Mercurial > repos > greg > assembly_post_processor

changeset 39:b0ea1e985a38 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author greg
date Wed, 26 Apr 2017 10:25:55 -0400
parents 9b5baf12bdbe
children 8102c8bf2414
files assembly_post_processor.xml macros.xml
diffstat 2 files changed, 88 insertions(+), 10 deletions(-) [+]
line wrap: on
line diff
--- a/assembly_post_processor.xml	Fri Apr 07 16:11:09 2017 -0400
+++ b/assembly_post_processor.xml	Wed Apr 26 10:25:55 2017 -0400
@@ -1,4 +1,4 @@
-<tool id="plant_tribes_assembly_post_processor" name="AssemblyPostProcessor" version="0.4.0">
+<tool id="plant_tribes_assembly_post_processor" name="AssemblyPostProcessor" version="@WRAPPER_VERSION@.0">
     <description>post-processes de novo transcriptome assembly</description>
     <macros>
         <import>macros.xml</import>
@@ -18,8 +18,8 @@
                     --gene_family_search '$options_type.target_gene_family_assembly_cond.orthogroups'
                     --scaffold '$options_type.target_gene_family_assembly_cond.scaffold.fields.path'
                     --method '$options_type.target_gene_family_assembly_cond.method'
+                    --gap_trimming $options_type.gap_trimming
                 #end if
-                --gap_trimming $options_type.gap_trimming
                 #if str($options_type.strand_specific) == 'yes':
                     --strand_specific
                 #end if
@@ -68,9 +68,9 @@
                             <option value="orthofinder">OrthoFinder</option>
                             <option value="orthomcl">OrthoMCL</option>
                         </param>
+                        <param name="gap_trimming" type="float" value="0.1" min="0" max="1.0" label="Trim alignments"/>
                     </when>
                 </conditional>
-                <param name="gap_trimming" type="float" value="0.1" min="0" max="1.0" label="Trim alignments"/>
                 <param name="strand_specific" type="select" label="Strand-specific assembly?">
                     <option value="no" selected="true">No</option>
                     <option value="yes">Yes</option>
@@ -136,11 +136,11 @@
 
  * **Perform targeted gene assembly?** - selecting 'Yes' enables local assembly of one or more targeted gene families in a specific scaffold.  Scaffolds are defined in PlantTribes as clusters of paralogous/orthologous sequences from a specified set of proteomes[5-7].
 
-   * **Targeted gene families** - select a history item containing a list of targeted orthogroup identifiers corresponding to the gene family classification from a specified scaffold.  Gene identifiers can be obtained from the function annotation table ("Orthogroup ID" field of .summary file) of scaffold data installed into Galaxy via the PlantTribes Scaffolds Download Data Manager tool, and also available at the PlantTribes github repository (https://github.com/dePamphilis/PlantTribes/tree/master/config).
+   * **Targeted gene families** - select a history item containing a list of targeted orthogroup identifiers corresponding to the gene family classification from a specified scaffold.  Gene family identifiers can be obtained from the function annotation table ("Orthogroup ID" field of .summary file) of scaffold data installed into Galaxy via the PlantTribes Scaffolds Download Data Manager tool, and also available at the PlantTribes github repository (https://github.com/dePamphilis/PlantTribes/tree/master/config).
    * **Gene family scaffold** - one of the PlantTribes gene family scaffolds (installed into Galaxy by the PlantTribes Scaffolds Download Data Manager tool) whose orthogroup(s) are targeted for the localized assembly.
    * **Protein clustering method** - gene family scaffold protein clustering method.  Each PlantTribes scaffold data has up to three sets of clusters - GFam[8] (clusters of consensus domain architecture), OrthoFinder[9] (broadly defined clusters) or OrthoMCL[10] (narrowly defined clusters).  You can also install your own data scaffold created using a different clustering method as long as it conforms to the PlantTribes scaffold data format.
+   * **Trim alignments** - trim gene family multiple sequence alignments that include scaffold backbone genes and locally assembled transcripts to remove non-conserved regions (gappy sites)[11].  The trimmed alignments are used in assigning scores to locally assembled transcripts to determine how well they compare to the backbone gene models.  The default setting of 0.1 removes sites that have gaps in 90% or more of the sequences in the multiple sequence alignment.  This option is restricted to the range 0.0 - 1.0.
 
