Mercurial > repos > nick > dunovo

annotate make_families.xml @ 11:0f8e0dc73d1d draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/galaxyproject/dunovo commit dbd33f95b486dc556c435f1b42736b818a2b9802-dirty"
author nick
date Wed, 16 Feb 2022 22:59:00 +0000
parents 9dc43bf7d1db
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
1 <?xml version="1.0"?>
11
0f8e0dc73d1d "planemo upload for repository https://github.com/galaxyproject/dunovo commit dbd33f95b486dc556c435f1b42736b818a2b9802-dirty"
nick
parents: 10
diff changeset
2 <tool id="make_families" name="Du Novo: Make families" version="3.0.2">
0
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
3 <description>of duplex sequencing reads</description>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
4 <requirements>
11
0f8e0dc73d1d "planemo upload for repository https://github.com/galaxyproject/dunovo commit dbd33f95b486dc556c435f1b42736b818a2b9802-dirty"
nick
parents: 10
diff changeset
5 <requirement type="package" version="3.0.2">dunovo</requirement>
0
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
6 </requirements>
7
e7b88ffb8294 planemo upload for repository https://github.com/galaxyproject/dunovo commit b'9101e88acb2d3dc022c47e0663fec1f6b9fa58a5\n'-dirty
nick
parents: 6
diff changeset
7 <version_command>make-consensi.py --version</version_command>
0
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
8 <command detect_errors="exit_code">make-families.sh -t $taglen -i $invariant '$fastq1' '$fastq2' &gt; '$output'
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
9 </command>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
10 <inputs>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
11 <param name="fastq1" type="data" format="fastq" label="Sequencing reads, mate 1"/>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
12 <param name="fastq2" type="data" format="fastq" label="Sequencing reads, mate 2"/>
9
fa563fa9b330 planemo upload for repository https://github.com/galaxyproject/dunovo commit b'74b84167148cb0a0d7c6ac83123e8c957f85fe37\n'-dirty
nick
parents: 8
diff changeset
13 <param name="taglen" type="integer" value="12" min="0" label="Tag length" help="Length of each random barcode on the ends of the fragments."/>
fa563fa9b330 planemo upload for repository https://github.com/galaxyproject/dunovo commit b'74b84167148cb0a0d7c6ac83123e8c957f85fe37\n'-dirty
nick
parents: 8
diff changeset
14 <param name="invariant" type="integer" value="5" min="0" label="Invariant sequence length" help="Length of the sequence between the tag and actual sample sequence (the restriction site, normally)."/>
0
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
15 </inputs>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
16 <outputs>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
17 <data name="output" format="tabular"/>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
18 </outputs>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
19 <tests>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
20 <test>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
21 <param name="fastq1" value="smoke_1.fq"/>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
22 <param name="fastq2" value="smoke_2.fq"/>
11
0f8e0dc73d1d "planemo upload for repository https://github.com/galaxyproject/dunovo commit dbd33f95b486dc556c435f1b42736b818a2b9802-dirty"
nick
parents: 10
diff changeset
23 <param name="taglen" value="4"/>
0
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
24 <param name="invariant" value="1"/>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
25 <output name="output" file="smoke.families.tsv"/>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
26 </test>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
27 <test>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
28 <param name="fastq1" value="smoke_1.fq"/>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
29 <param name="fastq2" value="smoke_2.fq"/>
11
0f8e0dc73d1d "planemo upload for repository https://github.com/galaxyproject/dunovo commit dbd33f95b486dc556c435f1b42736b818a2b9802-dirty"
nick
parents: 10
diff changeset
30 <param name="taglen" value="4"/>
0
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
31 <param name="invariant" value="0"/>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
32 <output name="output" file="smoke.families.i0.tsv"/>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
33 </test>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
34 </tests>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
35 <help>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
36
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
37 **What it does**
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
38
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
39 This tool is for processing raw duplex sequencing data, removing the barcodes and grouping by them into families of reads from the same fragment.
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
40
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
41 -----
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
42
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
43 **Output**
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
44
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
45 The output will be a tabular file where each line corresponds to a pair of input reads.
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
46
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
47 The columns are::
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
48
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
49 1: barcode (both tags joined and ordered)
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
50 2: tag order in barcode ("ab" or "ba")
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
51 3: read1 name
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
52 4: read1 sequence (minus the tag and invariant sequences)
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
53 5: read1 quality scores (minus the same tag and invariant)
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
54 6: read2 name
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
55 7: read2 sequence (minus the tag and invariant sequences)
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
56 8: read2 quality scores (minus the same tag and invariant)
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
57
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
58 -----
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
59
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
60 **Barcode creation**
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
61
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
62 For each pair, the tool will remove the tag at the beginning of each read and create a barcode by concatenating the two tags. The order of the tags is determined by a string comparison so that it will make an identical barcode from pairs of either order. The original tag order will be noted in the second column.
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
63
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
64 Since pairs from opposite strands will have the same tags, but in the reverse order, this produces the same barcode for reads from the same fragment, regardless of strand. Then a simple sort will group all reads from the same strand together, separated into strands by the different "order" values.
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
65
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
66 Examples::
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
67
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
68 +---------------+-----------------+
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
69 | input tags | output |
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
70 +-------+-------+-------+---------+
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
71 | read1 | read2 | order | barcode |
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
72 +-------+-------+-------+---------+
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
73 | ATG | CCT | ab | ATGCCT |
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
74 +-------+-------+-------+---------+
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
75 | CCT | ATG | ba | ATGCCT |
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
76 +-------+-------+-------+---------+
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
77
4
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
78 </help>
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
79 <citations>
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
80 <citation type="bibtex">@article{Stoler2016,
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
81 author = {Stoler, Nicholas and Arbeithuber, Barbara and Guiblet, Wilfried and Makova, Kateryna D and Nekrutenko, Anton},
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
82 doi = {10.1186/s13059-016-1039-4},
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
83 issn = {1474-760X},
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
84 journal = {Genome biology},
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
85 number = {1},
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
86 pages = {180},
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
87 pmid = {27566673},
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
88 publisher = {Genome Biology},
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
89 title = {{Streamlined analysis of duplex sequencing data with Du Novo.}},
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
90 url = {http://www.ncbi.nlm.nih.gov/pubmed/27566673},
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
91 volume = {17},
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
92 year = {2016}
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
93 }</citation>
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
94 </citations>
0
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
95 </tool>