Mercurial > repos > iuc > data_manager_malt_index_builder

comparison data_manager/malt_index_builder.xml @ 0:a0865793c152 draft default tip

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/data_managers/data_manager_malt_index_builder commit 710e56e0e522b0ed060dab2fecf05ed1c79c928f"
author iuc
date Wed, 17 Nov 2021 08:22:26 +0000
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:a0865793c152
1 <tool id="data_manager_malt_index_builder" name="MALT index builder" tool_type="manage_data" version="@TOOL_VERSION@+galaxy0" profile="21.01">
2 <description></description>
3 <requirements>
4 <requirement type="package" version="3.8">python</requirement>
5 <requirement type="package" version="0.53">malt</requirement>
6 </requirements>
7 <macros>
8 <token name="@TOOL_VERSION@">0.5.3</token>
9 </macros>
10 <command detect_errors="exit_code"><![CDATA[
11 python '$__tool_directory__/malt_index_builder.py'
12 '${out_file}'
13 --fasta_filename '${all_fasta_source.fields.path}'
14 --fasta_dbkey '${all_fasta_source.fields.dbkey}'
15 --fasta_description '${all_fasta_source.fields.name}'
16 --sequence_type '${sequence_type}'
17 #if str($protein_reduct_setting_cond.protein_reduct_setting) == 'yes':
18 --protein_reduct '${protein_reduct_setting_cond.protein_reduct}'
19 #end if
20 #if str($seed_setting_cond.seed_setting) == 'yes':
21 --shapes '${seed_setting_cond.shapes}'
22 ## malt-build requires a string here.
23 --max_hits_per_seed '${seed_setting_cond.max_hits_per_seed}'
24 #end if
25 ]]></command>
26 <inputs>
27 <param name="all_fasta_source" type="select" label="Source FASTA Sequence">
28 <options from_data_table="all_fasta"/>
29 </param>
30 <param name="sequence_name" type="text" value="" label="Name of sequence"/>
31 <param name="sequence_id" type="text" value="" label="ID for sequence"/>
32 <param name="sequence_type" type="select" label="Reference sequences type" help="Use the DNA setting For RNA sequences">
33 <option value="DNA" selected="true">DNA</option>
34 <option value="Protein">Protein</option>
35 </param>
36 <conditional name="protein_reduct_setting_cond">
37 <param name="protein_reduct_setting" type="select" label="Specify protein alphabet reduction?" help="Used only if the reference sequences are Protein sequences">
38 <option selected="true" value="no">No</option>
39 <option value="yes">Yes</option>
40 </param>
41 <when value="no"/>
42 <when value="yes">
43 <param name="protein_reduct" type="select" label="Name or definition of protein alphabet reduction">
44 <option selected="true" value="DIAMOND_11">DIAMOND_11</option>
45 <option value="BLOSUM50_10">BLOSUM50_10</option>
46 <option value="BLOSUM50_11">BLOSUM50_11</option>
47 <option value="BLOSUM50_15">BLOSUM50_15</option>
48 <option value="BLOSUM50_4">BLOSUM50_4</option>
49 <option value="BLOSUM50_8">BLOSUM50_8</option>
50 <option value="GBMR4">GBMR4</option>
51 <option value="HSDM17">HSDM17</option>
52 <option value="MALT_10">MALT_10</option>
53 <option value="SDM12">SDM12</option>
54 <option value="UNREDUCED">UNREDUCED</option>
55 </param>
56 </when>
57 </conditional>
58 <conditional name="seed_setting_cond">
59 <param name="seed_setting" type="select" label="Specify seed settings?">
60 <option selected="true" value="no">No</option>
61 <option value="yes">Yes</option>
62 </param>
63 <when value="no"/>
64 <when value="yes">
65 <param name="shapes" type="text" value="" label="Comma-separated list of seed shapes" help="See help text below">
66 <sanitizer invalid_char="">
67 <valid initial="string.printable">
68 <remove value="&apos;"/>
69 </valid>
70 <mapping initial="none">
71 <add source="&apos;" target="&apos;&quot;&apos;&quot;&apos;"/>
72 </mapping>
73 </sanitizer>
74 </param>
75 <param name="max_hits_per_seed" type="integer" value="1" min="1" label="Maximum number of hits per seed"/>
76 </when>
77 </conditional>
78 </inputs>
79 <outputs>
80 <data name="out_file" format="data_manager_json"/>
81 </outputs>
82 <tests>
83 <test>
84 <param name="all_fasta_source" value="phiX174"/>
85 <param name="sequence_name" value="Pretty name for phiX174"/>
86 <param name="sequence_id" value="phiX174-1"/>
87 <output name="out_file" value="malt_index_builder1.json"/>
88 </test>
89 <test>
90 <param name="all_fasta_source" value="phiX174"/>
91 <param name="sequence_name" value="Pretty name for phiX174"/>
92 <param name="sequence_id" value="phiX174-1"/>
93 <param name="seed_setting" value="yes"/>
94 <param name="shapes" value="111110111011110110111111"/>
95 <output name="out_file" value="malt_index_builder1.json"/>
96 </test>
97 <test>
98 <param name="all_fasta_source" value="phiX174"/>
99 <param name="sequence_name" value="Pretty name for phiX174"/>
100 <param name="sequence_id" value="phiX174-2"/>
101 <param name="sequence_type" value="Protein"/>
102 <param name="protein_reduct_setting" value="yes"/>
103 <param name="protein_reduct" value="BLOSUM50_10"/>
104 <output name="out_file" value="malt_index_builder2.json"/>
105 </test>
106 </tests>
107 <help>
108 .. class:: infomark
109
110 **Notice:** Values for Name and ID of sequence will be generated automatically if left blank.
111
112 **What it does**
113
114 Takes a reference sequence database (represented by a FastA file, possibly in gzip format) as input and produces an index that
115 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
116 alignment tool, then this MALT index builder tool must be provided with a number of mapping files that are used to map reference
117 sequences to taxonomic or functional classes or to locate genes in DNA reference sequences.
118
119 **Options**
120
121 * **Specify protein alphabet reduction** - specify the alphabet reduction in the case of protein reference sequences.
122 * **Specify seed settings** - specify the settings for controlling how MALT uses its seed-and-extend approach based on “spaced seeds”.
123
124 * **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.
125 * **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.
126
127 </help>
128 <citations>
129 <citation type="doi">https://doi.org/10.1101/050559</citation>
130 </citations>
131 </tool>