Mercurial > repos > tduigou > rpbasicdesign

changeset 3:e4821c820f7c draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload commit f40274f6b9f6a15eb4022aab21286d4c96cd8475-dirty"
author tduigou
date Wed, 30 Mar 2022 09:04:23 +0000
parents 8a087d7546b8
children 9ba4dab7f0ba
files rpbasicdesign.xml
diffstat 1 files changed, 27 insertions(+), 31 deletions(-) [+]
line wrap: on
line diff
--- a/rpbasicdesign.xml	Mon Mar 28 14:16:59 2022 +0000
+++ b/rpbasicdesign.xml	Wed Mar 30 09:04:23 2022 +0000
@@ -1,4 +1,4 @@
-<tool id="rpbasicdesign" name="BasicDesign" version="@TOOL_VERSION@" profile="19.09">
+<tool id="rpbasicdesign" name="BasicDesign" version="@TOOL_VERSION@" profile="21.09">
     <description>Build DNA-BOT input files from rpSBML</description>
     <macros>
         <token name="@TOOL_VERSION@">1.0.1</token>
@@ -23,7 +23,7 @@
         --max_enz_per_rxn $adv.max_enz_per_rxn
     ]]></command>
     <inputs>
-        <param name="rpsbml_file" type="data" format="xml" label="rpSBML file" help="SBML file from which enzymes UniProt IDs will be collected."/>
+        <param name="rpsbml_file" type="data" format="sbml" label="rpSBML file" help="SBML file from which enzymes UniProt IDs will be collected."/>
         <param argument="--backbone_id" type="text" value="BASIC_SEVA_37_CmR-p15A.1" label="Backbone part ID" help="Part ID to be used as the backbone.">
             <sanitizer invalid_char="">
                 <valid initial="string.letters,string.digits">
@@ -34,11 +34,10 @@
                 </valid>
             </sanitizer>
             <validator type="empty_field" message="Backbone ID is required"/>
-            <validator type="regex">[0-9a-zA-Z_:-]+</validator>
         </param>
-        <param argument="--sample_size" type="integer" value="88" min="1" max="88" label="Number of constructs to generate" help="Number of construct to generate."/>
+        <param argument="--sample_size" type="integer" value="88" min="1" max="88" label="Sample size" help="Number of construct to generate."/>
         <section name="adv" title="Advanced Options" expanded="false">
-            <param name="parts_files" type="data" format="csv" optional="true" multiple="true" label="Linkers and user parts" help="List of files providing available linkers and user parts (backbone, promoters, ...) for constructs. Default: Standard Biolegio Parts" />
+            <param name="parts_files" type="data" format="csv" optional="true" multiple="true" label="Linkers and user parts" help="List of files providing available linkers and user parts (backbone, promoters, ...) for constructs. Default: Standard Biolegio Parts (BBP-18500)" />
             <param argument="--lms_id" type="text" value="LMS" label="LMS part ID" help="Part ID to be used as the LMS methylated linker." >
                 <sanitizer invalid_char="">
                     <valid initial="string.letters,string.digits">
@@ -62,21 +61,21 @@
                 <validator type="empty_field" message="LMP ID is required"/>
             </param>
             <param argument="--cds_permutation" type="boolean" truevalue="--cds_permutation true" falsevalue="--cds_permutation false" checked="true" label="Perform CDS permutation?" help="Whether all combinations of CDS permutation should be built." />
-            <param argument="--sbol_output" type="boolean" checked="false" truevalue="--o_sbol_dir out/sbol_export" falsevalue="" label="Output SBOL results?" help="Output folder to write SBOL depictions of constructs." />
+            <param argument="--sbol_output" type="boolean" checked="false" truevalue="--o_sbol_dir out/sbol_export" falsevalue="" label="Output SBOL results?" help="Whether SBOL (Synthetic Biology Open Language) depictions of constructs should be outputted" />
             <param argument="--max_enz_per_rxn" type="integer" value="1" min="1" max="99" label="Maximum number of enyzme to consider per reaction." help="Maximum number of enyzme to consider per reaction. If more enzymes are available for a given reaction, then only the last one listed in the MIRIAM annotation section will be kept."/>
         </section>
     </inputs>
     <outputs>
         <data name="Constructs" format="csv" from_work_dir="out/dnabot_in/constructs.csv" label="${tool.name} on ${rpsbml_file.name}: constructs" />
-        <data name="User parts plate" format="csv" from_work_dir="out/dnabot_in/user_parts_plate.csv" label="${tool.name} on ${rpsbml_file.name}: User parts plate"/>
-        <data name="Biolegio plate" format="csv" from_work_dir="out/dnabot_in/biolegio_plate.csv" label="${tool.name} on ${rpsbml_file.name}: Biolegio plate"/>
+        <data name="User_parts_plate" format="csv" from_work_dir="out/dnabot_in/user_parts_plate.csv" label="${tool.name} on ${rpsbml_file.name}: User parts plate"/>
+        <data name="Biolegio_plate" format="csv" from_work_dir="out/dnabot_in/biolegio_plate.csv" label="${tool.name} on ${rpsbml_file.name}: Biolegio plate"/>
         <collection name="sbol_dir" type="list" label="${tool.name} on ${rpsbml_file.name}: SBOL constructs">
             <filter> adv['sbol_output'] </filter>
             <discover_datasets pattern="__designation_and_ext__" format="xml" directory="out/sbol_export" />
         </collection>
     </outputs>
     <tests>
-        <test>
+        <test expect_num_outputs="4">
             <!-- test 1: check if identical outputs are produced (Lycopene input)-->
             <param name="rpsbml_file" value="lycopene_CrtEBI_from_selenzy.xml" />
             <param name="sample_size" value="3" />
@@ -85,9 +84,9 @@
                     <has_n_lines n="4"/>
                 </assert_contents>
             </output>
-            <output name="User parts plate" file="user_parts_plate_lycopene.csv" ftype="csv" compare="diff"/>
-            <output name="Biolegio plate" file="biolegio_plate_lycopene.csv" ftype="csv" compare="diff"/>
-            <param name="sbol_output" value="--o_sbol_dir out/sbol_export" />
+            <output name="User_parts_plate" file="user_parts_plate_lycopene.csv" ftype="csv" compare="diff"/>
+            <output name="Biolegio_plate" file="biolegio_plate_lycopene.csv" ftype="csv" compare="diff"/>
+            <param name="sbol_output" value="true" />
             <output_collection name="sbol_dir" type="list" count="3">
                 <element name="BASIC_construct_A1">
                     <assert_contents>
@@ -112,7 +111,7 @@
                 </element>
             </output_collection>
         </test>
-        <test>
+        <test expect_num_outputs="3">
             <!-- test 2: check if identical outputs are produced (Muconate input)-->
             <param name="rpsbml_file" value="muconate_example.xml" />
             <param name="sample_size" value="88" />
@@ -121,43 +120,40 @@
                     <has_n_lines n="89"/>
                 </assert_contents>
             </output>
-            <output name="User parts plate" file="user_parts_plate_muconate.csv" ftype="csv" compare="diff"/>
-            <output name="Biolegio plate" file="biolegio_plate_muconate.csv" ftype="csv" compare="diff"/>
+            <output name="User_parts_plate" file="user_parts_plate_muconate.csv" ftype="csv" compare="diff"/>
+            <output name="Biolegio_plate" file="biolegio_plate_muconate.csv" ftype="csv" compare="diff"/>
         </test>
     </tests>
     <help><![CDATA[
 rpbasicdesign
 ================
 
