Mercurial > repos > iuc > bcftools_merge

changeset 4:df40d7f9737c 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-iuc/tree/master/tools/bcftools commit 3edcac645f34d5a94884dedaf95c5774f4afc5c7
author iuc
date Sat, 11 Mar 2017 18:00:12 -0500
parents d6f351f2d6a0
children c5c61f2f8757
files README.md bcftools_merge.xml macros.xml tool_dependencies.xml
diffstat 4 files changed, 40 insertions(+), 65 deletions(-) [+]
line wrap: on
line diff
--- a/README.md	Tue Jan 31 12:43:11 2017 -0500
+++ b/README.md	Sat Mar 11 18:00:12 2017 -0500
@@ -3,7 +3,7 @@
 Copied from branch bcftools1.2:
 
 This aims to be a "faithful" rendering of the bcftool suite. I.e. options are
-presented essentially as closely to the command line version as is useful. 
+presented essentially as closely to the command line version as is useful.
 
 This may not appeal to all, if you'd like to see smaller and more dedicated
 tools (e.g. "intersect", "union" and "complement" being separate tools instead
@@ -11,12 +11,12 @@
 
 Updated for bcftools v1.3
 
-This was extended from the bcftools1.2 branch then greatly hand edited to 
+This was extended from the bcftools1.2 branch then greatly hand edited to
 group params and manage param innteractions.
 
-In the macros.xml there are macros and tokens to handle file input and output.  
+In the macros.xml there are macros and tokens to handle file input and output.
 These use the datatypes currently available in galaxy: Vcf and Bcf
-The macros take care of bgzip and indexing of inputs.  
+The macros take care of bgzip and indexing of inputs.
 
 The convert command was split into 2 tools, "convert to vcf" and "convert from vcf"
 
@@ -27,7 +27,7 @@
 - cnv needs an input.vcf for testing, runs with bcftools cnv -s "HG00101" -o 'HG00101/' -p 5 mpileup.vcf
 - roh needs a more useful input.vcf for testing
 - plugin color chrs
-- plugin frameshifts 
+- plugin frameshifts
 
 ## Status
 
--- a/bcftools_merge.xml	Tue Jan 31 12:43:11 2017 -0500
+++ b/bcftools_merge.xml	Sat Mar 11 18:00:12 2017 -0500
@@ -1,5 +1,5 @@
 <?xml version='1.0' encoding='utf-8'?>
-<tool name="bcftools @EXECUTABLE@" id="bcftools_@EXECUTABLE@" version="@VERSION@.0">
+<tool name="bcftools @EXECUTABLE@" id="bcftools_@EXECUTABLE@" version="@VERSION@">
     <description>Merge multiple VCF/BCF files from non-overlapping sample sets to create one multi-sample file</description>
     <macros>
         <token name="@EXECUTABLE@">merge</token>
--- a/macros.xml	Tue Jan 31 12:43:11 2017 -0500
+++ b/macros.xml	Sat Mar 11 18:00:12 2017 -0500
@@ -1,6 +1,5 @@
-
 <macros>
-  <token name="@VERSION@">1.3</token>
+  <token name="@VERSION@">1.3.1</token>
   <xml name="stdio">
     <stdio>
       <exit_code range="1:" />
@@ -11,13 +10,10 @@
   </xml>
   <xml name="requirements">
     <requirements>
-      <requirement type="package" version="1.3">bcftools</requirement>
+      <requirement type="package" version="1.3.1">bcftools</requirement>
       <!-- conda dependency -->
-      <requirement type="package" version="1.3">htslib</requirement>
-      <!-- htslib provides tabix and bgzip
-      <requirement type="package" version="0.2.6">tabix</requirement>
-      -->
-      <requirement type="package" version="1.2">samtools</requirement>
+      <requirement type="package" version="1.3.2">htslib</requirement>
+      <yield />
     </requirements>
   </xml>
   <xml name="version_command">
@@ -48,20 +44,20 @@
 ## May need to symlink input if there is an associated
 #set $input_vcf = 'input.vcf.gz'
 #if $input_file.is_of_type('vcf')
-  bgzip -c "$input_file" > $input_vcf &&
+  bgzip -c '$input_file' > $input_vcf &&
   bcftools index $input_vcf &&
 #elif $input_file.is_of_type('vcf_bgzip')
-  ln -s "$input_file" $input_vcf
+  ln -s '$input_file' $input_vcf
 #elif $input_file.is_of_type('bcf')
   #set $input_vcf = 'input.bcf'
-  ln -s "$input_file" $input_vcf &&
+  ln -s '$input_file' $input_vcf &&
   #if $input_file.metadata.bcf_index:
-    ln -s $input_file.metadata.bcf_index ${input_vcf}.csi &&
+    ln -s '${input_file.metadata.bcf_index}' ${input_vcf}.csi &&
   #else
     bcftools index $input_vcf &&
   #end if
 #elif $input_file.is_of_type('bcf_bgzip')
-  ln -s "$input_file" $input_vcf
+  ln -s '$input_file' $input_vcf
 #end if
 ]]>
   </token>
@@ -77,24 +73,23 @@
 ## May need to symlink input if there is an associated
 #set $input_vcfs = []
 #set $vcfs_list_file = 'vcfs_list'
-#for (i,input_file) in enumerate($input_files):
+#for (i, input_file) in enumerate($input_files):
   #set $input_vcf = 'input' + str($i) + '.vcf.gz'
   #if $input_file.is_of_type('vcf')
-    bgzip -c "$input_file" > $input_vcf &&
+    bgzip -c '$input_file' > $input_vcf &&
     bcftools index $input_vcf &&
   #elif $input_file.is_of_type('vcf_bgz')
-    ln -s "$input_file" $input_vcf
+    ln -s '$input_file' $input_vcf
   #elif $input_file.is_of_type('bcf')
     #set $input_vcf = 'input' + str($i) + '.bcf.gz'
-    ## bgzip -c "$input_file" > $input_vcf &&
-    ln -s "$input_file" $input_vcf &&
+    ln -s '$input_file' $input_vcf &&
     #if $input_file.metadata.bcf_index:
-      ln -s $input_file.metadata.bcf_index ${input_vcf}.csi &&
+      ln -s '${input_file.metadata.bcf_index}' ${input_vcf}.csi &&
     #else
       bcftools index $input_vcf &&
     #end if
   #elif $input_file.is_of_type('bcfvcf_bgz')
-    ln -s "$input_file" $input_vcf &&
+    ln -s '$input_file' $input_vcf &&
   #end if
   echo '$input_vcf' >> $vcfs_list_file &&
   $input_vcfs.append($input_vcf)
@@ -109,23 +104,23 @@
   </token>
 
