Mercurial > repos > iuc > ont_fast5_api_fast5_subset

comparison fast5_subset.xml @ 1:3bdd8fa109b1 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/nanoporetech/ont_fast5_api/ commit a5d038871ff0e1b133039b59183dee795449b383"
author iuc
date Fri, 12 Jun 2020 15:08:23 -0400
parents eb1f4aa80c72
children 33a0ff1bb7df
comparison
equal deleted inserted replaced
0:eb1f4aa80c72 1:3bdd8fa109b1
1 <?xml version="1.0"?> 1 <?xml version="1.0"?>
2 <tool id="ont_fast5_api_fast5_subset" name="Fast5 subset" version="@TOOL_VERSION@+galaxy0" profile="18.01"> 2 <tool id="ont_fast5_api_fast5_subset" name="@TOOL_NAME@ Subset" version="@TOOL_VERSION@+galaxy1" profile="18.01">
3 <description>of multi read file</description> 3 <description>of multi read file(s)</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 <version_command></version_command> 8 <!-- no specific version command for subcommand fast5_subset available -->
9 <version_command><![CDATA[compress_fast5 -v]]></version_command>
9 <command detect_errors="exit_code"><![CDATA[ 10 <command detect_errors="exit_code"><![CDATA[
10 ## initialize 11 ## initialize
11 mkdir data && 12 mkdir -p './data' &&
12 #for $num, $current in enumerate($input): 13 tar -xf '$input' -C './data' &&
13 ln -s '$current' './data/batch${num}.fast5' &&
14 #end for
15 14
16 ## run 15 ## run
17 fast5_subset 16 fast5_subset
18 ## required 17 ## required
19 --input ./data 18 --input './data'
20 -s ./results 19 @SAVEPATH@
21 --read_id_list '$read_id_list' 20 --read_id_list '$read_id_list'
22 ## optional 21 ## optional
23 --batch_size $batch_size 22 @COMPRESSION@
24 -t \${GALAXY_SLOTS:-4} 23 @BATCHSIZE@
24 @THREADS@
25
26 ## create tarball
27 @TARBALL@
25 ]]></command> 28 ]]></command>
26 <inputs> 29 <inputs>
27 <param argument="--input" type="data" format="fast5" multiple="true" 30 <expand macro="input" argument="--input"/>
28 label="Select multi read input file(s)"/> 31 <param argument="--read_id_list" type="data" format="tabular" label="Select file with read IDs" help="Either containing 1 read_id per line or a tabular file with a column named read_id."/>
29 <param argument="--read_id_list" type="data" format="tabular" 32 <expand macro="batch_size"/>
30 label="Select file with read_ids" help="Either containing 1 read_id per line or a tabular file with a column named read_id."/> 33 <expand macro="compression">
31 <param argument="--batch_size" type="integer" value="4000" min="1" 34 <option value="none" selected="true">None</option>
32 label="Set batch size" help="Number of single reads to include in each multi read file"/> 35 <option value="vbz">VBZ</option>
36 </expand>
33 </inputs> 37 </inputs>
34 <outputs> 38 <outputs>
35 <data name="out_results" format="fast5"> 39 <expand macro="output"/>
36 <discover_datasets pattern="(?P&lt;designation&gt;.+)\.fast5" format="fast5" directory="results" assign_primary_output="true" visible="true"/>
37 </data>
38 </outputs> 40 </outputs>
39 <tests> 41 <tests>
42 <!-- #1 default -->
40 <test expect_num_outputs="1"> 43 <test expect_num_outputs="1">
41 <param name="input" value="batch.fast5"/> 44 <param name="input" value="multi.fast5.tar"/>
45 <param name="read_id_list" value="list.txt"/>
46 <output name="out_results">
47 <assert_contents>
48 <has_size value="30720"/>
49 </assert_contents>
50 </output>
51 </test>
52 <!-- #2 -->
53 <test expect_num_outputs="1">
54 <param name="input" value="multi.fast5.tar"/>
42 <param name="read_id_list" value="list.txt"/> 55 <param name="read_id_list" value="list.txt"/>
43 <param name="batch_size" value="2"/> 56 <param name="batch_size" value="2"/>
57 <param name="compression" value="gzip"/>
44 <output name="out_results"> 58 <output name="out_results">
45 <assert_contents> 59 <assert_contents>
46 <has_size value="23304"/> 60 <has_size value="51200"/>
47 </assert_contents> 61 </assert_contents>
48 <!-- batch0 is represented by out_results --> 62 </output>
49 <discovered_dataset designation="batch1" ftype="fast5"> 63 </test>
50 <assert_contents> 64 <!-- #3 -->
51 <has_size value="17328"/> 65 <test expect_num_outputs="1">
52 </assert_contents> 66 <param name="input" value="multi.fast5.tar"/>
53 </discovered_dataset> 67 <param name="read_id_list" value="list.txt"/>
68 <param name="compression" value="vbz"/>
69 <output name="out_results">
70 <assert_contents>
71 <has_size value="40960"/>
72 </assert_contents>
73 </output>
74 </test>
75 <!-- #4 -->
76 <test expect_num_outputs="1">
77 <param name="input" value="multi.fast5.tar"/>
78 <param name="read_id_list" value="list.txt"/>
79 <param name="compression" value="vbz_legacy_v0"/>
80 <output name="out_results">
81 <assert_contents>
82 <has_size value="40960"/>
83 </assert_contents>
54 </output> 84 </output>
55 </test> 85 </test>
56 </tests> 86 </tests>
57 <help><![CDATA[ 87 <help><![CDATA[
58 .. class:: infomark 88 .. class:: infomark
59 89
60 **What it does** 90 **What it does**
61 91
62 @WID@ 92 @WID@
63 93
64 fast5_subset extracts reads from multi_read_fast5_file(s) based on a list of read IDs. 94 *fast5_subset* extracts reads from multi read FAST5 file(s) based on a list of read IDs.
65 95
66 **Input** 96 **Input**
67 97
68 A multi read file in FAST5 format and a list of read IDs that should be extracted. 98 Multi read file(s) in FAST5 format, that are stored in a flat TAR, and a list of read IDs that should be extracted.
69 99
70 **Output** 100 **Output**
71 101
72 A multi read file in FAST5 format containing a subset of the input file. 102 Multi read file(s) in FAST5 format containing a subset of the input file(s). The rseults are are stored in a flat TAR.
73 103
74 .. class:: infomark 104 .. class:: infomark
75 105
76 **References** 106 **References**
77 107