def _bulkTest(self,bvs):
for metric in 'Tanimoto','Dice','AllBit','OnBit','RogotGoldberg':
bulk = getattr(DataStructs,f'Bulk{metric}Similarity')
single = getattr(DataStructs,f'{metric}Similarity')
sims = bulk(bvs[0],bvs)
for i in range(len(bvs)):
sim = single(bvs[0],bvs[i])
self.assertEqual(sim,sims[i])
self.assertEqual(sim, single(bvs[0],bvs[i].ToBinary()))
dists = bulk(bvs[0], bvs, returnDistance=True)
for i in range(len(bvs)):
dist = single(bvs[0], bvs[i], returnDistance=True)
self.assertEqual(dist, dists[i])
self.assertEqual(dist, single(bvs[0], bvs[i].ToBinary(), returnDistance=True))
sims = DataStructs.BulkTverskySimilarity(bvs[0], bvs, 1, 1)
for i in range(len(bvs)):
sim = DataStructs.TverskySimilarity(bvs[0], bvs[i], 1, 1)
self.assertEqual(sim, sims[i])
sim = DataStructs.TanimotoSimilarity(bvs[0], bvs[i])
self.assertEqual(sim, sims[i])
sims = DataStructs.BulkTverskySimilarity(bvs[0], bvs, 1, 1, returnDistance=True)
for i in range(len(bvs)):
sim = DataStructs.TverskySimilarity(bvs[0], bvs[i], 1, 1, returnDistance=True)
self.assertEqual(sim, sims[i])
sim = DataStructs.TanimotoSimilarity(bvs[0], bvs[i], returnDistance=True)
self.assertEqual(sim, sims[i])
def test10BulkOps2(self):
nbits = 10000
bvs = []
for bvi in range(10):
bv = DataStructs.ExplicitBitVect(nbits)
for j in range(nbits):
x = random.randrange(0, nbits)
bv.SetBit(x)
bvs.append(bv)
bvs = tuple(bvs)
sims = DataStructs.BulkTanimotoSimilarity(bvs[0], bvs)
for i in range(len(bvs)):
sim = DataStructs.TanimotoSimilarity(bvs[0], bvs[i])
self.failUnless(feq(sim, sims[i]))
sims = DataStructs.BulkDiceSimilarity(bvs[0], bvs)
for i in range(len(bvs)):
sim = DataStructs.DiceSimilarity(bvs[0], bvs[i])
self.failUnless(feq(sim, sims[i]))
sims = DataStructs.BulkAllBitSimilarity(bvs[0], bvs)
for i in range(len(bvs)):
sim = DataStructs.AllBitSimilarity(bvs[0], bvs[i])
self.failUnless(feq(sim, sims[i]))
sims = DataStructs.BulkOnBitSimilarity(bvs[0], bvs)
for i in range(len(bvs)):
sim = DataStructs.OnBitSimilarity(bvs[0], bvs[i])
self.failUnless(feq(sim, sims[i]))
sims = DataStructs.BulkRogotGoldbergSimilarity(bvs[0], bvs)
for i in range(len(bvs)):
sim = DataStructs.RogotGoldbergSimilarity(bvs[0], bvs[i])
self.failUnless(feq(sim, sims[i]))
sims = DataStructs.BulkTverskySimilarity(bvs[0], bvs, 1, 1)
for i in range(len(bvs)):
sim = DataStructs.TverskySimilarity(bvs[0], bvs[i], 1, 1)
self.failUnless(feq(sim, sims[i]))
sim = DataStructs.TanimotoSimilarity(bvs[0], bvs[i])
self.failUnless(feq(sim, sims[i]))
sims = DataStructs.BulkTverskySimilarity(bvs[0], bvs, .5, .5)
for i in range(len(bvs)):
sim = DataStructs.TverskySimilarity(bvs[0], bvs[i], .5, .5)
self.failUnless(feq(sim, sims[i]))
sim = DataStructs.DiceSimilarity(bvs[0], bvs[i])
self.failUnless(feq(sim, sims[i]))
def test6BulkTversky(self):
"""
"""
sz = 10
nToSet = 5
nVs = 6
import random
vs = []
for i in range(nVs):
v = ds.IntSparseIntVect(sz)
for j in range(nToSet):
v[random.randint(0, sz - 1)] = random.randint(1, 10)
vs.append(v)
baseDs = [ds.TverskySimilarity(vs[0], vs[x], .5, .5) for x in range(1, nVs)]
bulkDs = ds.BulkTverskySimilarity(vs[0], vs[1:], 0.5, 0.5)
diceDs = [ds.DiceSimilarity(vs[0], vs[x]) for x in range(1, nVs)]
for i in range(len(baseDs)):
self.assertTrue(feq(baseDs[i], bulkDs[i]))
self.assertTrue(feq(baseDs[i], diceDs[i]))
bulkDs = ds.BulkTverskySimilarity(vs[0], vs[1:], 1.0, 1.0)
taniDs = [ds.TanimotoSimilarity(vs[0], vs[x]) for x in range(1, nVs)]
for i in range(len(bulkDs)):
self.assertTrue(feq(bulkDs[i], taniDs[i]))
taniDs = ds.BulkTanimotoSimilarity(vs[0], vs[1:])
for i in range(len(bulkDs)):
self.assertTrue(feq(bulkDs[i], taniDs[i]))
