Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

EVA-3365 Filter by taxonomy when exporting data to Tempmongo #411

Closed
wants to merge 1 commit into from
Closed

EVA-3365 Filter by taxonomy when exporting data to Tempmongo #411

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 8 additions & 8 deletions ...ion-release-automation/run_release_in_embassy/copy_accessioning_collections_to_embassy.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,11 +40,15 @@
"clusteredVariantOperationEntity": "inactiveObjects.asm"
}

submitted_collections_taxonomy_attribute_map = {
collections_taxonomy_attribute_map = {
"dbsnpSubmittedVariantEntity": "tax",
"dbsnpSubmittedVariantOperationEntity": "inactiveObjects.tax",
"submittedVariantEntity": "tax",
"submittedVariantOperationEntity": "inactiveObjects.tax"
"submittedVariantOperationEntity": "inactiveObjects.tax",
"dbsnpClusteredVariantEntity": "tax",
Copy link
Member

@sundarvenkata-EBI sundarvenkata-EBI Aug 22, 2023 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

In the release, we only care about SS being confined to a given taxonomy but NOT where its RS comes from. I don't think we should do this for Clustered collections because there can be RS from one taxonomy being assigned to SS in a different taxonomy.

"dbsnpClusteredVariantOperationEntity": "inactiveObjects.tax",
"clusteredVariantEntity": "tax",
"clusteredVariantOperationEntity": "inactiveObjects.tax"
}


Expand All @@ -62,12 +66,8 @@ def mongo_data_copy_to_remote_host(local_forwarded_port, private_config_xml_file

for collection, collection_assembly_attribute_name in sorted(collections_to_copy_map.items()):
logger.info("Begin processing collection: " + collection)
if "clustered" in collection.lower():
# Curly braces when they are not positional parameters
query = """'{{"{0}": {{"$in":["{1}"]}}}}'""".format(collection_assembly_attribute_name, assembly_accession)
else:
taxonomy_attribute_path = submitted_collections_taxonomy_attribute_map[collection]
query = """'{{"{0}": {{"$in":["{1}"]}}, "{2}": {{"$in":[{3}]}}}}'""".format(
taxonomy_attribute_path = collections_taxonomy_attribute_map[collection]
query = """'{{"{0}": {{"$in":["{1}"]}}, "{2}": {{"$in":[{3}]}}}}'""".format(
collection_assembly_attribute_name, assembly_accession, taxonomy_attribute_path, taxonomy_id)
sharded_db_name = "eva_accession_sharded"
mongodump_args = {"db": sharded_db_name, "host": mongo_host,
Expand Down
4 changes: 2 additions & 2 deletions eva-accession-release-automation/run_release_in_embassy/validate_rs_release_files.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -29,7 +29,7 @@
from run_release_in_embassy.release_common_utils import open_mongo_port_to_tempmongo, close_mongo_port_to_tempmongo, \
get_release_db_name_in_tempmongo_instance
from run_release_in_embassy.copy_accessioning_collections_to_embassy import collections_assembly_attribute_map, \
submitted_collections_taxonomy_attribute_map
collections_taxonomy_attribute_map
from pymongo import MongoClient

logger = logging.getLogger(__name__)
Expand Down Expand Up @@ -425,7 +425,7 @@ def export_unique_rs_ids_from_mongo(mongo_database_handle, taxonomy_id, assembly
collection_rs_ids_file = mongo_unique_rs_ids_file.replace(".txt", "_{0}.txt".format(collection))
agg_pipeline = []
for sve_coll in (sve_collection_name, dbsnp_sve_collection_name):
taxonomy_attribute_path = submitted_collections_taxonomy_attribute_map[sve_coll]
taxonomy_attribute_path = collections_taxonomy_attribute_map[sve_coll]
assembly_attribute_path = collections_assembly_attribute_map[sve_coll]
agg_pipeline.append({
"$lookup": {
Expand Down
Loading