def test_majorAndMinor_allMinorsLumpedInTogether(self):
s = "lineage4.1.2.3.4.5"
actual = Lineage.from_str(s)
expected = Lineage(major="4", minor="1.2.3.4.5")
assert actual == expected
def test_oneLineage_returnsSameLineage(self):
lineage = Lineage(major="foo", minor="bar")
actual = Lineage.call([lineage])
expected = lineage
assert actual == expected
def test_withPrefixLineage_ignoresPrefix(self):
s = "lineageBovis"
actual = Lineage.from_str(s)
expected = Lineage(major="Bovis")
assert actual == expected
def test_sameMajorOneHasMinors_returnsMajor(self):
lineage = Lineage(major="4", minor="8.9")
other = Lineage(major="4")
actual = lineage.mrca(other)
expected = other
assert actual == expected
def test_sameMajorBothHaveMinorsOnSameBranches_returnsSecondMinor(self):
lineage = Lineage(major="4", minor="8.7.8")
other = Lineage(major="4", minor="8.7.6")
actual = lineage.mrca(other)
expected = Lineage(major="4", minor="8.7")
assert actual == expected
def test_sameMajorBothHaveMinorsOnDifferentBranches_returnsMajor(self):
lineage = Lineage(major="4", minor="8.9")
other = Lineage(major="4", minor="4.7.6")
actual = lineage.mrca(other)
expected = Lineage(major="4")
assert actual == expected
def test_twoLineagesSameMajorOneWithMinor_returnsOneWithMinor(self):
l1 = Lineage(major="foo", minor="bar")
l2 = Lineage(major="foo")
actual = Lineage.call([l1, l2])
expected = l1
assert actual == expected
def test_sameMajorAndMinors_returnsSame(self):
lineage = Lineage(major="4", minor="3.4.5.8")
other = Lineage(major="4", minor="3.4.5.8")
actual = lineage.mrca(other)
expected = lineage
assert actual == expected
def test_sameMajorNoMinors_returnsMajor(self):
lineage = Lineage(major="4")
other = Lineage(major="4")
actual = lineage.mrca(other)
expected = lineage
assert actual == expected
def test_threeLineagesSameMajorSameDepthMinor_returnsMRCA(self):
l1 = Lineage(major="4", minor="1.3.4.5")
l2 = Lineage(major="4", minor="1.3.6.6")
l3 = Lineage(major="4", minor="1.3.6.8")
actual = Lineage.call([l1, l2, l3])
expected = Lineage(major="4", minor="1.3")
assert actual == expected
def test_threeLineagesWithMinorsDiffLen_returnsLongest(self):
l1 = Lineage(major="4", minor="1.3.4.5.9")
l2 = Lineage(major="4", minor="1.3.6")
l3 = Lineage(major="4", minor="1.3.6.8")
actual = Lineage.call([l1, l2, l3])
expected = Lineage(major="4", minor="1.3.4.5.9")
assert actual == expected
def test_threeLineagesWithDiffMinorsSameLen_returnsMajor(self):
l1 = Lineage(major="4", minor="1.3.4")
l2 = Lineage(major="4", minor="2.3.6")
l3 = Lineage(major="4", minor="3.3.6")
actual = Lineage.call([l1, l2, l3])
expected = Lineage(major="4")
assert actual == expected
def test_twoLineagesSameMajor_returnsLowestOnTree(self):
l1 = Lineage(major="4", minor="1.3.4")
l2 = Lineage(major="4", minor="8.3")
classifier = Classifier()
sample_idx = 0
actual = classifier.call_sample_lineage([l1, l2], sample_idx)
expected = str(l1)
assert actual == expected
def test_twoLineagesDiffMajor_returnsMixedDisregardMaxAlt(self):
l1 = Lineage(major="4", minor="1.3.4")
l2 = Lineage(major="5", minor="8.3")
classifier = Classifier(max_alt_lineages=5)
sample_idx = 0
actual = classifier.call_sample_lineage([l1, l2], sample_idx)
expected = "mixed"
assert actual == expected
def test_mixedLineagesBelowThreshold_returnsMostCommon(self):
l1 = Lineage(major="4", minor="1.3.4")
l2 = Lineage(major="4", minor="1.3")
l3 = Lineage(major="5", minor="8.3")
classifier = Classifier(max_alt_lineages=1)
sample_idx = 0
actual = classifier.call_sample_lineage([l1, l2, l3], sample_idx)
expected = str(l1)
assert actual == expected
def test_onlyMajor_minorIsNone(self):
s = "lineage4"
actual = Lineage.from_str(s).minor
expected = ()
assert actual == expected
def test_noHeader_allPanelVariantsInPanel(self):
stream = StringIO(
"lineage1,615938,1104,G/A,368,GAG/GAA,E/E,Rv0524,hemL\n"
"lineage1.1,4404247,1056,G/A,352,CTG/CTA,L/L,Rv3915,-"
)
actual = load_panel(stream)
expected = {
615938: PanelVariant(
Lineage("1"), 615938, "G", "A", "Rv0524", "hemL", 1104
),
4404247: PanelVariant(
Lineage("1", "1"), 4404247, "G", "A", "Rv3915", "-", 1056
),
}
assert actual == expected
def test_geneNameIsEmpty_returnsNone(self):
row = ",".join(
["lineage1", "615938", "1104", "G/A", "368", "GAG/GAA", "E/E", "foo", "",]
)