def getSimilarity(self, reference, method='tanimoto', alpha=None, beta=None):
if method == 'tanimoto':
return DataStructs.TanimotoSimilarity(reference.IFPvector, self.IFPvector)
elif method == 'dice':
return DataStructs.DiceSimilarity(reference.IFPvector, self.IFPvector)
elif method == 'tversky':
return DataStructs.TverskySimilarity(reference.IFPvector, self.IFPvector, alpha, beta)
def test10BulkOps3(self):
nbits = 10000
bvs = numpy.empty((10, ), DataStructs.ExplicitBitVect)
for bvi in range(10):
bv = DataStructs.ExplicitBitVect(nbits)
for j in range(nbits):
x = random.randrange(0, nbits)
bv.SetBit(x)
bvs[bvi] = bv
sims = DataStructs.BulkTanimotoSimilarity(bvs[0], bvs)
for i in range(len(bvs)):
sim = DataStructs.TanimotoSimilarity(bvs[0], bvs[i])
self.assertTrue(feq(sim, sims[i]))
sims = DataStructs.BulkDiceSimilarity(bvs[0], bvs)
for i in range(len(bvs)):
sim = DataStructs.DiceSimilarity(bvs[0], bvs[i])
self.assertTrue(feq(sim, sims[i]))
sims = DataStructs.BulkAllBitSimilarity(bvs[0], bvs)
for i in range(len(bvs)):
sim = DataStructs.AllBitSimilarity(bvs[0], bvs[i])
self.assertTrue(feq(sim, sims[i]))
sims = DataStructs.BulkOnBitSimilarity(bvs[0], bvs)
for i in range(len(bvs)):
sim = DataStructs.OnBitSimilarity(bvs[0], bvs[i])
self.assertTrue(feq(sim, sims[i]))
sims = DataStructs.BulkRogotGoldbergSimilarity(bvs[0], bvs)
for i in range(len(bvs)):
sim = DataStructs.RogotGoldbergSimilarity(bvs[0], bvs[i])
self.assertTrue(feq(sim, sims[i]))
sims = DataStructs.BulkTverskySimilarity(bvs[0], bvs, 1, 1)
for i in range(len(bvs)):
sim = DataStructs.TverskySimilarity(bvs[0], bvs[i], 1, 1)
self.assertTrue(feq(sim, sims[i]))
sim = DataStructs.TanimotoSimilarity(bvs[0], bvs[i])
self.assertTrue(feq(sim, sims[i]))
sims = DataStructs.BulkTverskySimilarity(bvs[0], bvs, .5, .5)
for i in range(len(bvs)):
sim = DataStructs.TverskySimilarity(bvs[0], bvs[i], .5, .5)
self.assertTrue(feq(sim, sims[i]))
sim = DataStructs.DiceSimilarity(bvs[0], bvs[i])
self.assertTrue(feq(sim, sims[i]))
def partialFP(atomID, tverskyThresh):
#create empty fp
modifiedFP = DataStructs.ExplicitBitVect(1024)
modifiedFP.SetBitsFromList(aBits[atomID])
tverskySim = DataStructs.TverskySimilarity(subsFp, modifiedFP, 0, 1)
if (tverskySim < tverskyThresh):
#print "%i %s: %f" % (atomID+1, pMol.GetAtomWithIdx(atomID).GetSymbol(), tverskySim)
marked[atomID] = 1
def partialSimilarity(atomID):
""" Determine similarity for the atoms set by atomID """
# create empty fp
modifiedFP = DataStructs.ExplicitBitVect(1024)
modifiedFP.SetBitsFromList(aBits[atomID])
return DataStructs.TverskySimilarity(subsFp, modifiedFP, 0, 1)
# 'path':OEFPType_Path}
fpcodes = {
'rdkit': FingerprintMols.GetRDKFingerprint,
'maccs': MACCSkeys.GenMACCSKeys,
'morgan':
lambda mol: AllChem.GetMorganFingerprintAsBitVect(mol, morganradius),
'atompairs': lambda mol: Chem.GetAtomPairFingerPrint(mol, 2)
}
# tversky(F1, F2)= F1@F2 / ( a*sum(F1) + b*sum(F2) - (1-a-b)* F1@F2 )
dmetrics = {
'tanimoto': DataStructs.TanimotoSimilarity, # a, b = 1, 1
'dice': DataStructs.DiceSimilarity, # a, b = 0.5, 0.5
'cosine': DataStructs.CosineSimilarity,
'tversky': lambda m1, m2: DataStructs.TverskySimilarity(m1, m2, 0.5, 0.5),
'sokal': DataStructs.SokalSimilarity
}
#########################
# Module initialization #
#########################
def Init():
global dmetric, fpcode
#check requested fingerprint existance
if not fpcodes.has_key(fp):
print 'Unrecognized fingerprint (mprms.fp): ' + fp
count = 0
for i in range(fpA.GetNumBits()):
if fpA.GetBit(i): count += 1
print(count, size)
if fper == GenMACCSKeys:
onbits = tuple(fpA.GetOnBits())
print(str(onbits))
for i in onbits:
print(Chem.MACCSkeys.smartsPatts[i][0])
fpB = fper(molB)
