def genotype_ibs_segments(genotype,
id1,
id2,
snps,
error_filter='median',
error_filter_length=5,
margin=0.0,
min_ibs_len_snp=400,
debug=False):
'''Return Identical-by-State (IBS >= 1) segments between two genoypes of samples id1 and id2
in the SNP range [snp[0],snp[1]) (if snp is a tuple) or the subset of SNPs, if snps is an array.
See ibs_segments() for a description of optional parameters.'''
num_snps = genotype.num_snps
g = genotype.data
g1 = recode.recode_single_genotype(g[snps, id1, :])
g2 = recode.recode_single_genotype(g[snps, id2, :])
d = (recode.ibs_state(g1, g2) == 0).astype(np.byte)
# Consider informative or the specified SNPs only
filtered_diff = filter_diff(d, error_filter, error_filter_length)
error_snps = snps[np.nonzero(d - filtered_diff)[0]]
# Detect edges as non-zero gradient points; output sufficiently long segments
if np.size(filtered_diff) == 0:
# No data to consider ==> no IBD intervals can be identified
segments = []
else:
# Convert recombination locations to segments of no recombination; filter short segments
bp = genotype.snp['base_pair']
#print segment.segments_with_value(filtered_diff, 0, min_ibs_len_snp)
segments = [
Segment(((x[0], x[1])), [id1, id2],
(bp[x[0]], segment.stop_bp(bp, x[1], num_snps)),
error_snps=segment.in_segment(error_snps, x),
collapse_to_set=False) for x in
segment.segments_with_value(filtered_diff, 0, min_ibs_len_snp)
]
# Cut segment margins
if margin >= constants.SMALL_FLOAT:
segments = [
s for s in (s.middle_part(
genotype.nearest_snp, bp, margin, collapse_to_set=False)
for s in segments) if s
]
# Restrict errors to those inside segments
segment_set = SegmentSet(segments,
np.array(util.flattened_meshgrid(reduce(list.__add__, (s.error_snps.tolist() for s in segments)),
np.array([id1, id2])), dtype=int) \
if segments else gt.empty_errors_array())
if debug:
print 'ibs_segments()', segment_set
print 'errors', segment_set.errors
return segment_set
def genotype_ibs_segments(genotype, id1, id2, snps,
error_filter='median', error_filter_length=5, margin=0.0,
min_ibs_len_snp=400, debug=False):
'''Return Identical-by-State (IBS >= 1) segments between two genoypes of samples id1 and id2
in the SNP range [snp[0],snp[1]) (if snp is a tuple) or the subset of SNPs, if snps is an array.
See ibs_segments() for a description of optional parameters.'''
num_snps = genotype.num_snps
g = genotype.data
g1 = recode.recode_single_genotype(g[snps, id1, :])
g2 = recode.recode_single_genotype(g[snps, id2, :])
d = (recode.ibs_state(g1, g2) == 0).astype(np.byte)
# Consider informative or the specified SNPs only
filtered_diff = filter_diff(d, error_filter, error_filter_length)
error_snps = snps[np.nonzero(d - filtered_diff)[0]]
# Detect edges as non-zero gradient points; output sufficiently long segments
if np.size(filtered_diff) == 0:
# No data to consider ==> no IBD intervals can be identified
segments = []
else:
# Convert recombination locations to segments of no recombination; filter short segments
bp = genotype.snp['base_pair']
#print segment.segments_with_value(filtered_diff, 0, min_ibs_len_snp)
segments = [Segment(((x[0], x[1])), [id1, id2], (bp[x[0]], segment.stop_bp(bp, x[1], num_snps)),
error_snps=segment.in_segment(error_snps, x), collapse_to_set=False)
for x in segment.segments_with_value(filtered_diff, 0, min_ibs_len_snp)]
# Cut segment margins
if margin >= constants.SMALL_FLOAT:
segments = [s for s in (s.middle_part(genotype.nearest_snp, bp, margin, collapse_to_set=False)
for s in segments) if s]
# Restrict errors to those inside segments
segment_set = SegmentSet(segments,
np.array(util.flattened_meshgrid(reduce(list.__add__, (s.error_snps.tolist() for s in segments)),
np.array([id1, id2])), dtype=int) \
if segments else gt.empty_errors_array())
if debug:
print 'ibs_segments()', segment_set
print 'errors', segment_set.errors
return segment_set
def ibs_segments(haplotype,
id1,
id2,
hap1_type,
hap2_type,
snps=None,
include_alt_phase=False,
error_filter='median',
error_filter_length=5,
length_bound=None,
min_segment_length=INDETERMINATE,
margin=0.0,
debug=False):
'''Return 1) Identical-by-State (IBS) segments separated by recombination events between two
sample haplotypes (id1, hap1_type) and (id2, hap2_type). The 2-D output array's ith row format is
(segment_start, segment_stop),
(id1, hap1), (id2, hap2),
(segment_start_bp, segment_stop_bp, segment_length_in_bp, num_errors_in_segment)
The SNP range is [segment_start, segment_stop) where start=inclusive and stop is exclusive.
