def test_added_fusion_features():
genotype = Genotype.parse(
'+geneA -geneB:geneC +geneB:geneC +{geneA, geneB}')
assert genotype.added_fusion_features == {
Feature('geneA'),
CompositeAnnotation(Feature('geneA'), Feature('geneB'))
}
def test_parse_fusion(parse):
assert [Change(after=Fusion(Feature('foo'), Feature('bar')))
] == parse('+foo:bar')
assert [
Change(before=Fusion(Feature('foo'), Feature('bar')),
after=Feature('foo'))
] == parse('foo:bar>foo')
def test_feature_html_format_escape_html(html_formatter):
assert html_formatter.format_feature(
Feature('geneB&')) == '<span class="gnomic-feature">geneB&</span>'
assert html_formatter.format_feature(
Feature('geneB<')) == '<span class="gnomic-feature">geneB<</span>'
assert html_formatter.format_feature(
Feature('geneB>')) == '<span class="gnomic-feature">geneB></span>'
def test_match_on_delete(state):
state.change(Change(None, F.parse('species/gene.A')))
assert state.changes == (
Change(None, F.parse('species/gene.A')),
)
state.change(Change(F.parse('gene.A'), None))
assert state.changes == ()
def test_change_presence(state):
state.change(Present(F.parse('gene.foo(A)')))
assert state.changes == (Change(None, F.parse('gene.foo(A)')), )
state.change(Present(F.parse('gene.foo(B)')))
assert state.changes == (Change(None, F.parse('gene.foo(B)')), )
def test_added_features():
genotype = Genotype.parse('+geneA -geneB +geneB -geneC')
assert genotype.added_features == {Feature('geneA')}
genotype = Genotype.parse('+{geneA, geneB:geneC}')
assert genotype.added_features == {
Feature('geneA'), Feature('geneB'),
Feature('geneC')
}
def to_gnomic(self):
accession = Target.to_gnomic(self)
pairs = [(m.id for m in pair) for pair in self.swap_pairs]
wt_feature = Feature(name=self.id, accession=accession, type='reaction',
variant=["cofactors=%s" % ",".join(pairs[0])])
feature = Feature(name=self.id, accession=accession, type='reaction',
variant=["cofactors=%s" % ",".join(pairs[1])])
return Change(before=wt_feature, after=feature)
def test_match_whole_fusion_on_delete_with_variant(state):
state.change(+F.parse('gene.A')**F.parse('gene.B'))
state.change(+F.parse('gene.C'))
state.change(-F.parse('gene.A')**F.parse('gene.B(x)'))
assert state.changes == (
+F.parse('gene.A')**F.parse('gene.B'),
+F.parse('gene.C'),
-F.parse('gene.A')**F.parse('gene.B(x)'),
)
def test_replacement_replace_variant(state):
state.change(Change(F('a'), F.parse('a(x)')))
assert state.changes == (
Change(F('a'), F.parse('a(x)')),
)
state.change(Change(F('a'), F.parse('a(y)')))
assert state.changes == (
Change(F('a'), F.parse('a(y)')),
)
def test_change_presence(state):
state.change(Present(F.parse('gene.foo(A)')))
assert state.changes == (
Change(None, F.parse('gene.foo(A)')),
)
state.change(Present(F.parse('gene.foo(B)')))
assert state.changes == (
Change(None, F.parse('gene.foo(B)')),
)
def to_gnomic(self):
accession = Target.to_gnomic(self)
if self._value == 0:
old_feature = Feature(name=self.id, accession=accession, type=self.__gnomic_feature_type__)
new_feature = None
elif self.fold_change != 0:
old_feature = Feature(name=self.id, type=self.__gnomic_feature_type__,
variant=tuple(["value={}".format(self._reference_value)]))
new_feature = Feature(name=self.id, accession=accession, type=self.__gnomic_feature_type__,
variant=tuple(["value={}".format(self._value)]))
else:
raise RuntimeError("fold_change shouldn't be 0")
return Change(before=old_feature, after=new_feature)
