update methods

eva_submission/eload_ingestion.py

@@ -399,7 +399,9 @@ def _insert_new_supported_asm_from_ensembl(self, tax_id: int = None):
         tax_id = tax_id or self.taxonomy
         target_assembly = None
         try:
-            target_assembly = get_supported_asm_from_ensembl(tax_id)
+            target_assembly = get_supported_asm_from_ensembl(tax_id,
+                                                             private_config_xml_file=cfg['maven']['settings_file'],
+                                                             profile=cfg['maven']['environment'])
         except requests.exceptions.HTTPError as ex:
             # Ensembl throws HTTP 400 Error if it cannot resolve a tax ID
             if ex.errno == 400:

eva_submission/eload_preparation.py

@@ -2,6 +2,7 @@
 import os
 import shutil
 import requests
+from ebi_eva_common_pyutils.metadata_utils import get_metadata_connection_handle, ensure_taxonomy_is_in_evapro
 
 from retry import retry
 
@@ -151,6 +152,8 @@ def detect_metadata_attributes(self):
         taxonomy_id = eva_metadata.project.get('Tax ID')
         if taxonomy_id and (isinstance(taxonomy_id, int) or taxonomy_id.isdigit()):
             self.eload_cfg.set('submission', 'taxonomy_id', value=int(taxonomy_id))
+            with get_metadata_connection_handle(cfg['maven']['environment'], cfg['maven']['settings_file']) as pg_conn:
+                ensure_taxonomy_is_in_evapro(pg_conn, taxonomy_id)
             scientific_name = get_scientific_name_from_taxonomy(taxonomy_id,
                                                                 private_config_xml_file=cfg['maven']['settings_file'],
                                                                 profile=cfg['maven']['environment'])

eva_submission/vep_utils.py

@@ -9,8 +9,8 @@
 
 import pymongo
 import requests
-from ebi_eva_common_pyutils.ncbi_utils import get_ncbi_assembly_dicts_from_term, \
-    retrieve_species_scientific_name_from_tax_id_ncbi
+from ebi_eva_common_pyutils.ncbi_utils import get_ncbi_assembly_dicts_from_term
+from ebi_eva_common_pyutils.taxonomy.taxonomy import get_normalized_scientific_name
 from retry import retry
 
 from ebi_eva_common_pyutils.config import cfg
@@ -254,9 +254,9 @@ def recursive_nlst(ftp, root, pattern):
 
 @retry(tries=4, delay=2, backoff=1.2, jitter=(1, 3), logger=logger)
 def download_and_extract_vep_cache(ftp, vep_cache_file, taxonomy_id):
-    scientific_name = retrieve_species_scientific_name_from_tax_id_ncbi(taxonomy_id)
-    species_name = scientific_name.replace(' ', '_').lower()
-
+    species_name = get_normalized_scientific_name(taxonomy_id,
+                                                    private_config_xml_file=cfg['maven']['settings_file'],
+                                                    profile=cfg['maven']['environment'])
     tmp_dir = tempfile.TemporaryDirectory()
     destination = os.path.join(tmp_dir.name, f'{species_name}.tar.gz')
     with open(destination, 'wb+') as dest:

tests/test_eload_preparation.py

@@ -82,7 +82,9 @@ def test_detect_metadata_attributes(self):
         self.eload.eload_cfg.set('submission', 'metadata_spreadsheet', value=metadata)
         cfg.content['maven']['settings_file'] = None
         cfg.content['maven']['environment'] = None
-        with patch('eva_submission.eload_preparation.get_scientific_name_from_taxonomy') as m_sci_name:
+        with patch('eva_submission.eload_preparation.get_scientific_name_from_taxonomy') as m_sci_name, \
+            patch('eva_submission.eload_preparation.get_metadata_connection_handle', autospec=True), \
+            patch('eva_submission.eload_preparation.ensure_taxonomy_is_in_evapro'):
             m_sci_name.return_value = 'Homo sapiens'
             self.eload.detect_metadata_attributes()
 

tests/test_vep_utils.py

@@ -62,11 +62,13 @@ def fake_dir(path, callback):
         )
 
     def test_get_vep_versions_from_ensembl(self):
-        vep_version, cache_version = get_vep_and_vep_cache_version_from_ensembl('GCA_000827895.1')
-        self.assertEqual(vep_version, 110)
-        self.assertEqual(cache_version, 57)
-        assert os.path.exists(os.path.join(cfg['vep_cache_path'], 'thelohanellus_kitauei'))
-        assert os.listdir(os.path.join(cfg['vep_cache_path'], 'thelohanellus_kitauei')) == ['57_ASM82789v1']
+        with patch('eva_submission.vep_utils.get_normalized_scientific_name') as m_get_scf_name:
+            m_get_scf_name.return_value = 'thelohanellus_kitauei'
+            vep_version, cache_version = get_vep_and_vep_cache_version_from_ensembl('GCA_000827895.1')
+            self.assertEqual(vep_version, 110)
+            self.assertEqual(cache_version, 57)
+            assert os.path.exists(os.path.join(cfg['vep_cache_path'], 'thelohanellus_kitauei'))
+            assert os.listdir(os.path.join(cfg['vep_cache_path'], 'thelohanellus_kitauei')) == ['57_ASM82789v1']
 
     def test_get_vep_versions_from_ensembl_not_found(self):
         vep_version, cache_version = get_vep_and_vep_cache_version_from_ensembl('GCA_015220235.1')
@@ -120,7 +122,7 @@ def test_get_vep_versions(self):
                 get_vep_and_vep_cache_version('fake_mongo', 'fake_db', 'fake_assembly')
 
     def test_download_and_extract_vep_cache(self):
-        with patch('eva_submission.vep_utils.retrieve_species_scientific_name_from_tax_id_ncbi') as m_get_scf_name:
+        with patch('eva_submission.vep_utils.get_normalized_scientific_name') as m_get_scf_name:
             m_get_scf_name.return_value = 'whatever_species_name'
             download_and_extract_vep_cache(
                 get_ftp_connection('ftp.ensembl.org'),