comparison kraken.xml @ 0:0f17a8816b28 draft

planemo upload for repository https://github.com/galaxyproject/tools-devteam/blob/master/tool_collections/kraken/kraken/ commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
author devteam
date Thu, 23 Jul 2015 10:55:44 -0400
parents
children 7b3ef9b4af80
comparison
equal deleted inserted replaced
-1:000000000000 0:0f17a8816b28
1 <?xml version="1.0"?>
2 <tool id="kraken" name="Kraken" version="1.1.0">
3 <description>
4 assign taxonomic labels to sequencing reads
5 </description>
6 <macros>
7 <import>macros.xml</import>
8 </macros>
9 <command>
10 <![CDATA[
11 @SET_DATABASE_PATH@ &&
12 kraken --threads \${GALAXY_SLOTS:-1} @INPUT_DATABASE@
13
14 #if $input_sequences.is_of_type( 'fastq' ):
15 --fastq-input
16 #else:
17 --fasta-input
18 #end if
19
20 ${only_classified_output}
21
22 #if str( $quick_operation.quick ) == "yes":
23 --quick
24 --min-hits ${quick_operation.min_hits}
25
26 #end if
27
28 "$input_sequences"
29
30 #if $split_reads:
31 --classified-out "${classified_out}" --unclassified-out "${unclassified_out}"
32 #end if
33 --output "${output}"
34 ##kraken-translate --db ${kraken_database.fields.name} "${output}" > "${translated}"
35 ]]>
36 </command>
37 <inputs>
38 <param format="fasta,fastq" label="Input sequences" name="input_sequences" type="data" help="FASTA or FASTQ datasets"/>
39 <param label="Output classified and unclassified reads?" name="split_reads" type="boolean" help="Sets --unclassified-out and --classified-out"/>
40
41 <conditional name="quick_operation">
42 <param name="quick" type="select" label="Enable quick operation?" help="--quick; Rather than searching all k-mers in a sequence, stop classification after a specified number of database hit">
43 <option value="yes">Yes</option>
44 <option selected="True" value="no">No</option>
45 </param>
46 <when value="yes">
47 <param name="min_hits" type="integer" value="1" label="Number of hits required for classification" help="--min-hits; min-hits will allow you to require multiple hits before declaring a sequence classified, which can be especially useful with custom databases when testing to see if sequences either do or do not belong to a particular genome; default=1"/>
48 </when>
49 <when value="no">
50 <!-- Do absolutely nothing -->
51 </when>
52 </conditional>
53
54 <param name="only_classified_output" type="boolean" checked="False" truevalue="--only-classified-output" falsevalue="" label="Print no Kraken output for unclassified sequences" help="--only-classified-output"/>
55
56 <expand macro="input_database" />
57 </inputs>
58 <outputs>
59 <data format="tabular" label="${tool.name} on ${on_string}: Classified reads" name="classified_out">
60 <filter>(split_reads)</filter>
61 </data>
62 <data format="tabular" label="${tool.name} on ${on_string}: Unclassified reads" name="unclassified_out">
63 <filter>(split_reads)</filter>
64 </data>
65 <data format="tabular" label="${tool.name} on ${on_string}: Classification" name="output" />
66 <!--<data format="tabular" label="${tool.name} on ${on_string}: Translated classification" name="translated" />-->
67 </outputs>
68 <help>
69 <![CDATA[
70 **What it does**
71
72 Kraken is a taxonomic sequence classifier that assigns taxonomic labels to short DNA reads. It does this by examining the k-mers within a read and querying a database with those k-mers. This database contains a mapping of every k-mer in Kraken's genomic library to the lowest common ancestor (LCA) in a taxonomic tree of all genomes that contain that k-mer. The set of LCA taxa that correspond to the k-mers in a read are then analyzed to create a single taxonomic label for the read; this label can be any of the nodes in the taxonomic tree. Kraken is designed to be rapid, sensitive, and highly precise.
73
74 -----
75
76 **Kraken options**
77
78 The Galaxy version of Kraken implements the following options::
79
80
81 --fasta-input Input is FASTA format
82 --fastq-input Input is FASTQ format
83 --quick Quick operation (use first hit or hits)
84 --min-hits NUM In quick op., number of hits req'd for classification
85 NOTE: this is ignored if --quick is not specified
86 --unclassified-out Print unclassified sequences to filename
87 --classified-out Print classified sequences to filename
88
89 --only-classified-output Print no Kraken output for unclassified sequences
90
91 ------
92
93 **Output Format**
94
95 Each sequence classified by Kraken results in a single line of output. Output lines contain five tab-delimited fields; from left to right, they are::
96
97 1. "C"/"U": one letter code indicating that the sequence was either classified or unclassified.
98 2. The sequence ID, obtained from the FASTA/FASTQ header.
99 3. The taxonomy ID Kraken used to label the sequence; this is 0 if the sequence is unclassified.
100 4. The length of the sequence in bp.
101 5. A space-delimited list indicating the LCA mapping of each k-mer in the sequence. For example, "562:13 561:4 A:31 0:1 562:3" would indicate that:
102 a) the first 13 k-mers mapped to taxonomy ID #562
103 b) the next 4 k-mers mapped to taxonomy ID #561
104 c) the next 31 k-mers contained an ambiguous nucleotide
105 d) the next k-mer was not in the database
106 e) the last 3 k-mers mapped to taxonomy ID #562
107 ]]>
108 </help>
109 <expand macro="requirements" />
110 <expand macro="stdio" />
111 <expand macro="version_command" />
112 <expand macro="citations" />
113 </tool>