annotate sampleFasta.xml @ 6:f224513123a1 draft

Uploaded
author petr-novak
date Mon, 02 Dec 2019 03:45:28 -0500
parents e320ef2d105a
children c2c69c6090f0
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
3
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
1 <tool id="sampler" name="Sequence sampling" version="1.0.0">
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
2 <description> Tool for creating samples of sequences from larger dataset</description>
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
3 <requirements>
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
4 <requirement type="package">seqkit</requirement>
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
5 </requirements>
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
6 <stdio>
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
7 <exit_code range="1:" level="fatal" description="Error" />
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
8 </stdio>
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
9 <command>
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
10 #if str($paired)=="true"
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
11 ${__tool_directory__}/deinterlacer.py $input Afile Bfile
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
12 &amp;&amp;
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
13 seqkit sample -2 --number $number --rand-seed $seed -o Asample -w 0 Afile
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
14 &amp;&amp;
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
15 seqkit sample -2 --number $number --rand-seed $seed -o Bsample -w 0 Bfile
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
16 &amp;&amp;
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
17 ${__tool_directory__}/fasta_interlacer.py -a Asample -b Bsample -p $output -x tmpfile
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
18 #else
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
19 seqkit sample -2 --number $number --rand-seed $seed -o $output -w 0 $input
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
20 #end if
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
21 </command>
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
22
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
23 <inputs>
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
24 <param format="fasta" type="data" name="input" label="Choose your fasta file" />
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
25 <param name="number" type="integer" size="7" value="500000" min="1" label="number of sequences or sequence pairs"/>
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
26 <param name="seed" type="integer" size="10" value="10" min="0" label="random number generator seed " />
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
27 <param name="paired" type="boolean" truevalue="true" falsevalue="false" checked="False" label="All sequence reads are paired" help="check if you are using pair reads and and input sequences contain both read mates and left mates alternate with their right mates"/>
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
28
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
29
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
30 </inputs>
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
31
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
32
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
33 <outputs>
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
34 <data format="fasta" name="output" label="Random selection from dataset ${input.hid}, sample size ${number})" />
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
35 </outputs>
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
36
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
37 <help>
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
38 **What it does**
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
39
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
40 This tools is intended to create sample of sequences from by taking 'random' sample from larger data sets.
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
41 Using a same seed parameter make sampling reproducible.
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
42
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
43
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
44 </help>
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
45
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
46
e320ef2d105a Uploaded
petr-novak
parents:
diff changeset
47 </tool>