def test_parse_clnsig_():
## Test parsing classical clnsig representation
variant = {
'info_dict':{
'CLNACC': "RCV000014440.17|RCV000014441.25|RCV000014442.25|RCV000014443.17|RCV000184011.1|RCV000188658.1",
'CLNSIG': "5|5|5|5|5|5",
'CLNREVSTAT': "conf|single|single|single|conf|conf",
}
}
## WHEN parsing the clinical significance
clnsig_annotations = parse_clnsig(
acc=variant['info_dict']['CLNACC'],
sig=variant['info_dict']['CLNSIG'],
revstat=variant['info_dict']['CLNREVSTAT'],
transcripts=[]
)
## THEN assert that they where parsed correct
assert len(clnsig_annotations) == 6
for entry in clnsig_annotations:
if entry['accession'] == "RCV000014440.17":
assert entry['value'] == 5
assert entry['revstat'] == 'conf'
## Test parsing clnsig combination of values from different submitters:
variant = {
'info_dict':{
'CLNACC': "265359",
'CLNSIG': "Pathogenic/Likely pathogenic",
'CLNREVSTAT': "criteria_provided,_multiple_submitters,_no_conflicts",
}
}
clinrevstat = variant['info_dict']['CLNREVSTAT']
revstat_groups = [rev.lstrip('_') for rev in clinrevstat.split(',')]
clnsig_annotations = parse_clnsig(
acc=variant['info_dict']['CLNACC'],
sig=variant['info_dict']['CLNSIG'],
revstat=variant['info_dict']['CLNREVSTAT'],
transcripts=[]
)
## assert that they where parsed correct
assert len(clnsig_annotations) == 2
for entry in clnsig_annotations:
assert entry['accession'] == int(variant['info_dict']['CLNACC'])
assert entry['value'] in ['Pathogenic', 'Likely pathogenic']
assert entry['revstat'] == ', '.join(revstat_groups)
def test_parse_clnsig_():
## Test parsing classical clnsig representation
variant = {
'info_dict': {
'CLNACC':
"RCV000014440.17|RCV000014441.25|RCV000014442.25|RCV000014443.17|RCV000184011.1|RCV000188658.1",
'CLNSIG': "5|5|5|5|5|5",
'CLNREVSTAT': "conf|single|single|single|conf|conf",
}
}
## WHEN parsing the clinical significance
clnsig_annotations = parse_clnsig(
acc=variant['info_dict']['CLNACC'],
sig=variant['info_dict']['CLNSIG'],
revstat=variant['info_dict']['CLNREVSTAT'],
transcripts=[])
## THEN assert that they where parsed correct
assert len(clnsig_annotations) == 6
for entry in clnsig_annotations:
if entry['accession'] == "RCV000014440.17":
assert entry['value'] == 5
assert entry['revstat'] == 'conf'
## Test parsing clnsig combination of values from different submitters:
variant = {
'info_dict': {
'CLNACC': "265359",
'CLNSIG': "Pathogenic/Likely pathogenic",
'CLNREVSTAT':
"criteria_provided,_multiple_submitters,_no_conflicts",
}
}
clinrevstat = variant['info_dict']['CLNREVSTAT']
revstat_groups = [rev.lstrip('_') for rev in clinrevstat.split(',')]
clnsig_annotations = parse_clnsig(
acc=variant['info_dict']['CLNACC'],
sig=variant['info_dict']['CLNSIG'],
revstat=variant['info_dict']['CLNREVSTAT'],
transcripts=[])
## assert that they where parsed correct
assert len(clnsig_annotations) == 2
for entry in clnsig_annotations:
assert entry['accession'] == int(variant['info_dict']['CLNACC'])
assert entry['value'] in ['Pathogenic', 'Likely pathogenic']
assert entry['revstat'] == ', '.join(revstat_groups)
def test_parse_clnsig():
## GIVEN some clnsig information
variant = {
'info_dict': {
'CLNACC':
"RCV000014440.17|RCV000014441.25|RCV000014442.25|RCV000014443.17|RCV000184011.1|RCV000188658.1",
