Mercurial > repos > nick > dunovo
annotate align_families.xml @ 6:23f5d9316694 draft
Bugfix in kalign for very diverse read lengths.
author | nick |
---|---|
date | Thu, 02 Nov 2017 16:24:48 -0400 |
parents | 000969829a5d |
children | e7b88ffb8294 |
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"?> |
6 | 2 <tool id="align_families" name="Du Novo: Align families" version="2.0.8"> |
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> |
f875256c722e
planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff
changeset
|
5 <requirement type="package" version="7.221">mafft</requirement> |
6 | 6 <requirement type="package" version="2.0.8">dunovo</requirement> |
0
f875256c722e
planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff
changeset
|
7 <!-- TODO: require Python 2.7 --> |
f875256c722e
planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff
changeset
|
8 </requirements> |
5 | 9 <version_command>align_families.py --version</version_command> |
4 | 10 <command detect_errors="exit_code">align_families.py --aligner $aligner --galaxy $phone --processes \${GALAXY_SLOTS:-1} '$input' > '$output' |
0
f875256c722e
planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff
changeset
|
11 </command> |
f875256c722e
planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff
changeset
|
12 <inputs> |
f875256c722e
planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff
changeset
|
13 <param name="input" type="data" format="tabular" label="Input reads" help="with barcodes, grouped by family"/> |
4 | 14 <param name="aligner" type="select" value="mafft" label="Multiple sequence aligner" help="MAFFT is the original aligner Du Novo was published with in 2016. Kalign is much faster and has similar accuracy."> |
15 <option value="kalign">Kalign2</option> | |
16 <option value="mafft">MAFFT</option> | |
17 </param> | |
18 <param name="phone" type="boolean" truevalue="--phone-home" falsevalue="" checked="False" label="Send usage data" help="Report helpful usage data to the developer, to better understand the use cases and performance of the tool. The only data which will be recorded is the name and version of the tool, the size of the input data, the number of processes used, the time and memory taken to process it, the alignment algorithm selected, and the IP address of the machine running it. Also, if the tool fails, it will report the name of the exception thrown and the line of code it occurred in. The names of the input and output datasets are not sent. All the reporting and recording code is available at https://github.com/NickSto/ET."/> | |
0
f875256c722e
planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff
changeset
|
19 </inputs> |
f875256c722e
planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff
changeset
|
20 <outputs> |
f875256c722e
planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff
changeset
|
21 <data name="output" format="tabular"/> |
f875256c722e
planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff
changeset
|
22 </outputs> |
f875256c722e
planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff
changeset
|
23 <tests> |
f875256c722e
planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff
changeset
|
24 <test> |
f875256c722e
planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff
changeset
|
25 <param name="input" value="smoke.families.tsv"/> |
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.aligned.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> |
4 | 29 <param name="input" value="families.sort.tsv"/> |
30 <output name="output" file="families.msa.tsv"/> | |
0
f875256c722e
planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff
changeset
|
31 </test> |
f875256c722e
planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff
changeset
|
32 </tests> |
f875256c722e
planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff
changeset
|
33 <help> |
f875256c722e
planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff
changeset
|
34 |
f875256c722e
planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff
changeset
|
35 **What it does** |
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 This is for processing duplex sequencing data. It does a multiple sequence alignment on each (single-stranded) family of reads. |
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 ----- |
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 **Input** |
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 This expects the output format of the "Make families" tool. |
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 ----- |
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 **Output** |
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 The output is a tabular file where each line corresponds to a (single) read. |
f875256c722e
planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff
changeset
|
50 |
f875256c722e
planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff
changeset
|
51 The columns are:: |
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 1: barcode (both tags) |
f875256c722e
planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff
changeset
|
54 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
|
55 3: read mate ("1" or "2") |
f875256c722e
planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff
changeset
|
56 4: read name |
f875256c722e
planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff
changeset
|
57 5: read sequence, aligned ("-" for gaps) |
f875256c722e
planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff
changeset
|
58 6: read quality scores, aligned (" " for gaps) |
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 |
f875256c722e
planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff
changeset
|
62 **Alignments** |
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 The alignments are done using MAFFT, specifically the command |
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 |
f875256c722e
planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff
changeset
|
67 $ mafft --nuc --quiet family.fa > family.aligned.fa |
f875256c722e
planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff
changeset
|
68 |
4 | 69 </help> |
70 <citations> | |
71 <citation type="bibtex">@article{Stoler2016, | |
72 author = {Stoler, Nicholas and Arbeithuber, Barbara and Guiblet, Wilfried and Makova, Kateryna D and Nekrutenko, Anton}, | |
73 doi = {10.1186/s13059-016-1039-4}, | |
74 issn = {1474-760X}, | |
75 journal = {Genome biology}, | |
76 number = {1}, | |
77 pages = {180}, | |
78 pmid = {27566673}, | |
79 publisher = {Genome Biology}, | |
80 title = {{Streamlined analysis of duplex sequencing data with Du Novo.}}, | |
81 url = {http://www.ncbi.nlm.nih.gov/pubmed/27566673}, | |
82 volume = {17}, | |
83 year = {2016} | |
84 }</citation> | |
85 </citations> | |
0
f875256c722e
planemo upload for repository https://github.com/galaxyproject/dunovo commit b'd00f828e5768c5fac3e382b9d12f34bbdf9019e9\n'-dirty
nick
parents:
diff
changeset
|
86 </tool> |