Mercurial > repos > devteam > bwa

changeset 11:546ada4a9f43 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/bwa commit 610045611b00099e0a24183c8cf33aebfa9635cf
author devteam
date Tue, 19 Jan 2016 11:20:59 -0500
parents 6069ffa8b240
children bd3a1e0de84c
files bwa-mem.xml bwa.xml bwa_macros.xml
diffstat 3 files changed, 51 insertions(+), 85 deletions(-) [+]
line wrap: on
line diff
--- a/bwa-mem.xml	Fri Jan 08 17:02:09 2016 -0500
+++ b/bwa-mem.xml	Tue Jan 19 11:20:59 2016 -0500
@@ -1,5 +1,5 @@
 <?xml version="1.0"?>
-<tool id="bwa_mem" name="Map with BWA-MEM" version="0.7.12">
+<tool id="bwa_mem" name="Map with BWA-MEM" version="@VERSION@.1">
   <description>- map medium and long reads (&gt; 100 bp) against reference genome</description>
   <macros>
     <import>read_group_macros.xml</import>
@@ -9,28 +9,7 @@
   <expand macro="stdio" />
   <command>
 <![CDATA[
-    #set $reference_fasta_filename = "localref.fa"
-
-    #if str( $reference_source.reference_source_selector ) == "history":
-        ln -s "${reference_source.ref_file}" "${reference_fasta_filename}" &&
-
-        ## The following shell commands decide which of the BWA indexing algorithms (IS or BWTSW) will be run
-        ## depending on the size of the input FASTA dataset
-        ( size=`stat -c %s "${reference_source.ref_file}" 2>/dev/null`; ## Linux
-          if [ $? -ne 0 ]; then
-              size=\$(stat -f %z "${reference_source.ref_file}"); ## OSX
-          fi &&
-          if [ "\$size" -lt 2000000000 ]; then
-              echo "Reference genome size is \$size bytes, generating BWA index with is algorithm";
-              bwa index -a is "${reference_fasta_filename}";
-          else
-              echo "Reference genome size is \$size bytes, generating BWA index with bwtsw algorithm";
-              bwa index -a bwtsw "${reference_fasta_filename}";
-          fi
-        ) &&
-    #else:
-        #set $reference_fasta_filename = str( $reference_source.ref_file.fields.path )
-    #end if
+    @set_reference_fasta_filename@
 
     ## Begin BWA-MEM command line
 
@@ -124,25 +103,7 @@
   </command>
 
   <inputs>
-
-    <conditional name="reference_source">
-      <param name="reference_source_selector" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options. See `Indexes` section of help below">
-        <option value="cached">Use a built-in genome index</option>
-        <option value="history">Use a genome from history and build index</option>
-      </param>
-      <when value="cached">
-        <param name="ref_file" type="select" label="Using reference genome" help="Select genome from the list">
-          <options from_data_table="bwa_mem_indexes">
-            <filter type="sort_by" column="2" />
-            <validator type="no_options" message="No indexes are available" />
-          </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="You can upload a FASTA sequence to the history and use it as reference" />
-      </when>
-    </conditional>
+    <expand macro="reference_source_conditional" />
     <conditional name="fastq_input">
       <param name="fastq_input_selector" type="select" label="Single or Paired-end reads" help="Select between paired and single end data">
         <option value="paired">Paired</option>
@@ -290,6 +251,7 @@
     <test>
       <param name="reference_source_selector" value="history" />
       <param name="ref_file" ftype="fasta" value="bwa-mem-mt-genome.fa"/>
+      <param name="index_a" value="is"/>
       <param name="fastq_input_selector" value="paired"/>
       <param name="fastq_input1" ftype="fastqsanger" value="bwa-mem-fastq1.fq"/>
       <param name="fastq_input2" ftype="fastqsanger" value="bwa-mem-fastq2.fq"/>
--- a/bwa.xml	Fri Jan 08 17:02:09 2016 -0500
+++ b/bwa.xml	Tue Jan 19 11:20:59 2016 -0500
@@ -1,5 +1,5 @@
 <?xml version="1.0"?>
-<tool id="bwa" name="Map with BWA" version="0.7.12">
+<tool id="bwa" name="Map with BWA" version="@VERSION@.1">
   <description>- map short reads (&lt; 100 bp) against reference genome</description>
   <macros>
     <import>read_group_macros.xml</import>
@@ -69,28 +69,7 @@
   <expand macro="stdio" />
   <command>
 <![CDATA[
-    #set $reference_fasta_filename = "localref.fa"
-
-    #if str( $reference_source.reference_source_selector ) == "history":
-        ln -s "${reference_source.ref_file}" "${reference_fasta_filename}" &&
-
-        ## The following shell commands decide which of the BWA indexing algorithms (IS or BWTSW) will be run
-        ## depending on the size of the input FASTA dataset
-        ( size=`stat -c %s "${reference_source.ref_file}" 2>/dev/null`; ## Linux
-          if [ $? -ne 0 ]; then
-              size=\$(stat -f %z "${reference_source.ref_file}"); ## OSX
-          fi &&
-          if [ "\$size" -lt 2000000000 ]; then
-              echo "Reference genome size is \$size bytes, generating BWA index with is algorithm";
-              bwa index -a is "${reference_fasta_filename}";
-          else
-              echo "Reference genome size is \$size bytes, generating BWA index with bwtsw algorithm";
-              bwa index -a bwtsw "${reference_fasta_filename}";
-          fi
-        ) &&
-    #else:
-        #set $reference_fasta_filename = str( $reference_source.ref_file.fields.path )
-    #end if
+    @set_reference_fasta_filename@
 
