changeset 20:5924e53ef39c draft default tip

Uploaded

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/.shed.yml	Thu Sep 15 04:57:12 2016 -0400
@@ -0,0 +1,14 @@
+categories:
+- Sequence Analysis
+- Next Gen Mappers
+description: Fast and accurate alignment of BS-seq reads.
+long_description: |
+    A fast and accurate aligner of BS-seq data.
+
+    - Supports single-end and paired-end alignments
+    - Supports gapped alignments
+    - Faster and more sensitive than many other tools
+name: bwameth
+owner: iuc
+remote_repository_url: https://github.com/galaxyproject/tools-iuc/tools/bwameth
+type: unrestricted

--- a/bwameth.xml	Wed Sep 14 07:54:59 2016 -0400
+++ b/bwameth.xml	Thu Sep 15 04:57:12 2016 -0400
@@ -1,20 +1,11 @@
-<tool id="bwameth" name="bwameth" version="0.20">
-  <description>Fast and accurate aligner of BS-Seq reads.</description>
-  <requirements>
-    <requirement type="package" version="0.4.6">toolshed</requirement>
-    <requirement type="package" version="1.2">samtools</requirement>
-    <requirement type="package" version="0.7.12">bwa</requirement>
-    <requirement type="package" version="0.20">bwameth</requirement>
-  </requirements>
-  <stdio>
-    <exit_code range="1:" />
-    <exit_code range=":-1" />
-    <regex match="Error:" />
-    <regex match="Exception:" />
-    <regex match="Exception :" />
-  </stdio>
-  <version_command>bwameth.py --version</version_command>
-  <command>
+<tool id="bwameth" name="bwameth" version="0.2.0.2">
+    <description>Fast and accurate aligner of BS-Seq reads.</description>
+    <requirements>
+        <requirement type="package" version="1.2">samtools</requirement>
+        <requirement type="package" version="0.2.0">bwameth</requirement>
+    </requirements>
+    <version_command>bwameth.py --version</version_command>
+    <command detect_errors="aggressive">
 <![CDATA[
     #if $referenceSource.source != "indexed":
         mkdir index_dir &&
@@ -27,7 +18,7 @@
 
     bwameth.py
         -t "\${GALAXY_SLOTS:-4}"
-        --reference ${index}
+        --reference "${index}"
 
     #if str($readGroup).strip() != "":
         --read-group "${readGroup}"
@@ -35,67 +26,93 @@
 
     #if $single_or_paired.single_or_paired_opts == 'single':
         $single_or_paired.input_singles
-    #else:
+    #elif $single_or_paired.single_or_paired_opts == 'paired':
         $single_or_paired.input_mate1 $single_or_paired.input_mate2
+    #else:
+        $single_or_paired.input_mate1.forward $single_or_paired.input_mate1.reverse
     #end if
-    | samtools view -u - | samtools sort -@ "\${GALAXY_SLOTS:-4}" - output
+    | samtools view -u - | samtools sort -@ "\${GALAXY_SLOTS:-4}" -o output.bam -
 ]]>
-  </command>
-  <inputs>
-    <conditional name="referenceSource">
-      <param name="source" type="select" label="Select a genome reference from your history or a built-in index?">
-        <option value="history" selected="True">Use one from the history</option>
-        <option value="indexed">Use a built-in index</option>
-      </param>
-      <when value="history">
-        <param name="reference" type="data" format="fasta" metadata_name="dbkey" label="Select a genome" help="in FASTA format" />
-      </when>
-      <when value="indexed">
-        <param name="index" type="select" label="Select a reference genome" help="If your genome of interest is not listed, contact your Galaxy admin">
-          <options from_data_table="bwameth_indexes">
-            <filter type="sort_by" column="2"/>
-              <validator type="no_options" message="No indexes are available for the selected input dataset"/>
-          </options>
-        </param>
-      </when>
-    </conditional>
+    </command>
+    <inputs>
+        <conditional name="referenceSource">
+            <param name="source" type="select" label="Select a genome reference from your history or a built-in index?">
+                <option value="history" selected="True">Use one from the history</option>
+                <option value="indexed">Use a built-in index</option>
+            </param>
+            <when value="history">
+                <param name="reference" type="data" format="fasta" metadata_name="dbkey" label="Select a genome" help="in FASTA format" />
+            </when>
+            <when value="indexed">
+                <param name="index" type="select" label="Select a reference genome" help="If your genome of interest is not listed, contact your Galaxy admin">
+                    <options from_data_table="bwameth_indexes">
+                        <filter type="sort_by" column="2"/>
+                        <validator type="no_options" message="No indexes are available for the selected input dataset"/>
+                    </options>
+                </param>
+            </when>
+        </conditional>
 
