|
0
|
1 <tool id="discosnp_pp" name="discoSnp++" version="2.1.7">
|
|
|
2 <description>is an efficient tool for detecting SNPs without a reference genome.</description>
|
|
|
3 <requirements>
|
|
|
4 <requirement type="package" version="2.1.7">discoSnp_plus_plus</requirement>
|
|
|
5 <requirement type="package" version="0.6.2">bwa</requirement>
|
|
|
6 </requirements>
|
|
|
7 <command interpreter="python">
|
|
|
8 bbric_disco.py
|
|
|
9 -r ${datfile}
|
|
|
10 -b $branching_bubbles
|
|
|
11 -D $deletions
|
|
|
12 -P $limit_snp
|
|
|
13 #if $low_complexity
|
|
|
14 -l
|
|
|
15 #end if
|
|
|
16 -k $kmer
|
|
|
17 #if (str($extension) == 't'):
|
|
|
18 -t
|
|
|
19 #end if
|
|
|
20 #if (str($extension) == 'T'):
|
|
|
21 -T
|
|
|
22 #end if
|
|
|
23 -c $coverage
|
|
|
24 -C ${maxcoverage}
|
|
|
25 -d $error_threshold
|
|
|
26 #if (str($VCF_option.mapping) == 'reference'):
|
|
|
27 -G ${VCF_option.reference}
|
|
|
28 -M ${VCF_option.mapping_error}
|
|
|
29 #end if
|
|
|
30 </command>
|
|
|
31
|
|
|
32 <inputs>
|
|
|
33 <repeat name="input_list" title="input files" min="1">
|
|
|
34 <param name="input" type="data" format="fasta,fastq,fastq.gz" label="input"/>
|
|
|
35 </repeat>
|
|
|
36
|
|
|
37 <param name="kmer" type="integer" label="Size of kmers" value="31" />
|
|
|
38 <param name="coverage" type="integer" label="Minimal coverage per read set" value="4" />
|
|
|
39 <param name="maxcoverage" type="integer" label="Maximal coverage per read set" value="2147483647" help="default value = 2^31-1" />
|
|
|
40 <param name="error_threshold" type="integer" label="Max number of errors per read" value="1" help="Max number of errors per read" />
|
|
|
41
|
|
|
42 <param name="branching_bubbles" type="select" label="branching strategy">
|
|
|
43 <option value="0">variants for which any of the two paths is branching are discarded</option>
|
|
|
44 <option value="1">forbid SNPs for wich the two paths are branching</option>
|
|
|
45 <option value="2">No limitation on branching</option>
|
|
|
46 </param>
|
|
|
47
|
|
|
48 <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"/>
|
|
|
49 <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"/>
|
|
|
50 <param name="low_complexity" type="boolean" default="False" checked="False" label="accept low complexity bubbles" />
|
|
|
51
|
|
|
52 <param name="extension" type="select" label="extension strategy">
|
|
|
53 <option value="n">extends to 30bp on left and right</option>
|
|
|
54 <option value="t">extends left and right until a polymorphism s found (unitigs)</option>
|
|
|
55 <option value="T">extends left and right using local assembly (contigs)</option>
|
|
|
56 </param>
|
|
|
57 <conditional name="VCF_option" >
|
|
|
58 <param name="mapping" type="select" label="VCF option">
|
|
|
59 <option value="default">Do not use reference genome</option>
|
|
|
60 <option value="reference">Mapping with a reference genome</option>
|
|
|
61 </param>
|
|
|
62 <when value="defaut"></when>
|
|
|
63 <when value="reference">
|
|
|
64 <param name="reference" type="data" format="fasta,fastq" label="Reference genome file" />
|
|
|
65 <param name="mapping_error" type="integer" value="4" label="Maximal number of mapping errors" help="during BWA mapping phase" />
|
|
|
66 </when>
|
|
|
67 </conditional>
|
|
|
68
|
|
|
69 </inputs>
|
|
|
70
|
|
|
71 <outputs>
|
|
|
72 <!-- <data name="report" from_work_dir="report.txt" format="txt" label="Output of ${tool.name} on $on_string"/> -->
|
|
|
73 <data name="vcf" from_work_dir="coherent.vcf" format="vcf" label="VCF of ${tool.name} on $on_string"/>
|
|
|
74 <data name="fasta" from_work_dir="coherent.fasta" format="fasta" label="Multifasta of the polymorphisms - ${tool.name} on $on_string"/>
|
|
|
75 </outputs>
|
|
|
76
|
|
|
77 <configfiles>
|
|
|
78 <configfile name="datfile">
|
|
|
79 #for $i, $lib in enumerate ($input_list)
|
|
|
80 ${i}::${lib.input}
|
|
|
81 #end for
|
|
|
82 </configfile>
|
|
|
83 </configfiles>
|
|
|
84 <help>
|
|
|
85
|
|
|
86 **Description**
|
|
|
87
|
|
|
88 Software discoSnp is designed for discovering Single Nucleotide Polymorphism (SNP) from raw set(s) of reads obtained with Next Generation Sequencers (NGS).
|
|
|
89 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.
|
|
|
90 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.
|
|
|
91
|
|
|
92 Note that from release of DiscoSnp++-2.0.6, the tool also detects close SNPs and indels.
|
|
|
93
|
|
|
94 -------
|
|
|
95
|
|
|
96 .. class:: warningmark
|
|
|
97
|
|
|
98 **Input parameters**
|
|
|
99
|
|
|
100 -Sequences files in fasta, fastq or fastq.gz, each allele will be counted in each file individually
|
|
|
101
|
|
|
102 -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
|
|
|
103
|
|
|
104 -------
|
|
|
105
|
|
|
106 .. class:: warningmark
|
|
|
107
|
|
|
108 **Ouput parameters**
|
|
|
109
|
|
|
110 -VCF file with coordinates on the higher branch sequences or on a reference genome if provided
|
|
|
111
|
|
|
112 -Fasta file with sequence extensions around the SNP.
|
|
|
113
|
|
|
114
|
|
|
115 -------
|
|
|
116
|
|
|
117 **Web site**
|
|
|
118
|
|
|
119 https://colibread.inria.fr/software/discosnp/
|
|
|
120
|
|
|
121 -------
|
|
|
122
|
|
|
123 **Integrated by**
|
|
|
124
|
|
|
125 Cyril Monjeaud and Fabrice Legeai
|
|
|
126
|
|
|
127 GenOuest Bio-informatics Core Facility
|
|
|
128
|
|
|
129 UMR 6074 IRISA INRIA-CNRS-UR1 Rennes (France)
|
|
|
130
|
|
|
131 support@genouest.org
|
|
|
132
|
|
|
133 If you use this tool in Galaxy, please cite :
|
|
|
134
|
|
|
135 `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. <https://www.e-biogenouest.org/resources/128>`_
|
|
|
136
|
|
|
137 </help>
|
|
|
138 <citations>
|
|
|
139 <citation type="doi">10.1093/nar/gku1187</citation>
|
|
|
140 <citation type="bibtex">@INPROCEEDINGS{JOBIM2013,
|
|
|
141 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.},
|
|
|
142 title = {Towards a Life Sciences Virtual Research Environment: An e-Science initiative in Western France},
|
|
|
143 booktitle = {JOBIM 2013 Proceedings},
|
|
|
144 year = {2013},
|
|
|
145 url = {https://www.e-biogenouest.org/resources/128},
|
|
|
146 pages = {97-106}
|
|
|
147 }
|
|
|
148 </citation>
|
|
|
149 </citations>
|
|
|
150 </tool>
|
|
|
151
|
