Mercurial > repos > iuc > seqtk

comparison seqtk_sample.xml @ 6:288f7f69fe25 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/seqtk commit 50a0bd6d783a69e7303363a31130134767493e66"
author iuc
date Fri, 06 Sep 2019 09:10:07 -0400
parents a09586d5149a
children 3da72230c066
comparison
equal deleted inserted replaced
5:a09586d5149a 6:288f7f69fe25
1 <?xml version="1.0"?> 1 <?xml version="1.0"?>
2 <tool id="seqtk_sample" name="seqtk_sample" version="@TOOL_VERSION@.1"> 2 <tool id="seqtk_sample" name="seqtk_sample" version="@TOOL_VERSION@.2">
3 <description>random subsample of fasta or fastq sequences</description> 3 <description>random subsample of fasta or fastq sequences</description>
4 <macros> 4 <macros>
5 <import>macros.xml</import> 5 <import>macros.xml</import>
6 </macros> 6 </macros>
7 <expand macro="requirements"/> 7 <expand macro="requirements"/>
8 <expand macro="stdio"/> 8 <expand macro="stdio"/>
9 <command><![CDATA[ 9 <command><![CDATA[
10 seqtk sample 10 seqtk sample
11 -s $s 11 -s $s
12 $advanced.single_pass_mode
12 '$in_file' 13 '$in_file'
13 $subsample_size 14 $subsample_size
14 @CONDITIONAL_GZIP_OUT@ 15 @CONDITIONAL_GZIP_OUT@
15 ]]></command> 16 ]]></command>
16 <inputs> 17 <inputs>
17 <expand macro="in_faq" /> 18 <expand macro="in_faq" />
18 <param argument="-s" type="integer" value="4" label="RNG seed" help="The seed used for the random number generator. Manually specifying a number here is useful for reproducing the same subsampling over time" /> 19 <param argument="-s" type="integer" value="4" label="RNG seed" help="The seed used for the random number generator. Manually specifying a number here is useful for reproducing the same subsampling in different runs (e.g. read 1 and read 2)" />
19 <param name="subsample_size" type="float" value="100" label="Subsample (decimal fraction or number)" /> 20 <param name="subsample_size" type="float" value="100" label="Subsample (decimal fraction or number)" help="Use an integer > 1 to select a specific number of reads. Use a decimal (e.g. 0.5) to select a fraction of reads"/>
21 <section name="advanced" title="Advanced options" expanded="false">
22 <param name="single_pass_mode" type="boolean" truevalue="" falsevalue="-2" checked="false" label="Enable 1-pass mode" help="Use this if the number of reads you want to sample is small enough to fit into memory. If you're not sure, don't use this."/>
23 </section>
20 </inputs> 24 </inputs>
21 <outputs> 25 <outputs>
22 <data name="default" format_source="in_file" label="Subsample of reads from $in_file.name"/> 26 <data name="default" format_source="in_file" label="Subsample of reads from $in_file.name"/>
23 </outputs> 27 </outputs>
24 <tests> 28 <tests>
25 <test> 29 <test>
26 <param name="in_file" value="seqtk_sample.fa"/> 30 <param name="in_file" value="seqtk_sample.fa"/>
27 <param name="subsample_size" value="4"/> 31 <param name="subsample_size" value="4"/>
28 <param name="s" value="4"/> 32 <param name="s" value="4"/>
33 <param name="advanced|single_pass_mode" value="True"/>
29 <output name="default" file="seqtk_sample.out" ftype="fasta"/> 34 <output name="default" file="seqtk_sample.out" ftype="fasta"/>
30 </test> 35 </test>
31 <test> 36 <test>
32 <param name="in_file" value="seqtk_sample.fa.gz" ftype="fasta.gz"/> 37 <param name="in_file" value="seqtk_sample.fa.gz" ftype="fasta.gz"/>
33 <param name="subsample_size" value="4"/> 38 <param name="subsample_size" value="4"/>
34 <param name="s" value="4"/> 39 <param name="s" value="4"/>
40 <param name="advanced|single_pass_mode" value='True'/>
35 <output name="default" file="seqtk_sample.out.gz" ftype="fasta.gz"/> 41 <output name="default" file="seqtk_sample.out.gz" ftype="fasta.gz"/>
42 </test>
43 <test>
44 <param name="in_file" value="seqtk_sample.fa.gz" ftype="fasta.gz"/>
45 <param name="subsample_size" value="4"/>
46 <param name="s" value="4"/>
47 <param name="advanced|single_pass_mode" value='False'/>
48 <output name="default" file="seqtk_sample.lowmem.gz" ftype="fasta.gz"/>
36 </test> 49 </test>
37 </tests> 50 </tests>
38 <help><![CDATA[ 51 <help><![CDATA[
39 **What it does** 52 **What it does**
40 53
41 Takes a random subsample of FASTA or FASTQ sequences. The RNG is seedable to allow for reproducible results, and defaults to `4 <http://xkcd.com/221/>`__. 54 Takes a random subsample of FASTA or FASTQ sequences. The RNG is seedable to allow for reproducible results, and defaults to `4 <http://xkcd.com/221/>`__.
42 55
43 The subsample size can be a decimal fraction <=1, where 1 implies 100% of the reads should be used. If a number >1 is provided, that many reads will be taken from the dataset. 56 The subsample size can be a decimal fraction <=1, where 1 implies 100% of the reads should be used. If a number >1 is provided, that many reads will be taken from the dataset.
44 57
58 Two pass sampling mode reads the input file once to build a list of reads to output then again to output the reads. It is twice as slow, but uses much less RAM. It is only in effect when an integer number of reads (not a fraction) is specified as subsample size.
59
45 @ATTRIBUTION@ 60 @ATTRIBUTION@
46 ]]></help> 61 ]]></help>
47 <expand macro="citation" /> 62 <expand macro="citation" />
48 </tool> 63 </tool>