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 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 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
#generate fp of query_substructs
qfp = Chem.RDKFingerprint(qmol, maxPath=5, fpSize=1024, nBitsPerHash=2)
queries.append(qfp)
query_info.append((info[0], info[1], info[2]))
fragments = len(query_info)
for line in sys.stdin:
line = line.rstrip()
smi, id = re.split('\s|,', line)
#print smi,id
mol = Chem.MolFromSmiles(smi)
if mol is None:
sys.stderr.write("Can't generate mol for: %s\n" % (smi))
continue
mfp = Chem.RDKFingerprint(mol, maxPath=5, fpSize=1024, nBitsPerHash=2)
#print smi
res = DataStructs.BulkTverskySimilarity(mfp, queries, 0, 1, False)
#query_frag_smiles,query_smiles,query_id,retrieved_smi,retrieved_id,tversky_sim
for i in range(fragments):
if (res[i] >= options.cutoff):
print("%s,%s,%s,%s,%s,%s" % (query_info[i][2], query_info[i][0],
query_info[i][1], smi, id, res[i]))
def similarity_metric(x, y):
return DataStructs.BulkTverskySimilarity(x, y, 1.0, 1.5)
fp = gen_fp(mol)
fps1.append(fp)
smiles1.append(smi)
t2 = time.time()
print("Fingerprinting targets took:", (t2 - t1))
print("Number of targets:", len(fps1))
t3 = time.time()
hits = []
best_scores = []
best_target = []
for mol, smi in read_file(p2, True):
if mol:
fp2 = gen_fp(mol)
scores = DataStructs.BulkTverskySimilarity(fp2, fps1, alpha, 1.0 - alpha)
best_score = 0.0
best_target = None
for score, target in zip(scores, smiles1):
# print(score)
if score > best_score:
best_score = score
best_target = target
if threshold1 <= best_score <= threshold2:
print(smi, best_score)
print(best_target)
hits.append(smi)
# for score in scores:
# if threshold1 <= score <= threshold2:
