comparison trycycler_subsample.xml @ 0:85658cabbbed draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/trycycler commit 9d7c4277b0f96aacd466f2d497e08edcca3fa238"
author iuc
date Thu, 11 Feb 2021 19:25:20 +0000
parents
children 383bb5ad32e2
comparison
equal deleted inserted replaced
-1:000000000000 0:85658cabbbed
1 <tool id='trycycler_subsample' name='Trycycler subsample' version='@TOOL_VERSION@' profile='21.01'>
2 <description>make a maximally-independent read subsets of an appropiate depth for your genome</description>
3 <macros>
4 <import>macros.xml</import>
5 </macros>
6 <expand macro='edam_ontology'/>
7 <expand macro='requirements'/>
8 <version_command>trycycler --version</version_command>
9 <command detect_errors='exit_code'><![CDATA[
10 mkdir -p output_subsamples &&
11 trycycler subsample
12 --reads '${reads}'
13 --count $count
14 #if $option.genome == 'true'
15 --genome_size $option.genome_size
16 #end if
17 --min_read_depth $min_read_depth
18 --threads \${GALAXY_SLOTS:-2}
19 --out_dir output_subsamples
20 ]]></command>
21 <inputs>
22 <param name='reads' type='data'
23 format='fastq,fastq.gz'
24 label='Long-read dataset' help='--reads' />
25 <param argument='--count' type='integer'
26 min='2' max='20'
27 value='12' label='Number of subsampled reads set to output'
28 help='The number of subsamples reads to make maximally-independent read subsets. The default is 12, a good number for most cases.' />
29 <conditional name='option'>
30 <param name='genome' type='select'
31 label='Provide an estimated genomoe size'
32 help='If you do not provide this, Trycycler subsample will run miniasm to quickly assemble your read set to get a size. This value is used to calculate read depths and does not need to be exact, e.g. 10% error is fine.' >
33 <option value='true'>Provide estimeted genome size</option>
34 <option value='false'>Run miniasm for estimating genome size</option>
35 </param>
36 <when value='false'/>
37 <when value='true'>
38 <param argument='--genome_size' type='integer'
39 min='10000' max='15000000'
40 value='30000' label='Estimated total genome size'
41 help='An estimate of the isolate total genome size.' />
42 </when>
43 </conditional>
44 <param argument='--min_read_depth' type='integer' min='15' max='120'
45 value='25'
46 label='Minimum subset read depth'
47 help='This is the minimum allowed read depth and also controls the subsampled depths. If is not provided, Trycycle decides what read depth each subset will be.' />
48 </inputs>
49 <outputs>
50 <collection name='subsamples_fastq' type='list'>
51 <discover_datasets pattern='__designation_and_ext__' format='fastq' directory='output_subsamples' />
52 </collection>
53 </outputs>
54 <tests>
55 <test>
56 <param name='reads' value='reads.fastq.gz'/>
57 <conditional name='option'>
58 <param name='genome' value='true'/>
59 <param name='genome_size' value='10000'/>
60 </conditional>
61 <param name='min_read_depth' value='20'/>
62 <param name='count' value='4'/>
63 <output_collection name='subsamples_fastq' type='list' count='4'>
64 <element name='sample_01' file='sample_01_01.fastq' ftype='fastq'/>
65 <element name='sample_02' file='sample_02_01.fastq' ftype='fastq'/>
66 <element name='sample_03' file='sample_03_01.fastq' ftype='fastq'/>
67 <element name='sample_04' file='sample_04_01.fastq' ftype='fastq'/>
68 </output_collection>
69 </test>
70 <test>
71 <param name='reads' value='reads.fastq.gz'/>
72 <conditional name='option'>
73 <param name='genome' value='true'/>
74 <param name='genome_size' value='10000'/>
75 </conditional>
