def test_get_most_severe(self):
''' check that get_most_severe works correctly
'''
cq = ['missense_variant', 'protein_altering_variant',
'splice_region_variant', 'incomplete_terminal_codon_variant']
self.assertEqual(get_most_severe(cq), 'missense_variant')
cq = ['stop_lost', 'start_lost', 'transcript_amplification',
'conserved_exon_terminus_variant']
self.assertEqual(get_most_severe(cq), 'stop_lost')
# an empty list raises an error
with self.assertRaises(IndexError):
get_most_severe([])
def test_get_most_severe(self):
''' check that get_most_severe works correctly
'''
cq = [
'missense_variant', 'protein_altering_variant',
'splice_region_variant', 'incomplete_terminal_codon_variant'
]
self.assertEqual(get_most_severe(cq), 'missense_variant')
cq = [
'stop_lost', 'start_lost', 'transcript_amplification',
'conserved_exon_terminus_variant'
]
self.assertEqual(get_most_severe(cq), 'stop_lost')
# an empty list raises an error
with self.assertRaises(IndexError):
get_most_severe([])
def person_recurrence(de_novos):
""" identify de novos recurrent in a gene within individuals.
Find the de novos that are recurrent within a single individual in a
single gene. We shall treat these as a single de novo event. Prioritise
including the most severe event within a gene, then take the first variant
left after that.
Args:
de_novos: dataframe of de novo variants
Returns:
pandas Series for whether each candidate is a duplicate or not
"""
# find the variants which are recurrent within a person in a single gene
from_start = de_novos.duplicated(["person_stable_id", "symbol"])
from_end = de_novos.duplicated(["person_stable_id", "symbol"], keep='last')
person_dups = from_start | from_end
in_person_dups = de_novos[person_dups]
# split the dataset, so we can process gene by gene
genes = in_person_dups.groupby(["person_stable_id", "symbol"])
# pick a variant for each person, the first of the most severe consequence
retain = pandas.Series([], dtype=numpy.bool_)
for key, gene in genes:
consequence = get_most_severe(gene["consequence"])
first = gene[gene["consequence"] == consequence].index[0]
gene_retain = pandas.Series([True] * len(gene), index=gene.index)
gene_retain[first] = False
retain = retain.append(gene_retain)
# set the selected de novos
person_dups.loc[retain.index] = retain
return person_dups
def person_recurrence(de_novos):
""" identify de novos recurrent in a gene within individuals.
Find the de novos that are recurrent within a single individual in a
single gene. We shall treat these as a single de novo event. Prioritise
including the most severe event within a gene, then take the first variant
left after that.
Args:
de_novos: dataframe of de novo variants
Returns:
pandas Series for whether each candidate is a duplicate or not
"""
# find the variants which are recurrent within a person in a single gene
from_start = de_novos.duplicated(["person_stable_id", "symbol"])
from_end = de_novos.duplicated(["person_stable_id", "symbol"], take_last=True)
person_dups = from_start | from_end
in_person_dups = de_novos[person_dups]
# split the dataset, so we can process gene by gene
genes = in_person_dups.groupby(["person_stable_id", "symbol"])
# pick a variant for each person, the first of the most severe consequence
retain = pandas.Series([], dtype=numpy.bool_)
for key, gene in genes:
consequence = get_most_severe(gene["consequence"])
first = gene[gene["consequence"] == consequence].index[0]
gene_retain = pandas.Series([True] * len(gene), index=gene.index)
gene_retain[first] = False
retain = retain.append(gene_retain)
# set the selected de novos
person_dups.loc[retain.index] = retain
return person_dups