'CLNSIG': "5|5|5|5|5|5",
'CLNREVSTAT': "conf|single|single|single|conf|conf",
}
}
## WHEN parsing the clinical significance
clnsig_annotations = parse_clnsig(
acc=variant['info_dict']['CLNACC'],
sig=variant['info_dict']['CLNSIG'],
revstat=variant['info_dict']['CLNREVSTAT'],
transcripts=[])
## THEN assert that they where parsed correct
assert len(clnsig_annotations) == 6
for entry in clnsig_annotations:
if entry['accession'] == "RCV000014440.17":
assert entry['value'] == 5
assert entry['revstat'] == 'conf'
def test_parse_clnsig_transcripts(cyvcf2_variant):
## GIVEN a variant with classic clinvar annotations
transcripts = [{"clnsig": ["likely_benign"]}]
## WHEN parsing the annotations
clnsig_annotations = parse_clnsig(cyvcf2_variant, transcripts=transcripts)
## THEN assert that they where parsed correct
assert len(clnsig_annotations) == 1
assert clnsig_annotations[0]["value"] == "likely_benign"
def test_parse_complex_clnsig(cyvcf2_variant):
## GIVEN a variant with classic clinvar annotations
acc_nr = "265359"
clnsig = "Benign/Likely_benign,_other"
revstat = "criteria_provided,_multiple_submitters,_no_conflicts"
cyvcf2_variant.INFO["CLNACC"] = acc_nr
cyvcf2_variant.INFO["CLNSIG"] = clnsig
cyvcf2_variant.INFO["CLNREVSTAT"] = revstat
## WHEN parsing the annotations
clnsig_annotations = parse_clnsig(cyvcf2_variant)
## THEN assert that they where parsed correct
assert len(clnsig_annotations) == 3
def test_parse_clnsig_transcripts(cyvcf2_variant):
## GIVEN a variant with slash-separated values or values that start with underscore
transcripts = [{
"clnsig": [
"pathogenic/likely_pathogenic", "likely_pathogenic", "pathogenic",
"_other"
]
}]
## WHEN parsing the annotations
clnsig_annotations = parse_clnsig(cyvcf2_variant, transcripts=transcripts)
## THEN assert that they where parsed correct
assert len(clnsig_annotations) == 3
for clnsig in ["pathogenic", "likely_pathogenic", "other"]:
clnsig_dict = {"value": clnsig}
assert clnsig_dict in clnsig_annotations
def test_parse_classic_clnsig(cyvcf2_variant):
## GIVEN a variant with classic clinvar annotations
acc_nr = "RCV000014440.17|RCV000014441.25|RCV000014442.25|RCV000014443.17|RCV000184011.1|RCV000188658.1"
clnsig = "5|4|3|2|1|0"
revstat = "conf|single|single|single|conf|conf"
cyvcf2_variant.INFO["CLNACC"] = acc_nr
cyvcf2_variant.INFO["CLNSIG"] = clnsig
cyvcf2_variant.INFO["CLNREVSTAT"] = revstat
## WHEN parsing the annotations
clnsig_annotations = parse_clnsig(cyvcf2_variant)
## THEN assert that they where parsed correct
assert len(clnsig_annotations) == len(clnsig.split("|"))
## THEN assert that all accessions are there
assert {term["accession"]
for term in clnsig_annotations} == set(acc_nr.split("|"))
## THEN assert that all have been parsed as expected
for entry in clnsig_annotations:
if entry["accession"] == "RCV000014440.17":
assert entry["value"] == 5
assert entry["revstat"] == "conf"
if entry["accession"] == "RCV000014441.25":
assert entry["value"] == 4
assert entry["revstat"] == "single"
if entry["accession"] == "RCV000014442.25":
assert entry["value"] == 3
assert entry["revstat"] == "single"
if entry["accession"] == "RCV000014443.17":
assert entry["value"] == 2
assert entry["revstat"] == "single"
