Mercurial > repos > mvdbeek > tepid_refine

changeset 0:5d1f880c988b draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/ListerLab/TEPID commit 82fd0448ff5baa9822a388aee78753e4b1cd94d7
author mvdbeek
date Mon, 23 Jan 2017 10:05:22 -0500
parents
children
files macros.xml tepid-refine.xml test-data/conc.bam test-data/deletion_reads_2.txt test-data/insertion_reads_2.txt test-data/merged_flipped_deletions.bed test-data/merged_insertions.bed test-data/second_pass_deletion_2.bed test-data/second_pass_insertion_2.bed test-data/split.bam test-data/te.bed
diffstat 11 files changed, 149 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/macros.xml	Mon Jan 23 10:05:22 2017 -0500
@@ -0,0 +1,29 @@
+<macros>
+    <xml name="requirements">
+        <requirements>
+            <requirement type="package" version="0.8.0">tepid</requirement>
+            <yield/>
+        </requirements>
+    </xml>
+    <token name="@WRAPPER_VERSION@">0.8.0</token>
+    <token name="@REFERENCES@">
+<![CDATA[
+------
+This tool is part of the `TEPID`_ pipeline from the `Lister laboratory`_.
+.. _TEPID package: https://github.com/ListerLab/TEPID
+.. _Lister laboratory http://listerlab.org/
+]]>
+    </token>
+    <token name="@PROC@">-p \$GALAXY_SLOTS</token>
+    <token name="@NAME@">-n '$bowtie2_bam.element_identifier'</token>
+    <token name="@LINK_CONC@"><![CDATA[
+        ln -f -s '$bowtie2_bam' conc.bam &&
+        ln -f -s '$bowtie2_bam.metadata.bam_index' conc.bam.bai &&
+    ]]></token>
+    <xml name="citations">
+        <citations>
+            <citation type="doi">10.7554/eLife.20777</citation>
+            <yield />
+        </citations>
+    </xml>
+</macros>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tepid-refine.xml	Mon Jan 23 10:05:22 2017 -0500
@@ -0,0 +1,103 @@
+<tool id="tepid-refine" name="tepid-refine" version="0.1.0">
+    <description>refine and genotype TE insertion and deletion calls</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="requirements"/>
+    <version_command>tepid-refine --version</version_command>
+    <command detect_errors="exit_code"><![CDATA[
+    @LINK_CONC@
+    ln -s -f '$deletion_readsupport' deletion_reads_'$bowtie2_bam.element_identifier'.txt &&
+    ln -s -f '$insertion_readsupport' insertion_reads_'$bowtie2_bam.element_identifier'.txt &&
+    tepid-refine
+    -i '$insertions'
+    -d '$deletions'
+    -c conc.bam
+    -s '$split_bam'
+    -t '$te_annotation_bed'
+    -a '$all_sample_ids'  ## use collection and collapse names in cheetah
+    @PROC@
+    @NAME@ &&
+    mv second_pass_insertion_'$bowtie2_bam.element_identifier'.bed second_pass_insertion.bed &&
+    mv ambiguous_insertion_'$bowtie2_bam.element_identifier'.bed ambiguous_insertion.bed &&
+    mv second_pass_reads_insertion_'$bowtie2_bam.element_identifier'.txt second_pass_reads_insertion.txt &&
+    mv second_pass_deletion_'$bowtie2_bam.element_identifier'.bed second_pass_deletion.bed &&
+    mv ambiguous_deletion_'$bowtie2_bam.element_identifier'.bed  ambiguous_deletion.bed &&
+    mv second_pass_reads_deletion_'$bowtie2_bam.element_identifier'.txt second_pass_reads_deletion.txt
+    ]]></command>
+    <configfiles>
+        <configfile name="all_sample_ids">#if $sample_id_source.source == 'enter':
+    #set $sample_list = "\n".join([x for x in str($sample_id_source.sample_ids).split(',')])
+#else
+    #set $sample_list =  "\n".join([str(x.element_identifier) for x in $sample_id_source.sample_ids])
+#end if
+$sample_list</configfile>
+    </configfiles>
+    <inputs>
+        <param name="bowtie2_bam" argument="--conc" type="data" format="bam"/>
+        <param name="split_bam" argument="--split" type="data" format="bam"/>
+        <param name="insertion_readsupport" type="data" format="txt"/>
+        <param name="deletion_readsupport" type="data" format="txt"/>
+        <param name="insertions" argument="--insertions" type="data" format="bed" help="Merged insertions"/>
+        <param name="deletions" argument="--deletions" type="data" format="bed" help="Merged and flipped deletions"/>
+        <param name="te_annotation_bed" argument="--te" type="data" format="bed"/>
+        <conditional name="sample_id_source">
+            <param name="source" type="select">
+                <option value="enter">Enter all sample ids</option>
+                <option value="auto">Infer sample IDs from collection identifiers</option>
+            </param>
+            <when value="enter">
+                <param name="sample_ids" type="text"/>
+            </when>
+            <when value="auto">