def test_update_fusion_with_composite_annotation_in_replacement(state):
state.change(+F.parse('gene.A')**F.parse('gene.B'))
state.change(
F.parse('gene.B') > CompositeAnnotation(F.parse('gene.C'),
F.parse('gene.D')))
assert state.changes == (+F.parse('gene.A')**CompositeAnnotation(
F.parse('gene.C'), F.parse('gene.D')), )
def test_sequence_variants_dna_repeated(parse):
variants = [
'g.123_124[14]', 'g.123_124[14];[18]', 'c.-128_-126[79]',
'c.-128_-126[(600_800)]', 'c.54GCA[21]', 'c.54GCA[21]ACA[1]GCC[2]'
]
assert parse('geneA({})'.format('; '.join(variants))) == Feature(
'geneA', variant=tuple(variants))
def test_sequence_variants_dna_conversion(parse):
variants = [
'g.333_590con1844_2101',
# other possibilities with reference to a file or a gene
]
assert parse('geneA({})'.format('; '.join(variants))) == Feature(
'geneA', variant=tuple(variants))
def test_sequence_variants_protein_substitution(parse):
variants = [
'p.Trp24Cys', 'p.(Trp24Cys)', 'p.Trp24Ter', 'p.Trp24*', 'p.Cys188=',
'p.0', 'p.?', 'p.Met1?', 'p.(Tyr4*)'
]
assert parse('geneA({})'.format('; '.join(variants))) == Feature(
'geneA', variant=tuple(variants))
def test_sequence_variants_protein_duplication(parse):
variants = [
'p.Ala3dup',
'p.(Ala3dup)',
'p.Ala3_Ser5dup',
]
assert parse('geneA({})'.format('; '.join(variants))) == Feature(
'geneA', variant=tuple(variants))
def test_sequence_variants_dna_deletions(parse):
variants = [
'g.19del', 'g.10_21del', 'c.183_186+48del', 'c.1234del', 'c.1234+1del',
'c.4072-1234_5155-246del', 'c.(?_-245)_(31+1_32-1)del',
'c.(?_-1)_(*1_?)del', 'g.19_21=/del', 'g.19_21del=//del'
]
assert parse('geneA({})'.format('; '.join(variants))) == Feature(
'geneA', variant=tuple(variants))
def test_sequence_variants_dna_inversion(parse):
variants = [
'g.1234_1236inv',
'c.77_80inv',
'g.122_123ins123_234inv',
]
assert parse('geneA({})'.format('; '.join(variants))) == Feature(
'geneA', variant=tuple(variants))
def test_sequence_variants_dna_delins(parse):
variants = [
'g.6775delinsGA',
'g.6775_6777delinsC',
'g.9002_9009delinsTTT',
]
assert parse('geneA({})'.format('; '.join(variants))) == Feature(
'geneA', variant=tuple(variants))
def test_integrate_plasmid_with_fusion(state):
state.change(
F('site') > Plasmid('pA', [F.parse('gene.A')**F.parse('gene.B')]))
assert state.changes == (F('site') > Plasmid(
'pA', [F.parse('gene.A')**F.parse('gene.B')]), )
state.change(F.parse('gene.A')**F.parse('gene.B') > F.parse('gene.C'))
assert state.changes == (F('site') > CompositeAnnotation(
F.parse('gene.C')), )
def test_sequence_variants_protein_frameshift(parse):
variants = [
'p.Arg97ProfsTer23',
'p.Arg97fs',
'p.Ile327Argfs*?',
'p.Gln151Thrfs*9',
]
assert parse('geneA({})'.format('; '.join(variants))) == Feature(
'geneA', variant=tuple(variants))
def test_sequence_variants_protein_repeated(parse):
variants = [
'p.Ala2[10]',
'p.Ala2[10];[11]',
'p.Gln18[23]',
'p.(Gln18)[(70_80)]',
]
assert parse('geneA({})'.format('; '.join(variants))) == Feature(
'geneA', variant=tuple(variants))
def test_sequence_variants_protein_extension(parse):
variants = [
'p.Met1ext-5',
'p.Met1Valext-12',
'p.Ter110Clnext*17',
'p.(Ter315TyrextAsnLysGlyThrTer)',
'p.Ter327Argext*?',
'p.*327Argext*',
]
assert parse('geneA({})'.format('; '.join(variants))) == Feature(
'geneA', variant=tuple(variants))
def test_parse_composite_annotation(parse):
assert [
Change(after=CompositeAnnotation(Feature('geneA'), Feature('geneB')))