   <xml name="macro_fasta_ref">
-    <param name="fasta_ref" type="data" format="data" label="Fasta Ref" optional="True" help="reference sequence in fasta format" />
+    <param name="fasta_ref" argument="--fasta-ref" type="data" format="data" label="Reference sequence in FASTA format" optional="True" />
   </xml>
   <token name="@PREPARE_FASTA_REF@">
 <![CDATA[
 #set $input_fa_ref = None
 #if 'fasta_ref' in $section and $section.fasta_ref:
   #set $input_fa_ref = 'ref.fa'
-  ln -s $section.fasta_ref $input_fa_ref &&
+  ln -s '$section.fasta_ref' $input_fa_ref &&
   samtools faidx $input_fa_ref &&
 #end if
 ]]>
   </token>
   <token name="@FASTA_REF@">
 #if $input_fa_ref is not None:
-  --fasta-ref  "$input_fa_ref"
+  --fasta-ref $input_fa_ref
 #elif 'fasta_ref' in $section and $section.fasta_ref:
-  --fasta-ref "${section.fasta_ref}"
+  --fasta-ref '${section.fasta_ref}'
 #end if
   </token>
 
@@ -151,24 +146,24 @@
 
 
   <xml name="macro_AF_file">
-    <param name="AF_file" type="data" format="data" label="Af File" optional="True" help="read allele frequencies from file (CHR\tPOS\tREF,ALT\tAF)" />
+    <param name="AF_file" argument="--AF-file" type="data" format="tabular" label="Allele frequencies file" optional="True" help="Tab-delimited file containing the columns CHR,POS,REF,ALT,AF" />
   </xml>
   <!-- This may need to bgzip and tabix the file -->
   <token name="@PREPARE_AF_FILE@">
 <![CDATA[
 #if 'AF_file' in $section and $section.AF_file:
-#pass
+    #pass
 #end if
 ]]>
   </token>
   <token name="@AF_FILE@">
 #if 'AF_file' in $section and $section.AF_file:
-  --AF-file "${section.AF_file}"
+  --AF-file '${section.AF_file}'
 #end if
   </token>
 