-    <conditional name="single_or_paired">
-      <param name="single_or_paired_opts" type="select" label="Is this library mate-paired?">
-        <option value="single">Single-end</option>
-        <option value="paired">Paired-end</option>
-      </param>
-      <when value="single">
-        <param name="input_singles" type="data" format="fastq" label="FASTQ" help="FASTQ file." />
-      </when>
-      <when value="paired">
-        <param name="input_mate1" type="data" format="fastq" label="First read in pair" help="FASTQ file." />
-        <param name="input_mate2" type="data" format="fastq" label="Second read in pair" help="FASTQ file." />
-      </when>
-    </conditional>
-    <param name="readGroup" type="text" value="" label="Read group" help="If desired, you can manually add read group information to the resulting BAM file. To do so, you MUST manually specify the entire string, such as '@RG\tID:foo\tSM:bar'">
-      <sanitizer sanitize="False"/>
-    </param>
-  </inputs>
-  <outputs>
-    <data name="output" format="bam" from_work_dir="output.bam" label="${tool.name} on ${on_string}" />
-  </outputs>
-  <tests>
-    <test>
-      <param name="referenceSource" value="history" />
-      <param name="reference" value="ref.fa.gz" />
-      <param name="single_or_paired_opts" value="paired" />
-      <param name="input_mate1" value="t_R1.fastq.gz" />
-      <param name="input_mate2" value="t_R2.fastq.gz" />
-      <output file="output.bam" ftype="bam" name="output" lines_diff="2"/>
-    </test>
-  </tests>
-  <help>
+        <conditional name="single_or_paired">
+            <param name="single_or_paired_opts" type="select" label="Is this library mate-paired?">
+                <option value="single">Single-end</option>
+                <option value="paired">Paired-end</option>
+                <option value="paired_collection">Paired-end Dataset Collection</option>
+            </param>
+            <when value="single">
+                <param name="input_singles" type="data" format="fastqsanger" label="FASTQ" help="FASTQ file." />
+            </when>
+            <when value="paired">
+                <param name="input_mate1" type="data" format="fastqsanger" label="First read in pair" help="FASTQ file." />
+                <param name="input_mate2" type="data" format="fastqsanger" label="Second read in pair" help="FASTQ file." />
+            </when>
+            <when value="paired_collection">
+                <param name="input_mate1" type="data_collection" collection_type="paired" format="fastqsanger" label="FASTQ paired dataset" help="Must have a fastqsanger datatype." />
+            </when>
+        </conditional>
+        <param name="readGroup" type="text" value="" label="Read group" help="If desired, you can manually add read group information to the resulting BAM file. To do so, you MUST manually specify the entire string, such as '@RG\tID:foo\tSM:bar'">
+            <sanitizer sanitize="False"/>
+        </param>
+    </inputs>
+    <outputs>
+        <data name="output" format="bam" from_work_dir="output.bam" label="${tool.name} on ${on_string}" />
+    </outputs>
+    <tests>
+        <test>
+            <param name="referenceSource" value="history" />
+            <param name="reference" value="ref.fa.gz" />
+            <param name="single_or_paired_opts" value="paired" />
+            <param name="input_mate1" value="t_R1.fastq.gz" />
+            <param name="input_mate2" value="t_R2.fastq.gz" />
+            <output file="output.bam" ftype="bam" name="output" lines_diff="2"/>
+        </test>
+        <test>
+            <param name="referenceSource" value="history" />
+            <param name="reference" value="ref.fa.gz" />
+            <param name="single_or_paired_opts" value="paired_collection" />
+            <param name="input_mate1">
+                <collection type="paired">
+                    <element name="forward" value="t_R1.fastq.gz" />
+                    <element name="reverse" value="t_R2.fastq.gz" />
+                </collection>
+            </param>
+            <output file="output.bam" ftype="bam" name="output" lines_diff="2"/>
+        </test>
+    </tests>
+    <help>
 <![CDATA[
 
