def calcfst(pops, posdict, gtdict):
"""
"""
fst_obs = []
ix = 0
popiix = []
pw = len(pops)
fstarray = np.zeros([len(posdict.keys()), (pw*(pw-1))/2])
# Observed FST
for p in pops:
popiix.append(range(ix, ix + p))
ix += p
for r in gtdict.keys():
fst_obs = []
for i, pix in enumerate(popiix):
for j, jix in enumerate(popiix):
if i > j:
popX = gtdict[r][pix]
popY = gtdict[r][jix]
sdfst = simData()
geno_fst = np.vstack([popX, popY])
gtpop_fst = [''.join(str(n) for n in y) for y in geno_fst]
sdfst.assign_sep(posdict[r], gtpop_fst)
size = [popX.shape[0], popY.shape[0]]
f1 = fst(sdfst, size)
fst_obs.append(f1.slatkin())
fstarray[int(r), :] = fst_obs
return(fstarray)
def testShared(self):
x = [(0.1, "0011"), (0.2, "1100"), (0.3, "0100"), (0.4, "1101"),
(0.5, "0101")]
d = simData()
d.assign(x)
f = fst(d, [2, 2])
self.assertEqual(f.shared(0, 1), [0.5])
def permtest(gtdict, posdict, pops, n_perm, fstarray):
"""
"""
nhap = sum(pops)
fst_t = []
r = random.choice(gtdict.keys())
# FST random permutations
for p in range(n_perm):
popX = gtdict[r][np.random.randint(0, nhap, pops[0])]
popY = gtdict[r][np.random.randint(0, nhap, pops[0])]
sdfst = simData()
geno_fst = np.vstack([popX, popY])
gtpop_fst = [''.join(str(n) for n in y) for y in geno_fst]
sdfst.assign_sep(posdict[r], gtpop_fst)
size = [popX.shape[0], popY.shape[0]]
f1 = fst(sdfst, size)
# fst_t.append(f1.slatkin())
fst_t.append(f1.hsm())
# fst_t.appen(f1.hbk())
# mark significant FST
fst_tnp = np.array(fst_t)
Fstdist = [len(np.where(f > fst_tnp)[0]) for f in fstarray]
return ([1 - (f / float(n_perm)) for f in Fstdist])
def testShared(self):
x = [(0.1,b"0011"),(0.2,b"1100"),
(0.3,b"0100"),(0.4,b"1101"),
(0.5,b"0101")]
d = simData()
d.assign(x)
f = fst(d,[2,2])
self.assertEqual(f.shared(0,1),[0.5])
def testExceptionPriv(self):
with self.assertRaises(RuntimeError):
x = [(0.1, "0011"), (0.2, "1100"), (0.3, "0100"), (0.4, "1101"),
(0.5, "0101")]
d = simData()
d.assign(x)
f = fst(d, [2, 2])
#2 is out of range.
sh = f.priv(2, 1)
def testFixed(self):
x = [(0.1, "0011"), (0.2, "1100"), (0.3, "0100"), (0.4, "1101"),
(0.5, "0101")]
d = simData()
d.assign(x)
f = fst(d, [2, 2])
p = f.fixed(0, 1)
expected = [0.1, 0.2]
self.assertEqual(p, expected)
def testPriv(self):
x = [(0.1, "0011"), (0.2, "1100"), (0.3, "0100"), (0.4, "1101"),
(0.5, "0101")]
d = simData()
d.assign(x)
f = fst(d, [2, 2])
p = f.priv(0, 1)
expected = {0: [0.3], 1: [0.4]}
self.assertEqual(p, expected)
def testException1(self):
with self.assertRaises(RuntimeError):
x = [(0.1, "0011"), (0.2, "1100"), (0.3, "0100"), (0.4, "1101"),
(0.5, "0101")]
d = simData()
d.assign(x)
##the second argument's sum is > total sample size
##libsequence will throw a SeqException here,
##which gets tranlated to a RuntimeError
f = fst(d, [2, 3])
def testExceptionPriv(self):
with self.assertRaises(RuntimeError):
x = [(0.1,b"0011"),(0.2,b"1100"),
(0.3,b"0100"),(0.4,b"1101"),
(0.5,b"0101")]
d = simData()
d.assign(x)
f = fst(d,[2,2])
#2 is out of range.
sh = f.priv(2,1)
def testFixed(self):
x = [(0.1,b"0011"),(0.2,b"1100"),
(0.3,b"0100"),(0.4,b"1101"),
(0.5,b"0101")]
d = simData()
d.assign(x)
f = fst(d,[2,2])
p = f.fixed(0,1)
expected = [0.1,0.2]
self.assertEqual(p,expected)
def testPriv(self):
x = [(0.1,b"0011"),(0.2,b"1100"),
(0.3,b"0100"),(0.4,b"1101"),
(0.5,b"0101")]
d = simData()
d.assign(x)
f = fst(d,[2,2])
p = f.priv(0,1)
expected = {0:[0.3],1:[0.4]}
self.assertEqual(p,expected)
def testException1(self):
with self.assertRaises(RuntimeError):
x = [(0.1,b"0011"),(0.2,b"1100"),
(0.3,b"0100"),(0.4,b"1101"),
(0.5,b"0101")]
d = simData()
d.assign(x)
##the second argument's sum is > total sample size
##libsequence will throw a SeqException here,
##which gets tranlated to a RuntimeError
f = fst(d,[2,3])
def calcfst(pops, posdict, gtdict, L, snp=True, hud=True):
"""
"""
ix = 0
pw = len(pops)
fstarray = np.zeros([len(posdict.keys()), int((pw * (pw - 1)) / 2)])
# Observed FST
pix = 0
popdict = {}
for p in pops:
popdict[pix] = list(range(ix, ix + p))
ix += p
pix += 1
for r in gtdict.keys():
fst_obs = []
if snp:
pos_snp = [(np.random.choice(posdict[r]))]
gt_snp = np.where(posdict[r] == pos_snp)[0]
if len(gt_snp) > 1:
gt_snp = gt_snp[0]
else:
pos_snp = list(posdict[r])
for x, y in combinations(popdict.keys(), 2):
popX = gtdict[r][popdict[x]]
popY = gtdict[r][popdict[y]]
sdfst = simData()
geno = np.vstack([popX, popY])
geno_fst = geno[:, gt_snp]
gtpop = [''.join(str(n) for n in y) for y in geno_fst]
gtpop_fst = [i.encode() for i in gtpop]
sdfst.assign_sep(pos_snp, gtpop_fst)
size = [popX.shape[0], popY.shape[0]]
f1 = fst(sdfst, size)
if hud:
fst_obs.append(f1.hsm())
else:
fst_obs.append(f1.slatkin())
# fst_obs.append(f1.hbk())
# # pi
for z in popdict.keys():
sdpop = simData()
popZ = gtdict[r][popdict[z]]
geno = popZ[:, gt_snp]
gtpop = [''.join(str(n) for n in y) for y in geno]
gtpop_pi = [i.encode() for i in gtpop]
sdpop.assign_sep(pos_snp, gtpop_pi)
pspopr = polySIM(sdpop)
pi = pspopr.thetapi()
print("pop {} pi:{}".format(z, pi / L))
fstarray[int(r), :] = fst_obs
return (fstarray)