" />
                    </assert_contents>
                </element>
                <element name="construct_2">
                    <assert_contents>
                     <has_n_lines min="20" />
                    </assert_contents>
                </element>
                <element name="construct_3">
                    <assert_contents>
                     <has_n_lines min="20" />
                    </assert_contents>
                </element>
                 <element name="construct_4">
                    <assert_contents>
                     <has_n_lines min="20" />
                    </assert_contents>
                </element>
            </output_collection>
        </test>
        <!--test only domestication input-->
        <test> 
            <param name="domesticated_input">
                <collection type="list">
                    <element name="part_A" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_A.gb" />
                    <element name="part_B" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_B.gb" />
                    <element name="part_C" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_C.gb" />
                    <element name="part_D" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_D.gb" />
                    <element name="part_E" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_E.gb" />
                    <element name="part_F" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_F.gb" />
                    <element name="part_G" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_G.gb" />
                    <element name="part_H" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_H.gb" />
                    <element name="part_I" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_I.gb" />
                    <element name="part_J" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_J.gb" />
                    <element name="part_K" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_K.gb" />
                    <element name="part_L" value="2-step_golden_gate_parts/parts_for_2-step_golden_gate/part_L.gb" />
                </collection>
            </param>
            <param name="assembly_csv" value="2-step_golden_gate_parts/2-step-golden_gate_plan.csv" />
            <param name='assembly_plan_name' value='Type2sRestrictionAssembly' />
            <param name="topology" value="circular"/>
            <param name="adv|use_file_names_as_ids" value="True" />
            <output name="output_zip" ftype='zip'>
                <assert_contents>
                    <has_archive_member path=".*" n="62"/>
                    <has_archive_member path="assambly_simulation/assembly_plan_graph.pdf">
                        <has_size min="5"/>
                    </has_archive_member>
                </assert_contents>
            </output>
            <output_collection name="construct_gb" type="list" count="4">
                <element name="construct_1">
                    <assert_contents>
                     <has_n_lines min="20" />
                    </assert_contents>
                </element>
                <element name="construct_2">
                    <assert_contents>
                     <has_n_lines min="20" />
                    </assert_contents>
                </element>
                <element name="construct_3">
                    <assert_contents>
                     <has_n_lines min="20" />
                    </assert_contents>
                </element>
                 <element name="construct_4">
                    <assert_contents>
                     <has_n_lines min="20" />
                    </assert_contents>
                </element>
            </output_collection>
        </test>
    </tests>
    
    <help><![CDATA[
Cloning_Simulation
    ====================

The Cloning Simulation tool is based on the DnaCauldron package developed by the EGF Biofoundry. It enables rapid and accurate assembly simulation of DNA parts for modular cloning systems, such as Golden Gate Assembly (complete documentation `here <https://edinburgh-genome-foundry.github.io/DnaCauldron/>`_).

**Parameters**:
---------------
* **Assemby csv**: csv file containes the construct names with their parts. (Without Header)
* **GenBank files**: Upload all the parts sequences for your assembli(es). Don't forget the receptor vector(s).
* **Domesticated GenBank**: Dimesticated GenBank list (Optional)
* **Topology**: Can be "circular", "linear".
* **Enzyme**: It will be selected automatically, or you can set one from this dictionnary : `dict <https://github.com/biopython/biopython/blob/master/Bio/Restriction/Restriction_Dictionary.py>`_ 
* **Assembly Class**: 
    - "GoldenGate_assembly": Type2sRestrictionAssembly (recommended in Domesticated dataset) `ex. dataset <https://github.com/Edinburgh-Genome-Foundry/DnaCauldron/tree/master/examples/hierarchical_golden_gate>`_
    - "gibson_assembly": GibsonAssembly `ex. dataset <https://github.com/Edinburgh-Genome-Foundry/DnaCauldron/tree/master/examples/gibson_assembly>`_
    - "BASIC_assembly": BASICAssembly `ex. dataset <https://github.com/Edinburgh-Genome-Foundry/DnaCauldron/tree/master/examples/BASIC_assembly>`_
    - "biobrick_assembly": BioBrickStandardAssembly, `ex. dataset <https://github.com/Edinburgh-Genome-Foundry/DnaCauldron/tree/master/examples/hierarchical_biobrick>`_
    - "lcr_assembly": LigaseCyclingReactionAssembly `ex. dataset <https://github.com/Edinburgh-Genome-Foundry/DnaCauldron/tree/master/examples/lcr_assembly>`_
    ]]></help>
    <citations>
        <citation type="bibtex">
            @unpublished{cloning_simulation
                author = {Ramiz Khaled},
                title = {{cloning_simulation}},
                url = {https://github.com/Edinburgh-Genome-Foundry/Examples/blob/master/templates/template1.ipynb},
            }
        </citation>
    </citations>
</tool>