--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/bbric_disco.py	Fri Jun 05 11:40:18 2015 -0400
@@ -0,0 +1,126 @@
+import sys, tempfile, subprocess, glob
+import os, re, shutil, stat
+import optparse
+from os.path import basename
+
+"""
+
+Created by Cyril Monjeaud
+Cyril.Monjeaud@irisa.fr
+Modified by Fabrice Legeai
+fabrice.legeai@rennes.inra.fr
+
+Last modifications : 04/21/2015
+
+WARNING :
+
+discoSNP++.py needs:
+
+- run_discoSnp++.sh
+- discoSNP++_to_genotypes.py
+- the build repository next to the scripts
+
+All these files are available after compiling the sources of discoSNP :
+
+https://colibread.inria.fr/files/2013/10/DiscoSNPpp-2.0.6-Source.zip
+
+or with the package_discoSnp_plus_plus package in the toolshed
+
+"""
+
+
+def __main__():
+
+	# store inputs in an array
+	parser = optparse.OptionParser()
+	parser.add_option("-r", dest="data_files")
+	parser.add_option("-b", dest="branching_bubbles")
+	parser.add_option("-D", dest="deletions")
+	parser.add_option("-P", dest="min_snps")
+	parser.add_option("-l", action="store_true", dest="low_complexity")
+	parser.add_option("-k", dest="kmer")
+	parser.add_option("-t", action="store_true", dest="left_right_unitigs")
+	parser.add_option("-T", action="store_true", dest="left_right_contigs")
+	parser.add_option("-c", dest="coverage")
+        parser.add_option("-C", dest="maxcoverage")
+	parser.add_option("-d", dest="error_threshold")
+	parser.add_option("-n", action="store_true", dest="genotypes")
+	parser.add_option("-G", dest="reference")
+        parser.add_option("-M", dest="mapping_error")
+
+	(options, args) = parser.parse_args()
+
+        # create the working dir inside job_working_dir
+        output_dir = os.mkdir("job_outputs")
+
+	cmd_line=[]
+	cmd_line.append("/bin/bash")
+	#cmd_line.append("/home/genouest/inrarennes/flegeai/local/DiscoSNP/DiscoSNP++-2.1.4-Source/run_discoSnp++.sh")
+	cmd_line.append("run_discoSnp++.sh")
+	#cmd_line.append("-B /local/bwa/bwa-0.7.10/")
+
+	# transform .dat into .fasta or .fastq for kissreads2
+	link_files=[]
+	f = open(options.data_files, 'r')
+	files = f.readlines()
+	for file in files:
+		file=file.strip()
+		if re.search("^$",file): continue
+		tagfile=[]
+		tagfile=re.split('::', file)	
+		number = int(tagfile[0])+1
+		if re.search("^>.*", open(tagfile[1]).readline()):
+                        link_file = 'input'+str(number)+'.fasta'
+                else:
+                        link_file = 'input'+str(number)+'.fastq'
+
+                os.symlink(tagfile[1], link_file)
+                link_files.append(link_file)
+
+
+	# edit the command line
+	cmd_line.extend(["-r",' '.join(link_files),"-b",options.branching_bubbles,"-D",options.deletions,"-P",options.min_snps,"-k",options.kmer,"-c",options.coverage,"-C",options.maxcoverage,"-d",options.error_threshold])
+	if options.low_complexity:
+		cmd_line.append("-l")
+	if options.left_right_unitigs:
+		cmd_line.append("-t")
+	if options.left_right_contigs:
+                cmd_line.append("-T")
+	if options.genotypes:
+		cmd_line.append("-n")
+
+	# genotype part
+	if options.reference:
+		cmd_line.extend(["-G", options.reference])
+		cmd_line.extend(["-M", options.mapping_error])
+
+	cmd_line.extend(["-p","job_outputs/galaxy"])
+
+	# execute job
+	p=subprocess.Popen(cmd_line,
+                   stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+
+	stdoutput, stderror = p.communicate()
+
+	# report file
+        logfile=open("report.txt", "w")
+	logfile.write("[COMMAND LINE]"+' '.join(cmd_line)+"\n\n")
+	logfile.write(stdoutput)
+
+	# print stderror because it's informations
+        logfile.write(stderror)
+
+	# close logfile
+	logfile.close()
+
+	# change .fa extension to .fasta for a correct print inside Galaxy
+        fafiles = glob.glob("job_outputs/*_coherent.fa")
+	for fafile in fafiles:
+        	shutil.move(fafile, "coherent.fasta")
+        vcffiles = glob.glob("job_outputs/*_coherent.vcf")
+	for vcffile in vcffiles:
+        	shutil.move(vcffile, "coherent.vcf")
+
+
