def test_relatedness_coefficient():
kid = Sample('fam1', 'kid', 'dad', 'mom', '2', '2')
dad = Sample('fam1', 'dad', '-9', '-9', '1', '2')
mom = Sample('fam1', 'mom', '-9', '-9', '2', '2')
gma = Sample('fam1', 'gma', '-9', '-9', '2', '2')
ggma = Sample('fam1', 'ggma', '-9', '-9', '2', '2')
kid.mom = mom
kid.dad = dad
mom.mom = gma
gma.mom = ggma
unrelated = Sample('fam1', 'un', '-9', '-9', '2', '2')
from io import StringIO
p = Ped(StringIO())
p.families['fam1'] = Family([kid, mom, dad, gma, ggma, unrelated])
rel = p.relatedness_coefficient("mom", "dad")
assert rel == 0.0, rel
d = p.relatedness_coefficient("mom", "kid")
assert d == 0.5, d
d = p.relatedness_coefficient("dad", "gma")
assert d == 0.0, d
d = p.relatedness_coefficient("mom", "gma")
assert d == 0.5, d
d = p.relatedness_coefficient("kid", "gma")
assert d == 0.25, d
d = p.relatedness_coefficient("kid", "ggma")
assert d == 0.125, d
assert p.relatedness_coefficient("mom", "mom") == 1.0
def t_ped_check():
try:
import pandas as pd
import cyvcf2
cyvcf2
except ImportError:
return
p = Ped(op.join(HERE, 'peddy/tests/test.mendel.ped'))
v = p.ped_check(op.join(HERE, b'peddy/tests/test.mendel.vcf.gz'))
assert isinstance(v, pd.DataFrame), v
# remove samples
f = list(p.families.values())[0]
l = len(f.samples)
s = f.samples[-1]
f.samples = f.samples[:-1]
assert l - 1 == len(f.samples)
v = p.ped_check(op.join(HERE, b'peddy/tests/test.mendel.vcf.gz'))
assert isinstance(v, pd.DataFrame), v
assert "ibs0" in v.columns
# changed the sample id of a sample
s.sample_id = "XDFSDFX"
f.samples.append(s)
v = p.ped_check(op.join(HERE, b'peddy/tests/test.mendel.vcf.gz'))
assert isinstance(v, pd.DataFrame), v
def t_ped_check():
try:
import pandas as pd
import cyvcf2
cyvcf2
except ImportError:
return
p = Ped(op.join(HERE, 'peddy/tests/test.mendel.ped'))
v = p.ped_check(op.join(HERE, b'peddy/tests/test.mendel.vcf.gz'))
assert isinstance(v, pd.DataFrame), v
# remove samples
f = list(p.families.values())[0]
l = len(f.samples)
s = f.samples[-1]
f.samples = f.samples[:-1]
assert l -1 == len(f.samples)
v = p.ped_check(op.join(HERE, b'peddy/tests/test.mendel.vcf.gz'))
assert isinstance(v, pd.DataFrame), v
assert "ibs0" in v.columns
# changed the sample id of a sample
s.sample_id = "XDFSDFX"
f.samples.append(s)
v = p.ped_check(op.join(HERE, b'peddy/tests/test.mendel.vcf.gz'))
assert isinstance(v, pd.DataFrame), v
def create_samples(self):
ped = Ped(self.ped_path)
cols = [
'sample_id', 'family_id', 'name', 'paternal_id', 'maternal_id',
'sex', 'phenotype'
]
if ped.header is None:
ped.header = [x for x in cols if x != 'name']
samples = [fix_sample_name(s) for s in self.vcf.samples]
cols = [
'sample_id', 'family_id', 'name', 'paternal_id', 'maternal_id',
'sex', 'phenotype'
]
idxs, rows, not_in_vcf = [], [], []
cols.extend(ped.header[6:])
sample_id = 1
for i, s in enumerate(ped.samples(), start=1):
try:
idxs.append(samples.index(fix_sample_name(s.sample_id)))
except ValueError:
not_in_vcf.append(s.sample_id)
continue
rows.append([
sample_id,
s.family_id,
fix_sample_name(s.sample_id),
fix_sample_name(str(s.paternal_id)),
fix_sample_name(str(s.maternal_id)),
'1' if s.sex == 'male' else '2' if s.sex == 'female' else '-9',
'2' if s.affected is True else
'1' if s.affected is False else '-9',
] + s.attrs)
sample_id += 1
if len(not_in_vcf) > 0:
print("not in VCF: %s" % ",".join(not_in_vcf), file=sys.stderr)
scols = [sql.Column('sample_id', sql.Integer, primary_key=True)]
for i, col in enumerate(cols[1:], start=1):
vals = None
try:
vals = [r[i] for r in rows]
l = max(len(v) for v in vals)
scols.append(sql.Column(col, Unicode(l)))
except:
print(col, vals, file=sys.stderr)
raise
t = sql.Table('samples', self.metadata, *scols)
t.drop(checkfirst=True)
t.create()
self.engine.execute(t.insert(), [dict(zip(cols, r)) for r in rows])
