Mercurial > repos > nml > refseq_masher

annotate contains.xml @ 0:26df66c32861 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
author nml
date Thu, 15 Feb 2018 13:59:31 -0500
parents
children 2c1cb37a3ffe
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
1 <tool id="refseq_masher_contains" name="RefSeq Masher Contains" version="0.1.1">
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
2 <description>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
3 Find NCBI RefSeq Genomes contained in your sequences
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
4 </description>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
5 <requirements>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
6 <requirement type="package" version="0.1.1">refseq_masher</requirement>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
7 </requirements>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
8 <command detect_errors="exit_code">
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
9 <![CDATA[
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
10
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
11 #import re
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
12
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
13 #if $input.type == 'fasta'
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
14 #set $input_files = '"{}"'.format($input.fasta.name)
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
15 ln -s "$input.fasta" $input_files &&
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
16 #elif $input.type == 'paired'
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
17 #set $_forward_ext = '.fastq.gz' if $re.match(r'.*\.gz$', $input.forward.name) else '.fastq'
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
18 #set $_forward = '"{}_1{}"'.format($re.sub(r'_[12]\..+$', '', $input.forward.name), $_forward_ext)
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
19 #set $_reverse_ext = '.fastq.gz' if $re.match(r'.*\.gz$', $input.reverse.name) else '.fastq'
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
20 #set $_reverse = '"{}_2{}"'.format($re.sub(r'_[12]\..+$', '', $input.reverse.name), $_reverse_ext)
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
21 #set $input_files = '{} {}'.format($_forward, $_reverse)
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
22 ln -s "$input.forward" $_forward &&
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
23 ln -s "$input.reverse" $_reverse &&
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
24 #elif $input.type == 'single'
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
25 #set $input_files = '"{}"'.format($input.single.name)
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
26 ln -s "$input.single" $input_files &&
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
27 #elif $input.type == 'paired_collection'
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
28 #set $_forward_ext = '.fastq.gz' if $re.match(r'.*\.gz$', str($input.paired_collection.forward)) else '.fastq'
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
29 #set $_forward = '"{}_1{}"'.format($input.paired_collection.name, $_forward_ext)
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
30 #set $_reverse_ext = '.fastq.gz' if $re.match(r'.*\.gz$', str($input.paired_collection.reverse)) else '.fastq'
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
31 #set $_reverse = '"{}_2{}"'.format($input.paired_collection.name, $_reverse_ext)
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
32 #set $input_files = '{} {}'.format($_forward, $_reverse)
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
33 ln -s "$input.paired_collection.forward" $_forward &&
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
34 ln -s "$input.paired_collection.reverse" $_reverse &&
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
35 #end if
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
36
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
37 refseq_masher
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
38 $adv.verbosity
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
39 contains
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
40 --output refseq_masher-contains.${adv.output_type}
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
41 --output-type $adv.output_type
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
42 --top-n-results $adv.top_n_results
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
43 --parallelism "\${GALAXY_SLOTS:-1}"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
44 --min-identity $adv.min_identity
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
45 --max-pvalue $adv.max_pvalue
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
46 $input_files
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
47
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
48 ]]>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
49 </command>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
50 <inputs>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
51 <conditional name="input">
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
52 <param name="type" type="select" label="Sequence input type">
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
53 <option value="fasta">FASTA</option>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
54 <option value="paired">Paired-end FASTQs</option>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
55 <option value="single">Single-end FASTQ</option>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
56 <option value="paired_collection">Paired-end FASTQ collection</option>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
57 </param>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
58 <when value="fasta">
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
59 <param name="fasta"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
60 type="data" format="fasta"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
61 optional="false"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
62 label="FASTA file"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
63 />
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
64 </when>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
65 <when value="paired">
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
66 <param name="forward"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
67 type="data" format="fastq,fastqsanger,fastqillumina,fastqsolexa"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
68 optional="false"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
69 label="Forward FASTQ file"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
70 help="Must have ASCII encoded quality scores"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
71 />
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
72 <param name="reverse"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
73 type="data" format="fastq,fastqsanger,fastqillumina,fastqsolexa"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
74 optional="false"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
75 label="Reverse FASTQ file"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
76 help="File format must match the Forward FASTQ file"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
77 />
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
78 </when>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
79 <when value="single">
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
80 <param name="single"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
