def test_gene_info_with_variant_that_is_ref_v38(self) -> None:
"""Error when gene info has variant where variant allele is the ref allele"""
gene = "FAKE"
chromosome_v37 = "X"
chromosome_v38 = "chrX"
reference_haplotype_name = "*1"
drugs: FrozenSet[DrugInfo] = frozenset()
rs_id = "rs294924"
rs_id_to_ref_seq_difference_annotation = {
rs_id: Annotation("399483A>C", "399483C>A")
}
haplotypes = frozenset([
Haplotype("*3", "No Function",
frozenset([Variant("rs294924", "G")]))
])
rs_id_infos1 = frozenset([
RsIdInfo(rs_id, "A", "C", GeneCoordinate(chromosome_v37, 499593),
GeneCoordinate(chromosome_v38, 399483))
])
rs_id_infos2 = frozenset([
RsIdInfo(rs_id, "A", "G", GeneCoordinate(chromosome_v37, 499593),
GeneCoordinate(chromosome_v38, 399483))
])
GeneInfo(gene, reference_haplotype_name, haplotypes, rs_id_infos1,
drugs, rs_id_to_ref_seq_difference_annotation)
with self.assertRaises(ValueError):
GeneInfo(gene, reference_haplotype_name, haplotypes, rs_id_infos2,
drugs, rs_id_to_ref_seq_difference_annotation)
def test_genotype_reporter_non_empty_input_v37(self) -> None:
all_full_calls = frozenset({
FullCall(GeneCoordinate("1", 1), "C", None, None, ("C", "CAG"),
"DPYD", ("rs664",), "1A>C;1A>G", FullCallFilter.PASS, "1A>C;1A>G?", FullCallFilter.UNKNOWN),
FullCall(GeneCoordinate("1", 5), "A", GeneCoordinate("chr1", 25), "A", ("G", "C"),
"DPYD", (".",), "25A>C;25A>G", FullCallFilter.PASS, "25A>C;25A>G", FullCallFilter.PASS),
FullCall(GeneCoordinate("1", 15), "C", None, None, ("C", "CAG"),
"DPYD", ("rs536",), "35A>C;35A>G", FullCallFilter.PASS, "35A>C;35A>G?", FullCallFilter.UNKNOWN),
FullCall(GeneCoordinate("X", 15), "TT", GeneCoordinate("chrX", 40), "AA", ("TT", "TT"),
"GENE", ("rs23",), "REF_CALL", FullCallFilter.NO_CALL, "627AA>TT", FullCallFilter.INFERRED_PASS),
FullCall(GeneCoordinate("2", 154663), "T", GeneCoordinate("chr2", 40565464), "T", ("T", "T"),
"BRAF", ("rs154", "rs8839"), "REF_CALL", FullCallFilter.NO_CALL, "REF_CALL", FullCallFilter.NO_CALL),
FullCall(GeneCoordinate("15", 24113), "A", GeneCoordinate("chr15", 684633), "T", ("T", "T"),
".", ("rs462", "rs9820", "rs536"), "29482A>T", FullCallFilter.PASS, "REF_CALL", FullCallFilter.PASS),
})
pgx_analysis = PgxAnalysis(FullCallData(all_full_calls), {})
panel_id = "Panel_v0.2"
version = "V1"
result = GenotypeReporter.get_calls_tsv_text(pgx_analysis, panel_id, version, ReferenceAssembly.V37)
result_expected = (
"gene\tchromosome_v37\tposition_v37\tchromosome_v38\tposition_v38\tref_v37\tref_v38\tallele1\tallele2\t"
"rsid\tvariant_annotation_v37\tfilter_v37\tvariant_annotation_v38\tfilter_v38\tpanel_version\trepo_version\n"
"DPYD\t1\t1\tUNKNOWN\tUNKNOWN\tC\tUNKNOWN\tC\tCAG\trs664\t1A>C;1A>G\tPASS\t1A>C;1A>G?\tUNKNOWN\tPanel_v0.2\tV1\n"
"DPYD\t1\t5\tchr1\t25\tA\tA\tC\tG\t.\t25A>C;25A>G\tPASS\t25A>C;25A>G\tPASS\tPanel_v0.2\tV1\n"
"DPYD\t1\t15\tUNKNOWN\tUNKNOWN\tC\tUNKNOWN\tC\tCAG\trs536\t35A>C;35A>G\tPASS\t35A>C;35A>G?\tUNKNOWN\tPanel_v0.2\tV1\n"
"BRAF\t2\t154663\tchr2\t40565464\tT\tT\tT\tT\trs154;rs8839\tREF_CALL\tNO_CALL\tREF_CALL\tNO_CALL\tPanel_v0.2\tV1\n"