     ## setup vars for rg handling...
     @define_read_group_helpers@
@@ -246,25 +225,7 @@
   </command>
 
   <inputs>
-    
-    <conditional name="reference_source">
-      <param name="reference_source_selector" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options. See `Indexes` section of help below">
-        <option value="cached">Use a built-in genome index</option>
-        <option value="history">Use a genome from history and build index</option>
-      </param>
-      <when value="cached">
-        <param name="ref_file" type="select" label="Using reference genome" help="Select genome from the list">
-          <options from_data_table="bwa_mem_indexes">
-            <filter type="sort_by" column="2" />
-            <validator type="no_options" message="No indexes are available" />
-          </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="You can upload a FASTA sequence to the history and use it as reference" />
-      </when>
-    </conditional>
+    <expand macro="reference_source_conditional" />
     <conditional name="input_type">
       <param name="input_type_selector" type="select" label="Select input type" help="Select between fastq and bam datasets and between paired and single end data">
         <option value="paired">Paired fastq</option>
--- a/bwa_macros.xml	Fri Jan 08 17:02:09 2016 -0500
+++ b/bwa_macros.xml	Tue Jan 19 11:20:59 2016 -0500
@@ -1,5 +1,8 @@
 <macros>
   <import>read_group_macros.xml</import>
+
+  <token name="@VERSION@">0.7.12</token>
+
   <token name="@set_rg_string@">
       #set $rg_string = "@RG\\tID:" + str($rg_id)
       #set $rg_string += $format_read_group("\\tSM:", $rg_sm)
@@ -15,9 +18,23 @@
       #set $rg_string += $format_read_group("\\tPU:", $rg_pu)
   </token>
 
+  <token name="@set_reference_fasta_filename@"><![CDATA[
+    #if str( $reference_source.reference_source_selector ) == "history":
+        #set $reference_fasta_filename = "localref.fa"
+        ln -s "${reference_source.ref_file}" "${reference_fasta_filename}" &&
+        bwa index
+        #if str($reference_source.index_a) != 'auto'
+            -a ${reference_source.index_a}
+        #end if
+        "${reference_fasta_filename}" &&
+    #else:
+        #set $reference_fasta_filename = str( $reference_source.ref_file.fields.path )
+    #end if
+  ]]></token>
+
   <xml name="requirements">
     <requirements>
-      <requirement type="package" version="0.7.12">bwa</requirement>
+      <requirement type="package" version="@VERSION@">bwa</requirement>
       <requirement type="package" version="1.2">samtools</requirement>
     </requirements>
   </xml>
@@ -31,6 +48,32 @@
       </stdio>
   </xml>
 
+  <macro name="reference_source_conditional">
+    <conditional name="reference_source">
+      <param name="reference_source_selector" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options. See `Indexes` section of help below">
+        <option value="cached">Use a built-in genome index</option>
+        <option value="history">Use a genome from history and build index</option>
+      </param>
+      <when value="cached">
+        <param name="ref_file" type="select" label="Using reference genome" help="Select genome from the list">
+          <options from_data_table="bwa_mem_indexes">
+            <filter type="sort_by" column="2" />
+            <validator type="no_options" message="No indexes are available" />
+          </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="You can upload a FASTA sequence to the history and use it as reference" />
+        <param name="index_a" type="select" label="Algorithm for constructing the BWT index" help="(-a)">
+          <option value="auto">Auto. Let BWA decide the best algorithm to use</option>
+          <option value="is">IS linear-time algorithm for constructing suffix array. It requires 5.37N memory where N is the size of the database. IS is moderately fast, but does not work with database larger than 2GB</option>
+          <option value="bwtsw">BWT-SW algorithm. This method works also with big genomes</option>
+        </param>
+      </when>
+    </conditional>
+  </macro>
+
   <macro name="dbKeyActionsBwa">
     <expand macro="dbKeyActions">
       <option type="from_data_table" name="bwa_indexes" column="1" offset="0">