] == parse('+{geneA, geneB}')
assert [
Change(before=CompositeAnnotation(Feature('geneA'), Feature('geneB')))
] == parse('-{geneA, geneB}')
assert [
Change(before=Feature('geneX'),
after=Fusion(
CompositeAnnotation(Feature('geneA'), Feature('geneB')),
Feature('geneX')))
] == parse('geneX>{geneA, geneB}:geneX')
def test_sequence_variants_protein_insertion(parse):
variants = [
'p.His4_Gln5insAla',
'p.Lys2_Gly3insGlnSerLys',
'p.(Met3_His4insGlyTer)',
'p.Arg78_Gly79ins23',
'p.Cys28delinsTrpVal',
'p.Cys28_Lys29delinsTrp',
'p.(Pro578_Lys579delinsLeuTer)',
'p.[Ser44Arg;Trp46Arg]',
]
assert parse('geneA({})'.format('; '.join(variants))) == Feature(
'geneA', variant=tuple(variants))
def test_sequence_variants_dna_insertion(parse):
variants = [
'g.4426_4426insA',
'g.5756_5757insAGG',
'g.123_124insL1234.1:23_361',
'g.122_123ins123_234inv',
# 'g.122_123ins213_234invinsAins123_211inv',
'g.122_123ins212_234inv123_199inv',
'c.(67_70)insG(p.Gly23fs)',
'g.123_124ins(100)',
]
assert parse('geneA({})'.format('; '.join(variants))) == Feature(
'geneA', variant=tuple(variants))
def test_sequence_variants_dna_substitutions(parse):
variants = [
'g.123C>A',
'c.93+1G>T',
'c.79_80delinsTT',
'c.[12C>T;13C>G]',
'c.12G>H',
'c.123=',
'c.85=/T>C',
'c.85=//T>C',
]
assert parse('geneA({})'.format('; '.join(variants))) == Feature(
'geneA', variant=tuple(variants))
def test_imply_locus_with_substitution():
assert chain('gene.A>promoter.X:gene.B',
'gene.C>promoter.X:gene.D',
'[email protected]>promoter.Y').changes() == (
Change(Feature.parse('gene.C'), Fusion(Feature.parse('promoter.X'), Feature.parse('gene.D'))),
Change(Feature.parse('gene.A'), Fusion(Feature.parse('promoter.Y'), Feature.parse('gene.B'))),
)
def test_parse_feature():
assert Feature('foo') == Feature.parse('foo')
assert Feature('foo', type='gene') == Feature.parse('gene.foo')
assert Feature('foo', organism='organism') == Feature.parse('organism/foo')
assert Feature('foo', accession=Accession('id', 'database')) == Feature.parse('foo#database:id')
assert Feature('foo', accession=Accession('id123')) == Feature.parse('foo#id123')
assert Feature('foo', type='gene', organism='organism', accession=Accession('id', 'database'),
variant=tuple('variant')) == Feature.parse('organism/gene.foo#database:id(variant)')
def test_sequence_variants_dna_duplication(parse):
variants = [
'g.7dup',
'g.6_8dup',
'c.120_123+48dup',
'c.123dup',
'c.4072-1234_5146-246dup',
'c.(4071+1_4072-1)_(5145+1_5146-1)dup',
'c.(4071+1_4072-1)_(5145+1_5146-1)[3]',
'c.(?_-30)_(12+1_13-1)dup',
'c.(?_-1)_(*1_?)dup',
]
assert parse('geneA({})'.format('; '.join(variants))) == Feature(
'geneA', variant=tuple(variants))
def test_replacement_of_variants(state):
state.change(Change(F.parse('a(x)'), F('b')))
assert state.changes == (Change(F.parse('a(x)'), F('b')), )
state.change(Change(F.parse('a(y)'), F('b')))
assert state.changes == (
Change(F.parse('a(x)'), F('b')),
Change(F.parse('a(y)'), F('b')),
)
state.change(Change(F.parse('a(y)'), F('c')))
assert state.changes == (
Change(F.parse('a(x)'), F('b')),
Change(F.parse('a(y)'), F('c')),
)
def test_feature_gnomic_format(gnomic_formatter):
assert gnomic_formatter.format_annotation(Feature(name='foo')) == 'foo'
assert gnomic_formatter.format_annotation(Feature.parse('foo(f)')) == 'foo(f)'
assert gnomic_formatter.format_annotation(Feature.parse('foo(f, g)')) == 'foo(f; g)'
