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

[GEN-973] Fix bed file-clinical file cross-validation #540

Merged
merged 4 commits into from
Nov 16, 2023
Merged

[GEN-973] Fix bed file-clinical file cross-validation #540

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
ab7e882
fix bed/clinical file validation
rxu17 Nov 16, 2023
667d48b
lint
rxu17 Nov 16, 2023
f48037e
lint clinical
rxu17 Nov 16, 2023
f9f3e42
update bed file case for msg formatting purposes
rxu17 Nov 16, 2023
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
40 changes: 30 additions & 10 deletions genie_registry/clinical.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1012,28 +1012,45 @@ def _get_dataframe(self, filePathList):

return clinicaldf

def _cross_validate_bed_files_exist(self, clinicaldf) -> tuple:
def _cross_validate_bed_files_exist(self, clinicaldf) -> list:
"""Check that a bed file exist per SEQ_ASSAY_ID value in clinical file"""
errors = ""
warnings = ""
missing_files = []
seq_assay_ids = clinicaldf["SEQ_ASSAY_ID"].unique().tolist()
exception_params = {"ignore_case": True, "allow_underscore": True}

# standardize and get unique seq assay ids before searching bed files
seq_assay_ids = set(
[
validate.standardize_string_for_validation(sq_id, **exception_params)
for sq_id in clinicaldf["SEQ_ASSAY_ID"].unique()
]
)

for seq_assay_id in seq_assay_ids:
bed_files = validate.parse_file_info_in_nested_list(
nested_list=self.ancillary_files,
search_str=f"{seq_assay_id}.bed", # type: ignore[arg-type]
ignore_case=True,
allow_underscore=True,
**exception_params,
)
if not bed_files["files"]:
missing_files.append(f"{seq_assay_id}.bed")
missing_files.append(f"{seq_assay_id.upper()}.bed")
return missing_files

def _cross_validate_bed_files_exist_message(self, missing_bed_files: list) -> tuple:
"""Gets the warning/error messages given the missing bed files list

if missing_files:
Args:
missing_bed_files (list): list of missing bed files

Returns:
tuple: error + warning
"""
errors = ""
warnings = ""
if missing_bed_files:
errors = (
"At least one SEQ_ASSAY_ID in your clinical file does not have an associated BED file. "
"Please update your file(s) to be consistent.\n"
f"Missing BED files: {', '.join(missing_files)}\n"
f"Missing BED files: {', '.join(missing_bed_files)}\n"
)
return errors, warnings

Expand Down Expand Up @@ -1087,7 +1104,10 @@ def _cross_validate(self, clinicaldf) -> tuple:
errors_assay, warnings_assay = self._cross_validate_assay_info_has_seq(
clinicaldf
)
errors_bed, warnings_bed = self._cross_validate_bed_files_exist(clinicaldf)
missing_bed_files = self._cross_validate_bed_files_exist(clinicaldf)
errors_bed, warnings_bed = self._cross_validate_bed_files_exist_message(
missing_bed_files
)

errors = errors_assay + errors_bed
warnings = warnings_assay + warnings_bed
Expand Down
135 changes: 90 additions & 45 deletions tests/test_clinical.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
from collections import Counter
import datetime
import json
from unittest import mock
Expand Down Expand Up @@ -1061,65 +1062,76 @@ def test__check_int_dead_consistency_inconsistent(inconsistent_df):
)


@pytest.mark.parametrize(
"test_clinical_df,test_ancillary_files,expected_error,expected_warning",
[
(
pd.DataFrame(
{"SEQ_ASSAY_ID": ["SAGE-1-1", "SAGE-SAGE-1", "SAGE-1", "SAGE-1"]}
def get_cross_validate_bed_files_test_cases():
return [
{
"name": "all_match",
"test_clinical_df": pd.DataFrame(
{
"SEQ_ASSAY_ID": [
"SAGE-1-1",
"SAGE-SAGE-1",
"SAGE-1",
"SAGE-1",
"SaGe-1",
]
}
),
[
"test_ancillary_files": [
[{"name": "SAGE-SAGE-1.bed", "path": ""}],
[{"name": "SAGE-1-1.bed", "path": ""}],
[{"name": "SAGE-1.bed", "path": ""}],
],
"",
"",
),
(
pd.DataFrame({"SEQ_ASSAY_ID": ["SAGE-1-1", "SAGE-1-2"]}),
[
"expected_missing_files": [],
},
{
"name": "partial_match",
"test_clinical_df": pd.DataFrame(
{"SEQ_ASSAY_ID": ["SAGE-1-1", "SAGE-1-2", "SaGe-1_1"]}
),
"test_ancillary_files": [
[{"name": "SAGE-SAGE-1.bed", "path": ""}],
[{"name": "SAGE-1-1.bed", "path": ""}],
[{"name": "SAGE-1.bed", "path": ""}],
],
"At least one SEQ_ASSAY_ID in your clinical file does not have an associated BED file. "
"Please update your file(s) to be consistent.\n"
"Missing BED files: SAGE-1-2.bed\n",
"",
),
(
pd.DataFrame({"SEQ_ASSAY_ID": ["SAGE-1-2", "SAGE-1-3"]}),
[
"expected_missing_files": ["SAGE-1-2.bed"],
},
{
"name": "no_match",
"test_clinical_df": pd.DataFrame(
{"SEQ_ASSAY_ID": ["SAGE-1-2", "SAGE-1-3", "SaGe_1_2"]}
),
"test_ancillary_files": [
[{"name": "SAGE-SAGE-1.bed", "path": ""}],
[{"name": "SAGE-1-1.bed", "path": ""}],
[{"name": "SAGE-1.bed", "path": ""}],
],
"At least one SEQ_ASSAY_ID in your clinical file does not have an associated BED file. "
"Please update your file(s) to be consistent.\n"
"Missing BED files: SAGE-1-2.bed, SAGE-1-3.bed\n",
"",
),
(
pd.DataFrame({"SEQ_ASSAY_ID": ["SAGE-1-2", "SAGE-1-3"]}),
[
"expected_missing_files": ["SAGE-1-2.bed", "SAGE-1-3.bed"],
},
{
"name": "no_bed_files",
"test_clinical_df": pd.DataFrame(
{"SEQ_ASSAY_ID": ["SAGE-1-2", "SAGE-1-3", "SAge-1_2"]}
),
"test_ancillary_files": [
[{"name": "SAGE-1.txt", "path": ""}],
],
"At least one SEQ_ASSAY_ID in your clinical file does not have an associated BED file. "
"Please update your file(s) to be consistent.\n"
"Missing BED files: SAGE-1-2.bed, SAGE-1-3.bed\n",
"",
),
],
ids=["all_match", "partial_match", "no_match", "no_bed_files"],
"expected_missing_files": ["SAGE-1-2.bed", "SAGE-1-3.bed"],
},
]


