def get_bim_metadata(bim_file):
'''Return (a)
a dictionary of chromosome-to-bp-length from a BIM file. Note: the relevant length
is measured between the first and last SNPs, and may be shorter than the total chromosome length;
(b) a dictionary of chromosome-to-list-of-snp-names.'''
# a = list(itemutil.index_of_change(((int(x[0]), int(x[3]))
# for x in csv.reader(bim_file, delimiter='\t', skipinitialspace=True)),
# output_first=True, output_last=True,
# output_value=True,
# comparator=lambda x,y: x[0]==y[0]))
# endpoints = np.diff(np.array([(x[1][1] if x[1] else 0, x[2][1] if x[2] else 0) for x in a]).flatten())[1:2*22:2]
# A BIM file is sorted by chromosome, then by SNP base-pair location
snp_names = util.mdict()
chr_endpoints = {}
prev = start = None
for line in csv.reader(bim_file, delimiter='\t', skipinitialspace=True):
chrom = int(line[0])
curr = (chrom, int(line[3]))
snp_names[chrom] = line[1]
if not start: start = curr
if prev and chrom != prev[0]:
chr_endpoints[start[0]] = prev[1] - start[1]
start = curr
prev = curr
chr_endpoints[start[0]] = prev[1] - start[1] # Last chromosome
return dict((k, chr_endpoints[k]) for k in CHROMOSOMES
if chr_endpoints.has_key(k)), snp_names
def get_bim_metadata(bim_file):
'''Return (a)
a dictionary of chromosome-to-bp-length from a BIM file. Note: the relevant length
is measured between the first and last SNPs, and may be shorter than the total chromosome length;
(b) a dictionary of chromosome-to-list-of-snp-names.'''
# a = list(itemutil.index_of_change(((int(x[0]), int(x[3]))
# for x in csv.reader(bim_file, delimiter='\t', skipinitialspace=True)),
# output_first=True, output_last=True,
# output_value=True,
# comparator=lambda x,y: x[0]==y[0]))
# endpoints = np.diff(np.array([(x[1][1] if x[1] else 0, x[2][1] if x[2] else 0) for x in a]).flatten())[1:2*22:2]
# A BIM file is sorted by chromosome, then by SNP base-pair location
snp_names = util.mdict()
chr_endpoints = {}
prev = start = None
for line in csv.reader(bim_file, delimiter='\t', skipinitialspace=True):
chrom = int(line[0])
curr = (chrom, int(line[3]))
snp_names[chrom] = line[1]
if not start: start = curr
if prev and chrom != prev[0]:
chr_endpoints[start[0]] = prev[1] - start[1]
start = curr
prev = curr
chr_endpoints[start[0]] = prev[1] - start[1] # Last chromosome
return dict((k, chr_endpoints[k]) for k in CHROMOSOMES if chr_endpoints.has_key(k)), snp_names
def sub_problem(self, samples, snps=None):
'''Return a sub-problem that contains a subset 'samples' of the genotyped nodes.'''
# Re-order samples so that all genotyped appear before all non-genotyped
if isinstance(samples, list): samples = np.array(samples)
# Create pedigree object
p = self.sub_pedigree(samples)
genotyped = np.where(samples < self.pedigree.num_genotyped)[0]
num_genotyped = len(genotyped)
samples = samples[np.concatenate((genotyped, np.where(samples >= self.pedigree.num_genotyped)[0]))]
# Create deep copies of relevant parts of data arrays
g, h = self.data
g_snp, h_snp, qc = self.genotype.snp, self.haplotype.snp, self.haplotype.qc
frames = self.frames
if snps is not None:
g, h, qc = g[snps, :, :], h[snps, :, :], qc[snps, :, :] if qc.size else None
g_snp, h_snp = g_snp[snps], g_snp[snps]
# Restrict frames to snps, convert to new SNP indices
orig_snp = dict((v, k) for k, v in enumerate(snps))
def sub_frame(frame):
for x in frame:
if orig_snp.has_key(x): yield orig_snp[x]
frames = util.mdict()
for k, v in frames.iteritems():
for frame in v:
frames[k] = sub_frame(frame)
genotyped = p.sample_index[0:num_genotyped]
g, h = g[:, genotyped, :].copy(), h[:, genotyped, :].copy()
if qc.size: qc = qc[:, genotyped, ].copy()
g_snp, h_snp = g_snp.copy(), h_snp.copy()
# Build sub-problem object graph
g = im.factory.GenotypeFactory.new_instance('genotype', g, g_snp)
h = im.factory.GenotypeFactory.new_instance('haplotype', h, h_snp)
h.qc = qc
# Build restricted info object
error = self.error[:, genotyped].copy() if self.error.size else self.error
if snps is not None and error.size: error = error[snps, :]
sample_set = set(samples)
sample_index_map = util.dict_invert(dict(enumerate(p.sample_index)))
ibd = im.segment.SegmentSet(im.segment.Segment(x.snp, map(lambda y: (sample_index_map[y[0]], y[1]), x.samples),
x.bp, error_snps=x.error_snps) for x in self.info.ibd if (sample_set >= set([y[0] for y in x.samples])))
info = ProblemInfo(p, g, snp=(self.info.snp[snps] if snps is not None else self.info.snp), ibd=ibd)
return Problem(p, g, haplotype=h, info=info, error=error, frames=frames, lam=self.lam)
def sub_problem_of_snps(self, snps=None):
'''Return a sub-problem that contains a subset of the SNPs. Assumes at least two SNPs.'''
