Mercurial > repos > nick > duplex

annotate make_families.xml @ 28:71b765a4c494 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 b'53eba8ce731a5f8afd739f9b9c01229b54880e6c\n'-dirty
author nick
date Sat, 18 Feb 2017 04:56:38 -0500
parents f33b89fe9f82
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
19
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
1 <?xml version="1.0"?>
22
8ef925264516 planemo upload for repository https://github.com/galaxyproject/dunovo commit b'3eab56b30cc9d644798a290017bcc1188f028af8\n'-dirty
nick
parents: 21
diff changeset
2 <tool id="make_families" name="Du Novo: Make families" version="0.6">
19
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
3 <description>of duplex sequencing reads</description>
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
4 <requirements>
28
71b765a4c494 planemo upload for repository https://github.com/galaxyproject/dunovo commit b'53eba8ce731a5f8afd739f9b9c01229b54880e6c\n'-dirty
nick
parents: 27
diff changeset
5 <requirement type="package" version="0.6.2">duplex</requirement>
19
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
6 </requirements>
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
7 <!-- TODO: Add dependency on coreutils to get paste? -->
28
71b765a4c494 planemo upload for repository https://github.com/galaxyproject/dunovo commit b'53eba8ce731a5f8afd739f9b9c01229b54880e6c\n'-dirty
nick
parents: 27
diff changeset
8 <command detect_errors="exit_code">make-families.sh -t $taglen -i $invariant '$fastq1' '$fastq2' &gt; '$output'
19
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
9 </command>
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
10 <inputs>
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
11 <param name="fastq1" type="data" format="fastq" label="Sequencing reads, mate 1"/>
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
12 <param name="fastq2" type="data" format="fastq" label="Sequencing reads, mate 2"/>
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\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"/>
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\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)"/>
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
15 </inputs>
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
16 <outputs>
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
17 <data name="output" format="tabular"/>
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
18 </outputs>
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
19 <tests>
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
20 <test>
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
21 <param name="fastq1" value="smoke_1.fq"/>
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
22 <param name="fastq2" value="smoke_2.fq"/>
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
23 <param name="taglen" value="5"/>
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
24 <param name="invariant" value="1"/>
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
25 <output name="output" file="smoke.families.tsv"/>
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
26 </test>
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
27 <test>
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
28 <param name="fastq1" value="smoke_1.fq"/>
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
29 <param name="fastq2" value="smoke_2.fq"/>
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
30 <param name="taglen" value="5"/>
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
31 <param name="invariant" value="0"/>
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
32 <output name="output" file="smoke.families.i0.tsv"/>
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
33 </test>
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
34 </tests>
21
53cf867b305b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'a67987d921c6ee2f042597ba46b34dfbd86f415e\n'-dirty
nick
parents: 19
diff changeset
35 <citations>
53cf867b305b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'a67987d921c6ee2f042597ba46b34dfbd86f415e\n'-dirty
nick
parents: 19
diff changeset
36 <citation type="bibtex">@article{Stoler2016,
53cf867b305b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'a67987d921c6ee2f042597ba46b34dfbd86f415e\n'-dirty
nick
parents: 19
diff changeset
37 author = {Stoler, Nicholas and Arbeithuber, Barbara and Guiblet, Wilfried and Makova, Kateryna D and Nekrutenko, Anton},
53cf867b305b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'a67987d921c6ee2f042597ba46b34dfbd86f415e\n'-dirty
nick
parents: 19
diff changeset
38 doi = {10.1186/s13059-016-1039-4},
53cf867b305b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'a67987d921c6ee2f042597ba46b34dfbd86f415e\n'-dirty
nick
parents: 19
diff changeset
39 issn = {1474-760X},
53cf867b305b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'a67987d921c6ee2f042597ba46b34dfbd86f415e\n'-dirty
nick
parents: 19
diff changeset
40 journal = {Genome biology},
53cf867b305b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'a67987d921c6ee2f042597ba46b34dfbd86f415e\n'-dirty
nick
parents: 19
diff changeset
41 number = {1},
53cf867b305b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'a67987d921c6ee2f042597ba46b34dfbd86f415e\n'-dirty
nick
parents: 19
diff changeset
42 pages = {180},
53cf867b305b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'a67987d921c6ee2f042597ba46b34dfbd86f415e\n'-dirty
nick
parents: 19
diff changeset
43 pmid = {27566673},
53cf867b305b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'a67987d921c6ee2f042597ba46b34dfbd86f415e\n'-dirty
nick
parents: 19
diff changeset
44 publisher = {Genome Biology},
53cf867b305b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'a67987d921c6ee2f042597ba46b34dfbd86f415e\n'-dirty
nick
parents: 19
diff changeset
45 title = {{Streamlined analysis of duplex sequencing data with Du Novo.}},
53cf867b305b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'a67987d921c6ee2f042597ba46b34dfbd86f415e\n'-dirty
nick
parents: 19
diff changeset
46 url = {http://www.ncbi.nlm.nih.gov/pubmed/27566673},
53cf867b305b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'a67987d921c6ee2f042597ba46b34dfbd86f415e\n'-dirty
nick
parents: 19
diff changeset
47 volume = {17},
53cf867b305b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'a67987d921c6ee2f042597ba46b34dfbd86f415e\n'-dirty
nick
parents: 19
diff changeset
48 year = {2016}
53cf867b305b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'a67987d921c6ee2f042597ba46b34dfbd86f415e\n'-dirty
nick
parents: 19
diff changeset
49 }</citation>
53cf867b305b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'a67987d921c6ee2f042597ba46b34dfbd86f415e\n'-dirty
nick
parents: 19
diff changeset
50 </citations>
19
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
51 <help>
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
52
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
53 **What it does**
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
54
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\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.
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
56
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
57 -----
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
58
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
59 **Output**
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
60
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
61 The output will be a tabular file where each line corresponds to a pair of input reads.
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
62
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
63 The columns are::
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
64
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
65 1: barcode (both tags joined and ordered)
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
66 2: tag order in barcode ("ab" or "ba")
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
67 3: read1 name
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
68 4: read1 sequence (minus the tag and invariant sequences)
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
69 5: read1 quality scores (minus the same tag and invariant)
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
70 6: read2 name
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
71 7: read2 sequence (minus the tag and invariant sequences)
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
72 8: read2 quality scores (minus the same tag and invariant)
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
73
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
74 -----
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
75
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
76 **Barcode creation**
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
77
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\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.
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
79
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\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.
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
81
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
82 Examples::
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
83
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
84 +---------------+-----------------+
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
85 | input tags | output |
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
86 +-------+-------+-------+---------+
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
87 | read1 | read2 | order | barcode |
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
88 +-------+-------+-------+---------+
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
89 | ATG | CCT | ab | ATGCCT |
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
90 +-------+-------+-------+---------+
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
91 | CCT | ATG | ba | ATGCCT |
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
92 +-------+-------+-------+---------+
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
93
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
94 </help>
675a8370675b planemo upload for repository https://github.com/galaxyproject/dunovo commit b'4303231da9e48b2719b4429a29b72421d24310f4\n'-dirty
nick
parents:
diff changeset
95 </tool>