Mercurial > repos > iuc > data_manager_build_bracken_database

comparison data_manager/bracken_build_database.xml @ 6:a0f18c07696a 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/main/data_managers/data_manager_build_bracken_database commit a108f20aebc04574a8bd0a90b955064439a50852
author iuc
date Wed, 05 Nov 2025 13:31:43 +0000
parents cef566388a0f
children
comparison
equal deleted inserted replaced
5:cef566388a0f 6:a0f18c07696a
1 <?xml version="1.0"?>
2 <tool id="bracken_build_database" name="Bracken Database Builder" tool_type="manage_data" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@"> 1 <tool id="bracken_build_database" name="Bracken Database Builder" tool_type="manage_data" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
3 <description>bracken database builder</description> 2 <description>bracken database builder</description>
4 <macros> 3 <macros>
5 <token name="@TOOL_VERSION@">2.8</token> 4 <token name="@TOOL_VERSION@">3.1</token>
6 <token name="@VERSION_SUFFIX@">0</token> 5 <token name="@VERSION_SUFFIX@">0</token>
7 <token name="@PROFILE@">22.01</token> 6 <token name="@PROFILE@">24.0</token>
8 </macros> 7 </macros>
9 <requirements> 8 <requirements>
10 <requirement type="package" version="@TOOL_VERSION@">bracken</requirement> 9 <requirement type="package" version="@TOOL_VERSION@">bracken</requirement>
11 </requirements> 10 </requirements>
12 <command> 11 <command>
13 <![CDATA[ 12 <![CDATA[
14 #import os 13 #set $db_dir = $out_file.extra_files_path
15 #set db_dir = os.path.basename($kraken_db.fields.path) 14 mkdir '$db_dir' &&
16 15
17 mkdir '$db_dir' && 16 ## Create symlinks to the contents of the kraken database, since otherwise
18 ln -s '${kraken_db.fields.path}/*' '$db_dir/' && 17 ## the DM tool (ie bracken-build) would write to the kraken DB folder.
19 python '$__tool_directory__/bracken_build_database.py' 18 ##
20 '${out_file}' 19 ## These symlinks will be part of the final db_dir which will be moved
21 20 ## to the tool-data (except for some of the pre-exsting *mers.kraken
22 --threads \${GALAXY_SLOTS:-1} 21 ## and *mers.kmer_distrib which may be deleted -- depending on the
23 #if $check_prebuilt.prebuilt == "no" 22 ## choice of prebuilt).
24 --kraken-db '$db_dir' 23 ## Hence the final db_dir will have
25 --kmer-len ${check_prebuilt.kmer_len} 24 ## - either a created mers.kmer_distrib file or a symlink pointing to the kraken2 db source
26 #end if 25 ## - either a created mers.kraken file or a symlink pointing to the kraken2 db source
27 #if $check_prebuilt.prebuilt == "yes" 26 ## - and symlinks to the krakenDB
28 --kraken-db '${kraken_db.fields.path}' 27 ## Note that in the data table entry only the path to mers.kmer_distrib file is used
29 --prebuilt 28 ln -s '${kraken_db.fields.path}'/* '$db_dir/' &&
30 #end if 29
31 --read-len ${check_prebuilt.read_len} 30 #if $check_prebuilt.prebuilt == "no"
32 --database-name '${database_name}' 31 ## remove any other pre-existing bracken-build results
32 find '$db_dir' -maxdepth 1 -name "*mers*" -delete &&
33 bracken-build
34 -t "\${GALAXY_SLOTS:-1}"
35 -k $check_prebuilt.kmer_len
36 -l $check_prebuilt.read_len
37 -d '$db_dir/'
38 #else
39 if [ ! -e '$db_dir/database${check_prebuilt.read_len}mers.kmer_distrib' ]; then
40 >&2 echo "Have you chosen the correct k-mer length? file $db_dir/database${check_prebuilt.read_len}mers.kmer_distrib does not exist.";
41 exit 1;
42 fi
43 ## delete any other (links to) prebuilt bracken databases (except the one of the chosen read_len)
44 && find '$db_dir' -maxdepth 1 -name "*mers.kraken" -a \! -name "*${check_prebuilt.read_len}mers.kraken" -delete
45 && find '$db_dir' -maxdepth 1 -name "*mers.kmer_distrib" -a \! -name "*${check_prebuilt.read_len}mers.kmer_distrib" -delete
46 #end if
47 && cp '$dmjson' '$out_file'
33 ]]> 48 ]]>
34 </command> 49 </command>
50 <configfiles>
51 <configfile name="dmjson"><![CDATA[#slurp
52 #import uuid
53 #set $database_value = str(uuid.uuid4())
54 #set $db_dir = $out_file.extra_files_path
55
56 #if $database_name == ""
57 #if $check_prebuilt.prebuilt == "no"
58 #set $database_name = $kraken_db.fields.name + " (k-mer length = " + str($check_prebuilt.kmer_len) +", read length = " + str($check_prebuilt.read_len) + ")"
59 #else
60 #set $database_name = $kraken_db.fields.name + " (Prebuilt bracken DB with read length = " + str($check_prebuilt.read_len) + ")"
61 #end if
62 #end if
63 {
64 "data_tables":{
65 "bracken_databases":[
66 {
67 "value": "$database_value",
68 "name": "$database_name",
69 "path": "$db_dir/database${check_prebuilt.read_len}mers.kmer_distrib"
70 }
71 ]
72 }
73 }]]></configfile>
74 </configfiles>
35 <inputs> 75 <inputs>
36 <param name="kraken_db" type="select"> 76 <param name="kraken_db" type="select">
37 <options from_data_table="kraken2_databases"> 77 <options from_data_table="kraken2_databases">
38 <validator type="no_options" message="No Kraken2 databases are available" /> 78 <validator type="no_options" message="No Kraken2 databases are available" />
39 </options> 79 </options>
40 </param> 80 </param>
41 <conditional name="check_prebuilt"> 81 <conditional name="check_prebuilt">
42 <param name="prebuilt" type="select" label="Use Pre-built DB"> 82 <param name="prebuilt" type="select" label="Use Pre-built DB" help="Use existing pre-built DB. This only works for kraken DBs, that already contain additional bracken DBs. This is the case for DBs downloaded from https://benlangmead.github.io/aws-indexes/k2.">
