# HG changeset patch
# User trinity_ctat
# Date 1513363210 18000
# Node ID a01db6debed542c86cc9b018a64d233490ef3db2

Adding star_fusion tool.

diff -r 000000000000 -r a01db6debed5 star_fusion.xml
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/star_fusion.xml	Fri Dec 15 13:40:10 2017 -0500
@@ -0,0 +1,89 @@
+<tool id="star-fusion" name="Star Fusion" version="1.0.0" profile="17.05">
+    <description>Fusion-finding Pipeline Using the STAR Aligner</description>
+    <requirements>
+	<requirement type="package" version="1.1.0">star-fusion</requirement>
+    </requirements>
+    <command detect_errors="default">
+    STAR-Fusion
+    --genome_lib_dir "${genome_ref_lib.fields.path}"
+    --left_fq  "${left_input}
+    --right_fq "${right_input}
+    --output_dir subdir
+    </command>
+    <stdio>
+      <exit_code range="1:"  level="fatal"   description="Error returned from pipeline" />
+    </stdio>
+    <regex match="Must investigate error above."
+           source="stderr"
+           level="fatal"
+           description="Unknown error encountered" />
+    <inputs>
+      <param format="fastq" name="left_input" type="data" label="Left/Forward strand reads" help=""/>
+      <param format="fastq" name="right_input" type="data" label="Right/Reverse strand reads" help=""/>
+      <param name="genome_ref_lib" type="select" label="Select a reference genome">
+        <options from_data_table="ctat_genome_ref_libs">
+          <filter type="sort_by" column="2" />
+          <validator type="no_options" message="No indexes are available" />
+        </options>
+      </param>
+
+    </inputs>
+    <outputs>
+      <data format="txt" name="starfusion_log" label="${tool.name} on ${on_string}: log" from_work_dir="subdir/Log.out"/>
+      <data format="bam" name="aligned_bam" label="${tool.name} on ${on_string}: Aligned Bam" from_work_dir="subdir/Aligned.sortedByCoord.out.bam"/>
+      <data format="tabular" name="candidates" label="${tool.name} on ${on_string}: Fusion candidates" from_work_dir="subdir/star-fusion.fusion_candidates.final.abridged"/>
+      <data format="tabular" name="chimeric_junc" label="${tool.name} on ${on_string}: Chimeric.out.junction" from_work_dir="subdir/Chimeric.out.junction"/> 
+    </outputs>
+    <tests>
+      <test>
+        <param name="left_input" value="StarFusion/reads_1.fq.gz" />
+        <param name="right_input" value="StarFusion/reads_2.fq.gz" />
+        <!--
+        <param name="left_input" value="reads.left.simPE.fq" />
+        <param name="right_input" value="reads.right.simPE.fq" />
+        -->
+        <!--
+        <output name="aligned_bam" file="SF_out_aligned.bam" />
+        <output name="candidates" file="SF_out_fusion_candidates.dat" />
+        <output name="chimeric_junc" file="SF_out_chimeric.junction" />
+        <output name="starfusion_log" file="SF_out.log" />
+        -->
+        <output name="starfusion_log">
+            <assert_contents>
+               <has_line_matching expression=".+" />
+               <has_line line="ALL DONE!" />
+            </assert_contents>
+        </output>
+        <output name="aligned_bam">
+            <assert_contents>
+               <has_line_matching expression=".+" />
+               <!-- The following checks for the magic number at the start of the bam file -->
+               <!-- At first I thought "\x8B\x1F" was the number, but it turns out the file
+                    produced by the StarFusion test had that sequence in the file somewhere else.
+               -->
+               <has_text_matching expression="\x1F\x8B" />
+            </assert_contents>
+        </output>
+        <output name="candidates">
+            <assert_contents>
+               <has_line_matching expression=".+" />
+               <has_line line="#fusion_name&#009;JunctionReads&#009;SpanningFrags&#009;Splice_type&#009;LeftGene&#009;LeftBreakpoint&#009;RightGene&#009;RightBreakpoint&#009;Long_double_anchor_support" />
+            </assert_contents>
+        </output>
+        <output name="chimeric_junc">
+            <assert_contents>
+               <has_line_matching expression=".+" />
+               <has_line_matching expression="^chr20.*" />
+            </assert_contents>
+        </output>
+      </test>
+    </tests>
+    <help>
+.. class:: infomark
+
+STAR-Fusion is a component of the Trinity Cancer Transcriptome Analysis Toolkit (CTAT). STAR-Fusion uses the STAR aligner to identify candidate fusion transcripts supported by Illumina reads. STAR-Fusion further processes the output generated by the STAR aligner to map junction reads and spanning reads to a reference annotation set. Please read more here_.
+
+.. _here: https://github.com/STAR-Fusion/STAR-Fusion/wiki
+
+    </help>
+</tool>
diff -r 000000000000 -r a01db6debed5 test-data/StarFusion/reads_1.fq.gz
Binary file test-data/StarFusion/reads_1.fq.gz has changed
diff -r 000000000000 -r a01db6debed5 test-data/StarFusion/reads_2.fq.gz
Binary file test-data/StarFusion/reads_2.fq.gz has changed