annotate ssake.xml @ 2:f20db7280f89 draft default tip

Fix SSAKE download URL (thanks to Graham Etherington for reporting this). Update Orione citation.
author crs4
date Thu, 06 Mar 2014 11:50:08 -0500
parents 386166019772
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
1 <tool id="ssake" name="SSAKE" version="0.0.10">
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
2 <description>short DNA sequences assembler</description>
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
3 <requirements>
1
386166019772 Uploaded
crs4
parents: 0
diff changeset
4 <requirement type="package" version="3.8.1">ssake</requirement>
0
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
5 </requirements>
1
386166019772 Uploaded
crs4
parents: 0
diff changeset
6 <version_command>SSAKE 2&gt;&amp;1 | sed -n 's/.*\(SSAKE \[.*\]\).*/\1/p'</version_command>
0
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
7 <command interpreter="python">
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
8 ssake.py
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
9 #if $kind_of_reads.kind_of_reads_select == '0'
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
10 --if_unpaired $infile
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
11 #else
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
12 --if_paired_r1 $infile_r1
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
13 --if_paired_r2 $infile_r2
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
14 --iz ${kind_of_reads.insert_size}
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
15 -k ${kind_of_reads.minnumlinks}
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
16 -e ${kind_of_reads.error}
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
17 -a ${kind_of_reads.maxlinkratio}
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
18 -x ${kind_of_reads.minoverlap}
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
19 #end if
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
20 #if $seeds
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
21 -s $seeds
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
22 #end if
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
23 -w $mindepthofcoverage
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
24 -m $minoverlap
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
25 -o $mincall
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
26 -r $baseratio
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
27 --ignore_header 1
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
28 --kind_of_reads ${kind_of_reads.kind_of_reads_select}
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
29 --out1 $contig
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
30 --out2 $short
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
31 --out3 $singlets
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
32 --logfile $log
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
33 </command>
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
34 <inputs>
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
35 <conditional name="kind_of_reads">
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
36 <param name="kind_of_reads_select" type="select" label="Kind of reads (-p)">
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
37 <option value="0">Unpaired </option>
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
38 <option value="1">Paired and equal (both files must have the same number of sequences, arranged in the same order)</option>
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
39 <option value="2">Paired and unequal (files can have different number of sequences in any order)</option>
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
40 </param>
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
41 <when value="0">
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
42 <param name="infile" type="data" format="fasta" label="Input FASTA file" />
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
43 </when>
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
44 <when value="1">
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
45 <param name="infile_r1" type="data" format="fasta" label="Input FASTA file (read 1)" />
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
46 <param name="infile_r2" type="data" format="fasta" label="Input FASTA file (read 2)" />
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
47 <param name="insert_size" type="integer" value="200" label="Library insert size" />
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
48 <param name="minnumlinks" type="integer" value="4" label="Minimum number of links (read pairs) to compute scaffold (-k)" />
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
49 <param name="error" type="float" value="0.75" min="0" max="1" label="Error (%) allowed on mean distance (-e)" />
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
50 <param name="maxlinkratio" type="float" value="0.5" label="Maximum link ratio between two best contig pairs (-a)" />
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
51 <param name="minoverlap" type="integer" value="20" label="Minimum overlap required between contigs to merge adjacent contigs in a scaffold (-x)" />
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
52 </when>
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
53 <when value="2">
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
54 <param name="infile_r1" type="data" format="fasta" label="Input FASTA file (read 1)" />
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
55 <param name="infile_r2" type="data" format="fasta" label="Input FASTA file (read 2)" />
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
56 <param name="insert_size" type="integer" value="200" label="Library insert size" />
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
57 <param name="minnumlinks" type="integer" value="4" label="Minimum number of links (read pairs) to compute scaffold (-k)" />
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
58 <param name="error" type="float" value="0.75" min="0" max="1" label="Error (%) allowed on mean distance (-e)" />
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
59 <param name="maxlinkratio" type="float" value="0.5" label="Maximum link ratio between two best contig pairs (-a)" />
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
60 <param name="minoverlap" type="integer" value="20" label="Minimum overlap required between contigs to merge adjacent contigs in a scaffold (-x)" />
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
61 </when>
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
62 </conditional>
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
63 <param name="seeds" type="data" format="fasta" optional="true" label="FASTA file containing sequences to use as seeds exclusively (-s)" help="Optional, specify only if different from read set" />
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
64 <param name="mindepthofcoverage" type="integer" value="1" label="Minimum depth of coverage allowed for contigs (-w)" />
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
65 <param name="minoverlap" type="integer" value="20" label="Minimum number of overlapping bases with the seed/contig during overhang consensus build up (-m)" />
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
66 <param name="mincall" type="integer" value="2" label="Minimum number of reads needed to call a base during an extension (-o)" />
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
67 <param name="baseratio" type="float" value="0.7" label="Minimum base ratio used to accept a overhang consensus base (-r)" />
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
68 </inputs>
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
69
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
70 <outputs>
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
71 <data name="contig" format="fasta" label="${tool.name} on ${on_string}: contigs" />
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
72 <data name="log" format="txt" label="${tool.name} on ${on_string}: log" />
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
73 <data name="short" format="txt" label="${tool.name} on ${on_string}: unacceptable reads" />
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
74 <data name="singlets" format="fasta" label="${tool.name} on ${on_string}: unassembled reads" />
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
75 </outputs>
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
76 <help>
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
77 **What it does**
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
78
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
79 SSAKE is a genomics application for de novo assembly of millions of very short DNA sequences.
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
80 It is an easy-to-use, robust, reliable and tractable clustering algorithm for very short sequence reads, such as those generated by Illumina Ltd.
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
81
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
82 **License and citation**
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
83
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
84 This Galaxy tool is Copyright © 2012-2013 `CRS4 Srl.`_ and is released under the `MIT license`_.
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
85
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
86 .. _CRS4 Srl.: http://www.crs4.it/
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
87 .. _MIT license: http://opensource.org/licenses/MIT
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
88
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
89 If you use this tool in Galaxy, please cite |Cuccuru2013|_.
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
90
2
f20db7280f89 Fix SSAKE download URL (thanks to Graham Etherington for reporting this). Update Orione citation.
crs4
parents: 1
diff changeset
91 .. |Cuccuru2013| replace:: Cuccuru, G., Orsini, M., Pinna, A., Sbardellati, A., Soranzo, N., Travaglione, A., Uva, P., Zanetti, G., Fotia, G. (2014) Orione, a web-based framework for NGS analysis in microbiology. *Bioinformatics*, accepted
0
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
92 .. _Cuccuru2013: http://orione.crs4.it/
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
93
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
94 This tool uses `SSAKE`_, which is licensed separately. Please cite |Warren2007|_.
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
95
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
96 .. _SSAKE: http://www.bcgsc.ca/platform/bioinfo/software/ssake/
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
97 .. |Warren2007| replace:: Warren RL, Sutton GG, Jones SJM, Holt RA. 2007. Assembling millions of short DNA sequences using SSAKE. Bioinformatics. 23(4):500-501
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
98 .. _Warren2007: http://bioinformatics.oxfordjournals.org/content/23/4/500
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
99 </help>
0ec408bcfc80 Uploaded
crs4
parents:
diff changeset
100 </tool>