def calculate_sims(fps1, fps2, simtype='tanimoto'):
sim_mat = np.zeros((len(fps1), len(fps2))) # ,dtype=np.float32)
for i in range(len(fps1)):
fp_i = fps1[i]
if simtype == 'tanimoto':
sims = DataStructs.BulkTanimotoSimilarity(fp_i, fps2)
elif simtype == 'dice':
sims = DataStructs.BulkDiceSimilarity(fp_i, fps2)
sim_mat[i, :] = sims
return sim_mat
def ClusterFps(Fp, cutoff):
from rdkit import DataStructs
from rdkit.ML.Cluster import Butina
# first generate the distance matrix:
dists = []
nfps = len(Fp)
for i in range(1,nfps):
# sims = DataStructs.BulkTanimotoSimilarity(Fp[i], Fp[:i])
sims = DataStructs.BulkDiceSimilarity(Fp[i], Fp[:i])
dists.extend([1-x for x in sims])
# now cluster the data:
cs = Butina.ClusterData(dists, nfps, cutoff, isDistData=True)
return cs
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 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 GetNeighborLists(probes,
topN,
pool,
simMetric=DataStructs.DiceSimilarity,
simThresh=-1.,
silent=False,
**kwargs):
probeFps = [x[1] for x in probes]
validProbes = [x for x in range(len(probeFps)) if probeFps[x] is not None]
validFps = [probeFps[x] for x in validProbes]
from rdkit.DataStructs.TopNContainer import TopNContainer
if simThresh <= 0:
nbrLists = [TopNContainer(topN) for x in range(len(probeFps))]
else:
nbrLists = [TopNContainer(-1) for x in range(len(probeFps))]
nDone = 0
for nm, fp in pool:
nDone += 1
if not silent and not nDone % 1000:
logger.info(' searched %d rows' % nDone)
if (simMetric == DataStructs.DiceSimilarity):
scores = DataStructs.BulkDiceSimilarity(fp, validFps)
for i, score in enumerate(scores):
if score > simThresh:
nbrLists[validProbes[i]].Insert(score, nm)
elif (simMetric == DataStructs.TanimotoSimilarity):
scores = DataStructs.BulkTanimotoSimilarity(fp, validFps)
for i, score in enumerate(scores):
if score > simThresh:
nbrLists[validProbes[i]].Insert(score, nm)
elif (simMetric == DataStructs.TverskySimilarity):
av = float(kwargs.get('tverskyA', 0.5))
bv = float(kwargs.get('tverskyB', 0.5))
scores = DataStructs.BulkTverskySimilarity(fp, validFps, av, bv)
for i, score in enumerate(scores):
if score > simThresh:
nbrLists[validProbes[i]].Insert(score, nm)
else:
for i in range(len(probeFps)):
pfp = probeFps[i]
if pfp is not None:
score = simMetric(probeFps[i], fp)
if score > simThresh:
nbrLists[validProbes[i]].Insert(score, nm)
return nbrLists
def test6BulkDice(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.DiceSimilarity(vs[0], vs[x]) for x in range(1, nVs)]
bulkDs = ds.BulkDiceSimilarity(vs[0], vs[1:])
for i in range(len(baseDs)):
self.assertTrue(feq(baseDs[i], bulkDs[i]))
'''Gets the fingerprints from the fingerprint library
and stores them in a dictioanry'''
fp_dict = {}
for fp in fp_names:
fp_dict[fp] = fingerprint_lib.CalculateFP(fp, smiles)
return fp_dict
def getFP(fp_name, smiles):
'''Gets fingerprint from fingerprint library'''
return fingerprint_lib.CalculateFP(fp_name, smiles)
# dictionary for similarity measures
simil_dict = {}
simil_dict['Dice'] = lambda x, y: sorted(DataStructs.BulkDiceSimilarity(x, y),
reverse=True)
simil_dict['Tanimoto'] = lambda x, y: sorted(
DataStructs.BulkTanimotoSimilarity(x, y), reverse=True)
simil_dict['Cosine'] = lambda x, y: sorted(
DataStructs.BulkCosineSimilarity(x, y), reverse=True)
simil_dict['Russel'] = lambda x, y: sorted(
DataStructs.BulkRusselSimilarity(x, y), reverse=True)
simil_dict['Kulczynski'] = lambda x, y: sorted(
DataStructs.BulkKulczynskiSimilarity(x, y), reverse=True)
simil_dict['McConnaughey'] = lambda x, y: sorted(
DataStructs.BulkMcConnaugheySimilarity(x, y), reverse=True)
simil_dict['Manhattan'] = lambda x, y: sorted(
DataStructs.BulkAllBitSimilarity(x, y), reverse=True)
simil_dict['RogotGoldberg'] = lambda x, y: sorted(
DataStructs.BulkRogotGoldbergSimilarity(x, y), reverse=True)