-Convert rpSBML enzyme info in to BASIC construct. UniProt IDs corresponding
-enzyme variants are extracted rpSBMl files. Promoters and RBSs are randomly
-chosen from a default list. CDSs, in other words gene variants, of enzymes are
-randomly chosen from amongst the UniProt IDs extracted. Constructs generated
-can be stored as (i) a CSV file ready to be used by DNA-Bot, (ii) as SBOL
-files.
+rpbasicdesign extracts enzyme IDs from rpSBML (System Biology Markup Language) files containing additionnal annotations (e.g. reaction rules ID) and produced by the RP (RetroPath) suite available in `SynBioCAD Galaxy platform <https://galaxy-synbiocad.org/>`_, to generate genetic constructs compliant with the BASIC (Biopart Assembly Standard for Idempotent Cloning) assembly approach. CSV files produced are ready to be used with DNA-Bot to generate instructions for automated build of the genetic constructs using OpenTrons liquid handling robots.
 
 Input
 -----
 
 Required:
 
-* **rpsbml_file**\ : (string) rpSBML file from which enzymes UniProt IDs will be collected.
+* **rpSBML file**\ : rpSBML file from which enzymes UniProt IDs will be collected.
 
 Advanced options:
 
-* **parts_files**\ : (string) List of files providing available linkers and user parts (backbone, promoters, ...) for constructs. Default: [data/biolegio_parts.csv, data/user_parts.csv]
-* **lms_id**\ : (string) part ID to be used as the LMS methylated linker. Default: LMS.
-* **lmp_id**\ : (string) part ID to be used as the LMP methylated linker. Default: LMP.
-* **backbone_id**\ : (string) part ID to be used as the backbone. Default: BASIC_SEVA_37_CmR-p15A.1.
-* **sample_size**\ : (int) Number of construct to generate. Default: 88.
-* **cds_permutation**\ : (boolean) Whether all combinations of CDS permutation should be built Default: true.
-* **max_enz_per_rxn**\ : (integer) Maximum number of enyzme to consider per reaction. If more enzymes are available for a given reaction, then only the last one listed in the MIRIAM annotation section will be kept. (Default: 1). 
+* **Linkers and user parts**\ : (string) List of files providing available linkers and user parts (backbone, promoters, ...) for constructs. Default: ( `Standard Biolegio Parts <https://www.biolegio.com/>`_: BBP-18500).
+* **LMS part ID**\ : (string) part ID to be used as the LMS methylated linker. Default: LMS.
+* **LMP part ID**\ : (string) part ID to be used as the LMP methylated linker. Default: LMP.
+* **Backbone part ID**\ : (string) part ID to be used as the backbone. Default: BASIC_SEVA_37_CmR-p15A.1.
+* **Sample size**\ : (int) Number of construct to generate. Default: 88.
+* **Perform CDS permutation?**\ : (boolean) Whether all combinations of CDS permutation should be built Default: true.
+* **Maximum number of enyzme to consider per reaction**\ : (int) Maximum number of enyzme to consider per reaction. If more enzymes are available for a given reaction, then only the last one listed in the MIRIAM annotation section will be kept. (Default: 1). 
 
 Output
 ------
 
-* **o_dnabot_dir**\ : (string) Output folder to write construct and plate files. It will be created if it does not exist yet. Existing files will be overwritten. Default: out/dnabot_in.
-* **o_sbol_dir**\ : (string) Output folder to write SBOL depictions of constructs. Existing files will be overwritten. Default: not output.
+* **constructs**\ : CSV construct file listing the constructs to be built.
+* **User parts plate**\ : CSV file listing the DNA parts to be included into each construct.
+* **Biolegio plate**\ : CSV file listing the plate coordinates of the BASIC linkers.
+* **SBOL constructs**\ : (optional) one SBOL (Synthetic Biology Open Language) file is produced for each construct generated in XML format. 
 
 Project Links
 ------------------