".\t15\t24113\tchr15\t684633\tA\tT\tT\tT\trs462;rs9820;rs536\t29482A>T\tPASS\tREF_CALL\tPASS\tPanel_v0.2\tV1\n"
"GENE\tX\t15\tchrX\t40\tTT\tAA\tTT\tTT\trs23\tREF_CALL\tNO_CALL\t627AA>TT\tINFERRED_PASS\tPanel_v0.2\tV1\n"
)
self.assertEqual(result_expected, result)
def test_gene_info_with_overlapping_rs_id_infos(self) -> None:
"""Error when gene info has rs id infos for which the relevant coordinates overlap"""
gene = "FAKE"
chromosome_v37 = "X"
chromosome_v38 = "chrX"
reference_haplotype_name = "*1"
haplotypes: FrozenSet[Haplotype] = frozenset()
drugs: FrozenSet[DrugInfo] = frozenset()
rs_id_to_ref_seq_difference_annotation: Dict[str, Annotation] = dict()
rs_id_info1 = RsIdInfo("rs294924", "A", "A",
GeneCoordinate(chromosome_v37, 499593),
GeneCoordinate(chromosome_v38, 399483))
rs_id_info2 = RsIdInfo("rs294927", "AA", "AA",
GeneCoordinate(chromosome_v37, 499592),
GeneCoordinate(chromosome_v38, 399482))
single_rs_id_info = frozenset([rs_id_info1])
overlapping_rs_id_infos = frozenset([rs_id_info1, rs_id_info2])
GeneInfo(gene, reference_haplotype_name, haplotypes, single_rs_id_info,
drugs, rs_id_to_ref_seq_difference_annotation)
with self.assertRaises(ValueError):
GeneInfo(gene, reference_haplotype_name, haplotypes,
overlapping_rs_id_infos, drugs,
rs_id_to_ref_seq_difference_annotation)
def test_get_covered_coordinates_multiple(self) -> None:
start_coordinate = GeneCoordinate("X", 17)
result = get_covered_coordinates(start_coordinate, "AGTA")
result_expected = {
GeneCoordinate("X", 17),
GeneCoordinate("X", 18),
GeneCoordinate("X", 19),
GeneCoordinate("X", 20),
}
self.assertEqual(result_expected, result)
def from_json(cls, data: Json, chromosome_v37: str, chromosome_v38: str) -> "RsIdInfo":
rs_id = str(data['rsid'])
reference_allele_v37 = str(data['referenceAlleleV37'])
reference_allele_v38 = str(data['referenceAlleleV38'])
start_coordinate_v37 = GeneCoordinate(chromosome_v37, int(data['positionV37']))
start_coordinate_v38 = GeneCoordinate(chromosome_v38, int(data['positionV38']))
info = RsIdInfo(
rs_id,
reference_allele_v37,
reference_allele_v38,
start_coordinate_v37,
start_coordinate_v38,
)
return info
def get_covered_coordinates(start_coordinate: GeneCoordinate,
allele: str) -> Set[GeneCoordinate]:
return {
GeneCoordinate(start_coordinate.chromosome,
start_coordinate.position + i)
for i in range(len(allele))
}
def __get_call_from_variants(cls, call_index: int, sample_r_id: str,
variants: Dict[str, Any]) -> SimpleCall:
chromosome = cls.__get_chromosome_from_variants(call_index, variants)
position = cls.__get_position_from_variants(call_index, variants)
gene_coordinate = GeneCoordinate(chromosome, position)
reference_allele = cls.__get_reference_allele_from_variants(
call_index, variants)
alleles = cls.__get_called_alleles_from_variants(
call_index, sample_r_id, variants)
gene = cls.__get_gene_from_variants(call_index, variants)
rs_ids = cls.__get_rs_ids_from_variants(call_index, variants)
if alleles == (reference_allele, reference_allele):
variant_annotation = REF_CALL_ANNOTATION_STRING
