changeset 0:106dc0bf83c6 draft

Imported from capsule None
author bgruening
date Thu, 14 Aug 2014 07:41:51 -0400
parents
children 16f7587ab084
files readme.rst tool-data/fasta_indexes.loc.sample tool_data_table_conf.xml.sample tool_dependencies.xml vt_macros.xml vt_normalize.xml
diffstat 6 files changed, 213 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/readme.rst	Thu Aug 14 07:41:51 2014 -0400
@@ -0,0 +1,52 @@
+==========================================
+Galaxy wrapper for VT the Variant Tool Set
+==========================================
+
+A tool set for short variant discovery in genetic sequence data.
+
+http://genome.sph.umich.edu/wiki/vt
+
+============
+Installation
+============
+
+It is recommended to install this wrapper via the `Galaxy Tool Shed`.
+
+.. _`Galaxy Tool Shed`:  https://testtoolshed.g2.bx.psu.edu/view/iuc/vt
+
+
+=======
+History
+=======
+- 0.1: Initial public release
+
+
+====================
+Detailed description
+====================
+
+View the original GEMINI documentation: http://genome.sph.umich.edu/wiki/vt
+
+
+===============================
+Wrapper Licence (MIT/BSD style)
+===============================
+
+Permission to use, copy, modify, and distribute this software and its
+documentation with or without modifications and for any purpose and
+without fee is hereby granted, provided that any copyright notices
+appear in all copies and that both those copyright notices and this
+permission notice appear in supporting documentation, and that the
+names of the contributors or copyright holders not be used in
+advertising or publicity pertaining to distribution of the software
+without specific prior permission.
+
+THE CONTRIBUTORS AND COPYRIGHT HOLDERS OF THIS SOFTWARE DISCLAIM ALL
+WARRANTIES WITH REGARD TO THIS SOFTWARE, INCLUDING ALL IMPLIED
+WARRANTIES OF MERCHANTABILITY AND FITNESS, IN NO EVENT SHALL THE
+CONTRIBUTORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY SPECIAL, INDIRECT
+OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS
+OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE
+OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE
+OR PERFORMANCE OF THIS SOFTWARE.
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/fasta_indexes.loc.sample	Thu Aug 14 07:41:51 2014 -0400
@@ -0,0 +1,29 @@
+#This is a sample file distributed with Galaxy that enables tools
+#to use a directory of Samtools indexed sequences data files.  You will need
+#to create these data files and then create a fasta_indexes.loc file
+#similar to this one (store it in this directory) that points to
+#the directories in which those files are stored. The fasta_indexes.loc
+#file has this format (white space characters are TAB characters):
+#
+# <unique_build_id>	<dbkey>	<display_name>	<file_base_path>
+#
+#So, for example, if you had hg19 Canonical indexed stored in
+#
+# /depot/data2/galaxy/hg19/sam/,
+#
+#then the fasta_indexes.loc entry would look like this:
+#
+#hg19canon	hg19	Human (Homo sapiens): hg19 Canonical	/depot/data2/galaxy/hg19/sam/hg19canon.fa
+#
+#and your /depot/data2/galaxy/hg19/sam/ directory
+#would contain hg19canon.fa and hg19canon.fa.fai files.