+                <param name="sample_ids" type="data_collection" collection_type="list"/>
+            </when>
+        </conditional>
+    </inputs>
+    <outputs>
+        <data name="refined_insertions" format="bed" from_work_dir="second_pass_insertion.bed" label="Refined insertions"/>
+        <data name="ambiguous_insertions" format="bed" from_work_dir="ambiguous_insertion.bed" label="Amibguous insertions"/>
+        <data name="second_pass_insertion_support" format="txt" from_work_dir="second_pass_reads_insertion.txt" label="Second pass insertion readsupport"/>
+        <data name="refined_deletions" format="bed" from_work_dir="second_pass_deletion.bed" label="Refined deletions"/>
+        <data name="ambiguous_deletions" format="bed" from_work_dir="ambiguous_deletion.bed" label="Ambiguous deletions"/>
+        <data name="second_pass_deletion_support" format="txt" from_work_dir="second_pass_reads_deletion.txt" label="Second pass deletion readsupport"/>
+    </outputs>
+    <tests>
+        <test>
+            <param name="bowtie2_bam" value="conc.bam"/>
+            <param name="split_bam" value="split.bam"/>
+            <param name="insertion_readsupport" value="insertion_reads_2.txt"/>
+            <param name="deletion_readsupport" value="deletion_reads_2.txt"/>
+            <param name="insertions" value="merged_insertions.bed" ftype="bed"/>
+            <param name="deletions" value="merged_flipped_deletions.bed" ftype="bed"/>
+            <param name="te_annotation_bed" value="te.bed" ftype="bed"/>
+            <param name="source" value="enter"/>
+            <param name="sample_ids" value="1,conc.bam"/>
+            <output name="refined_insertions" file="second_pass_insertion_2.bed"/>
+            <output name="refined_deletions" file="second_pass_deletion_2.bed"/>
+        </test>
+    </tests>
+    <help><![CDATA[
+TEPID -- refine TE insertion and deletion calls
+
+optional arguments:
+  -h, --help            show this help message and exit
+  --version             show program's version number and exit
+  -k, --keep            keep all intermediate files
+  -i INSERTIONS, --insertions INSERTIONS
+                        File containing collapsed TE insertions for all
+                        samples in population
+  -d DELETIONS, --deletions DELETIONS
+                        File containing collapsed TE deletions for all samples
+                        in population
+  -p PROC, --proc PROC  number of processors
+  -t TE, --te TE        TE annotation bedfile
+  -n NAME, --name NAME  sample name
+  -c CONC, --conc CONC  bam file from bowtie2
+  -s SPLIT, --split SPLIT
+                        split reads bam file from yaha
+  -a ALL_SAMPLES, --all_samples ALL_SAMPLES
+                        List of all sample names
+    ]]></help>
+<expand macro="citations"/>
+</tool>
Binary file test-data/conc.bam has changed
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/deletion_reads_2.txt	Mon Jan 23 10:05:22 2017 -0500
@@ -0,0 +1,1 @@
+>0	HWI-D00405:129:C6KNAANXX:3:2215:9536:100099
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/insertion_reads_2.txt	Mon Jan 23 10:05:22 2017 -0500
@@ -0,0 +1,1 @@
+>0	HWI-D00405:129:C6KNAANXX:3:1101:12123:8046
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/merged_flipped_deletions.bed	Mon Jan 23 10:05:22 2017 -0500
@@ -0,0 +1,2 @@
+2L	16858765	16859500	FBti0061428	iso1,2
+2L	16958165	16962888	FBti0019186	iso1
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/merged_insertions.bed	Mon Jan 23 10:05:22 2017 -0500
@@ -0,0 +1,4 @@
+2L	16859330	16859445	2L	11897167	11900029	FBti0019153	1
+2L	16958163	16962894	2L	13405706	13410430	FBti0019166	1
+2L	16962080	16962891	2L	17144384	17151999	FBti0019187	1
+2L	16960487	16961577	2L	18408081	18412800	FBti0019198	1
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/second_pass_deletion_2.bed	Mon Jan 23 10:05:22 2017 -0500
@@ -0,0 +1,1 @@
+2L	16958165	16962888	FBti0019186	1
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/second_pass_insertion_2.bed	Mon Jan 23 10:05:22 2017 -0500
@@ -0,0 +1,2 @@
+2L	16958163	16962894	2L	13405706	13410430	FBti0019166	1
+2L	16962080	16962891	2L	17144384	17151999	FBti0019187	2
Binary file test-data/split.bam has changed
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/te.bed	Mon Jan 23 10:05:22 2017 -0500
@@ -0,0 +1,6 @@
+2L	11897167	11900029	+	FBti0019153	Dmel\X-element	LINE-like
+2L	13405706	13410430	+	FBti0019166	Doc	Jockey
+2L	16858765	16859500	-	FBti0061428	hobo	hAT
+2L	16958165	16962888	+	FBti0019186	Doc	Jockey
+2L	17144384	17151999	-	FBti0019187	opus	Gypsy
+2L	18408081	18412800	+	FBti0019198	Doc	Jockey