# track the order to pull from the genotype fields.
self.sample_idxs = np.array(idxs)
return [r[2] for r in rows]
def test_sex_check():
if sys.version_info[0] == 3:
return
p = Ped(op.join(HERE, 'peddy/tests/test.mendel.ped'))
df = p.sex_check(op.join(HERE, 'peddy/tests/test.mendel.vcf.gz'))
assert "predicted_sex" in df.columns
assert "ped_sex", df.columns
assert "error" in df.columns
def test_relatedness_coefficient():
kid = Sample('fam1', 'kid', 'dad', 'mom', '2', '2')
dad = Sample('fam1', 'dad', '-9', '-9', '1', '2')
mom = Sample('fam1', 'mom', '-9', '-9', '2', '2')
gma = Sample('fam1', 'gma', '-9', '-9', '2', '2')
ggma = Sample('fam1', 'ggma', '-9', '-9', '2', '2')
kid.mom = mom
kid.dad = dad
mom.mom = gma
gma.mom = ggma
unrelated = Sample('fam1', 'un', '-9', '-9', '2', '2')
from io import StringIO
p = Ped(StringIO())
p.families['fam1'] = Family([kid, mom, dad, gma, ggma, unrelated])
rel = p.relatedness_coefficient("mom", "dad")
assert rel == 0.0, rel
d = p.relatedness_coefficient("mom", "kid")
assert d == 0.5, d
d = p.relatedness_coefficient("dad", "gma")
assert d == 0.0, d
d = p.relatedness_coefficient("mom", "gma")
assert d == 0.5, d
d = p.relatedness_coefficient("kid", "gma")
assert d == 0.25, d
d = p.relatedness_coefficient("kid", "ggma")
assert d == 0.125, d
assert p.relatedness_coefficient("mom", "mom") == 1.0
def test_relatedness_coefficient_missing_parent():
gma = Sample('X28935', 'gma', '-9', '-9', '2', '1')
mom = Sample('X28935', 'mom', '-9', 'gma', '2', '1')
dad = Sample('X28935', 'dad', '-9', '-9', '1', '1')
kid1 = Sample('X28935', 'kid1', '-9', 'mom', '1', '1')
kid2 = Sample('X28935', 'kid2', '-9', 'mom', '2', '1')
kid1 = Sample('X28935', 'kid1', 'dad', 'mom', '1', '1')
kid2 = Sample('X28935', 'kid2', 'dad', 'mom', '2', '1')
kid1.mom = mom
kid2.mom = mom
mom.mom = gma
kid1.dad = dad
kid2.dad = dad
from io import StringIO
p = Ped(StringIO())
p.families['X28935'] = Family([kid1, kid2, mom, gma]) #, dad])
assert "siblings" in p.relation('kid1', 'kid2'), p.relation('kid1', 'kid2')
v = p.relatedness_coefficient('kid1', 'kid2')
assert v == 0.5, v
v = p.relatedness_coefficient('gma', 'kid2')
assert v == 0.25, v
v = p.relatedness_coefficient('gma', 'kid1')
assert v == 0.25, v
v = p.relatedness_coefficient('gma', 'mom')
assert v == 0.5, v
def test_relation():
kid = Sample('fam1', 'kid', 'dad', 'mom', '2', '2')
dad = Sample('fam1', 'dad', '-9', '-9', '1', '2')
mom = Sample('fam1', 'mom', '-9', '-9', '2', '2')
kid.mom = mom
kid.dad = dad
from io import StringIO
p = Ped(StringIO())
p.families['fam1'] = Family([kid, mom, dad])
assert p.relation("mom", "dad") == "mom-dad"
def test_relation():
kid = Sample('fam1', 'kid', 'dad', 'mom', '2', '2')
dad = Sample('fam1', 'dad', '-9', '-9', '1', '2')
mom = Sample('fam1', 'mom', '-9', '-9', '2', '2')
kid.mom = mom