   <xml name="macro_estimate_AF">
-      <param name="estimate_AF" type="data" format="data" label="Estimate Af" optional="True" help="calculate AC,AN counts on the fly, using either all samples (&quot;-&quot;) or samples listed in &lt;file&gt;" />
+      <param name="estimate_AF" argument="--estimate-AF" type="data" format="data" label="Estimate allele frequency" optional="True" help="calculate AC,AN counts on the fly, using either all samples (&quot;-&quot;) or samples listed in &lt;file&gt;" />
   </xml>
   <token name="@ESTIMATE_AF@">
 #if 'estimate_AF' in $section and $section.estimate_AF:
@@ -222,7 +217,7 @@
   </xml>
   <token name="@COLLAPSE@">
 #if $section.collapse:
-  --collapse "${section.collapse}"
+  --collapse ${section.collapse}
 #end if
   </token>
 
@@ -234,7 +229,7 @@
   </xml>
   <token name="@APPLY_FILTERS@">
 #if $section.apply_filters:
-  --apply-filters "${section.apply_filters}"
+  --apply-filters '${section.apply_filters}'
 #end if
   </token>
 
@@ -286,9 +281,9 @@
   </xml>
   <token name="@REGIONS@">
 #if $section.regions.regions_src == 'regions' and $section.regions.regions != '':
-  --regions "$section.regions.regions"
+  --regions '$section.regions.regions'
 #elif $section.regions.regions_src == 'regions_file' and $section.regions.regions_file:
-  --regions-file "$section.regions.regions_file"
+  --regions-file '$section.regions.regions_file'
 #end if
   </token>
 
@@ -351,7 +346,7 @@
   --targets-file "${section.targets.invert_targets_file}${targets_path}"
 #else:
   #if $section.targets.targets_src == 'targets' and $section.targets.targets != '':
-    --targets "${section.targets.invert_targets_file}${section.targets.targets}"
+    --targets '${section.targets.invert_targets_file}${section.targets.targets}'
   #elif $section.targets.targets_src == 'targets_file' and $section.targets.targets_file:
     --targets-file "${section.targets.invert_targets_file}${section.targets.targets_file}"
   #end if
@@ -375,7 +370,7 @@
 #set $samples_defined = False
 #if str($section.samples) != '':
   #set $samples_defined = True
-  --samples "${section.invert_samples}${section.samples}"
+  --samples '${section.invert_samples}${section.samples}'
 #end if
 #if $section.samples_file:
   #set $samples_defined = True
@@ -388,7 +383,7 @@
   </xml>
   <token name="@SAMPLE@">
 #if $section.sample:
-  --sample "${section.sample}"
+  --sample '${section.sample}'
 #end if
   </token>
 
@@ -425,7 +420,7 @@
   </xml>
   <token name="@COLUMNS@">
 #if $section.columns != '':
-  --columns "${section.columns}"
+  --columns '${section.columns}'
 #end if
   </token>
 
@@ -453,8 +448,7 @@
 This Galaxy tool recommends using the compressed BCF format
 as piping is not implemented, and uncompressed data would
 use unnecessary amounts of space.
-
-]]></token>
+  ]]></token>
   <token name="@REGIONS_HELP@">
       <![CDATA[
 Region Selections
@@ -475,8 +469,7 @@
 FILE. Note that overlapping regions in FILE can result in
 duplicated out of order positions in the output. This option
 requires indexed VCF/BCF files.
-
-]]></token>
+  ]]></token>
   <token name="@TARGETS_HELP@"><![CDATA[
 Targets
 -------
@@ -541,7 +534,6 @@
 | id         | only records with identical ID column are compatible.          |
 |            | Supportedby bcftools merge only.                               |
 +------------+----------------------------------------------------------------+
-
   </token>
 
   <token name="@EXPRESSIONS_HELP@">
@@ -666,10 +658,5 @@
       ID=@file       .. selects lines with ID present in the file
       ID!=@~/file    .. skip lines with ID present in the ~/file
       MAF[0]<0.05    .. select rare variants at 5% cutoff
-
-]]></token>
-
-
-
-
+  ]]></token>
 </macros>
--- a/tool_dependencies.xml	Tue Jan 31 12:43:11 2017 -0500
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,12 +0,0 @@
-<?xml version="1.0"?>
-<tool_dependency>
-    <package name="bcftools" version="1.3">
-        <repository changeset_revision="43a9aebf3adb" name="package_bcftools_1_3" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" />
-    </package>
-    <package name="tabix" version="0.2.6">
-        <repository changeset_revision="389d2376b60b" name="package_tabix_0_2_6" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" />
-    </package>
-    <package name="samtools" version="1.2">
-        <repository changeset_revision="f6ae3ba3f3c1" name="package_samtools_1_2" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" />
-    </package>
-</tool_dependency>