else:
variant_annotation = cls.__get_variant_annotation_from_variants(
call_index, variants)
call = SimpleCall(
gene_coordinate,
reference_allele,
alleles,
gene,
rs_ids,
variant_annotation,
SimpleCallFilter.PASS,
)
return call
def test_gene_info_with_rs_id_infos_for_different_chromosome(self) -> None:
"""Error when gene info has rs id infos for which the relevant coordinates have a different chromosome"""
gene = "FAKE"
chromosome_v37 = "X"
chromosome_v38 = "chrX"
reference_haplotype_name = "*1"
haplotypes: FrozenSet[Haplotype] = frozenset()
drugs: FrozenSet[DrugInfo] = frozenset()
rs_id_to_ref_seq_difference_annotation: Dict[str, Annotation] = dict()
other_chromosome_v37 = "1"
other_chromosome_v38 = "1"
rs_id_info1 = RsIdInfo("rs294924", "A", "A",
GeneCoordinate(chromosome_v37, 499593),
GeneCoordinate(chromosome_v38, 399483))
rs_id_info2 = RsIdInfo("rs294924", "A", "A",
GeneCoordinate(other_chromosome_v37, 499593),
GeneCoordinate(chromosome_v38, 399483))
rs_id_info3 = RsIdInfo("rs294924", "A", "A",
GeneCoordinate(chromosome_v37, 499593),
GeneCoordinate(other_chromosome_v38, 399483))
rs_id_info4 = RsIdInfo("rs294924", "A", "A",
GeneCoordinate(other_chromosome_v37, 499593),
GeneCoordinate(other_chromosome_v38, 399483))
GeneInfo(gene, reference_haplotype_name, haplotypes,
frozenset([rs_id_info1]), drugs,
rs_id_to_ref_seq_difference_annotation)
GeneInfo(gene, reference_haplotype_name, haplotypes,
frozenset([rs_id_info2]), drugs,
rs_id_to_ref_seq_difference_annotation)
GeneInfo(gene, reference_haplotype_name, haplotypes,
frozenset([rs_id_info3]), drugs,
rs_id_to_ref_seq_difference_annotation)
GeneInfo(gene, reference_haplotype_name, haplotypes,
frozenset([rs_id_info4]), drugs,
rs_id_to_ref_seq_difference_annotation)
with self.assertRaises(ValueError):
GeneInfo(gene, reference_haplotype_name, haplotypes,
frozenset([rs_id_info1, rs_id_info2]), drugs,
rs_id_to_ref_seq_difference_annotation)
with self.assertRaises(ValueError):
GeneInfo(gene, reference_haplotype_name, haplotypes,
frozenset([rs_id_info1, rs_id_info3]), drugs,
rs_id_to_ref_seq_difference_annotation)
with self.assertRaises(ValueError):
GeneInfo(
gene, reference_haplotype_name, haplotypes,
frozenset([rs_id_info1, rs_id_info2, rs_id_info3,
rs_id_info4]), drugs,
rs_id_to_ref_seq_difference_annotation)
def test_gene_info_with_overlapping_haplotype_names(self) -> None:
"""Error when haplotype name used multiple times for gene"""
gene = "FAKE"
chromosome_v37 = "X"
chromosome_v38 = "chrX"
reference_haplotype_name = "*1"
drugs: FrozenSet[DrugInfo] = frozenset()
rs_id_to_ref_seq_difference_annotation: Dict[str, Annotation] = dict()
variant1 = Variant("rs94982", "A")
variant2 = Variant("rs394934", "T")
rs_id_infos = frozenset([
RsIdInfo(variant1.rs_id, "C", "C",
GeneCoordinate(chromosome_v37, 4994545),
GeneCoordinate(chromosome_v38, 2993823)),
RsIdInfo(variant2.rs_id, "G", "G",
GeneCoordinate(chromosome_v37, 3993842),
GeneCoordinate(chromosome_v38, 2949923)),
])
haplotypes1 = frozenset([
Haplotype("*2", "No Function", frozenset([variant1])),