kid.dad = dad
from io import StringIO
p = Ped(StringIO())
p.families['fam1'] = Family([kid, mom, dad])
assert p.relation("mom", "dad") == "mom-dad"
def create_samples(self):
ped = Ped(self.ped_path)
cols = ["sample_id", "family_id", "name", "paternal_id", "maternal_id", "sex", "phenotype"]
if ped.header is None:
ped.header = [x for x in cols if x != "name"]
samples = [fix_sample_name(s) for s in self.vcf.samples]
cols = ["sample_id", "family_id", "name", "paternal_id", "maternal_id", "sex", "phenotype"]
idxs, rows, not_in_vcf = [], [], []
cols.extend(ped.header[6:])
sample_id = 1
for i, s in enumerate(ped.samples(), start=1):
try:
idxs.append(samples.index(fix_sample_name(s.sample_id)))
except ValueError:
not_in_vcf.append(s.sample_id)
continue
rows.append(
[
sample_id,
s.family_id,
fix_sample_name(s.sample_id),
fix_sample_name(str(s.paternal_id)),
fix_sample_name(str(s.maternal_id)),
"1" if s.sex == "male" else "2" if s.sex == "female" else "-9",
"2" if s.affected is True else "1" if s.affected is False else "-9",
]
+ s.attrs
)
sample_id += 1
if len(not_in_vcf) > 0:
print("not in VCF: %s" % ",".join(not_in_vcf), file=sys.stderr)
scols = [sql.Column("sample_id", sql.Integer, primary_key=True)]
for i, col in enumerate(cols[1:], start=1):
vals = None
try:
vals = [r[i] for r in rows]
l = max(len(v) for v in vals)
scols.append(sql.Column(col, Unicode(l)))
except:
print(col, vals, file=sys.stderr)
raise
t = sql.Table("samples", self.metadata, *scols)
t.drop(checkfirst=True)
t.create()
self.engine.execute(t.insert(), [dict(zip(cols, r)) for r in rows])
# track the order to pull from the genotype fields.
self.sample_idxs = np.array(idxs)
return [r[2] for r in rows]
def test_relatedness_coefficient_missing_parent():
gma = Sample('X28935', 'gma', '-9', '-9', '2', '1')
mom = Sample('X28935', 'mom', '-9', 'gma', '2', '1')
dad = Sample('X28935', 'dad', '-9', '-9', '1', '1')
kid1 = Sample('X28935', 'kid1', '-9', 'mom', '1', '1')
kid2 = Sample('X28935', 'kid2', '-9', 'mom', '2', '1')
kid1 = Sample('X28935', 'kid1', 'dad', 'mom', '1', '1')
kid2 = Sample('X28935', 'kid2', 'dad', 'mom', '2', '1')
kid1.mom = mom
kid2.mom = mom
mom.mom = gma
kid1.dad = dad
kid2.dad = dad
from io import StringIO
p = Ped(StringIO())
p.families['X28935'] = Family([kid1, kid2, mom, gma])#, dad])
assert "siblings" in p.relation('kid1', 'kid2'), p.relation('kid1', 'kid2')
v = p.relatedness_coefficient('kid1', 'kid2')
assert v == 0.5, v
v = p.relatedness_coefficient('gma', 'kid2')
assert v == 0.25, v
v = p.relatedness_coefficient('gma', 'kid1')
assert v == 0.25, v
v = p.relatedness_coefficient('gma', 'mom')
assert v == 0.5, v
def generate_trios(pedfile, f1=True):
"""
Given a PED file, specify whether you want
to output trios w/r/t the F1 or F2 generation
(i.e., whether the kid in each trio is an F1 or F2).
