Mercurial > repos > greg > gene_family_classifier

changeset 35:0fc60c5cb719 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author greg
date Thu, 02 Feb 2017 10:06:11 -0500
parents 9a60634252fd
children d485da50616b
files gene_family_classifier.xml
diffstat 1 files changed, 26 insertions(+), 13 deletions(-) [+]
line wrap: on
line diff
--- a/gene_family_classifier.xml	Wed Feb 01 15:01:19 2017 -0500
+++ b/gene_family_classifier.xml	Thu Feb 02 10:06:11 2017 -0500
@@ -13,6 +13,11 @@
     </stdio>
     <command>
         <![CDATA[
+        	#import os
+        	#set scaffold_path = $scaffold.fields.path
+        	#set scaffold_dir = $os.path.split($scaffold_path)[0]
+        	#set scaffold_selection = $os.path.split($scaffold_path)[1]
+
             #if str($options_type.options_type_selector) == 'advanced':
                 #set create_orthogroup_cond = $options_type.create_orthogroup_cond
                 #set create_orthogroup = $create_orthogroup_cond.create_orthogroup
@@ -25,7 +30,6 @@
                         #set create_corresponding_coding_sequences = False
                     #end if
 
-                    #import os
                     #set create_ortho_sequences = True
                     #set orthogroups_fasta_src_dir = $os.path.join('geneFamilyClassification_dir', 'orthogroups_fasta')
                     #if $create_corresponding_coding_sequences:
@@ -44,9 +48,9 @@
             #end if
 
             GeneFamilyClassifier
-            --proteins "$input"
-            --scaffold_dir "${GALAXY_DATA_INDEX_DIR}/plant_tribes/scaffolds"
-            --scaffold "$scaffold"
+            --proteins '$input'
+            --scaffold_dir '$scaffold_dir'
+            --scaffold '$scaffold_selection'
             --method $method
             --classifier $save_hmmscan_log_cond.classifier
             --num_threads \${GALAXY_SLOTS:-4}
@@ -60,7 +64,7 @@
                 #if str($create_orthogroup) == 'yes':
                     --orthogroup_fasta
                     #if $create_corresponding_coding_sequences:
-                        --coding_sequences "$create_corresponding_coding_sequences_cond.coding_sequences"
+                        --coding_sequences '$create_corresponding_coding_sequences_cond.coding_sequences'
                     #end if
                 #end if
             #end if
@@ -75,10 +79,10 @@
 
             #if $create_ortho_sequences:
                 #if $create_corresponding_coding_sequences:
-                    && echo "# Precomputed orthologous gene family clusters with corresponding coding sequences: `ls $orthogroups_fasta_src_dir | grep f | wc -l` files" > $output_pgfccs
+                    && echo '# Precomputed orthologous gene family clusters with corresponding coding sequences: `ls $orthogroups_fasta_src_dir | grep f | wc -l` files' > $output_pgfccs
                     && ls -al $orthogroups_fasta_src_dir | grep f >> $output_pgfccs
                 #else:
-                    && echo "# Precomputed orthologous gene family clusters: `ls $orthogroups_fasta_src_dir | grep f | wc -l` files" > $output_pgfc
+                    && echo '# Precomputed orthologous gene family clusters: `ls $orthogroups_fasta_src_dir | grep f | wc -l` files' > $output_pgfc
                     && ls -al $orthogroups_fasta_src_dir | grep f >> $output_pgfc
                 #end if
                 && mv $orthogroups_fasta_src_dir/* $dest_dir || true
@@ -176,8 +180,9 @@
         </collection>
     </outputs>
     <tests>
+    	<!-- Not sure how to test this since the tool requires scaffolds data which is extremely large and installed using a Data Manager -->
+    	<!--
         <test>
-        	<!-- Not sure how to test this since the tool requires scaffolds data which is extremely large and installed using a Data Manager -->
             <param name="input" value="transcripts.cleaned.nr.pep" ftype="fasta" />
             <param name="scaffold" value="22Gv1.1"/>
             <param name="method" value="orthomcl"/>
@@ -185,11 +190,12 @@
             <param name="dereplicate" value="yes"/>
             <param name="min_length" value="200"/>
             <output_collection name="orthos" type="list">
-                <element name="proteins.blastp.22Gv1.1" file="proteins.blastp.22Gv1.1" ftype="tabular" compare="contains"/>
-                <element name="proteins.blastp.22Gv1.1.bestOrthos" file="proteins.blastp.22Gv1.1.bestOrthos" ftype="tabular" compare="contains"/>
-                <element name="proteins.blastp.22Gv1.1.bestOrthos.summary" file="proteins.blastp.22Gv1.1.bestOrthos.summary" ftype="tabular" compare="contains"/>
+                <element name="proteins.blastp.22Gv1.1" file="proteins.blastp.22Gv1.1" ftype="tabular"/>
+                <element name="proteins.blastp.22Gv1.1.bestOrthos" file="proteins.blastp.22Gv1.1.bestOrthos" ftype="tabular"/>
+                <element name="proteins.blastp.22Gv1.1.bestOrthos.summary" file="proteins.blastp.22Gv1.1.bestOrthos.summary" ftype="tabular"/>
             </output_collection>
         </test>
+        -->
     </tests>
     <help>
 This tool is one of the PlantTribes' collection of automated modular analysis pipelines that utilize objective classifications of
@@ -222,8 +228,15 @@
                 author = {Eric Wafula},
                 title = {None},
                 year = {None},
-                eprint = {None},
-                url = {None}
+                url = {https://github.com/dePamphilis/PlantTribes}
+            }</citation>
+            <citation type="doi">10.1186/1471-2105-10-421</citation>
+            <citation type="bibtex">
+                @unpublished{None,
+                author = {None},
+                title = {HMMER 3.1+ hmmscan search sequence(s) against a profile database},
+                year = {2013},
+                url = {http://hmmer.org/}
             }</citation>
     </citations>
 </tool>