Mercurial > repos > tduigou > save_to_db

comparison seq_to_db.xml @ 0:7ff266aecf01 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/brsynth/galaxytools/tree/main/tools commit 3401816c949b538bd9c67e61cbe92badff6a4007-dirty
author tduigou
date Wed, 11 Jun 2025 09:42:24 +0000
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:7ff266aecf01
1 <tool id="seq_to_db" name="Save Sequence Data In DB" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.09">
2 <description>Save fragment's sequence in an accessible database and import it from .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 </requirements>
12 <command detect_errors="exit_code"><![CDATA[
13 #set genbank_file_paths = ','.join([str(f) for f in $genbank_files])
14 #set $file_name_mapping = ",".join(["%s:%s" % (file.file_name, file.name) for file in $genbank_files])
15 python '$__tool_directory__/save_to_db.py'
16 --input '$genbank_file_paths'
17 --sequence_column '$sequence_column'
18 --annotation_column '$annotation_column'
19 --db_uri '$db_uri'
20 --table '$table'
21 --fragment_column '$fragment_column'
22 --output '$output'
23 --file_name_mapping '$file_name_mapping'
24 --json_conf '$json_conf'
25 ]]></command>
26 <inputs>
27 <param name="genbank_files" type="data_collection" collection_type="list" format="genbank" label="GenBank File(s)"/>
28 <param name="table" type="text" label="DB Table Name" optional="true" help="It can be extracted from JSON file -key:'JSON_table'-" />
29 <param name="sequence_column" type="text" label="DB Column Contains Sequence For ganbank File" optional="true" help="It can be extracted from JSON file -key:'JSON_sequence_column'-" />
30 <param name="annotation_column" type="text" label="DB Column Contains Annotation For Ganbank File" optional="true" help="It can be extracted from JSON file -key:'JSON_annotation_column'-" />
31 <param name="fragment_column" type="text" label="DB IDs Column Name" optional="true" help="It can be extracted from JSON file -key:'JSON_fragment_column'-" />
32 <param name="db_uri" type="text" label="DB Connection URI" help="postgresql://container_name:password@host:port/path/to/database (It can be extracted from JSON file -key:'JSON_db_uri'-)" optional="true" />
33 <section name='adv' title='Advance' expanded='false'>
34 <param name="json_conf" type="data" format='json' label="DB config as a json file" help="JSON file specifying the database URI, table name and the column names for annotation and sequence data" optional="true" />
35 </section>
36 </inputs>
37 <outputs>
38 <data name="output" format="txt" label="saving report" />
39 </outputs>
40 <tests>
41 <!--Only 1 test can be execute because the fragment will be already saved for the second test and it will return error as the fragments are present in the DB (execut ../get_db_data/testMock.py to regenerate initial DB)-->
42 <!--test tool blocking from JSON. It is commented because it should faild as it is a test to validate that the tool can be blocked from json file -->
43 <test>
44 <param name="genbank_files">
45 <collection type="list">
46 <element name="p7_L7Ae-Weiss" value="p7_L7Ae-Weiss.gb" />
47 <element name="p7_gfp_sequence" value="p6_Nt-IgKLsequence.gb" />
48 <element name="p14_CMVp" value="p6_Kozak-ATG.gb" />
49 <element name="p16_bGHpolyA" value="p4_Kt-L7Ae-Weiss.gb" />
50 <element name="p18_CMVp" value="HC_Amp_ccdB.gb" />
51 </collection>
52 </param>
53 <param name="adv|json_conf" value="test-JSON_arg_block.json" />
54 <output name="output" file="test_raport.txt" ftype="txt" >
55 <assert_contents>
56 <has_n_lines n="5" />
57 <has_line_matching expression="p7_L7Ae-Weiss" />
58 <has_line_matching expression="p6_Nt-IgKLsequence" />
59 <has_line_matching expression="p6_Kozak-ATG" />
60 <has_line_matching expression="p4_Kt-L7Ae-Weiss" />
61 <has_line_matching expression="HC_Amp_ccdB" />
62 </assert_contents>
63 </output>