+#
+#Your fasta_indexes.loc file should include an entry per line for
+#each index set you have stored.  The file in the path does actually
+#exist, but it should never be directly used. Instead, the name serves
+#as a prefix for the index file.  For example:
+#
+#hg18canon	hg18	Human (Homo sapiens): hg18 Canonical	/depot/data2/galaxy/hg18/sam/hg18canon.fa
+#hg18full	hg18	Human (Homo sapiens): hg18 Full	/depot/data2/galaxy/hg18/sam/hg18full.fa
+#hg19canon	hg19	Human (Homo sapiens): hg19 Canonical	/depot/data2/galaxy/hg19/sam/hg19canon.fa
+#hg19full	hg19	Human (Homo sapiens): hg19 Full	/depot/data2/galaxy/hg19/sam/hg19full.fa
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.sample	Thu Aug 14 07:41:51 2014 -0400
@@ -0,0 +1,7 @@
+<!-- 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>
+    <table name="fasta_indexes" comment_char="#">
+        <columns>value, dbkey, name, path</columns>
+        <file path="tool-data/fasta_indexes.loc" />
+    </table>
+</tables>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml	Thu Aug 14 07:41:51 2014 -0400
@@ -0,0 +1,6 @@
+<?xml version="1.0"?>
+<tool_dependency>
+  <package name="vt" version="5c735ab14b5603d9f14da6ee0e63d86ba3779934">
+      <repository changeset_revision="91635ed3dceb" name="package_vt_5c735ab14b5603d9f14da6ee0e63d86ba3779934" owner="iuc" toolshed="https://toolshed.g2.bx.psu.edu" />
+    </package>
+</tool_dependency>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/vt_macros.xml	Thu Aug 14 07:41:51 2014 -0400
@@ -0,0 +1,42 @@
+<macros>
+    <xml name="requirements">
+        <requirements>
+            <requirement type="package" version="5c735ab14b5603d9f14da6ee0e63d86ba3779934">vt</requirement>
+            <yield />
+        </requirements>
+    </xml>
+
+    <xml name="version_command">
+        <version_command><![CDATA[
+            vt view --help 2>&1 >/dev/null | head -n 1
+        ]]>
+        </version_command>
+    </xml>
+
+    <xml name="stdio">
+        <stdio>
+            <exit_code range="1:" />
+            <exit_code range=":-1" />
+            <regex match="Error:" />
+            <regex match="Exception:" />
+        </stdio>
+    </xml>
+
+    <token name="@VERSION@">0.1</token>
+
+    <token name="@CITATION@">------
+
+**Citation**
+
+If you use VT in your research, please cite the following project site:
+
+https://github.com/atks/vt
+
+  </token>
+  <!--xml name="citations">
+    <citations>
+        <citation type="doi">10.1371/journal.pcbi.1003153</citation>
+        <yield />
+    </citations>
+  </xml-->
+</macros>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/vt_normalize.xml	Thu Aug 14 07:41:51 2014 -0400
@@ -0,0 +1,77 @@
+<tool id="vt_@BINARY@" name="VT @BINARY@" version="@VERSION@.0">
+    <description>normalizes variants in a VCF file</description>
+    <expand macro="requirements" />
+    <expand macro="version_command" />
+    <macros>
+        <import>vt_macros.xml</import>
+        <token name="@BINARY@">normalize</token>
+    </macros>
+    <command>
+<![CDATA[
+        vt @BINARY@
+            -o "${ outfile }"
+            ##-q  do not print options and summary []
+            -w  window size for local sorting of variants [10000]
+
+            #if str( $intervals_file ) != 'None':
+                -I  "${intervals_file}"
+            #end if
+
+            ##-i  intervals []
+
+            #if $reference_source.reference_source_selector != "history":
+                -r "${reference_source.reference_genome.fields.path}"'
+            #else:
+                -r "${reference_source.reference_genome}"
+            #end if
+
+            "${ infile }"
+]]>
+    </command>
+    <expand macro="stdio" />
+    <inputs>
+        <param name="infile" type="data" format="vcf" label="VCF file to be normalised" />
+
+
+        <conditional name="reference_source">
+            <param name="reference_source_selector" type="select" label="Choose the source for the reference list">
+                <option value="cached" selected="True">Locally cached</option>
+                <option value="history">History</option>
+            </param>
+            <when value="cached">
+                <param name="reference_genome" type="select" label="Using reference genome">
+                    <options from_data_table="fasta_indexes">
+                        <filter type="data_meta" ref="infile" key="dbkey" column="1" />
+                        <validator type="no_options" message="No reference genome is available for the build associated with the selected input dataset" />
+                    </options>
+                </param>
+          </when>
+          <when value="history">
+                <param name="reference_genome" type="data" format="fasta" label="Using reference file" />
+          </when>
+        </conditional>
+
+        <param name="intervals_file" type="data" format="bed" optional="True" label="File containing list of intervals" />
+        <param name="window" type="integer" value="10000" size="10" label="Window size for local sorting of variants" 
+            help="(-w)">
+            <validator type="in_range" min="0"/>
+        </param>
+
+    </inputs>
+    <outputs>
+        <data name="outfile" format="vcf" label="${tool.name} on ${on_string}" />
+    </outputs>
+    <tests>
+        <test>
+        </test>
+    </tests>
+    <help>
+**What it does**
+
+Normalize variants in a VCF file. Normalized variants may have their positions changed; in such cases, 
+the normalized variants are reordered and output in an ordered fashion. The local reordering takes place over a window of 10000 base pairs.
+
+@CITATION@
+    </help>
+    <!--expand macro="citations"/-->
+</tool>