2) List of het_snp indices at which there are likely genotype errors.
Options:
snps - list of SNPs to base the comparison on. For parent-child comparisons, these should
be heterozygous SNPs in the parent's genotype, distinguishing its haplotypes
and used to locate segments. For unphased-phased individuals, these should be the list of
homozygous SNPs at the unphased individual (those that have data).
If not specified, all SNPs are used.
length_bound - minimum segment length bound type:
None: no lower bound enforced
'base_pair': output segments of at least min_segment_length [base pair]
'snp': output segments of at least min_segment_length consecutive SNPs out of the snps list.
This is useful only if snps includes all SNPs (or is None)
*NOTE*: min_segment_length''s units are interpreted differently depending on length_bound.
margin = fraction of segment to discard near the endpoints (margin/2 is removed from each side).'''
if debug:
print 'Computing IBD segments between haplotypes (%d,%d), (%d,%d); filter %s length %d' % \
(id1, hap1_type, id2, hap2_type, error_filter, error_filter_length)
d = diff.all_diffs(haplotype.data,
id1,
id2,
hap1_type=hap1_type,
hap2_type=hap2_type)[0]
# Segment length, as defined by the input parameters
segment_length = lambda f: np.inf if not length_bound else (
f.length
if length_bound == 'base_pair' else f.num_snps) # @UnusedVariable
# Consider informative or the specified SNPs only
snps = snps if snps is not None else haplotype.snp_range
snps = np.intersect1d(snps, np.where(d != INDETERMINATE)[0])
d_snps = d[snps]
filtered_diff = filter_diff(d_snps, error_filter, error_filter_length)
error_snps = snps[np.nonzero(d_snps - filtered_diff)[0]]
# Detect edges as non-zero gradient points; output sufficiently long segments
bp = haplotype.snp['base_pair']
num_snps = haplotype.num_snps
if np.size(filtered_diff) == 0:
# No data to consider ==> no IBD intervals can be identified
segments = []
else:
deriv = ndimage.convolve(filtered_diff, [1, -1])
edge = np.where(deriv != 0)[0]
initial_phase = hap1_type if filtered_diff[0] == 0 else 1 - hap1_type
if debug:
print 'initial_phase', initial_phase # , 'edge', edge
# Convert recombination locations to segments of no recombination; filter short segments
segments = [
f for f in (
Segment(((x[0], x[1])),
set(((id1, x[2]), (id2, hap2_type))), (
bp[x[0]], segment.stop_bp(bp, x[1], num_snps)),
error_snps=segment.in_segment(error_snps, x))
for x in segment.edges_to_segments(
snps, edge, initial_phase, haplotype.num_snps, hap1_type))
if segment_length(f) >= min_segment_length
]
# Cut segment margins
if margin >= constants.SMALL_FLOAT:
segments = [
s for s in (s.middle_part(haplotype.nearest_snp, bp, margin)
for s in segments) if s
]
# Restrict errors to those inside segments
segment_set = SegmentSet(segments,
np.array(util.flattened_meshgrid(reduce(list.__add__, (s.error_snps.tolist() for s in segments)),
np.array([id1, id2])), dtype=int) \
if segments else gt.empty_errors_array())
if debug:
print 'ibs_segments()', segment_set
print 'errors', segment_set.errors
return segment_set
def ibs_segments(haplotype, id1, id2, hap1_type, hap2_type, snps=None, include_alt_phase=False,
error_filter='median', error_filter_length=5,
length_bound=None, min_segment_length=INDETERMINATE, margin=0.0, debug=False):
'''Return 1) Identical-by-State (IBS) segments separated by recombination events between two
sample haplotypes (id1, hap1_type) and (id2, hap2_type). The 2-D output array's ith row format is
(segment_start, segment_stop),
(id1, hap1), (id2, hap2),
(segment_start_bp, segment_stop_bp, segment_length_in_bp, num_errors_in_segment)
The SNP range is [segment_start, segment_stop) where start=inclusive and stop is exclusive.