"""
from peddy import Ped
ped = Ped(pedfile)
p0s = [k for k in ped.samples() if k.mom is None]
f1s = [k for k in ped.samples() if k.mom and k.dad and k.mom.mom is None]
f2s = [k for k in ped.samples() if k.mom and k.mom.mom]
if f1: trios = f1s
else: trios = f2s
for i in trios:
yield (i.sample_id, i.mom.sample_id, i.dad.sample_id)
def test_trios():
p = Ped(op.join(HERE, 'peddy/tests/a.ped'))
f = p.families['family_4']
trios = list(f.trios())
assert len(trios) == 3
assert [t[0] for t in trios] == list(f.affecteds)
def test_relatedness_coefficient_missing_gparent():
p = Ped(open(os.path.join(HERE, "peddy/tests/test.fam.ped")))
# uncle
v = p.relatedness_coefficient('101806-101806', '101811-101811')
assert v == 0.25, v
v = p.relatedness_coefficient('101806-101806', '101809-101809')
assert v == 0.25, v
# parent-child
v = p.relatedness_coefficient('101806-101806', '101653-101653')
assert v == 0.5, v
p = Ped(open(os.path.join(HERE, "peddy/tests/test.fam2.ped")))
v = p.relatedness_coefficient('101806-101806', '101811-101811')
assert v == 0.25, v
v = p.relatedness_coefficient('101806-101806', '101809-101809')
assert v == 0.25, v
# parent-child
v = p.relatedness_coefficient('101806-101806', '101653-101653')
assert v == 0.5, v
def test_relatedness_coefficient_missing_gparent():
p = Ped(open(os.path.join(HERE, "peddy/tests/test.fam.ped")))
# uncle
v = p.relatedness_coefficient('101806-101806', '101811-101811')
assert v == 0.25, v
v = p.relatedness_coefficient('101806-101806', '101809-101809')
assert v == 0.25, v
# parent-child
v = p.relatedness_coefficient('101806-101806', '101653-101653')
assert v == 0.5, v
p = Ped(open(os.path.join(HERE, "peddy/tests/test.fam2.ped")))
v = p.relatedness_coefficient('101806-101806', '101811-101811')
assert v == 0.25, v
v = p.relatedness_coefficient('101806-101806', '101809-101809')
assert v == 0.25, v
# parent-child
v = p.relatedness_coefficient('101806-101806', '101653-101653')
assert v == 0.5, v
def test_json():
p = Ped(op.join(HERE, 'peddy/tests/test.mendel.ped'))
json = p.to_json()
#expected = '[{"maternal_id": "-9", "paternal_id": "-9", "sex": "male", "family_id": "CEPH1463", "phenotype": "affected", "sample_id": "NA12889"}, {"maternal_id": "-9", "paternal_id": "-9", "sex": "female", "family_id": "CEPH1463", "phenotype": "affected", "sample_id": "NA12890"}, {"maternal_id": "NA12890", "paternal_id": "NA12889", "sex": "male", "family_id": "CEPH1463", "phenotype": "affected", "sample_id": "NA12877"}]'
# this test may fail if order of dicts is changed
assert "CEPH1463" in json, json
def run(args):
print ('\t'.join(['chrom', 'start', 'end', 'sample_id', 'parent_id', 'n_vars', 'hap_start']))
vcf = VCF(args.vcf)
ped = Ped(args.ped)
samples = [s for s in ped.samples()]
kids = [s for s in samples if s.mom is not None and s.dad is not None]
fams = set([s.family_id for s in samples])
smp2ped = dict(zip([s.sample_id for s in samples], samples))
exclude = read_exclude(args.exclude)
#kid = smp2ped[args.kid].sample_id
#dad, mom = smp2ped[kid].paternal_id, smp2ped[kid].maternal_id
#samples_in_ped = [s.sample_id for s in samples]
#samples_in_fam = [s.sample_id for s in samples if s.family_id == smp2ped[kid].family_id]
# restrict VCF to the samples in the current family
#vcf.set_samples(samples_in_ped)
smp2idx = dict(zip(vcf.samples, range(len(vcf.samples))))
bad_positions = []
v_feats = []
haps = defaultdict()
inf_positions = defaultdict(list)
fam_dict = defaultdict(lambda: defaultdict())
for fam in fams:
mom = [s for s in samples if s.family_id == fam and s.mom is None and s.dad is None and s.sex == 'female'][0]
