Added project accession assertion to the RNAcentral script

EBI-Metagenomics · Dec 7, 2023 · f276acb · f276acb
1 parent 3a57072
commit f276acb
Showing 1 changed file with 4 additions and 1 deletion.
diff --git a/helpers/database-import-scripts/rnacentral/generate_rnacentral_json.py b/helpers/database-import-scripts/rnacentral/generate_rnacentral_json.py
@@ -415,7 +415,10 @@ def get_project_accession(biosample):
         study_index = col_names.index("secondary_study_accession")
         for e in elements[1:]:
             if not e == "":
-                projects.append(e.strip().split("\t")[study_index])
+                project_to_add = e.strip().split("\t")[study_index]
+                assert any(project_to_add.startswith(prefix) for prefix in
+                           ["SRP", "ERP", "DRP", "PR"]), "Incorrect project format: {}".format(project_to_add)
+                projects.append(project_to_add)
         return set(projects)
     else:
         logging.error("Error when requesting study accession for biosample {}".format(biosample))