def __init__(self, data, snp, sample_id):
'''
Construct a genotype set from data arrays:
- snp: SNP metadata record array (contains chromosome, name, morgans, base-pair location)
- data: a 3-D genotype data array: (individual x SNP x allele)
- sample_id: genotyped individuals' ID set
'''
# People's IDs
self.sample_id = sample_id
self.data = data
self._num_snps = self.data.shape[0]
self._num_samples = self.data.shape[1]
self._snp_range = None
# SNP metadata: SNP label, chromosome number, Genetic distance in Morgans, and
# base pair location for each SNP
self.snp = snp
# Base-pair-location to snp-index map, lazily-initialized + cached
base_pair = self.snp['base_pair']
self._base_pair = base_pair # np.array([int(base_pair)]) if base_pair.size == 1 else base_pair
self._bp_to_snp = dict_invert(dict(enumerate(self._base_pair)))
# Construct a BST for fast bp queries
self._snp_tree = BinarySearchTree(values=self._base_pair[optimal_insertion_order(self._num_snps)])
self._snp_index_tree = util.list_index_tree(self._base_pair)
# A genetic map: lists the two allele letters corresponding to 1 and 2 for each SNP, according
# their order in the self.snp array.
self.map = []
# General metadata, for easy handling of CGI data
self.metadata = []
# samples for which the parent-of-origin phase is determined
self.poo_phase = np.zeros((self._num_samples,), dtype=np.byte)
def pipeline_monogenic_validation(work_dir=os.environ['OBER_OUT'] + '/requests/monogenic/work',
index_segments_dir=os.environ['OBER_OUT'] + '/requests/monogenic/work/index_segments',
region_size=100,
theta_affinity=0.95,
theta_weight=0.5,
regenerate_segments=True,
snps=None, # np.array([6, 8]),
debug=1,
debug_sample=512):
# Load SNPs
problem = im.io.read_plink(prefix=work_dir + '/monogenic.12', pedigree=im.itu.HUTT_PED, haplotype=None, frames=None)
# Testing: simulate aligned samples output (hap types should be 2 in the imputed genotype output line)
problem.haplotype.poo_phase = np.zeros((problem.num_samples,), dtype=np.byte)
problem.haplotype.poo_phase[np.array([0, 1])] = 1
problem.haplotype.poo_phase[np.array([2, 3])] = -1
# Create segments only for the regions around each snp
if regenerate_segments:
for row in (problem.info.snp[snps] if snps is not None else problem.info.snp):
# Find SNP's region (the one containing its base-pair position)
chrom, bp = row['chrom'], row['base_pair']
phasing_dir = '%s/phasing/chr%d' % (os.environ['OBER_OUT'], chrom)
index_segments_chrom_dir = '%s/chr%d' % (index_segments_dir, chrom)
info_file = '%s/hutt.phased.info.npz' % (phasing_dir,)
info = im.io.read_info_npz(info_file)
snp_bp = info.snp['base_pair']
snp_index = util.nearest_neighbor_in_list_tree(bp, snp_bp, util.list_index_tree(snp_bp))
snp_index = snp_index if snp_bp[snp_index] <= bp else snp_index - 1
start = region_size * (snp_index / region_size)
stop = start + region_size
segment_file = '%s/segments-%d-%d.out' % (index_segments_chrom_dir, start, stop)
if not os.path.exists(segment_file):
util.mkdir_if_not_exists(index_segments_chrom_dir)
util.run_command('find-segments-of-snp-range %d %d < %s/segments.out > %s' % (start, stop, phasing_dir, segment_file))
# Index segments
if regenerate_segments or \
not os.path.exists('%s/metadata.npz' % (index_segments_chrom_dir,)) or \
not os.path.exists('%s/region-%d.npz' % (index_segments_chrom_dir, start)):
index_segments_beagle.main(segment_file, info_file, segment_file, index_segments_chrom_dir,
snp_index=snp_index, debug=2,
theta_affinity=theta_affinity, theta_weight=theta_weight)
# Impute using the newly generated segment index
_, t = im.v.iv.impute_problem(problem, debug=debug, remove_partial_calls=True,
segment_location=index_segments_dir, # if regenerate_segments else None,
snps=snps, debug_sample=debug_sample)
im.io.write_plink(im.Problem(genotype=t.imputed, pedigree=im.examples.hutt_pedigree(), haplotype=None, frames=None),
work_dir + '/imputed.12', save_frames=False, save_haplotype=False)
im.cgi.io_cgi.write_imputed(t, sys.stdout, poo_phase=problem.haplotype.poo_phase)
with open(work_dir + '/imputed.12.lgen', 'wb') as f:
im.cgi.io_cgi.write_imputed_lgen(t, f)
return t
def _load_chrom(self, chrom):
'''Load index of a new chromosome number, chrom.'''