dad = [s for s in samples if s.family_id == fam and s.mom is None and s.dad is None and s.sex == 'male'][0]
sibs = [s.sample_id for s in kids if s.dad == dad and s.mom == mom]
fam_dict[fam]['mom'] = mom
fam_dict[fam]['dad'] = dad
fam_dict[fam]['sibs'] = ','.join(sibs)
nused, i, report_at, t0 = 0, 0, 1000, time.time()
for i,v in enumerate(vcf(args.chrom)):
if i != 0 and i % report_at == 0:
persec = i / float(time.time() - t0)
print("%s:%d (%.1f/sec) %.2f%% informative (%d/%d variants)" % (v.CHROM, v.POS,
persec, 100.0 * nused/i, nused, i), file=sys.stderr)
if args.exclude and len(exclude[v.CHROM].search(v.start, v.end)) > 0: continue
if v.var_type != 'snp': continue
if v.FILTER not in ('PASS', None): continue
if v.call_rate < 0.90: continue
if len(v.ALT) > 1: continue
if len(v.ALT[0]) > 1: continue
gts = v.gt_types
quals = v.gt_quals
rd, ad = v.gt_ref_depths, v.gt_alt_depths
for fam in fam_dict:
mom = fam_dict[fam]['mom']
dad = fam_dict[fam]['dad']
sibs = fam_dict[fam]['sibs'].split(',')
if args.inf_parent and args.inf_parent not in (mom, dad): continue
try:
mi, di = smp2idx[mom.sample_id], smp2idx[dad.sample_id]
except KeyError: sys.exit()
# ensure we're at an informative site
if gts[mi] != HOM_REF and gts[di] != HOM_REF: continue
if gts[mi] == HOM_REF and gts[di] == HOM_REF: continue
sib_gts = [gts[smp2idx[k]] for k in sibs]
inf_parent = None
if (gts[mi] == HET and gts[di] == HOM_REF): inf_parent = mom.sample_id
elif (gts[di] == HET and gts[mi] == HOM_REF): inf_parent = dad.sample_id
else: continue
# check that both parents are "high-quality"
if not is_good_site(mi, quals, gts, ad, rd, het_ab=args.ab): continue
if not is_good_site(di, quals, gts, ad, rd, het_ab=args.ab): continue
if args.inf_parent and inf_parent != args.inf_parent: continue
# catalog the "states" of each child w/r/t the informative parent
# if kids are HETs, their state w/r/t to the INF parent is 0
states = []
sib_pass = []
for i,k in enumerate(sibs):
k_idx = smp2idx[k]
k_pass = is_good_site(k_idx, quals, gts, ad, rd, het_ab=args.ab)
sib_pass.append(k_pass)
k_state = -1
if v.CHROM in ('chrX', 'X') and k.sex == "male":
k_state = 0 if gts[k_idx] == HOM_ALT else 1
else:
k_state = 0 if gts[k_idx] == HET else 1
states.append(k_state)
if not all([x is True for x in sib_pass]): continue
if sum([s < 0 for s in states]) > 0: continue
if inf_parent not in haps:
haps[inf_parent] = np.array(states)
else:
haps[inf_parent] = np.vstack((haps[inf_parent], np.array(states)))
inf_positions[inf_parent].append(v.start)
nused += 1
persec = i / float(time.time() - t0)
xos = get_xo(args, haps, inf_positions)
def test_6():
p = Ped(op.join(HERE, 'peddy/tests/a6.ped'))
assert len(list(p.samples())) == 14
for sam in p.samples():
assert sam.family_id[:3] == "fam"
def test_distant():
p = Ped(op.join(HERE, 'peddy/tests/test-unknown-gma.ped'))
d = p.relatedness_coefficient('kid1', 'cousin1')
assert d == 0.125, d
d = p.relatedness_coefficient('kid1', 'aunt')
assert d == 0.25, d
d = p.relatedness_coefficient('cousin1', 'aunt')
assert d == 0.5, d
d = p.relatedness_coefficient('mom', 'aunt')
assert d == 0.5, d
r = p.relation('kid1', 'cousin1')
assert r == 'cousins', r
r = p.relation('kid1', 'grandma')
assert r == 'grandchild', r
r = p.relation('kid1', 'aunt')
assert r == 'niece/nephew', r
# because we don't know that the uncle is related
r = p.relation('kid1', 'uncle')
assert r == 'related at unknown level', r
r = p.relation('cousin1', 'mom')
assert r == 'niece/nephew', r
r = p.relation('cousin1', 'dad')
# because we don't know that the dad is related
assert r == 'related at unknown level', r
def test_ped():
p = Ped(op.join(HERE, 'peddy/tests/a.ped'))
assert len(p.families) == 4