64 </test>
65 <!--test DB config in the tool -->
66 <test>
67 <param name="genbank_files">
68 <collection type="list">
69 <element name="p7_L7Ae-Weiss" value="p7_L7Ae-Weiss.gb" />
70 <element name="p7_gfp_sequence" value="p6_Nt-IgKLsequence.gb" />
71 <element name="p14_CMVp" value="p6_Kozak-ATG.gb" />
72 <element name="p16_bGHpolyA" value="p4_Kt-L7Ae-Weiss.gb" />
73 <element name="p18_CMVp" value="HC_Amp_ccdB.gb" />
74 </collection>
75 </param>
76 <param name="table" value="sample" />
77 <param name="sequence_column" value="sequence" />
78 <param name="annotation_column" value="annotation" />
79 <param name="fragment_column" value="fragment" />
80 <param name="db_uri" value="postgresql://postgres:RK17@localhost:5432/test_fragments_db" />
81 <output name="output" file="test_raport.txt" ftype="txt" >
82 <assert_contents>
83 <has_n_lines n="5" />
84 <has_line_matching expression="p7_L7Ae-Weiss" />
85 <has_line_matching expression="p6_Nt-IgKLsequence" />
86 <has_line_matching expression="p6_Kozak-ATG" />
87 <has_line_matching expression="p4_Kt-L7Ae-Weiss" />
88 <has_line_matching expression="HC_Amp_ccdB" />
89 </assert_contents>
90 </output>
91 </test>
92 <!--test DB config from JSON. It is commented because the save can be done only on time then the fragment willl be in the DB and it will return a failure. to run the test comment the test above (one saving test in the run)-->
93 <test>
94 <param name="genbank_files">
95 <collection type="list">
96 <element name="p7_L7Ae-Weiss" value="p7_L7Ae-Weiss.gb" />
97 <element name="p7_gfp_sequence" value="p6_Nt-IgKLsequence.gb" />
98 <element name="p14_CMVp" value="p6_Kozak-ATG.gb" />
99 <element name="p16_bGHpolyA" value="p4_Kt-L7Ae-Weiss.gb" />
100 <element name="p18_CMVp" value="HC_Amp_ccdB.gb" />
101 </collection>
102 </param>
103 <param name="adv|json_conf" value="test-JSON_arg.json" />
104 <output name="output" file="test_raport.txt" ftype="txt" >
105 <assert_contents>
106 <has_n_lines n="5" />
107 <has_line_matching expression="p7_L7Ae-Weiss" />
108 <has_line_matching expression="p6_Nt-IgKLsequence" />
109 <has_line_matching expression="p6_Kozak-ATG" />
110 <has_line_matching expression="p4_Kt-L7Ae-Weiss" />
111 <has_line_matching expression="HC_Amp_ccdB" />
112 </assert_contents>
113 </output>
114 </test>
115 </tests>
116
117 <help><![CDATA[
118 Save Sequence Data In DB
119 ========================
120
121 Implemented a system to save GenBank (.gb) files in an accessible DB, based on a connection via URI requests.
122
123 **Parameters**:
124 ---------------
125 * **GenBank File(s)**: List of GenBaks files.
126 * **DB Table Name**: Name of the target table in the PostgreSQL database.
127 * **DB Column Contains Sequence For ganbank File**: Column storing sequence data, expected to start with "ORIGIN".
128 * **DB Column Contains Annotation For Ganbank File**: Column containing annotation data, to save al part before "ORIGIN" in the .gb file.
129 * **DB IDs Column Name**: Column holding the unique fragment IDs.
130 * **DB Connection URI**: URI used to connect to the database (e.g., postgresql://postgres:pass@localhost:5432/test_fragments_db).
131 * **DB config as a json file**: JSON file contains the DB configuration:
132 - "JSON_table": will be the key to the table name.
133 - "JSON_sequence_column": will be the key to the sequence column.
134 - "JSON_annotation_column": will be the key to the annotation column.
135 - "JSON_fragment_column": will be the key to the fragment column.
136 - "JSON_db_uri": will be the key to the URI.
137 - "execution": It is the key to execute or block the tool during a workflow ("True" or "False").
138 ]]></help>
139 <citations>
140 <citation type="bibtex">
141 @unpublished{seq_to_db
142 author = {Ramiz Khaled},
143 title = {{seq_to_db}},
144 url = {https://github.com/brsynth/},
145 }
146 </citation>
147 </citations>
148 </tool>