fptxtB = DataStructs.BitVectToText(fpB)
print(fptxtB)
size = fpB.GetNumBits()
count = 0
for i in range(fpB.GetNumBits()):
if fpB.GetBit(i): count += 1
print(count, size)
if fper == GenMACCSKeys:
onbits = tuple(fpB.GetOnBits())
print(str(onbits))
for i in onbits:
print(Chem.MACCSkeys.smartsPatts[i][0])
sim = DataStructs.TanimotoSimilarity(fpA, fpB)
print(sim)
sim = DataStructs.TverskySimilarity(fpA, fpB, 0.9, 0.1)
print(sim)
bcom = DataStructs.NumBitsInCommon(fpA, fpB)
print(bcom)
def Similarities(fps1, fps2, fingerprint, measure='tanimoto'):
# Indigo fingerptins
if fingerprint in indigofps and measure in indigosims:
return np.array(
[[indigo.similarity(fp1, fp2, measure) for fp2 in fps2]
for fp1 in fps1])
# RDKit fingerprints
if fingerprint in rdkitfps and measure in rdkitsims:
if measure == 'allbit':
return np.array([[
DataStructs.FingerprintSimilarity(
fp1, fp2, metric=DataStructs.AllBitSimilarity)
for fp2 in fps2
] for fp1 in fps1])
elif measure == 'asymmetric':
return np.array([[
DataStructs.FingerprintSimilarity(
fp1, fp2, metric=DataStructs.AsymmetricSimilarity)
for fp2 in fps2
] for fp1 in fps1])
elif measure == 'asymmetric2':
return np.array([[
DataStructs.FingerprintSimilarity(
fp2, fp1, metric=DataStructs.AsymmetricSimilarity)
for fp2 in fps2
] for fp1 in fps1])
elif measure == 'braunblanquet':
return np.array([[
DataStructs.FingerprintSimilarity(
fp1, fp2, metric=DataStructs.BraunBlanquetSimilarity)
for fp2 in fps2
] for fp1 in fps1])
elif measure == 'cosine':
return np.array([[
DataStructs.FingerprintSimilarity(
fp1, fp2, metric=DataStructs.CosineSimilarity)
for fp2 in fps2
] for fp1 in fps1])
elif measure == 'dice':
return np.array([[
DataStructs.FingerprintSimilarity(
fp1, fp2, metric=DataStructs.DiceSimilarity)
for fp2 in fps2
] for fp1 in fps1])
elif measure == 'kulczynski':
return np.array([[
DataStructs.FingerprintSimilarity(
fp1, fp2, metric=DataStructs.KulczynskiSimilarity)
for fp2 in fps2
] for fp1 in fps1])
elif measure == 'mcconnaughey':
return np.array([[
DataStructs.FingerprintSimilarity(
fp1, fp2, metric=DataStructs.McConnaugheySimilarity)
for fp2 in fps2
] for fp1 in fps1])
elif measure == 'rogotgoldberg':
return np.array([[
DataStructs.FingerprintSimilarity(
fp1, fp2, metric=DataStructs.RogotGoldbergSimilarity)
for fp2 in fps2
] for fp1 in fps1])
elif measure == 'russel':
return np.array([[
DataStructs.FingerprintSimilarity(
fp1, fp2, metric=DataStructs.RusselSimilarity)
for fp2 in fps2
] for fp1 in fps1])
elif measure == 'sokal':
return np.array([[
DataStructs.FingerprintSimilarity(
fp1, fp2, metric=DataStructs.SokalSimilarity)
for fp2 in fps2
] for fp1 in fps1])
elif measure == 'tanimoto':
return np.array([[
DataStructs.FingerprintSimilarity(
fp1, fp2, metric=DataStructs.TanimotoSimilarity)
for fp2 in fps2
] for fp1 in fps1])
elif measure == 'tversky':
return np.array([[
DataStructs.TverskySimilarity(fp1, fp2, a=0.5, b=0.5)
for fp2 in fps2
] for fp1 in fps1])
# RDKit non-bit (integer or float) fingerprints
if fingerprint in rdkitnonbitfps and measure in rdkitnonbitsims:
if measure == 'dice':
return np.array(
[[DataStructs.DiceSimilarity(fp1, fp2) for fp2 in fps2]
for fp1 in fps1])
elif measure == 'tanimoto':
return np.array(
[[DataStructs.TanimotoSimilarity(fp1, fp2) for fp2 in fps2]
for fp1 in fps1])
# E-state fingerprints
if fingerprint in rdkitestatefps and measure in rdkitestatesims:
if measure == 'pearson':
sims = np.array([[np.corrcoef(fp1, fp2)[0][1] for fp2 in fps2]
for fp1 in fps1])
# check for nan's
if sum([sum(np.isnan(sim)) for sim in sims]) == 0:
return sims
else:
return None
# unknown fingerprint and/or similarity measure
return None