2) List of het_snp indices at which there are likely genotype errors.
Options:
snps - list of SNPs to base the comparison on. For parent-child comparisons, these should
be heterozygous SNPs in the parent's genotype, distinguishing its haplotypes
and used to locate segments. For unphased-phased individuals, these should be the list of
homozygous SNPs at the unphased individual (those that have data).
If not specified, all SNPs are used.
length_bound - minimum segment length bound type:
None: no lower bound enforced
'base_pair': output segments of at least min_segment_length [base pair]
'snp': output segments of at least min_segment_length consecutive SNPs out of the snps list.
This is useful only if snps includes all SNPs (or is None)
*NOTE*: min_segment_length''s units are interpreted differently depending on length_bound.
margin = fraction of segment to discard near the endpoints (margin/2 is removed from each side).'''
if debug:
print 'Computing IBD segments between haplotypes (%d,%d), (%d,%d); filter %s length %d' % \
(id1, hap1_type, id2, hap2_type, error_filter, error_filter_length)
d = diff.all_diffs(haplotype.data, id1, id2, hap1_type=hap1_type, hap2_type=hap2_type)[0]
# Segment length, as defined by the input parameters
segment_length = lambda f: np.inf if not length_bound else (f.length if length_bound == 'base_pair' else f.num_snps) # @UnusedVariable
# Consider informative or the specified SNPs only
snps = snps if snps is not None else haplotype.snp_range
snps = np.intersect1d(snps, np.where(d != INDETERMINATE)[0])
d_snps = d[snps]
filtered_diff = filter_diff(d_snps, error_filter, error_filter_length)
error_snps = snps[np.nonzero(d_snps - filtered_diff)[0]]
# Detect edges as non-zero gradient points; output sufficiently long segments
bp = haplotype.snp['base_pair']
num_snps = haplotype.num_snps
if np.size(filtered_diff) == 0:
# No data to consider ==> no IBD intervals can be identified
segments = []
else:
deriv = ndimage.convolve(filtered_diff, [1, -1])
edge = np.where(deriv != 0)[0]
initial_phase = hap1_type if filtered_diff[0] == 0 else 1 - hap1_type
if debug:
print 'initial_phase', initial_phase # , 'edge', edge
# Convert recombination locations to segments of no recombination; filter short segments
segments = [f for f in (Segment(((x[0], x[1])), set(((id1, x[2]), (id2, hap2_type))),
(bp[x[0]], segment.stop_bp(bp, x[1], num_snps)),
error_snps=segment.in_segment(error_snps, x))
for x in segment.edges_to_segments(snps, edge, initial_phase,
haplotype.num_snps, hap1_type))
if segment_length(f) >= min_segment_length]
# Cut segment margins
if margin >= constants.SMALL_FLOAT:
segments = [s for s in (s.middle_part(haplotype.nearest_snp, bp, margin) for s in segments) if s]
# Restrict errors to those inside segments
segment_set = SegmentSet(segments,
np.array(util.flattened_meshgrid(reduce(list.__add__, (s.error_snps.tolist() for s in segments)),
np.array([id1, id2])), dtype=int) \
if segments else gt.empty_errors_array())
if debug:
print 'ibs_segments()', segment_set
print 'errors', segment_set.errors
return segment_set