assert len(list(p.samples())) == 14
def test_getattr():
p = Ped(op.join(HERE, 'peddy/tests/a.ped'))
li = list(p.samples(ethnicity='caucasianNEuropean'))
assert len(li) == 5
for item in li:
assert item.ethnicity == 'caucasianNEuropean'
def test_distant():
p = Ped(op.join(HERE, 'peddy/tests/test-unknown-gma.ped'))
d = p.relatedness_coefficient('kid1', 'cousin1')
assert d == 0.125, d
d = p.relatedness_coefficient('kid1', 'aunt')
assert d == 0.25, d
d = p.relatedness_coefficient('cousin1', 'aunt')
assert d == 0.5, d
d = p.relatedness_coefficient('mom', 'aunt')
assert d == 0.5, d
r = p.relation('kid1', 'cousin1')
assert r == 'cousins', r
r = p.relation('kid1', 'grandma')
assert r == 'grandchild', r
r = p.relation('kid1', 'aunt')
assert r == 'niece/nephew', r
# because we don't know that the uncle is related
r = p.relation('kid1', 'uncle')
assert r == 'related at unknown level', r
r = p.relation('cousin1', 'mom')
assert r == 'niece/nephew', r
r = p.relation('cousin1', 'dad')
# because we don't know that the dad is related
assert r == 'related at unknown level', r
def test_json():
p = Ped(op.join(HERE, 'peddy/tests/test.mendel.ped'))
json = p.to_json()
#expected = '[{"maternal_id": "-9", "paternal_id": "-9", "sex": "male", "family_id": "CEPH1463", "phenotype": "affected", "sample_id": "NA12889"}, {"maternal_id": "-9", "paternal_id": "-9", "sex": "female", "family_id": "CEPH1463", "phenotype": "affected", "sample_id": "NA12890"}, {"maternal_id": "NA12890", "paternal_id": "NA12889", "sex": "male", "family_id": "CEPH1463", "phenotype": "affected", "sample_id": "NA12877"}]'
# this test may fail if order of dicts is changed
assert "CEPH1463" in json, json
import csv
import sys
from peddy import Ped
from collections import defaultdict
samples = [s for s in Ped(sys.argv[2]).samples()]
kids = [s for s in samples if s.mom is not None and s.dad is not None]
gt = defaultdict()
alleles = defaultdict()
reads = defaultdict()
with open(sys.argv[1]) as f:
fh = csv.reader(f, delimiter='\t')
for l in fh:
gt[l[0]] = l[1]
alleles[l[0]] = l[2]
reads[l[0]] = l[3]
md_seen = []
inh_errors = 0
total_inh = 0
for s in kids:
if s.dad.sample_id == '8477': continue
parent_gts = [gt[p] for p in (s.mom.sample_id, s.dad.sample_id)]
#if 'unk' in parent_gts: continue
#if gt[s.sample_id] == 'unk': continue
if gt[s.sample_id] not in parent_gts:
print ('\t'.join([s.family_id, s.sample_id, gt[s.sample_id], gt[s.mom.sample_id], gt[s.dad.sample_id], alleles[s.sample_id], alleles[s.mom.sample_id], alleles[s.dad.sample_id], reads[s.sample_id]]))
def test_getattr():
p = Ped(op.join(HERE, 'peddy/tests/a.ped'))
li = list(p.samples(ethnicity='caucasianNEuropean'))
assert len(li) == 5
for item in li:
assert item.ethnicity == 'caucasianNEuropean'
def run(args):
ped = Ped(args.ped)
vcf = VCF(args.vcf, gts012=True)
ped_samples = [s.sample_id for s in ped.samples()]
vcf_samples = set(vcf.samples)
samples = [s for s in ped_samples if s in vcf_samples]
exclude = read_exclude(args.exclude)
vcf = VCF(args.vcf, samples=samples, gts012=True)
if args.region:
vcf_iter = vcf(args.region)
else:
vcf_iter = vcf
pctile1 = 10
# build a dict of sample_id to sample index
smp2idx = dict(zip(vcf.samples, range(len(vcf.samples))))
# get the Ped objects for the family of interest
if args.families is None:
fams = ped.families.values()
else:
fams = [ped.families[f] for f in args.families.split(",")]
if len(fams) == 0:
sys.exit('Families %s not found in ped file' % args.families)
# create a simple dictionary of info for each family member
fs = [get_family_dict(fam, smp2idx, args) for fam in fams]
del fam
fsites = open("%s.sites" % args.prefix, "w")
