Mercurial > repos > greg > plant_tribes_assembly_post_processor

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/assembly_post_processor.xml	Fri Dec 09 08:28:49 2016 -0500
@@ -0,0 +1,143 @@
+<tool id="plant_tribes_assembly_post_processor" name="PlantTribes AssemblyPostProcessor" version="1.0.0">
+    <description>pipeline</description>
+    <requirements>
+        <requirement type="package" version="0.2">plant_tribes_assembly_post_processor</requirement>
+    </requirements>
+    <stdio>
+        <!-- Anything other than zero is an error -->
+        <exit_code range="1:" />
+        <!-- In case the return code has not been set properly check stderr too -->
+        <regex match="Error:" />
+        <regex match="Exception:" />
+    </stdio>
+    <command>
+        <![CDATA[
+            AssemblyPostProcesser
+            --transcripts "$input"
+            --prediction_method $prediction_method_cond.prediction_method
+            #if str($prediction_method_cond.prediction_method) == 'estscan':
+                --score_matrices "$score_matrices"
+            #end if
+            #if str($options_type.options_type_selector) == 'advanced':
+                #if str($options_type.target_gene_family_assembly_cond.target_gene_family_assembly) == 'yes':
+                    --gene_family_search "$options_type.target_gene_family_assembly_cond.orthogroups"
+                    --scaffold "$options_type.target_gene_family_assembly_cond.scaffold"
+                    --method "$options_type.target_gene_family_assembly_cond.method"
+                #end if
+                --gap_trimming $options_type.gap_trimming
+                #if str($options_type.strand_specific) == 'yes':
+                    --strand_specific
+                #end if
+                #if str($options_type.dereplicate) == 'yes':
+                    --dereplicate
+                #end if
+                --min_length $options_type.min_length
+            #end if
+            --num_threads \${GALAXY_SLOTS:-4}
+        ]]>
+    </command>
+    <inputs>
+        <param name="input" format="fasta" type="data" label="De novo transcriptome assembly fasta file"/>
+        <conditional name="prediction_method_cond">
+            <param name="prediction_method" type="select" label="Prediction method for coding regions">
+                <option value="transdecoder" selected="true">TransDecoder</option>
+                <option value="estscan">ESTScan</option>
+            </param>
+            <when value="transdecoder" />
+            <when value="estscan">
+                <param name="score_matrices" format="smat" type="data" label="Scores matrices"/>
+            </when>
+        </conditional>
+        <conditional name="options_type">
+            <param name="options_type_selector" type="select" label="Options Configuration">
+                <option value="basic" selected="true">Basic</option>
+                <option value="advanced">Advanced</option>
+            </param>
+            <when value="basic" />
+            <when value="advanced">
+                <conditional name="target_gene_family_assembly_cond">
+                    <param name="target_gene_family_assembly" type="select" label="Target gene family assembly?">
+                        <option value="no" selected="true">No</option>
+                        <option value="yes">Yes</option>
+                    </param>
+                    <when value="no" />
+                    <when value="yes">
+                        <param name="orthogroups" format="tabular" type="data" label="List of orthogroup identifiers for target gene families to assemble"/>
+                        <param name="scaffold" type="select" label="Orthogroups or gene families proteins scaffold">
+                            <options from_data_table="plant_tribes_scaffolds" />
+                            <validator type="no_options" message="No PlantTribes scaffolds are available.  Use the PlantTribes Scaffolds Download Data Manager tool to install and populate the PlantTribes scaffolds data table."/>
+                        </param>
+                        <param name="method" type="select" label="Protein clustering method">
+                            <option value="gfam" selected="true">GFam</option>
+                            <option value="orthofinder">OrthoFinder</option>
+                            <option value="orthomcl">OrthoMCL</option>
+                        </param>
+                    </when>
+                </conditional>
+                <param name="gap_trimming" type="float" value="0.1" min="0" max="1.0" label="Remove gappy sites in alignments" help="0.1 removes sites with 90% gaps"/>
+                <param name="strand_specific" type="select" label="De novo transcriptome assembly was performed with strand-specific library?">
+                    <option value="no" selected="true">No</option>
+                    <option value="yes">Yes</option>
+                </param>
+                <param name="dereplicate" type="select" label="Remove repeated sequences in predicted coding regions?">
+                    <option value="no" selected="true">No</option>
+                    <option value="yes">Yes</option>
+                </param>
+                <param name="min_length" type="integer" value="200" label="Minimum sequence length of predicted coding regions"/>
+            </when>
+        </conditional>
+    </inputs>
+    <outputs>
+        <collection name="transcripts" type="list">
+            <discover_datasets pattern="__name__" directory="assemblyPostProcessing_dir" visible="false" ext="fasta" />
+        </collection>
+    </outputs>
+    <tests>
+        <test>
+            <param name="input" value="assembly.fasta" ftype="fasta" />
+            <param name="prediction_method" value="transdecoder" />
+            <param name="options_type_selector" value="advanced" />
+            <param name="strand_specific" value="yes" />
+            <param name="dereplicate" value="yes" />
+            <output_collection name="transcripts" type="list">
+                <element name="transcripts.cds" file="transcripts.cds" ftype="fasta" />
+                <element name="transcripts.cleaned.cds" file="transcripts.cleaned.cds" ftype="fasta" />
+                <element name="transcripts.cleaned.nr.cds" file="transcripts.cleaned.nr.cds" ftype="fasta" />
+                <element name="transcripts.cleaned.nr.pep" file="transcripts.cleaned.nr.pep" ftype="fasta" />
+                <element name="transcripts.cleaned.pep" file="transcripts.cleaned.pep" ftype="fasta" />
+                <element name="transcripts.pep" file="transcripts.pep" ftype="fasta" />
+            </output_collection>
+        </test>
+    </tests>
+    <help>
+This tool is one of the PlantTribes' collection of automated modular analysis pipelines that utilize objective classifications of
+complete protein sequences from sequenced plant genomes to perform comparative evolutionary studies. It post-processes de novo assembly
+transcripts into putative coding sequences and their corresponding amino acid translations.
+
+-----
+
+**Options**
+
+ * **Prediction method for coding regions** - The prediction method for coding regions; one of ESTScan or TransDecoder.
+ * **Scores matrices** - Scores matrices that reflect the codons preferences in the studied organisms.
+ * **Target gene family assembly?** - Select yes to target gene families to assemble.
+ * **List of orthogroup identifiers for target gene families to assemble** - History item with a list of orthogroup identifiers for target gene families to assemble.  The next version of this tool will use a dynamic select list for this feature.
+ * **Orthogroups or gene families proteins scaffold** - PlantTribes scaffolds data.
+ * **Protein clustering method** - One of GFam, OrthoFinder or OrthoMCL.
+ * **Remove gappy sites in alignments** - Removes gappy sites in alignments (i.e. 0.1 removes sites with 90% gaps): [0.0 to 1.0]
+ * **De novo transcriptome assembly was performed with strand-specific library?** - Select yes if de novo transcriptome assembly was performed with strand-specific library.
+ * **Remove repeated sequences in predicted coding regions?** - Select yes to remove repeated sequences in predicted coding regions.
+ * **Minimum sequence length of predicted coding regions** - Set the minimum sequence length of predicted coding regions.
+
+    </help>
+    <citations>
+            <citation type="bibtex">
+                @unpublished{None,
+                author = {None},
+                title = {None},
+                year = {None},
+                eprint = {None},
+                url = {None}
+            }</citation>
+    </citations>
+</tool>