- * **Trim alignments** - trim gene family multiple sequence alignments that include scaffold backbone genes and locally assembled transcripts to remove non-conserved regions (gappy sites)[11].  The trimmed alignments are used in assigning scores to locally assembled transcripts to determine how well they compare to the backbone gene models.  The default setting of 0.1 removes sites that have gaps in 90% of the sequences in the multiple sequence alignment.  This option is restricted to the range 0.0 - 1.0.
  * **Strand-specific assembly?** - select 'Yes' if transcriptome library sequences were strand-specific.  If 'Yes" is selected, transcripts from the minority strand (antisense) are removed.
  * **Remove duplicate sequences?** - select 'Yes' to remove duplicated and exact subsequences[12].
  * **Minimum sequence length** - set the minimum sequence length of predicted coding regions. The default is 200 bp.
--- a/macros.xml	Fri Apr 07 16:11:09 2017 -0400
+++ b/macros.xml	Wed Apr 26 10:25:55 2017 -0400
@@ -1,10 +1,16 @@
 <?xml version='1.0' encoding='UTF-8'?>
 <macros>
+    <token name="@WRAPPER_VERSION@">0.8</token>
     <xml name="requirements_assembly_post_processor">
         <requirements>
             <requirement type="package" version="0.4">plant_tribes_assembly_post_processor</requirement>
         </requirements>
     </xml>
+    <xml name="requirements_gene_family_aligner">
+        <requirements>
+            <requirement type="package" version="0.8">plant_tribes_gene_family_aligner</requirement>
+        </requirements>
+    </xml>
     <xml name="requirements_gene_family_classifier">
         <requirements>
             <requirement type="package" version="0.8">plant_tribes_gene_family_classifier</requirement>
@@ -15,6 +21,16 @@
             <requirement type="package" version="0.8">plant_tribes_gene_family_integrator</requirement>
         </requirements>
     </xml>
+    <xml name="requirements_kaks_analysis">
+        <requirements>
+            <requirement type="package" version="0.8">plant_tribes_kaks_analysis</requirement>
+        </requirements>
+    </xml>
+    <xml name="requirements_gene_family_phylogeny_builder">
+        <requirements>
+            <requirement type="package" version="0.8">plant_tribes_gene_family_phylogeny_builder</requirement>
+        </requirements>
+    </xml>
     <xml name="stdio">
         <stdio>
             <exit_code range="1:"/>
@@ -23,10 +39,10 @@
             <regex match="Exception:"/>
         </stdio>
     </xml>
-    <xml name="param_scaffold">
-        <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 in Galaxy to install and populate the PlantTribes scaffolds data table." />
+    <xml name="param_codon_alignments">
+        <param name="codon_alignments" type="select" label="Construct orthogroup multiple codon alignments?">
+            <option value="yes" selected="true">Yes</option>
+            <option value="no">No</option>
         </param>
     </xml>
     <xml name="param_method">
@@ -36,12 +52,74 @@
             <option value="orthomcl">OrthoMCL</option>
         </param>
     </xml>
+    <xml name="param_options_type">
+        <param name="options_type" type="select" label="Options Configuration">
+            <option value="basic" selected="true">Basic</option>
+            <option value="advanced">Advanced</option>
+        </param>
+    </xml>
     <xml name="param_orthogroup_fna">
-        <param name="orthogroup_fna" type="select" display="radio" label="Process corresponding gene family classification orthogroups CDS fasta files?">
+        <param name="orthogroup_fna" type="select" label="Process corresponding gene family classification orthogroups CDS fasta files?">
             <option value="yes" selected="true">Yes</option>
             <option value="no">No</option>
         </param>
     </xml>
+    <xml name="param_scaffold">
+        <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 in Galaxy to install and populate the PlantTribes scaffolds data table." />
+        </param>
+    </xml>
+    <xml name="param_sequence_type">
+        <param name="sequence_type" type="select" label="Sequence type used in the phylogenetic inference (dna)">
+            <option value="protein" selected="true">Amino acid based</option>
+            <option value="dna">Nucleotide based</option>
+        </param>
+    </xml>
+    <xml name="cond_alignment_method">
+        <conditional name="alignment_method_cond">
+            <param name="alignment_method" type="select" force_select="true" label="Select method for multiple sequence alignments">
+                <option value="mafft" selected="true">MAFFT algorithm</option>
+                <option value="pasta">PASTA algorithm</option>
+            </param>
+            <when value="mafft" />
+            <when value="pasta">
+                <param name="pasta_iter_limit" type="integer" value="3" min="1" label="Maximum number of iterations that the PASTA algorithm will execute" />
+            </when>
+        </conditional>
+    </xml>
+    <xml name="cond_remove_gappy_sequences">
+        <conditional name="remove_gappy_sequences_cond">
+            <param name="remove_gappy_sequences" type="select" label="Remove gappy sequences in alignments?">
+                <option value="no" selected="true">No</option>
+                <option value="yes">Yes</option>
+            </param>
+            <when value="no" />
+            <when value="yes">
+                <conditional name="trim_type_cond">
+                    <param name="trim_type" type="select" label="Select process used for trimming">
+                        <option value="gap_trimming" selected="true">Remove gappy sites in alignments (gap trimming)</option>
+                        <option value="automated_trimming">Trim alignments using trimAl's ML heuristic trimming approach (automated trimming)</option>
+                    </param>
+                    <when value="gap_trimming">
+                        <param name="gap_trimming" type="float" optional="true" min="0" max="1.0" label="Remove sites in alignments with gaps of" />
+                    </when>
+                    <when value="automated_trimming" />
+                </conditional>
+                <conditional name="remove_sequences_with_gaps_cond">
+                    <param name="remove_sequences_with_gaps" type="select" label="Remove sequences with specified gaps?">
+                        <option value="no" selected="true">No</option>
+                        <option value="yes">Yes</option>
+                    </param>
+                    <when value="no" />
+                    <when value="yes">
+                        <param name="remove_sequences_with_gaps_of" type="float" optional="true" min="0" max="1" label="Remove sequences with gaps of" />
+                        <param name="iterative_realignment" type="integer" optional="true" min="0" label="Maximum number of iterations" />
+                    </when>
+                </conditional>
+            </when>
+        </conditional>
+    </xml>
     <xml name="citation1">
         <citation type="bibtex">
             @misc{None,