+if __name__ == "__main__": __main__()
+

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/bbric_disco.xml	Fri Jun 05 11:40:18 2015 -0400
@@ -0,0 +1,151 @@
+<tool id="discosnp_pp" name="discoSnp++" version="2.1.7">
+<description>is an efficient tool for detecting SNPs without a reference genome.</description>
+  <requirements>
+    <requirement type="package" version="2.1.7">discoSnp_plus_plus</requirement>
+    <requirement type="package" version="0.6.2">bwa</requirement>
+  </requirements>
+  <command interpreter="python">
+bbric_disco.py
+-r ${datfile}
+-b $branching_bubbles
+-D $deletions
+-P $limit_snp
+#if $low_complexity
+-l
+#end if
+-k $kmer
+#if (str($extension) == 't'):
+-t
+#end if
+#if (str($extension) == 'T'):
+-T
+#end if
+-c $coverage
+-C ${maxcoverage}
+-d $error_threshold
+#if (str($VCF_option.mapping) == 'reference'):
+-G ${VCF_option.reference}
+-M ${VCF_option.mapping_error}
+#end if
+  </command>
+
+  <inputs>             
+	<repeat name="input_list" title="input files" min="1">
+        	<param name="input" type="data" format="fasta,fastq,fastq.gz" label="input"/>
+	</repeat>
+
+	<param name="kmer" type="integer" label="Size of kmers" value="31" />
+	<param name="coverage" type="integer" label="Minimal coverage per read set" value="4" />
+  	<param name="maxcoverage" type="integer" label="Maximal coverage per read set" value="2147483647" help="default value = 2^31-1" />
+	<param name="error_threshold" type="integer" label="Max number of errors per read" value="1" help="Max number of errors per read" />
+	
+	<param name="branching_bubbles" type="select" label="branching strategy">
+		<option value="0">variants for which any of the two paths is branching are discarded</option>
+		<option value="1">forbid SNPs for wich the two paths are branching</option>
+		<option value="2">No limitation on branching</option>
+        </param>
+
+	<param name="deletions" type="integer" label="deletion size" value="0" help="If different of 0, discoSnp++ will search for deletions of size from 1 to the value included"/>
+	<param name="limit_snp" type="integer" label="maximum SNPs per bubble" value="1" help="discoSnp++ will search up to the value SNPs in a unique bubble"/>
+	<param name="low_complexity" type="boolean" default="False" checked="False" label="accept low complexity bubbles" />
+
+	<param name="extension" type="select" label="extension strategy">
+                <option value="n">extends to 30bp on left and right</option>
+                <option value="t">extends left and right until a polymorphism s found (unitigs)</option>
+                <option value="T">extends left and right using local assembly (contigs)</option>
+        </param>
+	<conditional name="VCF_option" >
+		<param name="mapping" type="select" label="VCF option">
+			<option value="default">Do not use reference genome</option>
+			<option value="reference">Mapping with a reference genome</option>
+		</param>
+		<when value="defaut"></when>
+		<when value="reference">
+			<param name="reference" type="data" format="fasta,fastq" label="Reference genome file" />
+			<param name="mapping_error" type="integer" value="4" label="Maximal number of mapping errors" help="during BWA mapping phase" />
+		</when>
+	</conditional>
+
+  </inputs>
+
+  <outputs>
+<!--	 <data name="report" from_work_dir="report.txt" format="txt" label="Output of ${tool.name} on $on_string"/> -->
+	 <data name="vcf" from_work_dir="coherent.vcf" format="vcf" label="VCF of ${tool.name} on $on_string"/>
+    	<data name="fasta" from_work_dir="coherent.fasta" format="fasta" label="Multifasta of the polymorphisms -  ${tool.name} on $on_string"/>
+</outputs>
+
+ <configfiles>
+        <configfile name="datfile">
+        #for $i, $lib in enumerate ($input_list)
+		${i}::${lib.input}
+        #end for
+ 	</configfile>
+   </configfiles>
+  <help>
+
+**Description**
+
+Software discoSnp is designed for discovering Single Nucleotide Polymorphism (SNP) from raw set(s) of reads obtained with Next Generation Sequencers (NGS).