@pytest.mark.parametrize(
"test_cases", get_cross_validate_bed_files_test_cases(), ids=lambda x: x["name"]
)
def test_that_cross_validate_bed_files_exist_returns_correct_msgs(
clin_class, test_clinical_df, test_ancillary_files, expected_error, expected_warning
clin_class, test_cases
):
clin_class.ancillary_files = test_ancillary_files
errors, warnings = clin_class._cross_validate_bed_files_exist(test_clinical_df)
assert errors == expected_error
assert warnings == expected_warning
clin_class.ancillary_files = test_cases["test_ancillary_files"]
missing_files = clin_class._cross_validate_bed_files_exist(
test_cases["test_clinical_df"]
)
assert Counter(test_cases["expected_missing_files"]) == Counter(missing_files)


def test_that_cross_validate_bed_files_exist_calls_expected_methods(clin_class):
Expand All @@ -1138,29 +1150,62 @@ def test_that_cross_validate_bed_files_exist_calls_expected_methods(clin_class):
clin_class._cross_validate_bed_files_exist(test_clinical_df)
patch_parse_file_info.assert_called_once_with(
nested_list=clin_class.ancillary_files,
search_str="SAGE-SAGE-1.bed",
search_str="sage-sage-1.bed",
ignore_case=True,
allow_underscore=True,
)


@pytest.mark.parametrize(
"missing_files,expected_error,expected_warning",
[
(
[],
"",
"",
),
(
["test1.bed", "test2.bed"],
"At least one SEQ_ASSAY_ID in your clinical file does not have an associated BED file. "
"Please update your file(s) to be consistent.\n"
"Missing BED files: test1.bed, test2.bed\n",
"",
),
],
ids=["no_missing_files", "missing_files"],
)
def test_that_cross_validate_bed_files_exist_message_returns_correct_msgs(
clin_class, missing_files, expected_error, expected_warning
):
errors, warnings = clin_class._cross_validate_bed_files_exist_message(missing_files)
assert errors == expected_error
assert warnings == expected_warning


def test_that__cross_validate_calls_expected_methods(clin_class):
with mock.patch.object(
Clinical, "_cross_validate_assay_info_has_seq", return_value=("", "")
) as patch__cross_validate_assay, mock.patch.object(
Clinical, "_cross_validate_bed_files_exist", return_value=("", "")
) as patch__cross_validate_bed:
) as patch__cross_validate_bed, mock.patch.object(
Clinical, "_cross_validate_bed_files_exist_message", return_value=("", "")
) as patch__cross_validate_bed_msg:
clin_class._cross_validate(clinicaldf=pd.DataFrame({"something": [1]}))
patch__cross_validate_assay.assert_called_once()
patch__cross_validate_bed.assert_called_once()
patch__cross_validate_bed_msg.assert_called_once()


def test_that__cross_validate_returns_correct_format_for_errors_warnings(clin_class):
with mock.patch.object(
Clinical, "_cross_validate_assay_info_has_seq", return_value=("test1", "")
) as patch__cross_validate_assay, mock.patch.object(
Clinical, "_cross_validate_bed_files_exist", return_value=("test3\n", "")
) as patch__cross_validate_bed:
Clinical, "_cross_validate_bed_files_exist", return_value=["something_missing"]
) as patch__cross_validate_bed, mock.patch.object(
Clinical,
"_cross_validate_bed_files_exist_message",
return_value=("test3\n", ""),
) as patch__cross_validate_bed_msg:
errors, warnings = clin_class._cross_validate(
clinicaldf=pd.DataFrame({"something": [1]})
)
Expand Down
Loading