def testCreatingAlreadyExistingGeneset(self):
"""
Testing that if we try to create an already created geneset
and annotations have not changed, fail gracefully.
"""
selected_go_term = self.go_terms[2]
geneset_response = load_to_tribe(
self.main_config_file, selected_go_term, self.tribe_token,
prefer_update=True)
self.assertEqual(geneset_response['title'],
'GO-BP-0000005:premier league')
self.assertEqual(geneset_response['tip_item_count'], 1)
# Do not change the annotations, just try to save to Tribe again
response = load_to_tribe(
self.main_config_file, selected_go_term, self.tribe_token,
prefer_update=True)
self.assertEqual(response['status_code'], 409)
self.assertEqual(
response['content'], 'There is already a geneset with the slug '
'"go0000005-h**o-sapiens" and annotations {\'A0A024R214\': []} '
'saved in Tribe. A new geneset has not been saved.')
def testCreateNewKEGGVersion(self):
"""
Test adding one gene to an existing KEGG set
"""
selected_kegg_term = self.kegg_sets[1]
geneset_response = load_to_tribe(self.main_config_file,
selected_kegg_term, self.tribe_token,
prefer_update=True)
self.assertEqual(
geneset_response['title'], 'KEGG-Pathway-hsa00020: Citrate cycle '
'(TCA cycle) - H**o sapiens (human)')
self.assertEqual(geneset_response['tip_item_count'], 10)
# Adding random gene 5432
selected_kegg_term['annotations'] = {
1431: [], 1737: [], 1738: [], 1743: [], 2271: [], 3417: [],
3418: [], 3419: [], 3420: [], 3421: [], 5432: []
}
version_response = load_to_tribe(self.main_config_file,
selected_kegg_term, self.tribe_token,
prefer_update=True)
self.assertEqual(len(version_response['annotations']), 11)
def testLoadGOToTribe(self):
geneset_response = load_to_tribe(self.main_config_file,
self.go_terms[0], self.tribe_token)
self.assertEqual(geneset_response['title'],
'GO-BP-0000006:la liga')
self.assertEqual(geneset_response['tip_item_count'], 3)
def testLoadKEGGToTribe(self):
geneset_response = load_to_tribe(self.main_config_file,
self.kegg_sets[0], self.tribe_token)
self.assertEqual(
geneset_response['title'], 'KEGG-Pathway-hsa00010: Glycolysis / '
'Gluconeogenesis - H**o sapiens (human)')
self.assertEqual(geneset_response['tip_item_count'], 10)
def testCreateNewDOVersion(self):
"""
Test adding one term and removing one term from an existing DO term
"""
selected_do_term = self.do_terms[1]
geneset_response = load_to_tribe(
self.main_config_file, selected_do_term, self.tribe_token,
prefer_update=True)
self.assertEqual(geneset_response['title'],
'DO-0014667:disease of metabolism')
self.assertEqual(geneset_response['tip_item_count'], 6)
# Remove gene 5468, add random gene 4321
selected_do_term['annotations'] = {
4160: [], 8431: [], 51738: [], 5443: [], 6492: [], 4321: []}
version_response = load_to_tribe(
self.main_config_file, selected_do_term, self.tribe_token,
prefer_update=True)
self.assertEqual(len(version_response['annotations']), 6)
def testCreateNewGOVersion(self):
"""
Test removing one gene from an existing GO term
"""
selected_go_term = self.go_terms[1]
geneset_response = load_to_tribe(
self.main_config_file, selected_go_term, self.tribe_token,
prefer_update=True)
self.assertEqual(geneset_response['title'],
'GO-BP-0000007:european team')
self.assertEqual(geneset_response['tip_item_count'], 4)
# Remove gene 'A0A024R1V6'
selected_go_term['annotations'] = {
'A0A024R214': [], 'A0A024QZP7': [], 'A0A024R216': []}
version_response = load_to_tribe(
self.main_config_file, selected_go_term, self.tribe_token,
prefer_update=True)
self.assertEqual(len(version_response['annotations']), 3)
def testLoadDOToTribe(self):
geneset_response = load_to_tribe(self.main_config_file,
self.do_terms[0], self.tribe_token)
self.assertEqual(geneset_response['title'], 'DO-374:nutrition disease')
self.assertEqual(geneset_response['tip_item_count'], 6)
def main(ini_file_path):
if not os.path.isfile(ini_file_path):
logger.error('Main INI configuration file not found in this path: ' +
ini_file_path)
sys.exit(1)
main_config_file = SafeConfigParser()
main_config_file.read(ini_file_path)
if not main_config_file.has_option('download_folder',
'BASE_DOWNLOAD_FOLDER'):
logger.error('Main configuration file must have a "download_folder" '
'section, which must contain a "BASE_DOWNLOAD_FOLDER" '
'parameter where download folders will be created for '
'each species. Common annotation files for all species'
' will also be saved here.')
sys.exit(1)
download_folder = main_config_file.get('download_folder',
'BASE_DOWNLOAD_FOLDER')
secrets_file = None
if main_config_file.has_option('main', 'SECRETS_FILE'):
secrets_file = main_config_file.get('main', 'SECRETS_FILE')
process_to = main_config_file.get('main', 'PROCESS_TO')
if main_config_file.has_option('Tribe parameters', 'TRIBE_PUBLIC'):
tribe_public = main_config_file.getboolean('Tribe parameters',
'TRIBE_PUBLIC')
else:
tribe_public = False
if main_config_file.has_option('Tribe parameters', 'PREFER_UPDATE'):
prefer_update = main_config_file.getboolean('Tribe parameters',
'PREFER_UPDATE')
else:
prefer_update = False
if main_config_file.has_option('Tribe parameters', 'TRIBE_URL'):
tribe_url = main_config_file.get('Tribe parameters', 'TRIBE_URL')
else:
tribe_url = False
species_dir = main_config_file.get('species files', 'SPECIES_DIR')
species_files = main_config_file.get('species files', 'SPECIES_FILES')
# Make a list of the locations of all species files:
species_files = [filename.strip() for filename in species_files.split(',')]
for species_file in species_files:
# Build full species_file path
species_file = os.path.join(species_dir, species_file)
all_org_genesets = process_all_organism_genesets(
species_file, download_folder, secrets_file)
if process_to == 'Tribe':
if not tribe_url:
logger.error('"Tribe parameters" section needs "TRIBE_URL" '
'option to be able to save to Tribe.')
sys.exit(1)
tribe_token, creator_username = get_oauth_token(
tribe_url, secrets_file)
if prefer_update:
genesets_to_save = get_all_changed_genesets(
species_file, all_org_genesets, tribe_token,
creator_username)
if genesets_to_save == []:
logger.info(
'Annotations have not changed in any gene sets'
' for species_file %s.', species_file)
else:
genesets_to_save = all_org_genesets
logger.info('Starting to save %s gene sets to Tribe',
len(genesets_to_save))
for geneset in genesets_to_save:
geneset['public'] = tribe_public
load_to_tribe(ini_file_path,
geneset,
tribe_token,
creator_username,
prefer_update=prefer_update)
logger.info('Finished saving gene sets to Tribe')
elif process_to == 'JSON file':
json_filepath = main_config_file.get('main', 'JSON_FILE')
with open(json_filepath, "w") as outfile:
json.dump(all_org_genesets, outfile, indent=2)