|
0
|
1 <tool id="circlator" name="A tool to circularize genome assemblies" version="0.1.0">
|
|
|
2 <description>
|
|
|
3 This task runs the complete Circlator pipeline. It runs the tasks: progcheck, mapreads, bam2reads, assemble, merge, clean, fixstart.
|
|
|
4 </description>
|
|
|
5 <requirements>
|
|
1
|
6 <requirement type="package" version="1.5.5=py_2">circlator</requirement>
|
|
|
7 <requirement type="package" version="3.23">mummer</requirement>
|
|
|
8 <requirement type="package" version="1.6">canu</requirement>
|
|
0
|
9 </requirements>
|
|
|
10 <command detect_errors="exit_code"><![CDATA[
|
|
|
11 circlator all
|
|
|
12 --threads \${GALAXY_SLOTS:-4}
|
|
|
13 #if str($assembly.canu_or_spades.assembler) == "spades"
|
|
|
14 --assembler spades
|
|
|
15 ${assembly.canu_or_spades.not_careful}
|
|
|
16 ${assembly.canu_or_spades.not_only_assembler}
|
|
|
17 #else if str($assembly.canu_or_spades.assembler) == "canu"
|
|
|
18 --assembler canu
|
|
|
19 --data_type ${assembly.canu_or_spades.datatype}
|
|
|
20 #end if
|
|
|
21 ${assembly.split_all_reads}
|
|
|
22 ${assembly.assemble_spades_use_first}
|
|
|
23 #if str($mapreads.bwa_opts) != ""
|
|
|
24 --bwa_opts "$mapreads.bwa_opts"
|
|
|
25 #end if
|
|
|
26 ${bam2read.b2r_discard}
|
|
|
27 #if str($bam2read.b2r_length_cutoff) != ""
|
|
|
28 --b2r_length_cutoff ${bam2read.b2r_length_cutoff}
|
|
|
29 #end if
|
|
|
30 #if str($bam2read.b2r_min_read_length) != ""
|
|
|
31 --b2r_min_read_length ${bam2read.b2r_min_read_length}
|
|
|
32 #end if
|
|
|
33 #if str($fix.fixstart_mincluster) != ""
|
|
|
34 --fixstart_mincluster $fix.fixstart_mincluster
|
|
|
35 #end if
|
|
|
36 #if str($fix.fixstart_min_id) != ""
|
|
|
37 --fixstart_min_id $fix.fixstart_min_id
|
|
|
38 #end if
|
|
|
39 $file_contigs $file_reads outdir
|
|
|
40 ]]></command>
|
|
1
|
41 <environment_variables>
|
|
|
42 <environment_variable name="LC_ALL">C</environment_variable>
|
|
|
43 </environment_variables>
|
|
0
|
44 <inputs>
|
|
|
45 <param type="data" name="file_reads" label="Reads to be mapped to contig, in any format BWA MEM accepts" format="fastqsanger,fastqsanger.gz,fasta, fasta.gz" />
|
|
|
46 <param type="data" name="file_contigs" label="Assembly (contigs)" format="fasta" />
|
|
|
47
|
|
|
48 <section name="assembly" title="Assembly">
|
|
1
|
49 <conditional name="canu_or_spades">
|
|
|
50 <param name="assembler" type="select" label="Assembler to use for reassemblies" >
|
|
|
51 <option value="spades" selected="true">SPAdes</option>
|
|
|
52 <option value="canu">Canu</option>
|
|
0
|
53 </param>
|
|
1
|
54 <when value="canu">
|
|
|
55 <param name="datatype" type="select" label="one of the 4 types of data analysed" >
|
|
|
56 <option value="pacbio-corrected" selected="true">pacbio corrected</option>
|
|
|
57 <option value="pacbio-raw">pacbio raw</option>
|
|
|
58 <option value="nanopore-corrected">nanopore corrected</option>
|
|
|
59 <option value="nanopore-raw">nanopore raw</option>
|
|
|
60 </param>
|
|
|
61 </when>
|
|
|
62 <when value="spades">
|
|
|
63 <param name="not_careful" argument="--assemble_not_careful" type="boolean" truevalue="--assemble_not_careful" falsevalue="" checked="false"
|
|
|
64 label="Do not use the --careful option with SPAdes" help="note that this circlator option is to NOT use an option from SPAdes; if unsure, leave it unchekced" />
|
|
|
65 <param name="not_only_assembler" argument="--assemble_not_only_assembler" truevalue="--assemble_not_only_assembler" falsevalue=""
|
|
|
66 type="boolean" checked="false" label="Do not use the --assemble-only option with SPAdes. Important: with this option, the input reads must
|
|
|
67 be in FASTQ format, otherwise SPAdes will crash because it needs quality scores to correct the reads."
