def screen_candidates(de_novos_path,
fails_path,
filter_function,
maf=0.01,
fix_symbols=True,
annotate_only=False,
build='grch37'):
""" load and optionally filter candidate de novo mutations.
Args:
de_novos_path: path to table of unfiltered canddiate DNMs
fails_path: path to file listing samples which failed QC, and therefore
all of their candidates need to be excluded.
filter_function: function for filtering the candidates, either
filter_denovogear_sites(), or filter_missing_indels().
maf: MAF threshold for filtering. This is 0.01 for denovogear sites,
and 0 for the missing indels.
fix_symbols: whether to annotate HGNC symbols for candidates
missing these.
annotate_only: whether to include a column indicating pass status, rather
than excluding all candidates which fail the filtering.
build: whether to use the 'grch37' or 'grch38' build to get
missing symbols.
Returns:
pandas DataFrame of candidate de novo mutations.
"""
if de_novos_path is None:
return None
# load the datasets
de_novos = load_candidates(de_novos_path)
sample_fails = []
if fails_path is not None:
sample_fails = [x.strip() for x in open(fails_path)]
# run some initial screening
status = preliminary_filtering(de_novos, sample_fails, maf_cutoff=maf)
segdup = check_segdups(de_novos)
if fix_symbols:
de_novos['symbol'] = fix_missing_gene_symbols(de_novos, build)
pass_status = filter_function(de_novos, status & segdup) & status & segdup
if annotate_only:
de_novos['pass'] = pass_status
else:
de_novos = de_novos[pass_status]
return standardise_columns(de_novos)
def test_exclude_segdups(self):
''' check that counting alleles from DP4 entries works correctly
'''
# define variants that lie around the boundaries of a segdup region
variants = DataFrame({'person_stable_id': ['a', 'a', 'a', 'a', 'a', 'a'],
'chrom': ['1', '1', '1', '1', '1', '1'],
'pos': [1379893, 1379895, 1379894, 1384309, 1384310, 1384311],
'ref': ['A', 'G', 'A', 'G', 'A', 'G'],
'alt': ['C', 'T', 'C', 'T', 'C', 'T'],
'symbol': ['TEST1', 'TEST1', 'TEST1', 'TEST1', 'TEST1', 'TEST1'],
})
expected = [True, False, False, False, False, True]
self.assertEqual(check_segdups(variants), expected)
def test_exclude_segdups(self):
''' check that counting alleles from DP4 entries works correctly
'''
# define variants that lie around the boundaries of a segdup region
variants = DataFrame({
'person_stable_id': ['a', 'a', 'a', 'a', 'a', 'a'],
'chrom': ['1', '1', '1', '1', '1', '1'],
'pos': [1379893, 1379895, 1379894, 1384309, 1384310, 1384311],
'ref': ['A', 'G', 'A', 'G', 'A', 'G'],
'alt': ['C', 'T', 'C', 'T', 'C', 'T'],
'symbol': ['TEST1', 'TEST1', 'TEST1', 'TEST1', 'TEST1', 'TEST1'],
})
expected = [True, False, False, False, False, True]
self.assertEqual(check_segdups(variants), expected)
def screen_candidates(de_novos_path, fails_path, filter_function, maf=0.01,
fix_symbols=True, annotate_only=False):
""" load and optionally filter candidate de novo mutations.
Args:
de_novos_path: path to table of unfiltered canddiate DNMs
fails_path: path to file listing samples which failed QC, and therefore
all of their candidates need to be excluded.
filter_function: function for filtering the candidates, either
filter_denovogear_sites(), or filter_missing_indels().
maf: MAF threshold for filtering. This is 0.01 for denovogear sites,
and 0 for the missing indels.
fix_symbols: whether to annotate HGNC symbols for candidates
missing these.
annotate_only: whether to include a column indicating pass status, rather
than excluding all candidates which fail the filtering.
Returns:
pandas DataFrame of candidate de novo mutations.
"""
if de_novos_path is None:
return None
# load the datasets
de_novos = load_candidates(de_novos_path)
sample_fails = []
if fails_path is not None:
sample_fails = [ x.strip() for x in open(fails_path) ]
# run some initial screening
status = preliminary_filtering(de_novos, sample_fails, maf_cutoff=maf)
segdup = check_segdups(de_novos)
if fix_symbols:
de_novos['symbol'] = fix_missing_gene_symbols(de_novos)
pass_status = filter_function(de_novos, status & segdup) & status & segdup
if annotate_only:
de_novos['pass'] = pass_status
else:
de_novos = de_novos[pass_status]
return standardise_columns(de_novos)
