changeset 0:70f710e91120

Initial upload

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/bowtie2_indices.loc.sample	Mon Jan 27 13:16:59 2014 -0500
@@ -0,0 +1,37 @@
+# bowtie2_indices.loc.sample
+# This is a *.loc.sample file distributed with Galaxy that enables tools
+# to use a directory of indexed data files. This one is for Bowtie2 and Tophat2.
+# See the wiki: http://wiki.galaxyproject.org/Admin/NGS%20Local%20Setup
+# First create these data files and save them in your own data directory structure.
+# Then, create a bowtie_indices.loc file to use those indexes with tools.
+# Copy this file, save it with the same name (minus the .sample), 
+# follow the format examples, and store the result in this directory.
+# The file should include an one line entry for each index set.
+# The path points to the "basename" for the set, not a specific file.
+# It has four text columns seperated by TABS.
+#
+# <unique_build_id>	<dbkey>	<display_name>	<file_base_path>
+#
+# So, for example, if you had hg18 indexes stored in:
+#
+#    /depot/data2/galaxy/hg19/bowtie2/
+#
+# containing hg19 genome and hg19.*.bt2 files, such as:
+#    -rw-rw-r-- 1 james   james   914M Feb 10 18:56 hg19canon.fa
+#    -rw-rw-r-- 1 james   james   914M Feb 10 18:56 hg19canon.1.bt2
+#    -rw-rw-r-- 1 james   james   683M Feb 10 18:56 hg19canon.2.bt2
+#    -rw-rw-r-- 1 james   james   3.3K Feb 10 16:54 hg19canon.3.bt2
+#    -rw-rw-r-- 1 james   james   683M Feb 10 16:54 hg19canon.4.bt2
+#    -rw-rw-r-- 1 james   james   914M Feb 10 20:45 hg19canon.rev.1.bt2
+#    -rw-rw-r-- 1 james   james   683M Feb 10 20:45 hg19canon.rev.2.bt2
+#
+# then the bowtie2_indices.loc entry could look like this:
+#
+#hg19	hg19	Human (hg19)	/depot/data2/galaxy/hg19/bowtie2/hg19canon
+#
+#More examples:
+#
+#mm10	mm10	Mouse (mm10)	/depot/data2/galaxy/mm10/bowtie2/mm10
+#dm3	dm3	      D. melanogaster (dm3)	/depot/data2/galaxy/mm10/bowtie2/dm3
+#
+#

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/tophat_fusion_blastdb.loc.sample	Mon Jan 27 13:16:59 2014 -0500
@@ -0,0 +1,37 @@
+#This is a sample file distributed with Galaxy that is used to define a
+#list of nucleotide BLAST databases, using three columns tab separated
+#(longer whitespace are TAB characters):
+#
+#<unique_id>	<database_caption>	<base_name_path>
+#
+#The captions typically contain spaces and might end with the build date.
+#It is important that the actual database name does not have a space in
+#it, and that there are only two tabs on each line.
+#
+#So, for example, if your database is nt and the path to your base name 
+#is /depot/data2/galaxy/blastdb/nt/nt.chunk, then the blastdb.loc entry 
+#would look like this:
+#
+#nt_02_Dec_2009      nt 02 Dec 2009      /depot/data2/galaxy/blastdb/nt/nt.chunk
+#
+#and your /depot/data2/galaxy/blastdb/nt directory would contain all of 
+#your "base names" (e.g.):
+#
+#-rw-r--r--  1 wychung galaxy  23437408 2008-04-09 11:26 nt.chunk.00.nhr
+#-rw-r--r--  1 wychung galaxy   3689920 2008-04-09 11:26 nt.chunk.00.nin
+#-rw-r--r--  1 wychung galaxy 251215198 2008-04-09 11:26 nt.chunk.00.nsq
+#...etc...
+#
+#Your blastdb.loc file should include an entry per line for each "base name" 
+#you have stored.  For example:
+#
+#nt_02_Dec_2009		nt 02 Dec 2009		/depot/data2/galaxy/blastdb/nt/nt.chunk
+#wgs_30_Nov_2009	wgs 30 Nov 2009	/depot/data2/galaxy/blastdb/wgs/wgs.chunk
+#test_20_Sep_2008	test 20 Sep 2008	/depot/data2/galaxy/blastdb/test/test
+#...etc...
+#
+#You can download the NCBI provided protein databases like NT from here:
+#ftp://ftp.ncbi.nlm.nih.gov/blast/db/
+#
+#See also blastdb_p.loc which is for any protein BLAST database, and
+#blastdb_d.loc which is for any protein domains databases (like CDD).
\ No newline at end of file