 **What it does**
 
 BWA-meth performs alignment of reads in a bisulfite-sequencing experiment (e.g., RRBS or WGBS) to a genome. The methodology employed for this is similar to bismark, where both the reads and the reference genome are *in silico* converted prior to alignment. Methylation extraction on the resulting BAM file can be done with the PileOMeth tool.
 ]]>
-  </help>
+    </help>
+    <citations>
+        <citation type="bibtex">@misc{1401.1129,
+        Author = {Brent S. Pedersen and Kenneth Eyring and Subhajyoti De and Ivana V. Yang and David A. Schwartz},
+        Title = {Fast and accurate alignment of long bisulfite-seq reads},
+        Year = {2014},
+        Eprint = {arXiv:1401.1129},
+        }</citation>
+    </citations>
 </tool>

Binary file test-data/output.bam has changed

Binary file test-data/ref.fa.gz has changed

Binary file test-data/t_R1.fastq.gz has changed

Binary file test-data/t_R2.fastq.gz has changed

--- a/tool-data/bwameth_indexes.loc.sample	Wed Sep 14 07:54:59 2016 -0400
+++ b/tool-data/bwameth_indexes.loc.sample	Thu Sep 15 04:57:12 2016 -0400
@@ -1,10 +1,15 @@
 # This is a sample file distributed with Galaxy that is used to define a
 # list of bwa-meth indices, using three columns tab separated:
 #
-# bwameth_index_id\tSome description text\t/path/to/genome.fasta
+# <unique_build_id>	<dbkey>	<display_name>	<genome_fasta_file_path>
 #
 # An index can be created with the following command:
 #
 # bwameth.py index /some/path/genome.fa
 #
 # "/some/path/genome.fa" would then be the last column in the line
+# If this were for the mm10 mouse genome, the resulting entry would look like:
+#
+#mm9	mm9	Mouse (mm9)	/some/path/genome.fa
+#
+#

--- a/tool_data_table_conf.xml.sample	Wed Sep 14 07:54:59 2016 -0400
+++ b/tool_data_table_conf.xml.sample	Thu Sep 15 04:57:12 2016 -0400
@@ -1,6 +1,6 @@
 <tables>
     <table name="bwameth_indexes" comment_char="#">
-        <columns>value, name, path</columns>
+        <columns>value, dbkey, name, path</columns>
         <file path="tool-data/bwameth_indexes.loc" />
     </table>
 </tables>

--- a/tool_dependencies.xml	Wed Sep 14 07:54:59 2016 -0400
+++ b/tool_dependencies.xml	Thu Sep 15 04:57:12 2016 -0400
@@ -1,12 +1,9 @@
 <?xml version="1.0"?>
 <tool_dependency>
-    <package name="bwa" version="0.7.12">
-       <repository changeset_revision="67aa12c8d449" name="package_bwa_0_7_12" owner="iuc" toolshed="https://testtoolshed.g2.bx.psu.edu" />
-    </package>
     <package name="samtools" version="1.2">
        <repository changeset_revision="5b7172f9b230" name="package_samtools_1_2" owner="iuc" toolshed="https://testtoolshed.g2.bx.psu.edu" />
     </package>
-    <package name="bwameth" version="0.20">
-       <repository changeset_revision="435f9d24c060" name="package_python_2_7_bwameth_0_20" owner="dpryan79" toolshed="https://testtoolshed.g2.bx.psu.edu" />
+    <package name="bwameth" version="0.2.0">
+       <repository changeset_revision="fd470f9ef129" name="package_python_2_7_bwameth_0_2_0" owner="iuc" toolshed="https://testtoolshed.g2.bx.psu.edu" />
     </package>
 </tool_dependency>