|
|
|
68 help="note that this circlator option is to NOT use an option from SPAdes; if unsure, leave it unchecked"/>
|
|
|
69 </when>
|
|
|
70 </conditional>
|
|
|
71 <param name="split_all_reads" argument="--split_all_reads" type="boolean" truevalue="--split_all_reads" falsevalue="" checked="false"
|
|
|
72 label="By default, reads mapped to shorter contigs are left unchanged. This option splits them into two, broken at the middle of the
|
|
|
73 contig to try to force circularization. May help if the assembler does not detect circular contigs (eg canu)" />
|
|
|
74 <param name="assemble_spades_use_first" argument="--assemble_spades_use_first" truevalue="--assemble_spades_use_first" falsevalue=""
|
|
|
75 checked="false" type="boolean" label="Use the first successful SPAdes assembly. Default is to try all kmers and use the assembly with
|
|
|
76 the largest N50" />
|
|
0
|
77
|
|
1
|
78 </section>
|
|
|
79 <section name="mapreads" title="mapreads options">
|
|
|
80 <param name="bwa_opts" type="text" label="text with BWA options (exactly as used by BWA MEM)"/>
|
|
|
81 </section>
|
|
0
|
82
|
|
1
|
83 <section name="bam2read" title="bam2reads options">
|
|
|
84 <param name="b2r_discard" argument="--b2r_discard_unmapped" truevalue="--b2r_discard_unmapped" falsevalue="" checked="false" type="boolean"
|
|
|
85 label="Check this to not keep unmapped reads" />
|
|
|
86 <param name="b2r_length_cutoff" type="integer" label="All reads mapped to contigs shorter than this will be kept (default=100000)" optional="true"/>
|
|
|
87 <param name="b2r_min_read_length" type="integer" label="Minimum length of read to output (defaul=250)" optional="true"/>
|
|
|
88 </section>
|
|
|
89
|
|
|
90 <section name="fix" title="fixstart options">
|
|
|
91 <param name="fixstart_mincluster" type="integer" label="The -c|mincluster option of promer. Overrides promer's default value" optional="true"/>
|
|
|
92 <param name="fixstart_min_id" type="float" label="Minimum percent identity of promer match between contigs and gene(s) to use as start point (dafault=70)" optional="true"/>
|
|
|
93 </section>
|
|
0
|
94
|
|
|
95 </inputs>
|
|
|
96 <outputs>
|
|
|
97 <data name="output_fasta" label="Output file of rearranged contigs" format="fasta" from_work_dir="outdir/06.fixstart.fasta" />
|
|
|
98 <data name="output_log" label="Log information" format="tabular" from_work_dir="outdir/06.fixstart.log" />
|
|
|
99 </outputs>
|
|
|
100 <tests>
|
|
|
101 <test>
|
|
|
102 <param name="file_contigs" value="test_contigs.fa"/>
|
|
|
103 <param name="file_reads" value="test_reads.fq.gz"/>
|
|
|
104 <output name="output_log" file="06.fixstart.log"/>
|
|
|
105 </test>
|
|
|
106 </tests>
|
|
|
107 <help><![CDATA[
|
|
|
108 The input is a genome assembly in FASTA format and corrected PacBio or nanopore reads in FASTA or FASTQ format.
|
|
|
109 Circlator will attempt to identify each circular sequence and output a linearised version of it.
|
|
|
110 It does this by assembling all reads that map to contig ends and comparing the resulting contigs with the input assembly.
|
|
|
111
|
|
|
112 The input assembly must not be too fragmented. Although Circlator will join contigs together, whenever it can identify contigs that can be
|
|
|
113 unambiguously joined, its main aim is to circularize the core genome and plasmids.
|
|
|
114
|
|
|
115 Any contigs that were identified as circular then have their start position changed.
|
|
|
116
|
|
1
|
117 Currently it does not download the uniprot database and it does not run the minimus2 pipeline. Even when running canu it may give warning messages about the SPAdes version,
|
|
|
118 you can safely ignore those.
|
|
0
|
119 ]]></help>
|
|
|
120 <citations>
|
|
|
121 <citation type="bibtex">
|
|
|
122 @misc{github,
|
|
|
123 publisher = {GitHub},
|
|
|
124 journal = {GitHub repository},
|
|
|
125 url = {https://github.com/sanger-pathogens/circlator/},
|
|
|
126 }</citation>
|
|
|
127 </citations>
|
|
|
128 </tool>
|
