diff align_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
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/align_families.xml	Sat Feb 18 05:58:44 2017 -0500
@@ -0,0 +1,80 @@
+<?xml version="1.0"?>
+<tool id="align_families" name="Du Novo: Align families" version="0.7">
+  <description>of duplex sequencing reads</description>
+  <requirements>
+    <requirement type="package" version="7.221">mafft</requirement>
+    <requirement type="package" version="0.7">dunovo</requirement>
+    <!-- TODO: require Python 2.7 -->
+  </requirements>
+  <command detect_errors="exit_code">align_families.py -p \${GALAXY_SLOTS:-1} '$input' &gt; '$output'
+  </command>
+  <inputs>
+    <param name="input" type="data" format="tabular" label="Input reads" help="with barcodes, grouped by family"/>
+  </inputs>
+  <outputs>
+    <data name="output" format="tabular"/>
+  </outputs>
+  <tests>
+    <test>
+      <param name="input" value="smoke.families.tsv"/>
+      <output name="output" file="smoke.families.aligned.tsv"/>
+    </test>
+    <test>
+      <param name="input" value="families.in.tsv"/>
+      <output name="output" file="families.sort.tsv"/>
+    </test>
+  </tests>
+  <citations>
+    <citation type="bibtex">@article{Stoler2016,
+      author = {Stoler, Nicholas and Arbeithuber, Barbara and Guiblet, Wilfried and Makova, Kateryna D and Nekrutenko, Anton},
+      doi = {10.1186/s13059-016-1039-4},
+      issn = {1474-760X},
+      journal = {Genome biology},
+      number = {1},
+      pages = {180},
+      pmid = {27566673},
+      publisher = {Genome Biology},
+      title = {{Streamlined analysis of duplex sequencing data with Du Novo.}},
+      url = {http://www.ncbi.nlm.nih.gov/pubmed/27566673},
+      volume = {17},
+      year = {2016}
+    }</citation>
+  </citations>
+  <help>
+
+**What it does**
+
+This is for processing duplex sequencing data. It does a multiple sequence alignment on each (single-stranded) family of reads.
+
+-----
+
+**Input**
+
+This expects the output format of the "Make families" tool.
+
+-----
+
+**Output**
+
+The output is a tabular file where each line corresponds to a (single) read.
+
+The columns are::
+
+  1: barcode (both tags)
+  2: tag order in barcode ("ab" or "ba")
+  3: read mate ("1" or "2")
+  4: read name
+  5: read sequence, aligned ("-" for gaps)
+  6: read quality scores, aligned (" " for gaps)
+
+-----
+
+**Alignments**
+
+The alignments are done using MAFFT, specifically the command
+::
+
+  $ mafft --nuc --quiet family.fa &gt; family.aligned.fa
+
+    </help>
+</tool>