Mercurial > repos > iuc > trycycler_partition

comparison trycycler_partition.xml @ 0:6a80be58a760 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/trycycler commit 9d7c4277b0f96aacd466f2d497e08edcca3fa238"
author iuc
date Thu, 11 Feb 2021 19:18:39 +0000
parents
children e5956fe0f881
comparison
equal deleted inserted replaced
-1:000000000000 0:6a80be58a760
1 <tool id='trycycler_partition' name='Trycycler partition' version='@TOOL_VERSION@' profile='21.01'>
2 <description>assign the reads to the clusters</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 'partitions'
11 #for $i in $input_cluster
12 #set $name = str($i.element_identifier)
13 #set $number = (str($name).split('_')[-1]).strip('.fasta')
14 #set $fullpath = '_'.join(['selected_cluster/cluster',str($number)])
15 mkdir -p $fullpath/ &&
16 ln -s '${i}' '$fullpath/2_all_seqs.fasta' &&
17 #end for
18 trycycler partition --cluster_dir 'selected_cluster'/cluster_*
19 --reads '$reads'
20 --min_aligned_len $min_aligned_len
21 --min_read_cov $min_read_cov
22 --threads \${GALAXY_SLOTS:-2} &&
23 #for $i in $input_cluster
24 #set $name = str($i.element_identifier)
25 #set $number = (str($name).split('_')[-1]).strip('.fasta')
26 #set $fullpath = '_'.join(['selected_cluster/cluster',str($number)])
27 mv '$fullpath/4_reads.fastq' 'partitions/partition_${number}.fastq' &&
28 #end for
29 echo 'bye!'
30 ]]></command>
31 <inputs>
32 <param name='input_cluster' type='data'
33 format='fasta' multiple='true' label='Cluster datasets'
34 help='Clustered contigs (multiple FASTA files)' />
35 <param name='reads' type='data'
36 format='fastq,fastq.gz' label='Long-read datasets'
37 help='Long reads (FASTQ format) used to generate the assemblies' />
38 <param argument='--min_aligned_len' type='integer' min='500' max='3500'
39 value='1000' label='Min bases aligned'
40 help='Reads with less than this many bases aligned (default = 1000) will be ignored.' />
41 <param argument='--min_read_cov' type='integer' min='0' max='100'
42 value='90' label='Min read length covered by alignments'
43 help='Reads with less than this percentage of their length covered by alignments (default = 90.0) will be ignored.' />
44 </inputs>
45 <outputs>
46 <collection name='partitions' type='list' label='${tool.name} on ${on_string}'>
47 <discover_datasets pattern='__designation_and_ext__' format='fastq' directory='partitions'/>
48 </collection>
49 </outputs>
50 <tests>
51 <test>
52 <param name='input_cluster' value='reconciled_cluster_01.fasta'/>
53 <param name='reads' value='reads.fastq.gz'/>
54 <param name='min_aligned_len' value='1000'/>
55 <param name='min_read_cov' value='90'/>
56 <output_collection name='partitions' type='list' count='1'>
57 <element name='partition_01' file='partition_01.fastq' ftype='fastq'/>
58 </output_collection>
59 </test>
60 <test>
61 <param name='input_cluster' value='reconciled_cluster_01.fasta'/>
62 <param name='reads' value='reads.fastq.gz'/>
63 <param name='min_aligned_len' value='1200'/>
64 <param name='min_read_cov' value='95'/>
65 <output_collection name='partitions' type='list' count='1'>
66 <element name='partition_01' file='partition_02.fastq' ftype='fastq'/>
67 </output_collection>
68 </test>
69 <test>
70 <param name='input_cluster' value='reconciled_cluster_01.fasta'/>
71 <param name='reads' value='reads.fastq.gz'/>
72 <param name='min_aligned_len' value='900'/>
73 <param name='min_read_cov' value='93'/>
74 <output_collection name='partitions' type='list' count='1'>
75 <element name='partition_01' file='partition_03.fastq' ftype='fastq'/>
76 </output_collection>
77 </test>
78 <test>
79 <param name='input_cluster' value='reconciled_cluster_01.fasta'/>
80 <param name='reads' value='reads.fastq.gz'/>
81 <param name='min_aligned_len' value='1000'/>
82 <param name='min_read_cov' value='90'/>
83 <output_collection name='partitions' type='list' count='1'>
84 <element name='partition_01' file='partition_04.fastq' ftype='fastq'/>
85 </output_collection>
86 </test>
87 </tests>
88 <help><![CDATA[
89
90 .. class:: infomark
91
92 **Purpose**
93
94 The *Trycycler partition* split the reads between the different clusters, i.e. each read will be assigned to whichever cluster it best aligns and saved into a file for that cluster. This step is run once for your entire genome (i.e. not on a per-cluster basis).
95
96 ----
97
98 .. class:: infomark
99
100 **Input**
101
102 This tool requires as input the set of clustered considered valuable, and the long-read dataset used previously.
103
104 ----
105
106 .. class:: infomark
107
108 **Output**
109
110 After **Trycycler partition** completes, if will generate a file per cluster, each of which contains its share of the total reads.
111
112
113 ----
114
115 .. class:: infomark
116
117 @PIPELINE@
118 ]]></help>
119 <expand macro='citations'/>
120 </tool>