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.sample	Mon Jan 27 13:16:59 2014 -0500
@@ -0,0 +1,10 @@
+<tables>
+    <table name="bowtie2_indexes" comment_char="#">
+        <columns>value, dbkey, name, path</columns>
+	 	<file path="tool-data/bowtie2_indices.loc" />
+    </table>
+    <table name="tophat_fusion_blastdb_indexes" comment_char="#">
+        <columns>value, dbkey, name, path</columns>
+	 	<file path="tool-data/tophat_fusion_blastdb.loc" />
+    </table>
+</tables>
\ No newline at end of file

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml	Mon Jan 27 13:16:59 2014 -0500
@@ -0,0 +1,6 @@
+<?xml version="1.0"?>
+<tool_dependency>
+    <package name="blast+" version="2.2.28">
+        <repository name="package_blast_plus_2_2_28" owner="iuc"/>
+    </package>
+</tool_dependency>

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tophat_fusion_post.xml	Mon Jan 27 13:16:59 2014 -0500
@@ -0,0 +1,53 @@
+<tool id="tophat_fusion_post" name="Tophat Fusion Post" version="0.1">
+    <description>post-processing to identify fusion genes</description>
+    <version_command>tophat-fusion-post --version</version_command>
+    <requirements>
+        <requirement type="package">tophat2</requirement>
+    </requirements>
+    <command>
+        ## Set up tophat_out structure.
+        mkdir tophat_out; ln -s $accepted_hits tophat_out/accepted_hits.bam; ln -s $fusions tophat_out/fusions.out;
+
+        ## Set up blast directory structure.
+        #set blast_db_path = ${__get_data_table_entry__('tophat_fusion_blastdb_indexes', 'dbkey', $accepted_hits.dbkey, 'path')}
+        ln -s ${blast_db_path}/ blast;
+
+        ## Set up additional files:
+	    ln -s ${blast_db_path}/refGene.txt .;
+	    ln -s ${blast_db_path}/ensGene.txt .;
+        ln -s ${blast_db_path}/mcl .;
+
+        ## Run tophat-fusion-post
+        tophat-fusion-post -p 22
+        --num-fusion-reads $num_fusion_reads --num-fusion-pairs $num_fusion_pairs --num-fusion-both $num_fusion_both --fusion-read-mismatches $fusion_read_mismatches --fusion-multireads $fusion_multireads
+        #if str($is_human) == 'No':
+              --non-human
+        #end if
+
+	## Bowtie2 indices.
+	${__get_data_table_entry__('bowtie2_indexes', 'dbkey', $accepted_hits.dbkey, 'path')}
+    </command>
+
+    <inputs>
+        <param format="bam" name="accepted_hits" type="data" label="BAM file of aligned RNA-Seq reads" help=""/>
+        <param format="tabular" name="fusions" type="data" label="Tabular file of potential fusions" help=""/>
+        <param name="num_fusion_reads" type="integer" value="3" label="Num Fusion Reads" help="Fusions with at least this many supporting reads will be reported."/>
+        <param name="num_fusion_pairs" type="integer" value="2" label="Num Fusion Pairs" help="Fusions with at least this many supporting pairs will be reported."/>
+        <param name="num_fusion_both" type="integer" value="0" label="Num Fusion Reads + Pairs" help="The sum of supporting reads and pairs is at least this number for a fusion to be reported."/>
+        <param name="fusion_read_mismatches" type="integer" value="2" label="Fusion Read Mismatches" help="Reads support fusions if they map across fusion with at most this many mismatches."/>
+        <param name="fusion_multireads" type="integer" value="2" label="Reads that map to more than this many places will be ignored." help=""/>
+        <param name="is_human" type="select" label="Is your data from humans?">
+            <option value="Yes" selected="True">Yes</option>
+            <option value="No">No</option>
+        </param>
+    </inputs>
+
+    <stdio>
+        <regex match=".*" source="both" level="log" description="tool progress"/>
+    </stdio>
+
+    <outputs>
+        <data format="txt" name="results_txt" label="${tool.name} on ${on_string}: text results" from_work_dir="tophatfusion_out/result.txt"/>
+        <data format="html" name="results_html" label="${tool.name} on ${on_string}: html results" from_work_dir="tophatfusion_out/result.html"/>
+    </outputs>
+</tool>