76 <param name='min_read_depth' value='22'/>
77 <param name='count' value='6'/>
78 <output_collection name='subsamples_fastq' type='list' count='6'>
79 <element name='sample_01' file='sample_01_02.fastq' ftype='fastq'/>
80 <element name='sample_02' file='sample_02_02.fastq' ftype='fastq'/>
81 <element name='sample_03' file='sample_03_02.fastq' ftype='fastq'/>
82 <element name='sample_04' file='sample_04_02.fastq' ftype='fastq'/>
83 <element name='sample_05' file='sample_05_02.fastq' ftype='fastq'/>
84 <element name='sample_06' file='sample_06_02.fastq' ftype='fastq'/>
85 </output_collection>
86 </test>
87 <test>
88 <param name='reads' value='reads.fastq.gz'/>
89 <conditional name='option'>
90 <param name='genome' value='true'/>
91 <param name='genome_size' value='10000'/>
92 </conditional>
93 <param name='min_read_depth' value='25'/>
94 <param name='count' value='5'/>
95 <output_collection name='subsamples_fastq' type='list' count='5'>
96 <element name='sample_01' file='sample_01_03.fastq' ftype='fastq'/>
97 <element name='sample_02' file='sample_02_03.fastq' ftype='fastq'/>
98 <element name='sample_03' file='sample_03_03.fastq' ftype='fastq'/>
99 <element name='sample_04' file='sample_04_03.fastq' ftype='fastq'/>
100 <element name='sample_05' file='sample_05_03.fastq' ftype='fastq'/>
101 </output_collection>
102 </test>
103 <test>
104 <param name='reads' value='reads.fastq.gz'/>
105 <conditional name='option'>
106 <param name='genome' value='true'/>
107 <param name='genome_size' value='10000'/>
108 </conditional>
109 <param name='min_read_depth' value='30'/>
110 <param name='count' value='12'/>
111 <output_collection name='subsamples_fastq' type='list' count='12'>
112 <element name='sample_01' file='sample_01_04.fastq' ftype='fastq'/>
113 <element name='sample_02' file='sample_02_04.fastq' ftype='fastq'/>
114 <element name='sample_03' file='sample_03_04.fastq' ftype='fastq'/>
115 <element name='sample_04' file='sample_04_04.fastq' ftype='fastq'/>
116 <element name='sample_05' file='sample_05_04.fastq' ftype='fastq'/>
117 <element name='sample_06' file='sample_06_04.fastq' ftype='fastq'/>
118 <element name='sample_07' file='sample_07_04.fastq' ftype='fastq'/>
119 <element name='sample_08' file='sample_08_04.fastq' ftype='fastq'/>
120 <element name='sample_09' file='sample_09_04.fastq' ftype='fastq'/>
121 <element name='sample_10' file='sample_10_04.fastq' ftype='fastq'/>
122 <element name='sample_11' file='sample_11_04.fastq' ftype='fastq'/>
123 <element name='sample_12' file='sample_12_04.fastq' ftype='fastq'/>
124 </output_collection>
125 </test>
126 </tests>
127 <help><![CDATA[
128 .. class:: infomark
129
130 **Purpose**
131
132 The *Trycycler subsample* tool tries to make maximally-independent read subsets of an appropriate depth for your genome. The goal is to use each subsample for generating varios assemblies by using different assemblers. It will also be handy to know the approximate size of your genome. If you're assembling something novel (i.e. you don't know the genome size), you could do a quick initial assembly at this point to get an estimate.
133
134 ----
135
136 .. class:: infomark
137
138 **Input**
139
140 This tool requires a long-read dataset. Ideally your reads should have a coverage of at least 100x.
141
142
143 ----
144
145 .. class:: infomark
146
147 **Output**
148
149 The result is a number of subsampled read sets, whose number is determined by the *count* parameter.
150
151 ----
152
153 .. class:: infomark
154
155 @PIPELINE@
156 ]]></help>
157 <expand macro='citations'/>
158 </tool>