81 type="data" format="fastq,fastqsanger,fastqillumina,fastqsolexa"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
82 optional="false"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
83 label="Single-end FASTQ file"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
84 />
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
85 </when>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
86 <when value="paired_collection">
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
87 <param name="paired_collection"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
88 type="data_collection" format="fastq,fastqsanger,fastqillumina,fastqsolexa,fastq.gz,txt"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
89 collection_type="paired"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
90 optional="false"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
91 label="Paired-end FASTQ collection"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
92 help=""
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
93 />
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
94 </when>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
95 </conditional>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
96 <section name="adv" title="Advanced Options" expanded="false">
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
97 <param name="top_n_results"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
98 type="integer"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
99 label="Top N matches to report (0 to report all)"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
100 min="0"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
101 value="0"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
102 optional="true"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
103 />
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
104 <param name="min_identity"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
105 type="float" value="0.9" min="0.0" max="1.0"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
106 label="Mash dist min. identity to report"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
107 optional="true"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
108 />
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
109 <param name="max_pvalue"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
110 type="float" value="0.01" min="0.0" max="1.0"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
111 label="Mash screen max. p-value to report"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
112 optional="true"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
113 />
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
114 <param name="output_type"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
115 type="select"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
116 label="Output type"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
117 multiple="false">
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
118 <option value="tab" selected="true">Tabular (tab-delimited values)</option>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
119 <option value="csv">CSV (Comma Separated Values)</option>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
120 </param>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
121 <param name="verbosity"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
122 type="select"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
123 label="Logging verbosity">
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
124 <option value="">Error messages only</option>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
125 <option value="-v">Show warning messages</option>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
126 <option value="-vv" selected="true">Show info messages</option>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
127 <option value="-vvv">Show debug messages</option>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
128 </param>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
129 </section>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
130 </inputs>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
131 <outputs>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
132 <data
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
133 name="output_path_csv"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
134 format="csv"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
135 label="RefSeq Masher contains table"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
136 from_work_dir="refseq_masher-contains.csv">
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
137 <filter>adv['output_type'] == 'csv'</filter>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
138 </data>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
139 <data
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
140 name="output_path_tab"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
141 format="tabular"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
142 label="RefSeq Masher contains table"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
143 from_work_dir="refseq_masher-contains.tab">
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
144 <filter>adv['output_type'] == 'tab'</filter>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
145 </data>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
146 </outputs>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
147 <tests>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
148 <test>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
149 <conditional name="input">
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
150 <param name="type" value="single"/>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
151 <param name="single" value="SRR1203042_1-head4000.fastq"/>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
152 </conditional>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
153 <section name="adv">
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
154 <param name="top_n_results" value="5"/>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
155 <param name="output_type" value="tab"/>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
156 <param name="min_identity" value="0.9"/>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
157 <param name="max_pvalue" value="0.01"/>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
158 </section>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
159 <output name="output_path_tab"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
160 value="SRR1203042_1-head4000-contains.tab"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
161 ftype="tabular"
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
162 lines_diff="0">
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
163 </output>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
164 </test>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
165 </tests>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
166 <help>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
167 <![CDATA[
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
168 RefSeq Masher - Containment
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
169 ===========================
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
170
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
171 Find what NCBI RefSeq genomes are contained within your sequence data using Mash_ with a Mash sketch database of 54,925 NCBI RefSeq Genomes.
