diff align_families.xml @ 0:4633a25d8c19 draft

planemo upload commit 801bf168032a13f6405518bddb35a24c9e9a8cd4-dirty

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/align_families.xml	Mon Nov 23 17:28:08 2015 -0500
@@ -0,0 +1,59 @@
+<?xml version="1.0"?>
+<tool id="align_families" name="Align families" version="0.1">
+  <description>from duplex sequencing data</description>
+  <command interpreter="python" detect_errors="exit_code">align_families.py $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>
+  <requirements>
+    <requirement type="package" version="7.221">mafft</requirement>
+    <requirement type="package" version="0.1">duplex</requirement>
+  </requirements>
+  <tests>
+    <test>
+      <param name="input" value="smoke.families.tsv"/>
+      <output name="output" file="smoke.families.aligned.tsv"/>
+    </test>
+  </tests>
+  <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>