+Note that number of input read sets is not constrained, it can be one, two, or more. Note also that no other data as reference genome or annotations are needed.
+The software is composed by two modules. First module, kissnp2, detects SNPs from read sets. A second module, kissreads, enhance the kissnp2 results by computing per read set  and for each found SNP i/ its mean read coverage and ii/ the (phred) quality of reads generating the polymorphism.
+
+Note that from release of DiscoSnp++-2.0.6, the tool also detects close SNPs and indels.
+
+-------
+
+.. class:: warningmark 
+
+**Input parameters**
+
+-Sequences files in fasta, fastq or fastq.gz, each allele will be counted in each file individually
+
+-Fasta sequence of a genome if case of you are willing to map the sequence extension on a reference in order to get a compliant VCF
+
+-------
+
+.. class:: warningmark 
+
+**Ouput parameters**
+
+-VCF file with coordinates on the higher branch sequences or on a reference genome if provided 
+
+-Fasta file with sequence extensions around the SNP. 
+ 
+
+-------
+
+**Web site**
+
+https://colibread.inria.fr/software/discosnp/
+
+-------
+
+**Integrated by**
+
+Cyril Monjeaud and Fabrice Legeai
+
+GenOuest Bio-informatics Core Facility
+
+UMR 6074 IRISA INRIA-CNRS-UR1 Rennes (France)
+
+support@genouest.org
+
+If you use this tool in Galaxy, please cite :
+
+`Y. Le Bras, A. Roult, C. Monjeaud, M. Bahin, O. Quenez, C. Heriveau, A. Bretaudeau, O. Sallou, O. Collin, Towards a Life Sciences Virtual Research Environment : an e-Science initiative in Western France. JOBIM 2013. &lt;https://www.e-biogenouest.org/resources/128&gt;`_
+
+  </help>
+<citations>
+<citation type="doi">10.1093/nar/gku1187</citation>
+<citation type="bibtex">@INPROCEEDINGS{JOBIM2013,
+    author = {Le Bras, Y. and ROULT, A. and Monjeaud, C. and Bahin, M. and Quenez, O. and Heriveau, C. and Bretaudeau, A. and Sallou, O. and Collin, O.},
+    title = {Towards a Life Sciences Virtual Research Environment: An e-Science initiative in Western France},
+    booktitle = {JOBIM 2013 Proceedings},
+    year = {2013},
+    url = {https://www.e-biogenouest.org/resources/128},
+    pages = {97-106}
+    }
+</citation>
+</citations>
+</tool>
+

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml	Fri Jun 05 11:40:18 2015 -0400
@@ -0,0 +1,9 @@
+<?xml version="1.0"?>
+<tool_dependency>
+  <package name="discoSnp_plus_plus" version="2.1.7">
+      <repository name="package_discosnp_plus_plus" owner="cmonjeau" toolshed="https://toolshed.g2.bx.psu.edu" />
+    </package>
+    <package name="bwa" version="0.6.2">
+      <repository name="package_bwa_0_6_2" owner="cmonjeau" toolshed="https://toolshed.g2.bx.psu.edu" />
+    </package>
+</tool_dependency>