43 <option value="no">No</option> 83 <option value="no">No</option>
44 <option value="yes">Yes</option> 84 <option value="yes">Yes</option>
45 </param> 85 </param>
46 <when value="no"> 86 <when value="no">
47 <param name="kmer_len" type="integer" min="8" max="256" value="35" label="K-mer length" /> 87 <param name="kmer_len" type="integer" min="8" max="256" value="35" label="K-mer length" help="The K-mer length of the bracken DB should be identical to the K-mer length used to build the kraken2 DB." />
48 <param name="read_len" type="integer" min="8" max="1000" value="100" label="Read length" /> 88 <param name="read_len" type="integer" min="8" max="1000" value="100" label="Read length" help="The read length of the bracken DB should be the same as the length of the reads to be analysis (one read in case of paired reads)." />
49 </when> 89 </when>
50 <when value="yes"> 90 <when value="yes">
51 <param name="read_len" type="select" label="Read length" > 91 <param name="read_len" type="select" label="Read length" help="The read length of the bracken DB should be the same as the length of the reads to be analysis (one read in case of paired reads). The prebuilt DBs where built using the same K-mer length as the kraken2 DB.">
52 <option value="50">50</option> 92 <option value="50">50</option>
53 <option value="75">75</option> 93 <option value="75">75</option>
54 <option value="100" selected="true">100</option> 94 <option value="100" selected="true">100</option>
55 <option value="150">150</option> 95 <option value="150">150</option>
56 <option value="200">200</option> 96 <option value="200">200</option>
57 <option value="250">250</option> 97 <option value="250">250</option>
58 <option value="300">300</option> 98 <option value="300">300</option>
59 </param> 99 </param>
60 </when> 100 </when>
61 </conditional> 101 </conditional>
62 <param name="database_name" type="text" label="Database Name" /> 102 <param name="database_name" type="text" label="Database Name" help="If left empty a name will be constructed from the name of the Kraken2 database suffixed by info on read and k-mer length. Otherwise please add a clear reference to the corresponding kraken2 DB the read length and kmer length to the name." />
63 </inputs> 103 </inputs>
64 <outputs> 104 <outputs>
65 <data name="out_file" format="data_manager_json" /> 105 <data name="out_file" format="data_manager_json" />
66 </outputs> 106 </outputs>
67 <tests> 107 <tests>
68 <test> 108 <test>
69 <param name="kraken_db" value="test_entry" /> 109 <param name="kraken_db" value="test_entry" />
70 <param name="database_name" value="database" /> 110 <param name="database_name" value="" />
111 <conditional name="check_prebuilt">
112 <param name="prebuilt" value="yes" />
113 <param name="read_len" value="100" />
114 </conditional>
71 <output name="out_file"> 115 <output name="out_file">
72 <assert_contents> 116 <assert_contents>
73 <has_text text="test_db/database100mers.kmer_distrib" /> 117 <has_text text="Prebuilt bracken DB with read length = 100" />
118 <has_text text="database100mers.kmer_distrib" />
119 </assert_contents>
120 </output>
121 </test>
122 <test>
123 <param name="kraken_db" value="test_entry" />
124 <param name="database_name" value="custom database name" />
125 <conditional name="check_prebuilt">
126 <param name="prebuilt" value="no" />
127 <param name="read_len" value="150" />
128 </conditional>
129 <output name="out_file">
130 <assert_contents>
131 <has_text text="custom database name" />
132 <has_text text="database150mers.kmer_distrib" />
74 </assert_contents> 133 </assert_contents>
75 </output> 134 </output>
76 </test> 135 </test>
77 </tests> 136 </tests>
78 <help> 137 <help>
138 A bracken DB can only be built as an addition to an existing kracken2 DB (see `Bracken docs`_).
139
140 .. _Bracken docs: https://github.com/jenniferlu717/Bracken?tab=readme-ov-file#step-1-generate-the-bracken-database-file-databasexmerskmer_distrib-1
141
142 ======================================
143 Using prebuilt DBs
144 ======================================
145
146 The prebuilt option does use existing bracken DBs, that are shipped with kraken2 DBs. This is the case for DBs downloaded from https://benlangmead.github.io/aws-indexes/k2.
147 All prebuilt databases contain a Kraken 2 database along with Bracken databases built for 50, 75, 100, 150, 200, 250 and 300 read lengths (referring to the length of the sequenced reads to be analysis using that database (one read in case of paired reads)).
148 In this case the data manager points to the same DB as the kracken2 DB.
149 Note the Kraken 2 / Bracken 16s DBs only contain the Bracken databases built for 100mers, 150mers, and 200mers.
150 **The prebuilt option must not be used for custom kraken2 DBs ! For this the bracken DB needs to be build.**
151
152 ======================================
153 Building new DBs
154 ======================================
155
156 Use the same K-mer length as the kraken2 DB and choose read lengths that are close to the read length of the analysis you want to perform (one read in case of paired reads).
79 </help> 157 </help>
80 <citations> 158 <citations>
81 <citation type="doi">10.7717/peerj-cs.104</citation> 159 <citation type="doi">10.7717/peerj-cs.104</citation>
82 </citations> 160 </citations>
83 </tool> 161 </tool>