Mercurial > repos > bgruening > nanopolish_variants

changeset 1:1ebed8b65752 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/nanopolish commit d3227eb74ad38fac307911b60c8a20a13349bcf9
author bgruening
date Tue, 05 Jun 2018 17:58:46 -0400
parents 639b3a5bb415
children f1cb13497323
files macros.xml nanopolish_variants.xml test-data/all_fasta.loc tool_data_table_conf.xml.sample tool_data_table_conf.xml.test
diffstat 5 files changed, 60 insertions(+), 16 deletions(-) [+]
line wrap: on
line diff
--- a/macros.xml	Wed May 30 11:56:35 2018 -0400
+++ b/macros.xml	Tue Jun 05 17:58:46 2018 -0400
@@ -1,7 +1,7 @@
 <macros>
     <xml name="requirements">
         <requirements>
-        <requirement type="package" version="0.9.0">nanopolish</requirement>
+        <requirement type="package" version="0.9.2">nanopolish</requirement>
             <yield/>
         </requirements>
     </xml>
@@ -33,4 +33,4 @@
             <yield />
         </citations>
     </xml>
-</macros>
\ No newline at end of file
+</macros>
--- a/nanopolish_variants.xml	Wed May 30 11:56:35 2018 -0400
+++ b/nanopolish_variants.xml	Tue Jun 05 17:58:46 2018 -0400
@@ -17,7 +17,11 @@
         nanopolish index -d fast5_files/ reads.fasta &&
         ln -s '$b' reads.bam &&
         ln -s '${b.metadata.bam_index}' reads.bam.bai &&
-        ln -s '$g' genome.fa &&
+        #if $reference_source.reference_source_selector == 'history':
+            ln -f -s '$reference_source.ref_file' genome.fa &&
+        #else:
+            ln -f -s '$reference_source.ref_file.fields.path' genome.fa &&
+        #end if
         
         nanopolish variants
         -r reads.fasta
@@ -38,6 +42,10 @@
         -d $min_candidate_depth
         -x $max_haplotypes
         --max-rounds $max_rounds
+        --threads "\${GALAXY_SLOTS:-4}"
+        #if str($min_flanking_sequence):
+            --min-flanking-sequence $min_flanking_sequence
+        #end if
         #if $ploidy != -1:
             --ploidy $ploidy
         #end if
@@ -64,8 +72,6 @@
         #if $adv.input_models_fofn:
           --models-fofn '$input_models_fofn'
         #end if
-       
-
 
     ]]></command>
     <inputs>
@@ -75,7 +81,22 @@
 
         <!-- variants consensus inputs -->
         <param type="data" argument="-b" format="bam" label="Reads aligned to the reference genome" />
-        <param type="data" argument="-g" format="fasta" label="The reference genome"/>
+        <conditional name="reference_source">
+          <param name="reference_source_selector" type="select" label="Load reference genome from">
+            <option value="cached">Local cache</option>
+            <option value="history">History</option>
+          </param>
+          <when value="cached">
+            <param name="ref_file" type="select" label="Using reference genome" help="REFERENCE_SEQUENCE">
+              <options from_data_table="all_fasta">
+              </options>
+              <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
+            </param>
+          </when>
+          <when value="history">
+            <param name="ref_file" type="data" format="fasta" label="Use the following dataset as the reference sequence" help="REFERENCE_SEQUENCE; You can upload a FASTA sequence to the history and use it as reference" />
+          </when>
+        </conditional>
 
         <section name="adv" title="Optional data inputs">
             <!-- optional inputs -->
@@ -98,6 +119,7 @@
         <param name="max_haplotypes" type="integer" optional="true" value="1000" label="Consider at most N haplotype combinations" help="(-x)"/>
         <param name="max_rounds" type="integer" optional="true" value="50" label="Perform N rounds of consensus sequence improvement" help="(--max_rounds)"/>
         <param name="ploidy" type="integer" optional="true" value="-1" label="The ploidy level of the sequenced genome. -1:disabled" help="(-p)"/>
+        <param name="min_flanking_sequence" type="integer" optional="true" value="" label="Distance from alignment end to calculate variants" help="(--min-flanking-sequence)"/>
 