actual = PanelVariant.from_row(row)
expected = PanelVariant(Lineage("1"), 615938, "G", "A", "foo", None, 1104)
assert actual == expected
def test_nonDefaultDelim_loadsOk(self):
stream = StringIO(
"lineage1|615938|1104|G/A|368|GAG/GAA|E/E|Rv0524|hemL\n"
"lineage1.1|4404247|1056|G/A|352|CTG/CTA|L/L|Rv3915|-"
)
delim = "|"
actual = load_panel(stream, delim=delim)
expected = {
615938: PanelVariant(
Lineage("1"), 615938, "G", "A", "Rv0524", "hemL", 1104
),
4404247: PanelVariant(
Lineage("1", "1"), 4404247, "G", "A", "Rv3915", "-", 1056
),
}
assert actual == expected
def test_oneLineage_returnsOnlyElement(self):
l1 = Lineage(major="4", minor="1.3.4")
classifier = Classifier()
sample_idx = 0
actual = classifier.call_sample_lineage([l1], sample_idx)
expected = str(l1)
assert actual == expected
def test_fileWithNoIssues_loadsOk(self):
stream = StringIO(
"lineage,position,gene_coord,allele_change,codon_number,codon_change,amino_acid_change,locus_id,gene_name\n"
"lineage1,615938,1104,G/A,368,GAG/GAA,E/E,Rv0524,hemL\n"
"lineage1.1,4404247,1056,G/A,352,CTG/CTA,L/L,Rv3915,-"
)
actual = load_panel(stream, no_header=False)
expected = {
615938: PanelVariant(
Lineage("1"), 615938, "G", "A", "Rv0524", "hemL", 1104
),
4404247: PanelVariant(
Lineage("1", "1"), 4404247, "G", "A", "Rv3915", "-", 1056
),
}
assert actual == expected
def test_oneLineageTooManyHets_returnsTooManyHets(self):
l1 = Lineage(major="4", minor="1.3.4")
classifier = Classifier(max_het=1)
sample_idx = 0
classifier.het_counts[sample_idx] = 5
actual = classifier.call_sample_lineage([l1], sample_idx)
expected = "too_many_hets"
assert actual == expected
def test_posNotInPanel_returnsFalse(self, mock_variant):
index = {
1: PanelVariant(Lineage("1"), 1, "G", "A"),
}
classifier = Classifier(index)
mock_variant.POS = 4
mock_variant.REF = "G"
mock_variant.FILTER = None
assert not classifier.is_variant_valid(mock_variant)
def test_tabAsDelim_returnsExpected(self):
delim = "\t"
row = delim.join(
["lineage1", "615938", "1104", "G/A", "368", "GAG/GAA", "E/E", "foo", "",]
)
actual = PanelVariant.from_row(row, delim=delim)
expected = PanelVariant(Lineage("1"), 615938, "G", "A", "foo", None, 1104)
assert actual == expected
def test_variantRefDoesntMatchPanel_returnsFalse(self, mock_variant):
index = {
1: PanelVariant(Lineage("1"), 1, "G", "A"),
}
classifier = Classifier(index)
mock_variant.POS = 1
mock_variant.REF = "d"
mock_variant.FILTER = None
assert not classifier.is_variant_valid(mock_variant)
def test_panelVariantAltNotInVariantAlts_returnsFalse(self, mock_variant):
index = {
1: PanelVariant(Lineage("1"), 1, "G", "A"),
}
classifier = Classifier(index)
mock_variant.POS = 1
mock_variant.REF = "G"
mock_variant.ALT = ["T", "C"]
mock_variant.FILTER = None
assert not classifier.is_variant_valid(mock_variant)
def test_refLineagePosPanelRefInAlt_returnsTrue(self, mock_variant):
index = {
1: PanelVariant(Lineage("1"), 1, "G", "A"),
}
classifier = Classifier(index)
mock_variant.POS = 1
mock_variant.REF = "G"
mock_variant.ALT = ["T", "C"]
mock_variant.FILTER = None
assert not classifier.is_variant_valid(mock_variant)
def test_panelVariantFailsFilter_returnsFalse(self, mock_variant):
index = {
1: PanelVariant(Lineage("1"), 1, "G", "A"),
}
classifier = Classifier(index)
mock_variant.POS = 1
mock_variant.REF = "G"
mock_variant.ALT = ["T", "A"]
mock_variant.FILTER = "FAIL"
assert not classifier.is_variant_valid(mock_variant)
def test_panelVariantAltIsNotVariantRef_returnsFalse(self, mock_variant):
pos = 1692141
index = {
pos: PanelVariant(Lineage.from_str("4.10"), position=pos, ref="C", alt="T"),
}
classifier = Classifier(index, ref_lineage_position=pos)
mock_variant.POS = pos
mock_variant.REF = "A"
mock_variant.ALT = ["C"]
mock_variant.FILTER = None
assert not classifier.is_variant_valid(mock_variant)
def test_sampleHasLineageVariantAndPassesFilter_returnsIndex(self, mocked_variant):
index = {
1: PanelVariant(Lineage("1"), 1, "G", "A"),
}
classifier = Classifier(index)
mocked_variant.POS = 1
mocked_variant.REF = "G"
mocked_variant.ALT = ["T", "A", "N"]
mocked_variant.genotypes = [[-1, -1, False], [2, 2, False]]
mocked_variant.format.return_value = ["PASS", "PASS"]
actual = classifier.samples_with_lineage_variant(mocked_variant)
expected = [1]
assert actual == expected