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
172
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
173
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
174 Source code available on Github at https://github.com/phac-nml/refseq_masher
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
175
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
176
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
177 `contains` - find what NCBI RefSeq Genomes are contained in your input sequences
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
178 --------------------------------------------------------------------------------
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
179
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
180 If you have a metagenomic sample or maybe a sample with some contamination, you may be interested in seeing what's in your sample. You can do this with `refseq_masher contains <INPUT>`.::
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
181
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
182 Usage: refseq_masher contains [OPTIONS] INPUT...
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
183
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
184 Find the NCBI RefSeq genomes contained in your sequence files using Mash
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
185 Screen
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
186
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
187 Input is expected to be one or more FASTA/FASTQ files or one or more
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
188 directories containing FASTA/FASTQ files. Files can be Gzipped.
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
189
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
190 Options:
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
191 --mash-bin TEXT Mash binary path (default="mash")
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
192 -o, --output PATH Output file path (default="-"/stdout)
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
193 --output-type [tab|csv] Output file type (tab|csv)
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
194 -n, --top-n-results INTEGER Output top N results sorted by identity in
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
195 ascending order (default=0/all)
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
196 -i, --min-identity FLOAT Mash screen min identity to report
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
197 (default=0.9)
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
198 -v, --max-pvalue FLOAT Mash screen max p-value to report
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
199 (default=0.01)
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
200 -p, --parallelism INTEGER Mash screen parallelism; number of threads to
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
201 spawn (default=1)
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
202 -h, --help Show this message and exit.
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
203
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
204
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
205 Example - metagenomic a sample SAMEA1877340_
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
206 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
207
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
208 For this example, we're going to see what RefSeq genomes are contained within sample SAMEA1877340_ from BioProject PRJEB1775_.
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
209
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
210
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
211 Description from BioProject PRJEB1775_:
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
212
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
213 .. epigraph::
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
214
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
215 Design, Setting and Patients Forty-five samples were selected from a set of fecal specimens obtained from patients with diarrhea during the 2011 outbreak of STEC O104:H4 in Germany. Samples were chosen to represent STEC-positive patients with a range of clinical conditions and colony counts together with a small number of patients with other infections (Campylobacter jejnuni, Clostridium difficile and Salmonella enterica). Samples were subjected to high-throughput sequencing on the Illumina MiSeq and HiSeq 2500, followed by bioinformatics analysis.
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
216
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
217
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
218 We're going to download the FASTQ files for ERR260489_::
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
219
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
220 wget ftp://ftp.sra.ebi.ac.uk/vol1/fastq/ERR260/ERR260489/ERR260489_1.fastq.gz
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
221 wget ftp://ftp.sra.ebi.ac.uk/vol1/fastq/ERR260/ERR260489/ERR260489_2.fastq.gz
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
222
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
223
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
224 We're going to run `refseq_masher` against these FASTQ files::
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
225
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
226 refseq_masher -vv contains --top-n-results 50 -p 12 -o containment-ERR260489.tab ERR260489_1.fastq.gz ERR260489_2.fastq.gz
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
227
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
228 **Log**::
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
229
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
230 2018-01-29 10:59:25,849 INFO: Grouped 2 fastqs into 1 groups [in ...refseq_masher/refseq_masher/utils.py:174]
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
231 2018-01-29 10:59:25,849 INFO: Collected 0 FASTA inputs and 1 read sets [in ...refseq_masher/refseq_masher/utils.py:185]
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
232 2018-01-29 10:59:25,849 INFO: Running Mash Screen with NCBI RefSeq sketch database against sample "ERR260489" with inputs: ['../ERR260489_1.fastq.gz', '../ERR260489_2.fastq.gz'] [in ...refseq_masher/refseq_masher/mash/screen.py:44]
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
233 Loading ...refseq_masher/refseq_masher/data/RefSeqSketches.msh...
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
234 4669418 distinct hashes.
