# HG changeset patch
# User sanbi-uwc
# Date 1587046019 0
# Node ID c401f63b3d124875dc1b11ee44776c94f5a9f047
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/data_managers/data_manager_fetch_refseq commit 120c6491f4b0888220e432693a9805d8198d7397"
diff -r 000000000000 -r c401f63b3d12 data_manager/fetch_artic_primers.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager/fetch_artic_primers.py Thu Apr 16 14:06:59 2020 +0000
@@ -0,0 +1,52 @@
+#!/usr/bin/env python
+
+from __future__ import print_function, division
+
+import argparse
+import json
+import os
+import os.path
+import sys
+
+import requests
+
+DATA_TABLE_NAME = 'artic_primers'
+def fetch_artic_primers(output_filename, output_directory, primers):
+ primer_sets = {
+ 'ARTICv1': 'https://raw.githubusercontent.com/artic-network/artic-ncov2019/master/primer_schemes/nCoV-2019/V1/nCoV-2019.bed',
+ 'ARTICv2': 'https://raw.githubusercontent.com/artic-network/artic-ncov2019/master/primer_schemes/nCoV-2019/V2/nCoV-2019.bed',
+ 'ARTICv3': 'https://raw.githubusercontent.com/artic-network/artic-ncov2019/master/primer_schemes/nCoV-2019/V3/nCoV-2019.bed'
+ }
+
+ if not os.path.isdir(output_directory):
+ os.makedirs(output_directory)
+ data_manager_dict = json.load(open(output_filename))
+ data_manager_dict['data_tables'] = data_manager_dict.get('data_tables', {})
+ data_manager_dict['data_tables'][DATA_TABLE_NAME] = data_manager_dict['data_tables'].get(DATA_TABLE_NAME, [])
+
+ data = []
+ for name, url in primer_sets.items():
+ response = requests.get(url)
+ if response.status_code != 200:
+ print('Error: download of', url, 'failed with code', response.status_code, file=sys.stderr)
+ exit(response.status_code)
+ bed_output_filename = os.path.join(output_directory, name + '.bed')
+ open(bed_output_filename, 'w').write(response.text)
+ description = name[:-2] + ' ' + name[-2:] + ' primer set'
+ data.append(dict(value=name, path=bed_output_filename, description=description))
+ data_manager_dict['data_tables'][DATA_TABLE_NAME].extend(data)
+ print(data_manager_dict)
+ json.dump(data_manager_dict, open(output_filename, 'w'))
+
+class SplitArgs(argparse.Action):
+ def __call__(self, parser, namespace, values, option_string=None):
+ setattr(namespace, self.dest, values.split(','))
+
+
+if __name__ == '__main__':
+ parser = argparse.ArgumentParser(description='Fetch ARTIC primer files for Galaxy use')
+ parser.add_argument('--output_directory', default='tmp', help='Directory to write output to')
+ parser.add_argument('--galaxy_datamanager_filename', help='Galaxy JSON format file describing data manager inputs')
+ parser.add_argument('--primers', default='ARTCIv1,ARTICv2,ARTICv3', action=SplitArgs, help='Comma separated list of primers to fetch')
+ args = parser.parse_args()
+ fetch_artic_primers(args.galaxy_datamanager_filename, args.output_directory, args.primers)
\ No newline at end of file
diff -r 000000000000 -r c401f63b3d12 data_manager/fetch_artic_primers.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager/fetch_artic_primers.xml Thu Apr 16 14:06:59 2020 +0000
@@ -0,0 +1,31 @@
+
+
+ python
+ requests
+
+
+
+ python '$__tool_directory__/fetch_artic_primers.py'
+ --galaxy_datamanager_filename '${output_file}'
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
\ No newline at end of file
diff -r 000000000000 -r c401f63b3d12 data_manager_conf.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/data_manager_conf.xml Thu Apr 16 14:06:59 2020 +0000
@@ -0,0 +1,19 @@
+
+
+
+
+
+
+
+
diff -r 000000000000 -r c401f63b3d12 test-data/artic.json
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/artic.json Thu Apr 16 14:06:59 2020 +0000
@@ -0,0 +1,21 @@
+{
+ "data_tables": {
+ "artic_primers": [
+ {
+ "value": "ARTICv1",
+ "description": "ARTIC v1 primer set",
+ "path": "tmp/ARTICv1.bed"
+ },
+ {
+ "value": "ARTICv2",
+ "description": "ARTIC v2 primer set",
+ "path": "tmp/ARTICv2.bed"
+ },
+ {
+ "value": "ARTICv3",
+ "description": "ARTIC v3 primer set",
+ "path": "tmp/ARTICv3.bed"
+ }
+ ]
+ }
+}
diff -r 000000000000 -r c401f63b3d12 tool-data/all_fasta.loc.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/all_fasta.loc.sample Thu Apr 16 14:06:59 2020 +0000
@@ -0,0 +1,18 @@
+#This file lists the locations and dbkeys of all the fasta files
+#under the "genome" directory (a directory that contains a directory
+#for each build). The script extract_fasta.py will generate the file
+#all_fasta.loc. This file has the format (white space characters are
+#TAB characters):
+#
+#
+#
+#So, all_fasta.loc could look something like this:
+#
+#apiMel3 apiMel3 Honeybee (Apis mellifera): apiMel3 /path/to/genome/apiMel3/apiMel3.fa
+#hg19canon hg19 Human (Homo sapiens): hg19 Canonical /path/to/genome/hg19/hg19canon.fa
+#hg19full hg19 Human (Homo sapiens): hg19 Full /path/to/genome/hg19/hg19full.fa
+#
+#Your all_fasta.loc file should contain an entry for each individual
+#fasta file. So there will be multiple fasta files for each build,
+#such as with hg19 above.
+#
diff -r 000000000000 -r c401f63b3d12 tool-data/artic_primers.loc.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/artic_primers.loc.sample Thu Apr 16 14:06:59 2020 +0000
@@ -0,0 +1,7 @@
+# this is a tab separated file describing the location of ARTIC primers for use in SARS-CoV-2 sequencing
+#
+# the columns are:
+# value description path
+#
+# for example
+# ARTICv1 ARTIC v1 primers /data/galaxy/tool_data/artic_primers/ARTICv1.bed
\ No newline at end of file
diff -r 000000000000 -r c401f63b3d12 tool_data_table_conf.xml.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.sample Thu Apr 16 14:06:59 2020 +0000
@@ -0,0 +1,7 @@
+
+
+
+ value, description, path
+
+
+
\ No newline at end of file