if entry["accession"] == "RCV000184011.1":
assert entry["value"] == 1
assert entry["revstat"] == "conf"
if entry["accession"] == "RCV000188658.1":
assert entry["value"] == 0
assert entry["revstat"] == "conf"
def test_parse_modern_clnsig_clnvid(cyvcf2_variant):
## GIVEN a variant with classic clinvar annotations
acc_nr = "10"
clnsig = "conflicting_interpretations_of_pathogenicity&_other"
revstat = "criteria_provided&_conflicting_interpretations"
cyvcf2_variant.INFO["CLNVID"] = acc_nr
cyvcf2_variant.INFO["CLNSIG"] = clnsig
cyvcf2_variant.INFO["CLNREVSTAT"] = revstat
## WHEN parsing the annotations
clnsig_annotations = parse_clnsig(cyvcf2_variant)
## THEN assert that the correct terms are parsed
assert set(["conflicting_interpretations_of_pathogenicity",
"other"]) == {term["value"]
for term in clnsig_annotations}
## THEN assert that they where parsed correct
assert len(clnsig_annotations) == 2
def test_parse_modern_clnsig(cyvcf2_variant):
## GIVEN a variant with classic clinvar annotations
acc_nr = "265359"
clnsig = "Pathogenic/Likely_pathogenic"
revstat = "criteria_provided,_multiple_submitters,_no_conflicts"
cyvcf2_variant.INFO["CLNACC"] = acc_nr
cyvcf2_variant.INFO["CLNSIG"] = clnsig
cyvcf2_variant.INFO["CLNREVSTAT"] = revstat
## WHEN parsing the annotations
clnsig_annotations = parse_clnsig(cyvcf2_variant)
## THEN assert that the correct terms are parsed
assert set(["pathogenic", "likely_pathogenic"
]) == {term["value"]
for term in clnsig_annotations}
## THEN assert that they where parsed correct
assert len(clnsig_annotations) == len(clnsig.split("/"))
def test_parse_clnsig_all(cyvcf2_variant):
## GIVEN a variant with classic clinvar annotations
acc_nr = "265359"
clnsig = "Pathogenic/Likely pathogenic"
revstat = "criteria_provided,_multiple_submitters,_no_conflicts"
cyvcf2_variant.INFO["CLNACC"] = acc_nr
cyvcf2_variant.INFO["CLNSIG"] = clnsig
cyvcf2_variant.INFO["CLNREVSTAT"] = revstat
revstat_groups = [rev.lstrip("_") for rev in revstat.split(",")]
clnsig_annotations = parse_clnsig(cyvcf2_variant)
## assert that they where parsed correct
assert len(clnsig_annotations) == 2
for entry in clnsig_annotations:
assert entry["accession"] == int(acc_nr)
assert entry["value"] in ["pathogenic", "likely_pathogenic"]
assert entry["revstat"] == ",".join(revstat_groups)
def test_parse_semi_modern_clnsig(cyvcf2_variant):
## GIVEN a variant with semi modern clinvar annotations
# This means that there can be spaces between words
acc_nr = "265359"
clnsig = "Pathogenic/Likely pathogenic"
revstat = "criteria_provided,_multiple_submitters,_no_conflicts"
cyvcf2_variant.INFO["CLNACC"] = acc_nr
cyvcf2_variant.INFO["CLNSIG"] = clnsig
cyvcf2_variant.INFO["CLNREVSTAT"] = revstat
## WHEN parsing the annotations
clnsig_annotations = parse_clnsig(cyvcf2_variant)
## THEN assert that the correct terms are parsed
assert set(["pathogenic", "likely_pathogenic"
]) == {term["value"]
for term in clnsig_annotations}
## THEN assert that they where parsed correct
assert len(clnsig_annotations) == len(clnsig.split("/"))
for annotation in clnsig_annotations:
assert annotation["accession"] == int(acc_nr)
assert set(annotation["revstat"].split(",")) == set(
["criteria_provided", "multiple_submitters", "no_conflicts"])
