|
0
|
1 <tool id="data_manager_malt_index_builder" name="MALT index builder" tool_type="manage_data" version="0.5.3+galaxy0" profile="21.01">
|
|
|
2 <description></description>
|
|
|
3 <requirements>
|
|
|
4 <requirement type="package" version="0.53">malt</requirement>
|
|
|
5 </requirements>
|
|
|
6 <command detect_errors="exit_code"><![CDATA[
|
|
|
7 python '$__tool_directory__/malt_index_builder.py'
|
|
|
8 '${out_file}'
|
|
|
9 --fasta_filename '${all_fasta_source.fields.path}'
|
|
|
10 --fasta_dbkey '${all_fasta_source.fields.dbkey}'
|
|
|
11 --fasta_description '${all_fasta_source.fields.name}'
|
|
|
12 --sequence_type '${sequence_type}'
|
|
|
13 #if str($seed_setting_cond.seed_setting) == 'yes':
|
|
|
14 --shapes '${seed_setting_cond.shapes}'
|
|
|
15 --max_hits_per_seed $seed_setting_cond.max_hits_per_seed
|
|
|
16 --protein_reduct '${seed_setting_cond.protein_reduct}'
|
|
|
17 #end if
|
|
|
18 ]]></command>
|
|
|
19 <inputs>
|
|
|
20 <param name="all_fasta_source" type="select" label="Source FASTA Sequence">
|
|
|
21 <options from_data_table="all_fasta"/>
|
|
|
22 </param>
|
|
|
23 <param name="sequence_name" type="text" value="" label="Name of sequence" />
|
|
|
24 <param name="sequence_id" type="text" value="" label="ID for sequence" />
|
|
|
25 <param name="sequence_type" type="select" label="Specify whether the reference sequences are DNA or Protein sequences" help="Use the DNA setting For RNA sequences">
|
|
|
26 <option value="DNA" selected="true">DNA</option>
|
|
|
27 <option value="Protein">Protein</option>
|
|
|
28 </param>
|
|
|
29 <conditional name="seed_setting_cond">
|
|
|
30 <param name="seed_setting" type="select" label="Specify seed settings?">
|
|
|
31 <option selected="true" value="no">No</option>
|
|
|
32 <option value="yes">Yes</option>
|
|
|
33 </param>
|
|
|
34 <when value="no"/>
|
|
|
35 <when value="yes">
|
|
|
36 <param name="shapes" type="text" value="" label="Comma-separated list of seed shapes" help="See help text below">
|
|
|
37 <sanitizer invalid_char="">
|
|
|
38 <valid initial="string.printable">
|
|
|
39 <remove value="'" />
|
|
|
40 </valid>
|
|
|
41 <mapping initial="none">
|
|
|
42 <add source="'" target="'"'"'" />
|
|
|
43 </mapping>
|
|
|
44 </sanitizer>
|
|
|
45 </param>
|
|
|
46 <param name="max_hits_per_seed" type="integer" value="1" min="1" label="Maximum number of hits per seed"/>
|
|
|
47 <param name="protein_reduct" type="select" label="Name or definition of protein alphabet reduction">
|
|
|
48 <option selected="true" value="DIAMOND_11">DIAMOND_11</option>
|
|
|
49 <option value="BLOSUM50_10">BLOSUM50_10</option>
|
|
|
50 <option value="BLOSUM50_11">BLOSUM50_11</option>
|
|
|
51 <option value="BLOSUM50_15">BLOSUM50_15</option>
|
|
|
52 <option value="BLOSUM50_4">BLOSUM50_4</option>
|
|
|
53 <option value="BLOSUM50_8">BLOSUM50_8</option>
|
|
|
54 <option value="GBMR4">GBMR4</option>
|
|
|
55 <option value="HSDM17">HSDM17</option>
|
|
|
56 <option value="MALT_10">MALT_10</option>
|
|
|
57 <option value="SDM12">SDM12</option>
|
|
|
58 <option value="UNREDUCED">UNREDUCED</option>
|
|
|
59 </param>
|
|
|
60 </when>
|
|
|
61 </conditional>
|
|
|
62 </inputs>
|
|
|
63 <outputs>
|
|
|
64 <data name="out_file" format="data_manager_json" />
|
|
|
65 </outputs>
|
|
|
66 <tests>
|
|
|
67 <test>
|
|
|
68 <param name="all_fasta_source" value="phiX174"/>
|
|
|
69 <output name="out_file" value="malt_index_builder.json"/>
|
|
|
70 </test>
|
|
|
71 </tests>
|
|
|
72 <help>
|
|
|
73 .. class:: infomark
|
|
|
74
|
|
|
75 **Notice:** Values for name, description, and id will be generated automatically if left blank.
|
|
|
76
|
|
|
77 **What it does**
|
|
|
78
|
|
|
79 Takes a reference sequence database (represented by a FastA file, possibly in gzip format) as input and produces an index that
|
|
|
80 can be used by the malt tool as input. If MALT is to be used as a taxonomic and/or functional analysis tool as well as an
|
|
|
81 alignment tool, then this MALT index builder tool must be provided with a number of mapping files that are used to map reference
|
|
|
82 sequences to taxonomic or functional classes or to locate genes in DNA reference sequences.
|
|
|
83
|
|
|
84 **Options**
|
|
|
85
|
|
|
86 * **Specify seed settings** - specify the settings for controlling how MALT uses its seed-and-extend approach based on “spaced seeds”.
|
|
|
87
|
|
|
88 * **Shapes** - specify the seed shapes used. For DNA sequences, the default seed shape is: 111110111011110110111111. For protein sequences, by default MALT uses the following four shapes: 111101101110111, 1111000101011001111, 11101001001000100101111 and 11101001000010100010100111.
|
|
|
89 * **Maximim hits per seed** - specify the maximum number of hits per seed - MALT uses this to calculate a maximum number of hits per hash value.
|
|
|
90 * **Protein reduction** - specify the alphabet reduction in the case of protein reference sequences. By default, MALT reduces amino acids to 8 different letters, grouped as follows: [LVIMC] [AG] [ST] [P] [FYW] [EDNQ] [KR] [H].
|
|
|
91 </help>
|
|
|
92 <citations>
|
|
|
93 <citation type="doi">https://doi.org/10.1101/050559</citation>
|
|
|
94 </citations>
|
|
|
95 </tool>
|
