def do_access(fa_fname, exclude_fnames=(), min_gap_size=5000):
"""List the locations of accessible sequence regions in a FASTA file."""
access_regions = GA.from_rows(get_regions(fa_fname))
for ex_fname in exclude_fnames:
excluded = tabio.read(ex_fname, 'bed3')
access_regions = access_regions.subtract(excluded)
return GA.from_rows(join_regions(access_regions, min_gap_size))
def _from_intervals(coords):
garr = GA(
pd.DataFrame(list(coords),
columns=['start', 'end',
'gene']).assign(chromosome='chr0'))
garr.sort_columns()
return garr
def do_access(fa_fname, exclude_fnames=(), min_gap_size=5000,
skip_noncanonical=True):
"""List the locations of accessible sequence regions in a FASTA file."""
fa_regions = get_regions(fa_fname)
if skip_noncanonical:
fa_regions = drop_noncanonical_contigs(fa_regions)
access_regions = GA.from_rows(fa_regions)
for ex_fname in exclude_fnames:
excluded = tabio.read(ex_fname, 'bed3')
access_regions = access_regions.subtract(excluded)
return GA.from_rows(join_regions(access_regions, min_gap_size))
def guess_chromosome_regions(targets, telomere_size):
"""Determine (minimum) chromosome lengths from target coordinates."""
endpoints = [subarr.end.iat[-1] for _c, subarr in targets.by_chromosome()]
whole_chroms = GA.from_columns({
'chromosome': targets.chromosome.drop_duplicates(),
'start': telomere_size,
'end': endpoints})
return whole_chroms
def guess_chromosome_regions(targets, telomere_size):
"""Determine (minimum) chromosome lengths from target coordinates."""
endpoints = [subarr.end.iat[-1] for _c, subarr in targets.by_chromosome()]
whole_chroms = GA.from_columns({
'chromosome': targets.chromosome.drop_duplicates(),
'start': telomere_size,
'end': endpoints})
return whole_chroms
def test_residuals(self):
cnarr = cnvlib.read("formats/amplicon.cnr")
segments = cnvlib.read("formats/amplicon.cns")
regions = GenomicArray(segments.data).drop_extra_columns()
for grouping_arg in (None, segments, regions):
resid = cnarr.residuals(grouping_arg)
self.assertAlmostEqual(0, resid.mean(), delta=.3)
self.assertAlmostEqual(1, np.percentile(resid, 80), delta=.2)
self.assertAlmostEqual(2, resid.std(), delta=.5)
def __init__(self, data_table, meta_dict=None):
GenomicArray.__init__(self, data_table, meta_dict)
def __init__(self, data_table, meta_dict=None):
GenomicArray.__init__(self, data_table, meta_dict)
def _from_intervals(coords):
garr = GA(pd.DataFrame(list(coords),
columns=['start', 'end', 'gene'])
.assign(chromosome='chr0'))
garr.sort_columns()
return garr