Mercurial > repos > tduigou > seq_from_db

comparison seq_form_db.xml @ 0:3dfba58f44f1 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/brsynth/galaxytools/tree/main/tools commit 3401816c949b538bd9c67e61cbe92badff6a4007-dirty
author tduigou
date Wed, 11 Jun 2025 13:35:34 +0000
parents
children 7680420caf9f
comparison
equal deleted inserted replaced
-1:000000000000 0:3dfba58f44f1
1 <tool id="seq_form_db" name="Get sequences Data From DB" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.09">
2 <description>Import fragment's data from an accessible DB and export it as .gb files</description>
3 <macros>
4 <token name="@VERSION_SUFFIX@">0</token>
5 <token name="@TOOL_VERSION@">0.1.0</token>
6 </macros>
7 <requirements>
8 <requirement type="package" version="2.2.3">pandas</requirement>
9 <requirement type="package" version="2.0.40">sqlalchemy</requirement>
10 <requirement type="package" version="2.9.9">psycopg2</requirement>
11 <requirement type="package" version="1.85">biopython</requirement>
12 </requirements>
13 <command detect_errors="exit_code"><![CDATA[
14 mkdir 'outdir' &&
15 python '$__tool_directory__/get_db_info.py'
16 --input '$input'
17 --sequence_column '$sequence_column'
18 --annotation_columns '$annotation_columns'
19 --db_uri '$db_uri'
20 --table '$table'
21 --fragment_column '$fragment_column'
22 --output 'outdir'
23 ]]></command>
24 <inputs>
25 <param name="input" type="data" format="csv" label="Input CSV File" />
26 <param name="table" type="text" label="DB Table Name" optional="false" />
27 <param name="sequence_column" type="text" label="DB Column Contains Sequence For ganbank File" optional="false" />
28 <param name="annotation_columns" type="text" label="DB Column Contains Annotation For Ganbank File" optional="false" />
29 <param name="fragment_column" type="text" label="DB IDs Column Name" optional="false" />
30 <param name="db_uri" type="text" label="DB Connection URI" help="postgresql://container_name:password@host:port/path/to/database" optional="false" />
31 </inputs>
32 <outputs>
33 <collection name="output_gb" type="list" label="GenBank Files collection" >
34 <discover_datasets pattern="(?P&lt;name&gt;.*).gb" format="genbank" directory="outdir" />
35 </collection>
36 </outputs>
37 <tests>
38 <!--python get_db_info.py -input 'test-data/test_input.csv' -sequence_column 'sequence' -annotation_column 'annotation' -db_uri 'postgresql://postgres:RK17@localhost:5432/test_fragments_db' -table 'sample' -fragment_column 'fragment' -output 'test-data/output'-->
39 <test>
40 <param name="input" value="2-step-golden_gate_plan.csv" />
41 <param name="table" value="sample" />
42 <param name="sequence_column" value="sequence" />
43 <param name="annotation_columns" value="annotation" />
44 <param name="fragment_column" value="fragment" />
45 <param name="db_uri" value="postgresql://postgres:RK17@localhost:5432/test_fragments_db" />
46 <output_collection name="output_gb" type="list" count="12">
47 <element name="part_A">
48 <assert_contents>
49 <has_n_lines min="10" />
50 </assert_contents>
51 </element>
52 <element name="part_B">
53 <assert_contents>
54 <has_n_lines min="10" />
55 </assert_contents>
56 </element>
57 <element name="part_C">
58 <assert_contents>
59 <has_n_lines min="10" />
60 </assert_contents>
61 </element>
62 <element name="part_D">
63 <assert_contents>
64 <has_n_lines min="10" />
65 </assert_contents>
66 </element>
67 <element name="part_E">
68 <assert_contents>
69 <has_n_lines min="10" />
70 </assert_contents>
71 </element>
72 <element name="part_F">
73 <assert_contents>
74 <has_n_lines min="10" />
75 </assert_contents>
76 </element>
77 <element name="part_G">
78 <assert_contents>
79 <has_n_lines min="10" />
80 </assert_contents>
81 </element>
82 <element name="part_H">
83 <assert_contents>
84 <has_n_lines min="10" />
85 </assert_contents>
86 </element>
87 <element name="part_I">
88 <assert_contents>
89 <has_n_lines min="10" />
90 </assert_contents>
91 </element>
92 <element name="part_J">
93 <assert_contents>
94 <has_n_lines min="10" />
95 </assert_contents>
96 </element>
97 <element name="part_K">
98 <assert_contents>
99 <has_n_lines min="10" />
100 </assert_contents>
101 </element>
102 <element name="part_L">
103 <assert_contents>
104 <has_n_lines min="10" />
105 </assert_contents>
106 </element>
107 </output_collection>
108 </test>
109 </tests>
110
111 <help><![CDATA[
112 Get sequences Data From DB
113 ==========================
114
115 Implemented a system to generate GenBank (.gb) files for ADN fragments in CSV input, based on data retrieved from an accessible database via URI requests.
116
117 **Parameters**:
118 ---------------
119 * **Input CSV File**: Assembly csv contains construct IDs in the first column and their corresponding fragments in the following columns. (Without Header)
120 * **DB Table Name**: Name of the target table in the database.
121 * **DB Column Contains Sequence For ganbank File**: Column storing sequence data, expected to start with "ORIGIN".
122 * **DB Column Contains Annotation For Ganbank File**: Column containing annotation data, starting with "FEATURES" and including "LOCUS" information. Other metadata is optional.
123 * **DB IDs Column Name**: Column holding the unique fragment IDs.
124 * **DB Connection URI**: URI used to connect to the database (e.g., postgresql://postgres:pass@localhost:5432/test_fragments_db).
125 ]]></help>
126 <citations>
127 <citation type="bibtex">
128 @unpublished{seq_form_db
129 author = {Ramiz Khaled},
130 title = {{seq_form_db}},
131 url = {https://github.com/brsynth/},
132 }
133 </citation>
134 </citations>
135 </tool>