Mercurial > repos > nick > dunovo

annotate make_families.xml @ 9:fa563fa9b330 draft

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 b'74b84167148cb0a0d7c6ac83123e8c957f85fe37\n'-dirty
author nick
date Fri, 23 Mar 2018 22:26:23 -0400
parents 658eefb99fd7
children 9dc43bf7d1db
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"?>
9
fa563fa9b330 planemo upload for repository https://github.com/galaxyproject/dunovo commit b'74b84167148cb0a0d7c6ac83123e8c957f85fe37\n'-dirty
nick
parents: 8
diff changeset
2 <tool id="make_families" name="Du Novo: Make families" version="2.14">
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>
9
fa563fa9b330 planemo upload for repository https://github.com/galaxyproject/dunovo commit b'74b84167148cb0a0d7c6ac83123e8c957f85fe37\n'-dirty
nick
parents: 8
diff changeset
5 <requirement type="package" version="2.14">dunovo</requirement>
0
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
6 </requirements>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
7 <!-- TODO: Add dependency on coreutils to get paste? -->
7
e7b88ffb8294 planemo upload for repository https://github.com/galaxyproject/dunovo commit b'9101e88acb2d3dc022c47e0663fec1f6b9fa58a5\n'-dirty
nick
parents: 6
diff changeset
8 <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
9 <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
10 </command>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
11 <inputs>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
12 <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
13 <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
14 <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
15 <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
16 </inputs>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
17 <outputs>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
18 <data name="output" format="tabular"/>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
19 </outputs>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
20 <tests>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
21 <test>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
22 <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
23 <param name="fastq2" value="smoke_2.fq"/>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
24 <param name="taglen" value="5"/>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
25 <param name="invariant" value="1"/>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
26 <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
27 </test>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
28 <test>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
29 <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
30 <param name="fastq2" value="smoke_2.fq"/>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
31 <param name="taglen" value="5"/>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
32 <param name="invariant" value="0"/>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
33 <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
34 </test>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
35 </tests>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
36 <help>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
37
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
38 **What it does**
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
39
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
40 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
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
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
44 **Output**
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
45
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
46 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
47
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
48 The columns are::
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
49
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
50 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
51 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
52 3: read1 name
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
53 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
54 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
55 6: read2 name
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
56 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
57 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
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
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
61 **Barcode creation**
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
62
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
63 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
64
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
65 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
66
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
67 Examples::
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 +---------------+-----------------+
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
70 | input tags | output |
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
71 +-------+-------+-------+---------+
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
72 | read1 | read2 | order | barcode |
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
73 +-------+-------+-------+---------+
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
74 | ATG | CCT | ab | ATGCCT |
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
75 +-------+-------+-------+---------+
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
76 | CCT | ATG | ba | ATGCCT |
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
77 +-------+-------+-------+---------+
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
78
4
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
79 </help>
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
80 <citations>
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
81 <citation type="bibtex">@article{Stoler2016,
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
82 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
83 doi = {10.1186/s13059-016-1039-4},
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
84 issn = {1474-760X},
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
85 journal = {Genome biology},
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
86 number = {1},
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
87 pages = {180},
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
88 pmid = {27566673},
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
89 publisher = {Genome Biology},
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
90 title = {{Streamlined analysis of duplex sequencing data with Du Novo.}},
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
91 url = {http://www.ncbi.nlm.nih.gov/pubmed/27566673},
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
92 volume = {17},
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
93 year = {2016}
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
94 }</citation>
5fbeaa41b223 Update to Du Novo 2.0.6.
nick
parents: 3
diff changeset
95 </citations>
0
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
96 </tool>