annotate make_families.xml @ 0:f875256c722e draft

planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
author nick
date Sat, 18 Feb 2017 05:58:44 -0500
parents
children ea832c221ec9
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"?>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
2 <tool id="make_families" name="Du Novo: Make families" version="0.7">
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>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
5 <requirement type="package" version="0.7">dunovo</requirement>
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? -->
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"/>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
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"/>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
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)"/>
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"/>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
23 <param name="taglen" value="5"/>
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"/>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
30 <param name="taglen" value="5"/>
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 <citations>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
36 <citation type="bibtex">@article{Stoler2016,
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
37 author = {Stoler, Nicholas and Arbeithuber, Barbara and Guiblet, Wilfried and Makova, Kateryna D and Nekrutenko, Anton},
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
38 doi = {10.1186/s13059-016-1039-4},
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
39 issn = {1474-760X},
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
40 journal = {Genome biology},
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
41 number = {1},
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
42 pages = {180},
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
43 pmid = {27566673},
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
44 publisher = {Genome Biology},
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
45 title = {{Streamlined analysis of duplex sequencing data with Du Novo.}},
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
46 url = {http://www.ncbi.nlm.nih.gov/pubmed/27566673},
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
47 volume = {17},
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
48 year = {2016}
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
49 }</citation>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
50 </citations>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
51 <help>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
52
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
53 **What it does**
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
54
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
55 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
56
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 **Output**
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 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
62
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
63 The columns are::
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 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
66 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
67 3: read1 name
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
68 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
69 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
70 6: read2 name
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
71 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
72 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
73
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
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
76 **Barcode creation**
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 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
79
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
80 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
81
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
82 Examples::
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
83
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
84 +---------------+-----------------+
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
85 | input tags | output |
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
86 +-------+-------+-------+---------+
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
87 | read1 | read2 | order | barcode |
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
88 +-------+-------+-------+---------+
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
89 | ATG | CCT | ab | ATGCCT |
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
90 +-------+-------+-------+---------+
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
91 | CCT | ATG | ba | ATGCCT |
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
92 +-------+-------+-------+---------+
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
93
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
94 </help>
f875256c722e planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff changeset
95 </tool>