         <!-- optional flags -->
         <param argument="--consensus" type="boolean" truevalue="--consensus" falsevalue="" checked="true" label="Consensus calling mode and output polished sequence" />
@@ -117,36 +139,41 @@
     </outputs>
     <tests>
         <test>
-      <!-- index test -->
             <param name="input_merged" ftype="fasta" value="reads.fasta" />
             <param name="input_reads_raw" ftype="fast5.tar.gz" value="fast5_files.tar.gz" />
-            
-      <!-- variants consensus test -->
             <param name="b" value="reads.sorted.bam" />
-            <param name="g" value="draft.fa" />
+            <param name="reference_source_selector" value="history" />
+            <param name="ref_file" value="draft.fa" />
             <param name="w" value="tig00000001:200000-202000" />
-            
             <output name="output_polished" file="polished.fa" />
             <output name="output_variants" file="variants.vcf"/>
         </test>
         <test>
-      <!-- index test -->
             <param name="input_merged" ftype="fasta" value="reads.fasta" />
             <param name="input_reads_raw" ftype="fast5.tar.gz" value="fast5_files.tar.gz" />
-            
-      <!-- variants consensus test -->
             <param name="b" value="reads.sorted.bam" />
-            <param name="g" value="draft.fa" />
+            <param name="reference_source_selector" value="history" />
+            <param name="ref_file" value="draft.fa" />
             <param name="w" value="tig00000001:200000-202000" />
             <param name="ploidy" value="2" />
             <param name="snps" value="true" />            
             <param name="faster" value="true" />            
             <param name="all_bases" value="true" /> 
             <param name="consensus" value="false" /> 
+            <param name="min_flanking_sequence" value="30" />
             <output name="output_polished" file="t2-polished.fa" />
             <output name="output_variants" file="t2-variants.vcf"/>
         </test>
-
+        <test>
+            <param name="input_merged" ftype="fasta" value="reads.fasta" />
+            <param name="input_reads_raw" ftype="fast5.tar.gz" value="fast5_files.tar.gz" />
+            <param name="b" value="reads.sorted.bam" />
+            <param name="reference_source_selector" value="cached" />
+            <param name="ref_file" value="draft"/>
+            <param name="w" value="tig00000001:200000-202000" />
+            <output name="output_polished" file="polished.fa" />
+            <output name="output_variants" file="variants.vcf"/>
+        </test>
     </tests>
     <help><![CDATA[
 
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/all_fasta.loc	Tue Jun 05 17:58:46 2018 -0400
@@ -0,0 +1,1 @@
+draft	draft	draft	${__HERE__}/draft.fa
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.sample	Tue Jun 05 17:58:46 2018 -0400
@@ -0,0 +1,9 @@
+<!-- Use the file tool_data_table_conf.xml.oldlocstyle if you don't want to update your loc files as changed in revision 4550:535d276c92bc-->
+<tables>
+    <!-- Locations of all fasta files under genome directory -->
+    <table name="all_fasta" comment_char="#" allow_duplicate_entries="False">
+        <columns>value, dbkey, name, path</columns>
+        <file path="tool-data/all_fasta.loc" />
+    </table>
+</tables>
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.test	Tue Jun 05 17:58:46 2018 -0400
@@ -0,0 +1,7 @@
+<tables>
+    <!-- Locations of all fasta files under genome directory -->
+    <table name="all_fasta" comment_char="#" allow_duplicate_entries="False">
+        <columns>value, dbkey, name, path</columns>
+        <file path="${__HERE__}/test-data/all_fasta.loc" />
+    </table>
+</tables>