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
235 Streaming from 2 inputs...
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
236 Estimated distinct k-mers in pool: 206836855
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
237 Summing shared...
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
238 Computing coverage medians...
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
239 Writing output...
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
240 2018-01-29 11:00:19,665 INFO: Ran Mash Screen on all input. Merging NCBI taxonomic information into results output. [in ...refseq_masher/refseq_masher/cli.py:134]
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
241 2018-01-29 11:00:19,666 INFO: Fetching all taxonomy info for 23 unique NCBI Taxonomy UIDs [in ...refseq_masher/refseq_masher/taxonomy.py:35]
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
242 2018-01-29 11:00:19,669 INFO: Dropping columns with all NA values (ncol=32) [in ...refseq_masher/refseq_masher/taxonomy.py:38]
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
243 2018-01-29 11:00:19,671 INFO: Columns with all NA values dropped (ncol=12) [in ...refseq_masher/refseq_masher/taxonomy.py:40]
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
244 2018-01-29 11:00:19,671 INFO: Merging Mash results with relevant taxonomic information [in ...refseq_masher/refseq_masher/taxonomy.py:41]
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
245 2018-01-29 11:00:19,674 INFO: Merged Mash results with taxonomy info [in ...refseq_masher/refseq_masher/taxonomy.py:43]
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
246 2018-01-29 11:00:19,674 INFO: Merged taxonomic information into results output [in ...refseq_masher/refseq_masher/cli.py:136]
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
247 2018-01-29 11:00:19,674 INFO: Reordering output columns [in ...refseq_masher/refseq_masher/cli.py:137]
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
248 2018-01-29 11:00:19,677 INFO: Wrote output to "containment-ERR260489.tab" [in ...refseq_masher/refseq_masher/writers.py:20]
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
249
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
250
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
251
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
252 **Output**
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
253
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
254 +-----------+--------------------------------------+----------+----------------+----------------------+--------+--------------------------------------------------------------------------------------------------------------------------------------------------+-----------------------+------------------------------+------------------+--------------------+------------------+---------------------+-------------------+-------------------------+------------+---------+----------+------------+-----------+---------+---------------------+----------------------------------------------------------------------------------------------+--------------------------+----------------+
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
255 | sample | top_taxonomy_name | identity | shared_hashes | median_multiplicity | pvalue | full_taxonomy | taxonomic_subspecies | taxonomic_species | taxonomic_genus | taxonomic_family | taxonomic_order | taxonomic_class | taxonomic_phylum | taxonomic_superkingdom | subspecies | serovar | plasmid | bioproject | biosample | taxid | assembly_accession | match_id | taxonomic_species group | match_comment |
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
256 +===========+======================================+==========+================+======================+========+==================================================================================================================================================+=======================+==============================+==================+====================+==================+=====================+===================+=========================+============+=========+==========+============+===========+=========+=====================+==============================================================================================+==========================+================+
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
257 | ERR260489 | Bacteroides fragilis | 1.0 | 400/400 | 786 | 0.0 | Bacteria; FCB group; Bacteroidetes/Chlorobi group; Bacteroidetes; Bacteroidia; Bacteroidales; Bacteroidaceae; Bacteroides; fragilis | | Bacteroides fragilis | Bacteroides | Bacteroidaceae | Bacteroidales | Bacteroidia | Bacteroidetes | Bacteria | | | pLV22a | | | 817 | | ./rcn/refseq-NG-817-.-.-.-pLV22a-Bacteroides_fragilis.fna | | |
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
258 +-----------+--------------------------------------+----------+----------------+----------------------+--------+--------------------------------------------------------------------------------------------------------------------------------------------------+-----------------------+------------------------------+------------------+--------------------+------------------+---------------------+-------------------+-------------------------+------------+---------+----------+------------+-----------+---------+---------------------+----------------------------------------------------------------------------------------------+--------------------------+----------------+
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
259 | [1 row] | | | | | | | | | | | | | | | | | | | | | | | | |
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
260 +-----------+--------------------------------------+----------+----------------+----------------------+--------+--------------------------------------------------------------------------------------------------------------------------------------------------+-----------------------+------------------------------+------------------+--------------------+------------------+---------------------+-------------------+-------------------------+------------+---------+----------+------------+-----------+---------+---------------------+----------------------------------------------------------------------------------------------+--------------------------+----------------+