assert gnomic_formatter.format_annotation(Feature.parse('organism/type.gene#db:123(f, g)')) \
== 'organism/type.gene#db:123(f; g)'
assert gnomic_formatter.format_annotation(Feature.parse('#db:123')) == '#db:123'
assert gnomic_formatter.format_annotation(Feature.parse('gene#123')) == 'gene#123'
assert gnomic_formatter.format_annotation(Feature.parse('foo(mutant; variant)')) == 'foo(mutant; variant)'
def test_feature_gnomic_format(gnomic_formatter):
assert gnomic_formatter.format_annotation(Feature(name='foo')) == 'foo'
assert gnomic_formatter.format_annotation(
Feature.parse('foo(f)')) == 'foo(f)'
assert gnomic_formatter.format_annotation(
Feature.parse('foo(f, g)')) == 'foo(f; g)'
assert gnomic_formatter.format_annotation(Feature.parse('organism/type.gene#db:123(f, g)')) \
== 'organism/type.gene#db:123(f; g)'
assert gnomic_formatter.format_annotation(
Feature.parse('#db:123')) == '#db:123'
assert gnomic_formatter.format_annotation(
Feature.parse('gene#123')) == 'gene#123'
assert gnomic_formatter.format_annotation(
Feature.parse('foo(mutant; variant)')) == 'foo(mutant; variant)'
def test_replacement_of_variants(state):
state.change(Change(F.parse('a(x)'), F('b')))
assert state.changes == (
Change(F.parse('a(x)'), F('b')),
)
state.change(Change(F.parse('a(y)'), F('b')))
assert state.changes == (
Change(F.parse('a(x)'), F('b')),
Change(F.parse('a(y)'), F('b')),
)
state.change(Change(F.parse('a(y)'), F('c')))
assert state.changes == (
Change(F.parse('a(x)'), F('b')),
Change(F.parse('a(y)'), F('c')),
)
def test_imply_locus_with_substitution():
assert chain('gene.A>promoter.X:gene.B', 'gene.C>promoter.X:gene.D',
'[email protected]>promoter.Y').changes() == (
Change(
Feature.parse('gene.C'),
Fusion(Feature.parse('promoter.X'),
Feature.parse('gene.D'))),
Change(
Feature.parse('gene.A'),
Fusion(Feature.parse('promoter.Y'),
Feature.parse('gene.B'))),
)
def test_scenario_1c_disambiguate_site_using_repeat_site(state):
state.change(Change(F.parse('gene.A'), F.parse('promoter.X') ** F.parse('gene.B')))
state.change(Change(F.parse('gene.C'), F.parse('promoter.X') ** F.parse('gene.D')))
state.change(Change(F.parse('gene.A'), F.parse('promoter.Y') ** F.parse('gene.B')))
assert state.changes == (
Change(F.parse('gene.C'), F.parse('promoter.X') ** F.parse('gene.D')),
Change(F.parse('gene.A'), F.parse('promoter.Y') ** F.parse('gene.B'))
)
def test_genotype_parse_plasmid_insertion(parse):
assert [Change(after=Plasmid('foo'))] == parse('(foo)')
assert [Change(after=Plasmid('foo', [Feature.parse('gene.A')]))] == parse('(foo gene.A)')
def to_gnomic(self):
accession = Target.to_gnomic(self)
feature = Feature(name=self.id, accession=accession)
return Change(before=feature)
def to_gnomic(self):
accession = Target.to_gnomic(self)
feature = Feature(accession=accession, type='reaction', name=self.id)
return Change(after=feature)
def test_scenario_2_change_at_unknown_locus(state):
state.change(Change(F.parse('promoter.A') % F.parse('gene.foo'), F.parse('promoter.B')))
assert state.changes == (
Change(F.parse('promoter.A') % F.parse('gene.foo'), F.parse('promoter.B')),
)
state.change(Change(None, F.parse('gene.foo')))
assert state.changes == (
Change(F.parse('promoter.A') % F.parse('gene.foo'), F.parse('promoter.B')),
Change(None, F.parse('gene.foo')),
)
state.change(Change(F.parse('promoter.B') % F.parse('gene.foo'), F.parse('promoter.A')))
assert state.changes == (
Change(None, F.parse('gene.foo')),
)