Skip to content

small fixes for mutation of input data for filter_pmo_by_target_ids; #82

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

Open
nickjhathaway wants to merge 2 commits into
base: develop
Choose a base branch
from
Open

small fixes for mutation of input data for filter_pmo_by_target_ids; #82

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
374e14e
small fixes for mutation of input data for filter_pmo_by_target_ids;
nickjhathaway Jun 29, 2026
6ad954b
update the hashes because now reads_by_stage is now properly exported…
nickjhathaway Jun 29, 2026
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
19 changes: 11 additions & 8 deletions src/pmotools/pmo_engine/pmo_processor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -646,8 +646,6 @@ def filter_pmo_by_library_sample_ids(pmodata, library_sample_ids: set[int]):
if "targeted_genomes" in pmodata:
pmo_out["targeted_genomes"] = copy.deepcopy(pmodata["targeted_genomes"])

if "read_counts_by_stage" in pmodata:
pmo_out["read_counts_by_stage"] = []
# need to update read_counts_by_stage, library_sample_info, specimen_info, detected_microhaplotypes

# specimen_info
Expand Down Expand Up @@ -703,6 +701,7 @@ def filter_pmo_by_library_sample_ids(pmodata, library_sample_ids: set[int]):
pmo_out["detected_microhaplotypes"].append(new_detected_microhaplotypes)
# read_counts_by_stage
if "read_counts_by_stage" in pmodata:
pmo_out["read_counts_by_stage"] = []
for read_count in pmodata["read_counts_by_stage"]:
new_read_count = {
"read_counts_by_library_sample_by_stage": [],
Expand All @@ -725,6 +724,7 @@ def filter_pmo_by_library_sample_ids(pmodata, library_sample_ids: set[int]):
]["library_sample_id"] = library_id_index_key[
sample["library_sample_id"]
]
pmo_out["read_counts_by_stage"].append(new_read_count)
return pmo_out

@staticmethod
Expand Down Expand Up @@ -884,11 +884,12 @@ def filter_pmo_by_target_ids(pmodata, target_ids: set[int]):
pmo_out["representative_microhaplotypes"]["targets"]
)
# update new target_id index
microhap_info["target_id"] = target_info_index_key[
microhap_info_copy = copy.deepcopy(microhap_info)
microhap_info_copy["target_id"] = target_info_index_key[
microhap_info["target_id"]
]
pmo_out["representative_microhaplotypes"]["targets"].append(
copy.deepcopy(microhap_info)
microhap_info_copy
)
# representative_microhaplotypes
pmo_out["detected_microhaplotypes"] = []
Expand All @@ -908,10 +909,11 @@ def filter_pmo_by_target_ids(pmodata, target_ids: set[int]):
for target in sample["target_results"]:
if target["mhaps_target_id"] in mhaps_target_id_new_key:
# update with new mhaps_target_id id
target["mhaps_target_id"] = mhaps_target_id_new_key[
target_copy = copy.deepcopy(target)
target_copy["mhaps_target_id"] = mhaps_target_id_new_key[
target["mhaps_target_id"]
]
new_sample["target_results"].append(copy.deepcopy(target))
new_sample["target_results"].append(target_copy)
new_detected_microhaplotypes["library_samples"].append(new_sample)
pmo_out["detected_microhaplotypes"].append(new_detected_microhaplotypes)

Expand All @@ -938,11 +940,12 @@ def filter_pmo_by_target_ids(pmodata, target_ids: set[int]):
for target in sample["read_counts_for_targets"]:
if target["target_id"] in target_ids:
# update with new target_id index
target["target_id"] = target_info_index_key[
target_copy = copy.deepcopy(target)
target_copy["target_id"] = target_info_index_key[
target["target_id"]
]
new_samples["read_counts_for_targets"].append(
copy.deepcopy(target)
target_copy
)
new_read_counts_by_bioid[
"read_counts_by_library_sample_by_stage"
Expand Down
10 changes: 5 additions & 5 deletions tests/test_pmo_engine/test_pmo_processor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -358,7 +358,7 @@ def test_filter_pmo_by_library_sample_ids(self):
)
with open(output_fnp, "w") as f:
json.dump(pmo_data_select_targets, f)
self.assertEqual("4a2c7b9d84322cc43adf2b9f0c518244", md5sum_of_fnp(output_fnp))
self.assertEqual("36d5cb8a79962707374fae86ba1a6f90", md5sum_of_fnp(output_fnp))
# check pmo extracted against PMO schema
checker = PMOChecker(self.pmo_jsonschema_data)
checker.validate_pmo_json(pmo_data_select_targets)
Expand All @@ -374,7 +374,7 @@ def test_filter_pmo_by_library_sample_names(self):
)
with open(output_fnp, "w") as f:
json.dump(pmo_data_select_library_sample_names, f)
self.assertEqual("ffdaeb6b57ed9a5c51e56cfaa4621796", md5sum_of_fnp(output_fnp))
self.assertEqual("6bd4e6367a62f1eb3c73f481a5ae9013", md5sum_of_fnp(output_fnp))
# check pmo extracted against PMO schema
checker = PMOChecker(self.pmo_jsonschema_data)
checker.validate_pmo_json(pmo_data_select_library_sample_names)
Expand All @@ -388,7 +388,7 @@ def test_filter_pmo_by_specimen_ids(self):
)
with open(output_fnp, "w") as f:
json.dump(pmo_data_select_targets, f)
self.assertEqual("f3dd2e0aee9afa82336ff48475a3c69c", md5sum_of_fnp(output_fnp))
self.assertEqual("664de0f14180de852f3f5d8942454004", md5sum_of_fnp(output_fnp))
# check pmo extracted against PMO schema
checker = PMOChecker(self.pmo_jsonschema_data)
checker.validate_pmo_json(pmo_data_select_targets)
Expand All @@ -402,7 +402,7 @@ def test_filter_pmo_by_specimen_names(self):
)
with open(output_fnp, "w") as f:
json.dump(pmo_data_select_targets, f)
self.assertEqual("f3dd2e0aee9afa82336ff48475a3c69c", md5sum_of_fnp(output_fnp))
self.assertEqual("664de0f14180de852f3f5d8942454004", md5sum_of_fnp(output_fnp))
# check pmo extracted against PMO schema
checker = PMOChecker(self.pmo_jsonschema_data)
checker.validate_pmo_json(pmo_data_select_targets)
Expand All @@ -420,7 +420,7 @@ def test_extract_from_pmo_samples_with_meta_groupings(self):
with open(output_fnp, "w") as f:
json.dump(pmo_data_select_meta, f)

self.assertEqual("f0f67e399885824a7aa318ead8b3d09c", md5sum_of_fnp(output_fnp))
self.assertEqual("9deb0bccc0017593697190d45ae6c0a4", md5sum_of_fnp(output_fnp))
# check pmo extracted against PMO schema
checker = PMOChecker(self.pmo_jsonschema_data)
checker.validate_pmo_json(pmo_data_select_meta)
Expand Down
Loading