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
261 | ERR260489 | Escherichia coli O104:H4 str. E92/11 | 1.0 | 400/400 | 48 | 0.0 | Bacteria; Proteobacteria; Gammaproteobacteria; Enterobacterales; Enterobacteriaceae; Escherichia; coli; O104:H4; str. E92/11 | | Escherichia coli | Escherichia | Enterobacteriaceae | Enterobacterales | Gammaproteobacteria | Proteobacteria | Bacteria | | | pE9211p3 | | | 1090927 | NZ_AHAU | ./rcn/refseq-NZ-1090927-.-.-NZ_AHAU-pE9211p3-Escherichia_coli_O104_H4_str._E92_11.fna | | |
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
262 +-----------+--------------------------------------+----------+----------------+----------------------+--------+--------------------------------------------------------------------------------------------------------------------------------------------------+-----------------------+------------------------------+------------------+--------------------+------------------+---------------------+-------------------+-------------------------+------------+---------+----------+------------+-----------+---------+---------------------+----------------------------------------------------------------------------------------------+--------------------------+----------------+
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
263 | [3 rows] | | | | | | | | | | | | | | | | | | | | | | | | |
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
264 +-----------+--------------------------------------+----------+----------------+----------------------+--------+--------------------------------------------------------------------------------------------------------------------------------------------------+-----------------------+------------------------------+------------------+--------------------+------------------+---------------------+-------------------+-------------------------+------------+---------+----------+------------+-----------+---------+---------------------+----------------------------------------------------------------------------------------------+--------------------------+----------------+
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
265 | ERR260489 | Kingella kingae KKC2005004457 | 1.0 | 400/400 | 5 | 0.0 | Bacteria; Proteobacteria; Betaproteobacteria; Neisseriales; Neisseriaceae; Kingella; kingae; KKC2005004457 | | Kingella kingae | Kingella | Neisseriaceae | Neisseriales | Betaproteobacteria | Proteobacteria | Bacteria | | | unnamed | | | 1229911 | | ./rcn/refseq-NG-1229911-.-.-.-unnamed-Kingella_kingae_KKC2005004457.fna | | |
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
266 +-----------+--------------------------------------+----------+----------------+----------------------+--------+--------------------------------------------------------------------------------------------------------------------------------------------------+-----------------------+------------------------------+------------------+--------------------+------------------+---------------------+-------------------+-------------------------+------------+---------+----------+------------+-----------+---------+---------------------+----------------------------------------------------------------------------------------------+--------------------------+----------------+
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
267 | ERR260489 | Bacteroides cellulosilyticus WH2 | 0.99984 | 399/400 | 772 | 0.0 | Bacteria; FCB group; Bacteroidetes/Chlorobi group; Bacteroidetes; Bacteroidia; Bacteroidales; Bacteroidaceae; Bacteroides; cellulosilyticus; WH2 | | Bacteroides cellulosilyticus | Bacteroides | Bacteroidaceae | Bacteroidales | Bacteroidia | Bacteroidetes | Bacteria | | | pBWH2B | | | 1268240 | NZ_ATFI | ./rcn/refseq-NZ-1268240-.-.-NZ_ATFI-pBWH2B-Bacteroides_cellulosilyticus_WH2.fna | | |
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
268 +-----------+--------------------------------------+----------+----------------+----------------------+--------+--------------------------------------------------------------------------------------------------------------------------------------------------+-----------------------+------------------------------+------------------+--------------------+------------------+---------------------+-------------------+-------------------------+------------+---------+----------+------------+-----------+---------+---------------------+----------------------------------------------------------------------------------------------+--------------------------+----------------+
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
269 | [1 row] | | | | | | | | | | | | | | | | | | | | | | | | |
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
270 +-----------+--------------------------------------+----------+----------------+----------------------+--------+--------------------------------------------------------------------------------------------------------------------------------------------------+-----------------------+------------------------------+------------------+--------------------+------------------+---------------------+-------------------+-------------------------+------------+---------+----------+------------+-----------+---------+---------------------+----------------------------------------------------------------------------------------------+--------------------------+----------------+
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
271 | ERR260489 | Klebsiella pneumoniae | 0.99984 | 399/400 | 4 | 0.0 | Bacteria; Proteobacteria; Gammaproteobacteria; Enterobacterales; Enterobacteriaceae; Klebsiella; pneumoniae | | Klebsiella pneumoniae | Klebsiella | Enterobacteriaceae | Enterobacterales | Gammaproteobacteria | Proteobacteria | Bacteria | | | pMRC151 | | | 573 | | ./rcn/refseq-NG-573-.-.-.-pMRC151-Klebsiella_pneumoniae.fna | | |
