|
11
|
1 <tool id="spotyping" name="Spoligotype Prediction" version="1.0.4">
|
|
6
|
2 <description>fast and accurate in silico Mycobacterium spoligotyping from sequence reads</description>
|
|
0
|
3 <requirements>
|
|
|
4 <requirement type="package" version="2.1">spotyping</requirement>
|
|
|
5 </requirements>
|
|
3
|
6 <command detect_errors="aggressive"><![CDATA[
|
|
6
|
7 SpoTyping.py
|
|
|
8 $advanced.seq
|
|
|
9 $advanced.swift
|
|
|
10 --min=$advanced.min
|
|
|
11 --rmin=$advanced.min_relax
|
|
0
|
12 #if str( $data_input.data_selector ) == "paired"
|
|
|
13 $data_input.input1.forward $data_input.input1.reverse
|
|
|
14 #end if
|
|
|
15 #if str( $data_input.data_selector ) == "single"
|
|
6
|
16 $data_input.input2
|
|
0
|
17 #end if
|
|
5
|
18 && cp SITVIT_ONLINE.*.xls spotyping.xls
|
|
3
|
19 ]]>
|
|
1
|
20 </command>
|
|
0
|
21 <inputs>
|
|
|
22 <conditional name="data_input">
|
|
6
|
23 <param name="data_selector" type="select" label="Single or Paired-end Data" help="Select between paired and single end data to add name to dataset">
|
|
|
24 <option value="paired">Paired</option>
|
|
|
25 <option value="single">Single</option>
|
|
|
26 </param>
|
|
|
27 <when value="paired">
|
|
11
|
28 <param name="input1" format="data" type="data_collection" collection_type="paired" label="Select a paired collection" help="a paired data"/>
|
|
6
|
29 </when>
|
|
|
30 <when value="single">
|
|
7
|
31 <param name="input2" format="data" type="data_collection" label="input" help="Specify dataset with single reads"/>
|
|
6
|
32 </when>
|
|
0
|
33 </conditional>
|
|
6
|
34 <section name="advanced" title="Advanced options" expanded="false">
|
|
|
35 <param type="boolean" argument="--seq" label="Input is assembled sequence" help="Input is either a complete genomic sequence or assembled contigs from an isolate" truevalue="--seq" falsevalue="" checked="false" />
|
|
|
36 <param type="boolean" argument="--swift" label="Swift mode" checked="true" truevalue="--swift=on" falsevalue="--swift=off" />
|
|
|
37 <param name="min" type="integer" value="5" label="MIN" help="minimum number of error-free hits to support presence of a spacer" />
|
|
|
38 <param name="min_relax" type="integer" value="6" label="MIN RELAX" help="minimum number of 1-error-tolerant hits to support presence of a spacer " />
|
|
|
39 </section>
|
|
0
|
40 </inputs>
|
|
|
41 <outputs>
|
|
8
|
42 <data name="spotyping_results" label="spoligotyping results" format="txt" from_work_dir="SpoTyping"/>
|
|
|
43 <data name="spotyping_log" label="spoligotyping log" format="txt" from_work_dir="SpoTyping.log"/>
|
|
|
44 <data name="sitvit_database_query" label="query" format="excel.xls" from_work_dir="spotyping.xls"/>
|
|
0
|
45 </outputs>
|
|
|
46 <help><![CDATA[
|
|
7
|
47 This is a modified version of IUC's wrapper of spotyping without the concatenation and renaming of the input files. The wrapper also runs properly when supplied with paired-end reads
|
|
6
|
48
|
|
|
49 SpoTyping_ is a software for predicting spoligotype_ from sequencing reads, complete genomic sequences and assembled contigs.
|
|
|
50
|
|
|
51 **Input:**
|
|
|
52
|
|
|
53 - Fastq file - if paired end data is used, you may choose to concatenate paired reads into a single input (e.g. using the cat tool)
|
|
|
54 - Fasta file of a complete genomic sequence or assembled contigs of an isolate (with --seq option)
|
|
|
55
|
|
|
56 *Note on input size*: In swift mode the sampling threshold is reached in approximately 30x coverage when using
|
|
|
57 paired end sequencing of a *M. tuberculosis* genome.
|
|
|
58
|
|
|
59 **Output:**
|
|
|
60
|
|
|
61 Count of hits from BLAST result for each spacer sequence and predicted spoligotype in the format of binary code and octal code.
|
|
|
62
|
|
|
63 **Options:**
|
|
|
64
|
|
|
65
|
|
|
66 \--seq
|
|
|
67 Set this if input is a fasta file that contains only complete genomic sequence or assembled contigs from an isolate. [Default is off]
|
|
|
68
|
|
|
69 \-s SWIFT, --swift=SWIFT
|
|
|
70 Swift mode, either "on" or "off" [Default: on] - swift mode samples 250 million bases to use for spoligotyping
|
|
|
71
|
|
7
|
72 \-m MIN, --min=MIN
|
|
|
73 minimum number of error-free hits to support presence of a spacer [Default: 5]
|
|
|
74
|
|
|
75 \-r MIN_RELAX, --rmin=MIN_RELAX
|
|
|
76 minimum number of 1-error-tolerant hits to support presence of a spacer [Default: 6].
|
|
6
|
77
|
|
|
78
|
|
|
79
|
|
|
80 **Got weird spoligotype prediction?**
|
|
|
81
|
|
|
82 Sequencing throughput is very low (<40Mbp, for example): SpoTyping may not be able to give accurate prediction due to the relatively low read depth.
|
|
|
83
|
|
|
84 **Interpreting the spoligotype**
|
|
|
85
|
|
|
86 The binary or octal spoligotype can be used to look up lineage information using a service
|
|
|
87 like `TB Lineage`_.
|
|
|
88
|
|
|
89 **SITVIT reports**
|
|
|
90
|
|
|
91 Optionally a report on the detected spoligotype can be retrieved from the SITVIT_ database. If such a report is requested it can also be
|
|
|
92 illustrated as a (PDF format) plot.
|
|
|
93
|
|
|
94 .. _SpoTyping: https://github.com/xiaeryu/SpoTyping
|
|
|
95 .. _spoligotype: https://www.ncbi.nlm.nih.gov/pubmed/19521871
|
|
|
96 .. _TB Lineage: http://tbinsight.cs.rpi.edu/run_tb_lineage.html
|
|
|
97 .. _SITVIT: http://www.pasteur-guadeloupe.fr:8081/SITVIT_ONLINE/
|
|
0
|
98 ]]></help>
|
|
|
99 <citations>
|
|
|
100 <citation type="bibtex">
|
|
|
101 @misc{githubSpoTyping,
|
|
|
102 author = {Xia, Eryu},
|
|
|
103 year = {2016},
|
|
|
104 title = {SpoTyping},
|
|
|
105 publisher = {GitHub},
|
|
|
106 journal = {GitHub repository},
|
|
|
107 url = {https://github.com/xiaeryu/SpoTyping},
|
|
|
108 }</citation>
|
|
6
|
109 <citation type="doi">10.1186/s13073-016-0270-7</citation>
|
|
0
|
110 </citations>
|
|
|
111 </tool>
|