Haplotype("*4", "Partial Function", frozenset([variant1,
variant2])),
])
haplotypes2 = frozenset([
Haplotype("*2", "No Function", frozenset([variant1])),
Haplotype("*2", "Partial Function", frozenset([variant1,
variant2])),
])
GeneInfo(gene, reference_haplotype_name, haplotypes1, rs_id_infos,
drugs, rs_id_to_ref_seq_difference_annotation)
with self.assertRaises(ValueError):
GeneInfo(gene, reference_haplotype_name, haplotypes2, rs_id_infos,
drugs, rs_id_to_ref_seq_difference_annotation)
def test_gene_info_with_ref_seq_difference_without_annotation(
self) -> None:
"""Error when a ref seq difference does not have an annotation"""
gene = "FAKE"
chromosome_v37 = "X"
chromosome_v38 = "chrX"
reference_haplotype_name = "*1"
haplotypes: FrozenSet[Haplotype] = frozenset()
drugs: FrozenSet[DrugInfo] = frozenset()
rs_id_to_ref_seq_difference_annotation: Dict[str, Annotation] = dict()
empty_rs_id_infos: FrozenSet[RsIdInfo] = frozenset()
non_empty_rs_id_infos = frozenset([
RsIdInfo("rs294924", "A", "C",
GeneCoordinate(chromosome_v37, 499593),
GeneCoordinate(chromosome_v38, 399483))
])
GeneInfo(gene, reference_haplotype_name, haplotypes, empty_rs_id_infos,
drugs, rs_id_to_ref_seq_difference_annotation)
with self.assertRaises(ValueError):
GeneInfo(gene, reference_haplotype_name, haplotypes,
non_empty_rs_id_infos, drugs,
rs_id_to_ref_seq_difference_annotation)
def __get_relevant_coordinates(
cls, chromosome: str, position: int,
ref_allele: str) -> Tuple[GeneCoordinate, ...]:
return tuple(
GeneCoordinate(chromosome, position + i)
for i in range(len(ref_allele)))
def __get_example_panel(cls) -> Panel:
dpyd_two_a_variant = Variant("rs3918290", "T")
dpyd_two_b_variant = Variant("rs1801159", "C")
dpyd_three_variant = Variant("rs72549303", "TG")
fake_variant = Variant("rs1212125", "C")
fake2_variant = Variant("rs1212127", "C")
dpyd_haplotypes = frozenset({
Haplotype("*2A", "No Function", frozenset({dpyd_two_a_variant})),
Haplotype("*2B", "No Function", frozenset({dpyd_two_a_variant, dpyd_two_b_variant})),
Haplotype("*3", "Normal Function", frozenset({dpyd_three_variant})),
})
dpyd_rs_id_infos = frozenset({
RsIdInfo("rs3918290", "C", "C", GeneCoordinate("1", 97915614), GeneCoordinate("chr1", 97450058)),
RsIdInfo("rs72549309", "GATGA", "GATGA", GeneCoordinate("1", 98205966), GeneCoordinate("chr1", 97740410)),
RsIdInfo("rs1801159", "T", "T", GeneCoordinate("1", 97981395), GeneCoordinate("chr1", 97515839)),
RsIdInfo("rs72549303", "TG", "TC", GeneCoordinate("1", 97915621), GeneCoordinate("chr1", 97450065)),
})
dpyd_drugs = frozenset({
DrugInfo("5-Fluorouracil", "https://www.pharmgkb.org/chemical/PA128406956/guidelineAnnotation/PA166104939"),
DrugInfo("Capecitabine", "https://www.pharmgkb.org/chemical/PA448771/guidelineAnnotation/PA166104963"),
})
dpyd_rs_id_to_difference_annotations = {
"rs72549303": Annotation("6744CA>GA", "6744GA>CA"),
}
fake_haplotypes = frozenset({
Haplotype("*4A", "Reduced Function", frozenset({fake_variant})),
})
fake_rs_id_infos = frozenset({