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
272 +-----------+--------------------------------------+----------+----------------+----------------------+--------+--------------------------------------------------------------------------------------------------------------------------------------------------+-----------------------+------------------------------+------------------+--------------------+------------------+---------------------+-------------------+-------------------------+------------+---------+----------+------------+-----------+---------+---------------------+----------------------------------------------------------------------------------------------+--------------------------+----------------+
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
273 | [37 rows] | | | | | | | | | | | | | | | | | | | | | | | | |
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
274 +-----------+--------------------------------------+----------+----------------+----------------------+--------+--------------------------------------------------------------------------------------------------------------------------------------------------+-----------------------+------------------------------+------------------+--------------------+------------------+---------------------+-------------------+-------------------------+------------+---------+----------+------------+-----------+---------+---------------------+----------------------------------------------------------------------------------------------+--------------------------+----------------+
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
275
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
276 Some of the top genomes contained in this sample are sorted by identity and median multiplicity are:
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
277
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
278 - *Bacteroides fragilis* - fully contained (400/400) and high multiplicity (768)
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
279 - *Escherichia coli* O104:H4 - fully contained (400/400) and median multiplicity of 48
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
280 - *Kingella kingae* - fully contained (400/400) and median multiplicity of 5
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
281 - *Klebsiella pneumoniae* - 399/400 sketches contained with median multiplicity of 4
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
282
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
283 So with Mash we are able to find that the sample contained the expected genomic data (especially *E. coli* O104:H4).
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
284
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
285
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
286
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
287 Legal
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
288 -----
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
289
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
290 Copyright Government of Canada 2017
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
291
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
292 Written by: National Microbiology Laboratory, Public Health Agency of Canada
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
293
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
294 Licensed under the Apache License, Version 2.0 (the "License"); you may not use
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
295 this work except in compliance with the License. You may obtain a copy of the
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
296 License at:
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
297
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
298 http://www.apache.org/licenses/LICENSE-2.0
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
299
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
300 Unless required by applicable law or agreed to in writing, software distributed
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
301 under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
302 CONDITIONS OF ANY KIND, either express or implied. See the License for the
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
303 specific language governing permissions and limitations under the License.
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
304
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
305 Contact
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
306 -------
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
307
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
308 **Gary van Domselaar**: gary.vandomselaar@phac-aspc.gc.ca
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
309
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
310
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
311
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
312 .. _Mash: https://genomebiology.biomedcentral.com/articles/10.1186/s13059-016-0997-x
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
313 .. _SAMEA1877340: https://www.ebi.ac.uk/ena/data/view/SAMEA1877340
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
314 .. _PRJEB1775: https://www.ebi.ac.uk/ena/data/view/PRJEB1775
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
315 .. _ERR260489: https://www.ebi.ac.uk/ena/data/view/ERR260489&display=html
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
316
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
317 ]]>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
318 </help>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
319 <citations>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
320 <!-- Citation for Mash paper -->
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
321 <citation type="doi">10.1186/s13059-016-0997-x</citation>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
322 </citations>
26df66c32861 planemo upload commit 80c22275be05e29208e991019309dfffa9704f39
nml
parents:
diff changeset
323 </tool>