Mercurial > repos > petr-novak > re_utils
comparison sampleFasta.xml @ 3:e320ef2d105a draft
Uploaded
author | petr-novak |
---|---|
date | Thu, 05 Sep 2019 09:04:56 -0400 |
parents | |
children | c2c69c6090f0 |
comparison
equal
deleted
inserted
replaced
2:ff658cf87f16 | 3:e320ef2d105a |
---|---|
1 <tool id="sampler" name="Sequence sampling" version="1.0.0"> | |
2 <description> Tool for creating samples of sequences from larger dataset</description> | |
3 <requirements> | |
4 <requirement type="package">seqkit</requirement> | |
5 </requirements> | |
6 <stdio> | |
7 <exit_code range="1:" level="fatal" description="Error" /> | |
8 </stdio> | |
9 <command> | |
10 #if str($paired)=="true" | |
11 ${__tool_directory__}/deinterlacer.py $input Afile Bfile | |
12 && | |
13 seqkit sample -2 --number $number --rand-seed $seed -o Asample -w 0 Afile | |
14 && | |
15 seqkit sample -2 --number $number --rand-seed $seed -o Bsample -w 0 Bfile | |
16 && | |
17 ${__tool_directory__}/fasta_interlacer.py -a Asample -b Bsample -p $output -x tmpfile | |
18 #else | |
19 seqkit sample -2 --number $number --rand-seed $seed -o $output -w 0 $input | |
20 #end if | |
21 </command> | |
22 | |
23 <inputs> | |
24 <param format="fasta" type="data" name="input" label="Choose your fasta file" /> | |
25 <param name="number" type="integer" size="7" value="500000" min="1" label="number of sequences or sequence pairs"/> | |
26 <param name="seed" type="integer" size="10" value="10" min="0" label="random number generator seed " /> | |
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"/> | |
28 | |
29 | |
30 </inputs> | |
31 | |
32 | |
33 <outputs> | |
34 <data format="fasta" name="output" label="Random selection from dataset ${input.hid}, sample size ${number})" /> | |
35 </outputs> | |
36 | |
37 <help> | |
38 **What it does** | |
39 | |
40 This tools is intended to create sample of sequences from by taking 'random' sample from larger data sets. | |
41 Using a same seed parameter make sampling reproducible. | |
42 | |
43 | |
44 </help> | |
45 | |
46 | |
47 </tool> |