RsIdInfo("rs1212125", "T", "T", GeneCoordinate("5", 97915617), GeneCoordinate("chr5", 97450060)),
})
fake_drugs = frozenset({
DrugInfo("Aspirin", "https://www.pharmgkb.org/some_other_url"),
})
fake_rs_id_to_difference_annotations: Dict[str, Annotation] = {}
fake2_haplotypes = frozenset({
Haplotype("*4A", "Reduced Function", frozenset({fake2_variant})),
})
fake2_rs_id_infos = frozenset({
RsIdInfo("rs1212127", "C", "T", GeneCoordinate("16", 97915617), GeneCoordinate("chr16", 97450060)),
})
fake2_drugs = frozenset({
DrugInfo("Aspirin", "https://www.pharmgkb.org/some_other_url"),
})
fake2_rs_id_to_difference_annotations = {"rs1212127": Annotation("1324C>T", "1324T>C")}
gene_infos = frozenset({
GeneInfo("DPYD", "*1", dpyd_haplotypes, dpyd_rs_id_infos,
dpyd_drugs, dpyd_rs_id_to_difference_annotations),
GeneInfo("FAKE", "*1", fake_haplotypes, fake_rs_id_infos,
fake_drugs, fake_rs_id_to_difference_annotations),
GeneInfo("FAKE2", "*1", fake2_haplotypes, fake2_rs_id_infos,
fake2_drugs, fake2_rs_id_to_difference_annotations),
})
name = "Panel"
version = "0.2"
return Panel(name, version, gene_infos)
def test_get_covered_coordinates_single(self) -> None:
start_coordinate = GeneCoordinate("X", 17)
result = get_covered_coordinates(start_coordinate, "A")
result_expected = {start_coordinate}
self.assertEqual(result_expected, result)
def test_get_covered_coordinates_empty(self) -> None:
start_coordinate = GeneCoordinate("X", 17)
result = get_covered_coordinates(start_coordinate, "")
result_expected: Set[GeneCoordinate] = set()
self.assertEqual(result_expected, result)
def test_panel_with_overlapping_rs_id_infos_for_different_genes(
self) -> None:
"""Error when panel has overlapping rs id infos for different genes, but not when they are exactly the same"""
name = "FakePanel"
version = "1.0"
gene1 = "FAKE"
gene2 = "OTHER"
chromosome_v37 = "X"
chromosome_v38 = "chrX"
reference_haplotype_name = "*1"
haplotypes: FrozenSet[Haplotype] = frozenset()
drugs: FrozenSet[DrugInfo] = frozenset()
rs_id_to_ref_seq_difference_annotation: Dict[str, Annotation] = dict()
rs_id_info1 = RsIdInfo(
"rs294924",
"AT",
"AT",
GeneCoordinate(chromosome_v37, 499593),
GeneCoordinate(chromosome_v38, 399483),
)
rs_id_info2 = RsIdInfo(
"rs3949923",
"C",
"C",
GeneCoordinate(chromosome_v37, 293993),
GeneCoordinate(chromosome_v38, 1388323),
)
rs_id_info3 = RsIdInfo(
"rs12993",
"GG",
"GG",
GeneCoordinate(chromosome_v37, 499592),
GeneCoordinate(chromosome_v38, 399482),
)
rs_id_infos1 = frozenset([rs_id_info1])
rs_id_infos2 = frozenset([rs_id_info1, rs_id_info2])
rs_id_infos3 = frozenset([rs_id_info3])
gene_info1 = GeneInfo(
gene1,
reference_haplotype_name,
haplotypes,
rs_id_infos1,
drugs,
rs_id_to_ref_seq_difference_annotation,
)
gene_info2 = GeneInfo(
gene2,
reference_haplotype_name,
haplotypes,
rs_id_infos2,
drugs,
rs_id_to_ref_seq_difference_annotation,
)
gene_info3 = GeneInfo(
gene2,
reference_haplotype_name,
haplotypes,
rs_id_infos3,
drugs,
rs_id_to_ref_seq_difference_annotation,
)
Panel(name, version, frozenset([gene_info1, gene_info2]))
with self.assertRaises(ValueError):
