diff kaks_analysis.xml @ 3:1fb0f2092177 draft

Uploaded

--- a/kaks_analysis.xml	Thu Aug 24 13:41:07 2017 -0400
+++ b/kaks_analysis.xml	Mon Oct 30 09:54:20 2017 -0400
@@ -1,9 +1,11 @@
-<tool id="plant_tribes_kaks_analysis" name="KaKsAnalysis" version="@WRAPPER_VERSION@.2">
+<tool id="plant_tribes_kaks_analysis" name="KaKsAnalysis" version="@WRAPPER_VERSION@.3.0">
     <description>estimates paralogous and orthologous pairwise synonymous (Ks) and non-synonymous (Ka) substitution rates</description>
     <macros>
         <import>macros.xml</import>
     </macros>
-    <expand macro="requirements_kaks_analysis" />
+    <requirements>
+        <requirement type="package" version="1.0.3">plant_tribes_kaks_analysis</requirement>
+    </requirements>
     <command detect_errors="exit_code"><![CDATA[
 #set output_dir = 'kaksAnalysis_dir'
 #set comparison = $comparison_cond.comparison
@@ -34,6 +36,9 @@
 #if str($comparison) == 'orthologs':
     --coding_sequences_species_2 '$comparison_cond.coding_sequences_species_2'
     --proteins_species_2 '$comparison_cond.proteins_species_2'
+    #if str($comparison_cond.blast_option) == 'crbblast':
+        --crb_blast
+    #end if
 #end if
 #if str($options_type.options_type_selector) == 'advanced':
     #if str($set_min_coverage) == 'yes':
@@ -58,18 +63,19 @@
         --max_ks $set_upper_ks_limit_cond.max_ks
     #end if
 #end if
->/dev/null
+&>proc.log
 && mv $output_dir/species1.fna '$output_species1_fna'
 && mv $output_dir/species1.faa '$output_species1_faa'
 #if str($comparison) == 'paralogs':
     && mv $output_dir/species1.fna.blastn.paralogs '$output_species1_paralog'
+    && mv $output_dir/*.rbhb '$output_rbhb_paralog'
 #else:
     && mv $output_dir/species2.faa '$output_species2_faa'
     && mv $output_dir/species2.fna '$output_species2_fna'
     && mv $output_dir/species1.fna.blastn.orthologs '$output_species1_ortholog'
     && mv $output_dir/species2.fna.blastn.orthologs '$output_species2_ortholog'
+    && mv $output_dir/*.rbhb '$output_rbhb_ortholog'
 #end if
-&& mv $output_dir/*.rbhb '$output_rbhb'
 && mv $output_dir/*.kaks '$output_kaks'
 #if str($fit_components) == 'yes':
     && mv $output_dir/*.components '$output_components'
@@ -87,6 +93,10 @@
             <when value="orthologs">
                 <param name="coding_sequences_species_2" format="fasta" type="data" label="Coding sequences for the second species" />
                 <param name="proteins_species_2" format="fasta" type="data" label="Protein sequences for the second species" />
+                <param name="blast_option" type="select" display="radio" label="Determine for cross-species orthologs using">
+                    <option value="blast" selected="true">reciprocal best BLAST</option>
+                    <option value="crbblast">conditional reciprocal best BLAST</option>
+                </param>
             </when>
         </conditional>
         <conditional name="options_type">
@@ -164,26 +174,31 @@
         </param>
     </inputs>
     <outputs>
-        <data name="output_species1_fna" format="fasta" label="${tool.name} (coding sequences) on ${on_string}" />
-        <data name="output_species1_faa" format="fasta" label="${tool.name} (amino acids) on ${on_string}" />
-        <data name="output_species2_fna" format="fasta" label="${tool.name} (coding sequences) on ${on_string}">
+        <data name="output_species1_fna" format="fasta" label="${tool.name} (coding sequences species1) on ${on_string}" />
+        <data name="output_species1_faa" format="fasta" label="${tool.name} (amino acids species1) on ${on_string}" />
+        <data name="output_species2_fna" format="fasta" label="${tool.name} (coding sequences species2) on ${on_string}">
             <filter>comparison_cond['comparison'] == 'orthologs'</filter>
         </data>
-        <data name="output_species2_faa" format="fasta" label="${tool.name} (amino acids) on ${on_string}">
+        <data name="output_species2_faa" format="fasta" label="${tool.name} (amino acids species2) on ${on_string}">
             <filter>comparison_cond['comparison'] == 'orthologs'</filter>
         </data>
-        <data name="output_species1_paralog" format="tabular" label="${tool.name} (blastn results) on ${on_string}">