# fcalls contains the crossovers for all samples.
try:
vcf["AB"]
has_abs = True
except KeyError:
has_abs = False
smp2gt = defaultdict(int)
nused, i, report_at, t0 = 0, 0, 20000, time.time()
for i, v in enumerate(vcf_iter, start=1):
if i % report_at == 0:
persec = i / float(time.time() - t0)
print("%s:%d (%.1f/sec) %.2f%% informative (%d/%d variants)" %
(v.CHROM, v.POS, persec, 100.0 * nused / i, nused, i),
file=sys.stderr)
if i == 20000:
report_at = 100000
if i == 100000:
report_at = 200000
for f in fs:
for k in f:
if k.startswith('fh'): f[k].flush()
sys.stderr.flush()
if v.var_type != 'snp': continue ### no indels
if len(v.ALT) > 1: continue
#if len(v.REF) > 3 or len(v.ALT) > 1 or len(v.ALT[0]) > 3:
# continue
#if v.call_rate < 0.95: continue
if v.call_rate < 0.90: continue
if v.FILTER is not None: continue
if int(v.INFO.get('AC')) == 1: continue
if exclude is not None and 0 != len(exclude[v.CHROM].search(
v.start, v.end)):
continue
# expensive to get gt_bases and we only need it at the crossover.
gt_bases = None
gt_types, gt_quals, gt_depths = v.gt_types, v.gt_quals, v.gt_depths
### added by tom 2019-11-13, as 1st percentile of depths on chr17
### were often negative...
#gt_depths[gt_depths < 0] = 0
gt_phases = v.gt_phases
ipctiles, pctiles = None, None
sample_abs = None
nsites = 0 # track the number of families that had this as an informative site.
for f in fs:
#if ipctiles is not None and ipctiles[0] < pctile1:
# break
# is_informative only needs gt_types, so we check that first...
add_genotype_info(f, gt_types=gt_types, gt_phases=gt_phases)
# ############## PHASED ####################
if all(f['gt_phase']):
if gt_bases is None:
gt_bases = v.gt_bases
nsites += phased_check(f, v, gt_bases)
continue
# ############ END PHASED ####################
# need exactly 1 het parent for unphased checks.
if 1 != ((f['gt_type'][0] == HET) + (f['gt_type'][1] == HET)):
continue
if not is_informative(f):
continue
# now wee need to add quality and depth.
add_genotype_info(f, gt_quals=gt_quals, gt_depths=gt_depths)
if not passes_quality_control(f, args):
continue
# detect crossovers.
for parent, (p1, p2) in [("dad", (0, 1)), ("mom", (1, 0))]:
if not (f['gt_type'][p1] == HET
and f['gt_type'][p2] == HOM_REF):
continue
if gt_bases is None:
gt_bases = v.gt_bases
if sample_abs is None:
sample_abs = get_allele_balance(v, has_abs)
if sample_abs is None: break
fam_abs = sample_abs[f['idxs']]
if all(np.isnan(fam_abs)): continue
off = 0.31 # require that off <= alt/(ref+alt) <= 1-off
if ((fam_abs[p1] >= 1 - off) | (fam_abs[p1] <= off)): continue
if np.any((1 - off < fam_abs[2:]) | (fam_abs[2:] <= off)):
continue
fam_bases = "\t".join(gt_bases[f['idxs']])
fam_abs = "|".join("%.2f" % val for val in fam_abs)