Panel(name, version, frozenset([gene_info1, gene_info3]))
def test_load_panel(self) -> None:
"""Load panel from json"""
panel_path = get_test_resource("test_panel.json")
panel = load_panel(str(panel_path))
dpyd_two_a_variant = Variant("rs3918290", "T")
dpyd_two_b_variant = Variant("rs1801159", "C")
dpyd_three_variant = Variant("rs72549303", "TG")
fake_variant = Variant("rs1212125", "C")
fake2_variant = Variant("rs1212127", "C")
dpyd_haplotypes_expected = frozenset({
Haplotype("*2A", "No Function", frozenset({dpyd_two_a_variant})),
Haplotype("*2B", "No Function",
frozenset({dpyd_two_a_variant, dpyd_two_b_variant})),
Haplotype("*3", "Normal Function",
frozenset({dpyd_three_variant})),
})
dpyd_rs_id_infos_expected = frozenset({
RsIdInfo("rs3918290", "C", "C", GeneCoordinate("1", 97915614),
GeneCoordinate("chr1", 97450058)),
RsIdInfo("rs72549309", "GATGA", "GATGA",
GeneCoordinate("1", 98205966),
GeneCoordinate("chr1", 97740410)),
RsIdInfo("rs1801159", "T", "T", GeneCoordinate("1", 97981395),
GeneCoordinate("chr1", 97515839)),
RsIdInfo("rs72549303", "TG", "TC", GeneCoordinate("1", 97915621),
GeneCoordinate("chr1", 97450065)),
RsIdInfo("rs1801265", "G", "A", GeneCoordinate("1", 98348885),
GeneCoordinate("chr1", 97883329)),
})
dpyd_drugs_expected = frozenset({
DrugInfo("5-Fluorouracil",
"https://www.source_url.org/5-Fluorouracil"),
DrugInfo("Capecitabine",
"https://www.source_url.org/Capecitabine"),
})
dpyd_rs_id_to_difference_annotations = {
"rs72549303": Annotation("6744CA>GA", "6744GA>CA"),
"rs1801265": Annotation("85C>T", "85T>C"),
}
fake_haplotypes_expected = frozenset({
Haplotype("*4A", "Reduced Function", frozenset({fake_variant})),
})
fake_rs_id_infos_expected = frozenset({
RsIdInfo("rs1212125", "T", "T", GeneCoordinate("5", 97915617),
GeneCoordinate("chr5", 97450060)),
})
fake_drugs_expected = frozenset({
DrugInfo("Aspirin", "https://www.source_url.org/Aspirin"),
})
fake_rs_id_to_difference_annotations: Dict[str, Annotation] = {}
fake2_haplotypes_expected = frozenset({
Haplotype("*4A", "Reduced Function", frozenset({fake2_variant})),
})
fake2_rs_id_infos_expected = frozenset({
RsIdInfo("rs1212127", "C", "T", GeneCoordinate("16", 97915617),
GeneCoordinate("chr16", 97450060)),
})
fake2_drugs_expected = frozenset({
DrugInfo("Aspirin", "https://www.source_url.org/Aspirin"),
})
fake2_rs_id_to_difference_annotations = {
"rs1212127": Annotation("1324C>T", "1324T>C")
}
gene_infos_expected = frozenset({
GeneInfo("DPYD", "*1", dpyd_haplotypes_expected,
dpyd_rs_id_infos_expected, dpyd_drugs_expected,
dpyd_rs_id_to_difference_annotations),
GeneInfo("FAKE", "*1", fake_haplotypes_expected,
fake_rs_id_infos_expected, fake_drugs_expected,
fake_rs_id_to_difference_annotations),
GeneInfo("FAKE2", "*1", fake2_haplotypes_expected,
fake2_rs_id_infos_expected, fake2_drugs_expected,
fake2_rs_id_to_difference_annotations),
})
name_expected = "fake_panel"
version_expected = "0.3"
panel_expected = Panel(name_expected, version_expected,
gene_infos_expected)
self.assertEqual(panel_expected, panel)