+        <data name="output_species1_paralog" format="tabular" label="${tool.name} (blastn results species1 vs species1) on ${on_string}">
             <filter>comparison_cond['comparison'] == 'paralogs'</filter>
         </data>
-        <data name="output_species1_ortholog" format="tabular" label="${tool.name} (blastn results) on ${on_string}">
+        <data name="output_species1_ortholog" format="tabular" label="${tool.name} (blastn results species1 vs species2) on ${on_string}">
+            <filter>comparison_cond['comparison'] == 'orthologs'</filter>
+        </data>
+        <data name="output_species2_ortholog" format="tabular" label="${tool.name} (blastn results species2 vs species1) on ${on_string}">
             <filter>comparison_cond['comparison'] == 'orthologs'</filter>
         </data>
-        <data name="output_species2_ortholog" format="tabular" label="${tool.name} (blastn results) on ${on_string}">
+        <data name="output_rbhb_paralog" format="tabular" label="${tool.name} (paralogous pairs) on ${on_string}">
+            <filter>comparison_cond['comparison'] == 'paralogs'</filter>
+        </data>
+        <data name="output_rbhb_ortholog" format="tabular" label="${tool.name} (orthologous pairs) on ${on_string}">
             <filter>comparison_cond['comparison'] == 'orthologs'</filter>
         </data>
-        <data name="output_rbhb" format="tabular" label="${tool.name} (paralogous pairs) on ${on_string}" />
-        <data name="output_kaks" format="tabular" label="${tool.name} on ${on_string}" />
-        <data name="output_components" format="ptkscmp" label="${tool.name} (significant components in the ks distribution) on ${on_string}">
+        <data name="output_kaks" format="tabular" label="${tool.name} (KaKs distribution) on ${on_string}" />
+        <data name="output_components" format="ptkscmp" label="${tool.name} (significant components in the KaKs distribution) on ${on_string}">
             <filter>options_type['options_type_selector'] == 'advanced' and options_type['fit_components_cond']['fit_components'] == 'yes'</filter>
         </data>
     </outputs>
@@ -195,7 +210,7 @@
             <output name="output_species1_fna" file="species1_cds.fasta" ftype="fasta" compare="contains"/>
             <output name="output_species1_faa" file="species1_pep.fasta" ftype="fasta" compare="contains"/>
             <output name="output_species1_paralog" file="output_blastn_results1.tabular" ftype="tabular" compare="contains"/>
-            <output name="output_rbhb" file="output_paralogous_pairs.tabular" ftype="tabular"/>
+            <output name="output_rbhb_paralog" file="output_paralogous_pairs.tabular" ftype="tabular"/>
             <output name="output_kaks" file="output1.tabular" ftype="tabular"/>
         </test>
     </tests>
@@ -218,6 +233,12 @@
 
   - **Coding sequences for the second species** - coding sequence fasta file for the second species either produced by the AssemblyPostProcessor tool or from an external source selected from your history.  This option is required only for orthologous comparison.
   - **Protein sequences for the second species** - corresponding protein sequence fasta files for the second species either produced by the AssemblyPostProcessor tool or from an external source selected from your history.  This option is required only for orthologous comparison.
+
+  - **Determine for cross-species orthologs using** - select option for blast orthology.
+
+    - **reciprocal best BLAST** - use the default stringent reciprocal BLAST package for orthology assignment.
+    - **conditional reciprocal best BLAST** - use the CRB-BLAST package for orthology assignment which increases sensitivity to orthology comparisons and determines additional cross-species orthologs that are being left out by the defaul stringent reciprocal BLAST.
+
   - **Alignment coverage configuration** - select 'Yes' to set the minimum allowable alignment coverage length between homologous pairs.  PlantTribes uses global codon alignment match score to determine the pairwise alignment coverage.  By default, the match score is set to 0.5 if 'No' is selected.
 
     - **match score** - number of base matches in a pairwise sequence alignment divided by the length of shorter sequence.  Positions in the alignment corresponding to gaps are not considered.  The score is restricted to the range 0.3 - 1.0.