# Re-order samples so that all genotyped appear before all non-genotyped
# Create deep copies of relevant parts of data arrays
g, h = self.data
g_snp, h_snp, qc = self.genotype.snp, self.haplotype.snp, self.haplotype.qc
frames = self.frames
if snps is not None:
g, h = g[snps, :, :], h[snps, :, :]
if qc.size: qc = qc[snps, :, :]
g_snp, h_snp = g_snp[snps], g_snp[snps]
# Restrict frames to snps, convert to new SNP indices
orig_snp = dict((v, k) for k, v in enumerate(snps))
def sub_frame(frame):
for x in frame:
if orig_snp.has_key(x): yield orig_snp[x]
frames = util.mdict()
for k, v in frames.iteritems():
for frame in v:
frames[k] = sub_frame(frame)
g, h = g.copy(), h.copy()
if qc.size:
qc = qc.copy()
g_snp, h_snp = g_snp.copy(), h_snp.copy()
# Build sub-problem object graph
g = im.factory.GenotypeFactory.new_instance('genotype', g, g_snp)
h = im.factory.GenotypeFactory.new_instance('haplotype', h, h_snp)
h.qc = qc
if self.haplotype.poo_phase is not None:
h.poo_phase = self.haplotype.poo_phase.copy()
if self.haplotype.hap_type is not None:
h.hap_type = self.haplotype.hap_type[snps].copy()
# Build restricted info object
error = self.error.copy() if self.error.size else self.error
if error.size: error = error[snps, :]
ibd = im.segment.SegmentSet(im.segment.Segment(x.snp, map(lambda y: (self.sample_index[y[0]], y[1]), x.samples),
x.bp, error_snps=x.error_snps) for x in self.info.ibd)
info = ProblemInfo(self.pedigree, g, snp=(self.info.snp[snps] if snps is not None else self.info.snp), ibd=ibd)
return Problem(self.pedigree, g, haplotype=h, info=info, error=error, frames=frames, lam=self.lam)
def __init__(self, items):
self._frames = util.mdict()
for k, v in items:
self._frames[k] = v
# Initialize
daos = db_gene.snp.snp_db_dao.Daos(url=options.db_url)
util.mkdir_if_not_exists(os.path.dirname(options.out_base_name))
# Set genetic distance column in BIM file (read locations from snp db) and save a new copy of it
snp_data = np.genfromtxt(input_file,
dtype=[
('chrom', np.uint8), # Chromosome # containing the SNP
('name', np.chararray), # SNP name (e.g., 'rs...')
('dist_cm', np.float), # Genetic position [CENTI-Morgans!!]
('base_pair', np.uint), # Base pair position on chromosome
('allele1', np.chararray),
('allele2', np.chararray)
])
snp_names = snp_data['name']
a = dict((x.name, x) for x in daos.snp_dao.get_snps_iter(snp_names))
# Note: our genetic distance unit is cM
snp_data['dist_cm'] = map(lambda x: x if x else 0.0, ((a[x].genetic_pos if a.has_key(x) else None) for x in snp_names))
np.savetxt(options.out_base_name + '.bim.new', snp_data, fmt='%d\t%s\t%f\t%d\t%s\t%s')
# For each chromosome in the PLINK file: load LD data, generate frame numbers, save them to a file
(c, s), frames = bu.get_bim_metadata(open(input_file, 'rb')), util.mdict()
for chrom in s.iterkeys():
for x in db_gene.snp.ld_graph.frames(chrom, s[chrom], daos.snp_dao, daos.ld_dao):
frames[chrom] = x
with open(options.out_base_name + '.frm', 'wb') as frm_file:
db_gene.snp.ld_graph.write_frames(frames, frm_file)
except:
traceback.print_exc(file=sys.stdout)
sys.exit(util.EXIT_FAILURE)
def __init__(self, items):
self._frames = util.mdict()
for k, v in items: self._frames[k] = v
dtype=[
('chrom', np.uint8), # Chromosome # containing the SNP
('name', np.chararray), # SNP name (e.g., 'rs...')
('dist_cm', np.float), # Genetic position [CENTI-Morgans!!]
('base_pair', np.uint), # Base pair position on chromosome
('allele1', np.chararray),
('allele2', np.chararray)
])
snp_names = snp_data['name']
a = dict((x.name, x) for x in daos.snp_dao.get_snps_iter(snp_names))
# Note: our genetic distance unit is cM
snp_data['dist_cm'] = map(lambda x: x if x else 0.0,
((a[x].genetic_pos if a.has_key(x) else None)
for x in snp_names))
np.savetxt(options.out_base_name + '.bim.new',
snp_data,
fmt='%d\t%s\t%f\t%d\t%s\t%s')
# For each chromosome in the PLINK file: load LD data, generate frame numbers, save them to a file
(c, s), frames = bu.get_bim_metadata(open(input_file,
'rb')), util.mdict()
for chrom in s.iterkeys():
for x in db_gene.snp.ld_graph.frames(chrom, s[chrom], daos.snp_dao,
daos.ld_dao):
frames[chrom] = x
with open(options.out_base_name + '.frm', 'wb') as frm_file:
db_gene.snp.ld_graph.write_frames(frames, frm_file)
except:
traceback.print_exc(file=sys.stdout)
sys.exit(util.EXIT_FAILURE)