Mercurial > repos > iuc > data_manager_mmseqs2_database

comparison data_manager/data_manager_mmseqs2_download.xml @ 0:75cc3fb4c10f 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/data_managers/data_manager_mmseqs2_database commit 1400593429eb4e9c6e307df3621825a8b84a6fa7
author iuc
date Thu, 27 Mar 2025 14:37:32 +0000
parents
children 35885ec2e59b
comparison
equal deleted inserted replaced
-1:000000000000 0:75cc3fb4c10f
1 <tool id="data_manager_mmseqs2_download" name="Download MMseqs2 databases" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" tool_type="manage_data" profile="22.05">
2 <description></description>
3 <macros>
4 <token name="@TOOL_VERSION@">15.6f452</token>
5 <token name="@VERSION_SUFFIX@">0</token>
6 </macros>
7 <requirements>
8 <requirement type="package" version="@TOOL_VERSION@">mmseqs2</requirement>
9 </requirements>
10 <command detect_errors="exit_code"><![CDATA[
11 #set $database_name = str($database).split('/')[-1] if '/' in str($database) else str($database)
12
13 mkdir -p '$out_file.extra_files_path'/'$database_name' &&
14 mmseqs databases
15 '$database' '$out_file.extra_files_path'/'$database_name'/database
16 'tmp'
17 --threads "\${GALAXY_SLOTS:-1}" &&
18 cp '$dmjson' '$out_file'
19 ]]></command>
20 <configfiles>
21 <configfile name="dmjson"><![CDATA[
22 #from datetime import date
23 #set $database_name = str($database).split('/')[-1] if '/' in str($database) else str($database)
24 {
25 "data_tables":{
26 "mmseqs2_databases":[
27 {
28 "value": "${database}-@TOOL_VERSION@-#echo date.today().strftime('%d%m%Y')#",
29 "name": "${database} #echo date.today().strftime('%d%m%Y')#",
30 "type": "${db_type}",
31 "taxonomy": "${db_taxonomy}",
32 "path": "$database_name",
33 "version": "@TOOL_VERSION@"
34 }
35 ]
36 }
37 }]]>
38 </configfile>
39 </configfiles>
40 <inputs>
41 <conditional name="db_name">
42 <param argument="type" type="select" label="Type of Databases">
43 <option value="aminoacid">Aminoacid databases</option>
44 <option value="aminoacid_taxonomy">Aminoacid databases that can be used for taxonomy</option>
45 <option value="nucleotide">Nucleotide databases</option>
46 <option value="nucleotide_taxonomy">Nucleotide databases that can be used for taxonomy</option>
47 <option value="profile">Profile databases</option>
48 </param>
49 <when value="aminoacid">
50 <param name="db_type" value="aminoacid" type="hidden"/>
51 <param name="db_taxonomy" value="no" type="hidden"/>
52 <param name="database" type="select" label="MMseqs2 aminoacid databases">
53 <option value="UniRef100" selected="true">UniRef100</option>
54 <option value="UniRef90">UniRef90</option>
55 <option value="UniRef50">UniRef50</option>
56 <option value="UniProtKB">UniProtKB</option>
57 <option value="UniProtKB/TrEMBL">TrEMBL (UniProtKB)</option>
58 <option value="UniProtKB/Swiss-Prot">Swiss-Prot (UniProtKB)</option>
59 <option value="NR">NR (Non-redundant protein sequences from GenPept, Swissprot, PIR, PDF, PDB, and NCBI RefSeq)</option>
60 <option value="GTDB">GTDB (Genome Taxonomy Database)</option>
61 <option value="PDB">PDB (The Protein Data Bank)</option>
62 </param>
63 </when>
64 <when value="aminoacid_taxonomy">
65 <param name="db_type" value="aminoacid" type="hidden"/>
66 <param name="db_taxonomy" value="yes" type="hidden"/>
67 <param name="database" type="select" label="MMseqs2 aminoacid databases that can be used for taxonomy">
68 <option value="UniRef100" selected="true">UniRef100</option>
69 <option value="UniRef90">UniRef90</option>
70 <option value="UniRef50">UniRef50</option>
71 <option value="UniProtKB">UniProtKB</option>
72 <option value="UniProtKB/TrEMBL">TrEMBL (UniProtKB)</option>
73 <option value="UniProtKB/Swiss-Prot">Swiss-Prot (UniProtKB)</option>