# Load index metadata
self._chrom = chrom
metadata = np.load('%s/chr%d/metadata.npz' % (self._index_dir, chrom))
self._snp = metadata['snp']
self._region_size = metadata['region_size']
# Currently-active region is [start,stop)
self._start = 0
self._stop = 0
self._region_num = -1
# Construct a BST for fast queries of the left-neighboring SNP of a base-pair position
base_pair = self._snp['base_pair']
self._base_pair = np.array([int(base_pair)]) if base_pair.size == 1 else base_pair
self._snp_index_tree = util.list_index_tree(self._base_pair)
def _load_chrom(self, chrom):
'''Load index of a new chromosome number, chrom.'''
# Load index metadata
self._chrom = chrom
metadata = np.load('%s/chr%d/metadata.npz' % (self._index_dir, chrom))
self._snp = metadata['snp']
self._region_size = metadata['region_size']
# Currently-active region is [start,stop)
self._start = 0
self._stop = 0
self._region_num = -1
# Construct a BST for fast queries of the left-neighboring SNP of a base-pair position
base_pair = self._snp['base_pair']
self._base_pair = np.array([int(base_pair)
]) if base_pair.size == 1 else base_pair
self._snp_index_tree = util.list_index_tree(self._base_pair)
def pipeline_monogenic_validation(
work_dir=os.environ['OBER_OUT'] + '/requests/monogenic/work',
index_segments_dir=os.environ['OBER_OUT'] +
'/requests/monogenic/work/index_segments',
region_size=100,
theta_affinity=0.95,
theta_weight=0.5,
regenerate_segments=True,
snps=None, # np.array([6, 8]),
debug=1,
debug_sample=512):
# Load SNPs
problem = im.io.read_plink(prefix=work_dir + '/monogenic.12',
pedigree=im.itu.HUTT_PED,
haplotype=None,
frames=None)
# Testing: simulate aligned samples output (hap types should be 2 in the imputed genotype output line)
problem.haplotype.poo_phase = np.zeros((problem.num_samples, ),
dtype=np.byte)
problem.haplotype.poo_phase[np.array([0, 1])] = 1
problem.haplotype.poo_phase[np.array([2, 3])] = -1
# Create segments only for the regions around each snp
if regenerate_segments:
for row in (problem.info.snp[snps]
if snps is not None else problem.info.snp):
# Find SNP's region (the one containing its base-pair position)
chrom, bp = row['chrom'], row['base_pair']
phasing_dir = '%s/phasing/chr%d' % (os.environ['OBER_OUT'], chrom)
index_segments_chrom_dir = '%s/chr%d' % (index_segments_dir, chrom)
info_file = '%s/hutt.phased.info.npz' % (phasing_dir, )
info = im.io.read_info_npz(info_file)
snp_bp = info.snp['base_pair']
snp_index = util.nearest_neighbor_in_list_tree(
bp, snp_bp, util.list_index_tree(snp_bp))
snp_index = snp_index if snp_bp[snp_index] <= bp else snp_index - 1
start = region_size * (snp_index / region_size)
stop = start + region_size
segment_file = '%s/segments-%d-%d.out' % (index_segments_chrom_dir,
start, stop)
if not os.path.exists(segment_file):
util.mkdir_if_not_exists(index_segments_chrom_dir)
util.run_command(
'find-segments-of-snp-range %d %d < %s/segments.out > %s' %
(start, stop, phasing_dir, segment_file))
# Index segments
if regenerate_segments or \
not os.path.exists('%s/metadata.npz' % (index_segments_chrom_dir,)) or \
not os.path.exists('%s/region-%d.npz' % (index_segments_chrom_dir, start)):
index_segments_beagle.main(segment_file,
info_file,
segment_file,
index_segments_chrom_dir,
snp_index=snp_index,
debug=2,
theta_affinity=theta_affinity,
theta_weight=theta_weight)
# Impute using the newly generated segment index
_, t = im.v.iv.impute_problem(
problem,
debug=debug,
remove_partial_calls=True,
segment_location=index_segments_dir, # if regenerate_segments else None,
snps=snps,
debug_sample=debug_sample)
im.io.write_plink(im.Problem(genotype=t.imputed,
pedigree=im.examples.hutt_pedigree(),
haplotype=None,
frames=None),
work_dir + '/imputed.12',
save_frames=False,
save_haplotype=False)
im.cgi.io_cgi.write_imputed(t,
sys.stdout,
poo_phase=problem.haplotype.poo_phase)
with open(work_dir + '/imputed.12.lgen', 'wb') as f:
im.cgi.io_cgi.write_imputed_lgen(t, f)
return t