# calculate on first use. we found that having a low 1st pctile
# was a good indicator of increased chance of spurious XO even
# in families with decent depth.
#print (np.mean(gt_depths), np.median(gt_depths))
if pctiles is None:
ipctiles = np.percentile(gt_depths, (1, 5, 10, 50, 90))
pctiles = "|".join("%.0f" % de for de in ipctiles)
#if ipctiles[0] < pctile1:
# break
fam_depths = "|".join(map(str, gt_depths[f['idxs']]))
nsites += 1
val = 1 if f['gt_type'][2] == f['gt_type'][3] else 0
f['fh-%s' % parent].write('\t'.join(
str(s) for s in [
v.CHROM, v.POS - 1, v.POS, f['ids'][p1],
f['family_id'], val, fam_bases, fam_depths,
"%.2f" % v.call_rate, pctiles, fam_abs
]) + '\n')
fsites.write("%s:%d\t%d\n" % (v.CHROM, v.POS, nsites))
if nsites > 0:
nused += 1
fsites.close()
persec = i / float(time.time() - t0)
print("finished at %s:%d (%.1f/sec) %.2f%% informative (%d/%d variants)" %
(v.CHROM, v.POS, persec, 100.0 * nused / i, nused, i),
file=sys.stderr)
kept = _remove_empty(fs)
call_all(kept, args.prefix, min_sites=20)
def test_ped():
p = Ped('peddy/tests/a.ped')
assert len(p.families) == 4
assert len(list(p.samples())) == 14
def test_ped():
p = Ped(op.join(HERE, 'peddy/tests/a.ped'))
assert len(p.families) == 4
assert len(list(p.samples())) == 14
def run(pedf, region, ref, bams, min_req_alts=MIN_REQ_ALTS):
print(pedf, file=sys.stderr)
ped = Ped(pedf)
bams = " ".join(bams)
cmd = CMD.format(**locals())
sample_names = None
trios = []
for f in ped.families.values():
trios.extend(f.trios(affected=None))
print("found: %d trios" % len(trios), file=sys.stderr)
if len(trios) == 0:
raise Exception("found no trios")
p = sp.Popen(cmd, shell=True, stderr=sys.stderr, stdout=sp.PIPE)
atexit.register(p.kill)
for i, line in enumerate(p.stdout):
if line[0] == '#':
if line.startswith("#CHROM"):
sample_names = line.rstrip().split("\t")[9:]
print(
"""##INFO=<ID=MOSAIC,Number=1,Type=String,Description="Pipe-delimited list of samples with evidence of mosaicism">"""
)
print(line, end="")
continue
toks = line.rstrip().split("\t")
format = toks[8].split(":")
if i % 1000 == 0:
print("mosaic: checked ...", i, file=sys.stderr)
sys.stderr.flush()
samples = {
sample_names[k]: dict(zip(format, t.split(":")))
for k, t in enumerate(toks[9:])
}
candidates = []
for kid, mom, dad in trios:
try:
mom = samples[mom.sample_id]['AO'].split(",")
if not any('0' == m for m in mom): continue
dad = samples[dad.sample_id]['AO'].split(",")
if not any('0' == d for d in dad): continue
parents = [mom[k] + dad[k] for k in range(len(dad))]
if not '00' in parents: continue
skid = samples[kid.sample_id]
kid_alts = map(int, skid['AO'].split(","))
except KeyError: # require all samples to be called.
continue
if not any(a >= MIN_REQ_ALTS and parents[k] == '00'
for k, a in enumerate(kid_alts)):
continue
candidates.append(
"%s:%s:%s:%s" %
(kid.sample_id, skid['RO'], skid['AO'], skid['QA']))
if not candidates:
continue
toks[7] = "MOSAIC=%s;%s" % ("|".join(candidates), toks[7])
print("\t".join(toks))
sys.stdout.flush()
def test_6():
p = Ped(op.join(HERE, 'peddy/tests/a6.ped'))
assert len(list(p.samples())) == 14
for sam in p.samples():
assert sam.family_id[:3] == "fam"