74 <option value="NR">NR (Non-redundant protein sequences from GenPept, Swissprot, PIR, PDF, PDB, and NCBI RefSeq)</option>
75 <option value="GTDB">GTDB (Genome Taxonomy Database)</option>
76 </param>
77 </when>
78 <when value="nucleotide">
79 <param name="db_type" value="nucleotide" type="hidden"/>
80 <param name="db_taxonomy" value="no" type="hidden"/>
81 <param name="database" type="select" label="MMseqs2 nucleotide databases">
82 <option value="SILVA">SILVA</option>
83 <option value="Kalamari">Kalamari</option>
84 <option value="NT">NT (Partially non-redundant nucleotide sequences from all traditional divisions of GenBank, EMBL, and DDBJ excluding GSS, STS, PAT, EST, HTG, and WGS)</option>
85 <option value="Resfinder">Resfinder</option>
86 </param>
87 </when>
88 <when value="nucleotide_taxonomy">
89 <param name="db_type" value="nucleotide" type="hidden"/>
90 <param name="db_taxonomy" value="yes" type="hidden"/>
91 <param name="database" type="select" label="MMseqs2 nucleotide databases that can be used for taxonomy">
92 <option value="SILVA">SILVA</option>
93 <option value="Kalamari">Kalamari</option>
94 </param>
95 </when>
96 <when value="profile">
97 <param name="db_type" value="profile" type="hidden"/>
98 <param name="db_taxonomy" value="no" type="hidden"/>
99 <param name="database" type="select" label="MMseqs2 profile databases">
100 <option value="PDB70">PDB70 (PDB clustered to 70% sequence identity)</option>
101 <option value="Pfam-A.full">Pfam-A.full</option>
102 <option value="Pfam-A.seed">Pfam-A.seed</option>
103 <option value="Pfam-B">Pfam-B</option>
104 <option value="CDD">CDD (Conserved Domain Database)</option>
105 <option value="VOGDB">VOGDB (Virus Orthologous Groups)</option>
106 <option value="dbCAN2">dbCAN2 (database of carbohydrate-active enzymes)</option>
107 </param>
108 </when>
109 </conditional>
110 </inputs>
111 <outputs>
112 <data name="out_file" format="data_manager_json" label="${tool.name}"/>
113 </outputs>
114 <tests>
115 <test expect_num_outputs="1">
116 <conditional name="db_name">
117 <param name="type" value="nucleotide_taxonomy" />
118 <param name="db_type" value="nucleotide" />
119 <param name="db_taxonomy" value="yes" />
120 <param name="database" value="SILVA" />
121 </conditional>
122 <output name="out_file">
123 <assert_contents>
124 <has_text text='"mmseqs2_databases":'/>
125 <has_text text='"version": "15.6f452"'/>
126 <has_text_matching expression='"value": "SILVA-15.6f452-[0-9]{8}"'/>
127 <has_text_matching expression='"name": "SILVA [0-9]{8}"'/>
128 <has_text text='"type": "nucleotide"'/>
129 <has_text text='"taxonomy": "yes"'/>
130 <has_text text='"path": "SILVA"'/>
131 </assert_contents>
132 </output>
133 </test>
134 <test expect_num_outputs="1">
135 <conditional name="db_name">
136 <param name="type" value="aminoacid_taxonomy" />
137 <param name="db_type" value="aminoacid" />
138 <param name="db_taxonomy" value="yes" />
139 <param name="database" value="UniProtKB/Swiss-Prot" />
140 </conditional>
141 <output name="out_file">
142 <assert_contents>
143 <has_text text='"mmseqs2_databases":'/>
144 <has_text text='"version": "15.6f452"'/>
145 <has_text_matching expression='"value": "UniProtKB/Swiss-Prot-15.6f452-[0-9]{8}"'/>
146 <has_text_matching expression='"name": "UniProtKB/Swiss-Prot [0-9]{8}"'/>
147 <has_text text='"type": "aminoacid"'/>
148 <has_text text='"taxonomy": "yes"'/>
149 <has_text text='"path": "Swiss-Prot"'/>
150 </assert_contents>
151 </output>
152 </test>
153 </tests>
154 <help><![CDATA[
155 This tool downloads databases that can be used with MMseqs2.
156 ]]></help>
157 <citations>
158 <citation type="doi">10.1038/nbt.3988</citation>
159 </citations>
160 </tool>