def score_model(self, model_configuration: dict, fragments_file: str,
descriptors_file: str, output_file: str):
inputoutput_utils.create_parent_directory(output_file)
model_data = model_configuration["data"]
active_molecules_ap = []
for active_molecule in model_data["active"]:
molecule_smiles = active_molecule.strip("\"")
molecule = Chem.MolFromSmiles(molecule_smiles)
ecfp_fingerprint = Pairs.GetAtomPairFingerprint(molecule)
active_molecules_ap.append(ecfp_fingerprint)
first_line = True
with open(output_file, "w", encoding="utf-8") as output_stream:
with open(fragments_file, "r", encoding="utf-8") as input_stream:
for new_line in input_stream:
line = json.loads(new_line)
test_molecule_input = line["smiles"]
test_molecule_smiles = test_molecule_input.strip("\"")
test_molecule = Chem.MolFromSmiles(test_molecule_smiles)
test_mol_fingerprint = Pairs.GetAtomPairFingerprint(
test_molecule)
max_sim = max([
DataStructs.TanimotoSimilarity(test_mol_fingerprint,
fingerprint)
for fingerprint in active_molecules_ap
])
score = {"name": line["name"], "score": max_sim}
if first_line:
first_line = False
else:
output_stream.write("\n")
json.dump(score, output_stream)
def caculate_similarity_atomPairs(smiles_A, smiles_B):
try:
m1 = Chem.MolFromSmiles(smiles_A)
m2 = Chem.MolFromSmiles(smiles_B)
p1 = Pairs.GetAtomPairFingerprint(m1)
p2 = Pairs.GetAtomPairFingerprint(m2)
similarity_p1_p2 = DataStructs.DiceSimilarity(p1, p2)
return round(similarity_p1_p2, 4)
except:
return -1
def sim_rdk_topo_fps(smiA, smisT):
""" calculate the fingerprint similarity using the RDK atompair fingerprints
input are a smiles string and a list of smiles strings
returned is a list of similarities
"""
fp_A = Pairs.GetAtomPairFingerprint(getMolFromSmiles(smiA))
fps_T = [Pairs.GetAtomPairFingerprint(getMolFromSmiles(y)) for y in smisT]
sim_vector = []
for t in fps_T:
sim_vector.append(DataStructs.DiceSimilarity(fp_A, t))
return sim_vector
def atom_pairs(self):
ms = np.array([Chem.MolFromSmiles(i) for i in self.data.SMILES])
# compute Atom Pair
fp = [
Pairs.GetAtomPairFingerprint(
Chem.RemoveHs(x)).GetNonzeroElements() for x in ms
]
# obtain all bits present
bits_ap = set()
for i in fp:
bits_ap.update([*i]) # add bits for each molecule
bits_ap = sorted(bits_ap)
feature_matrix = list()
# convert fp to bits
for item in fp:
vect_rep = np.isin(
bits_ap, [*item]) # vect_rep, var that indicates bits presents
# identify axis to replace
ids_to_update = np.where(vect_rep == True)
vect_rep = 1 * vect_rep
vect_rep = np.array(vect_rep).astype(int)
# replace indices with bict values
vect_rep[ids_to_update] = list(item.values())
feature_matrix.append(vect_rep)
return feature_matrix
def computeFP(self, typeFP):
from rdkit.Chem.Fingerprints import FingerprintMols
from rdkit.Chem import MACCSkeys
from rdkit.Chem.AtomPairs import Pairs, Torsions
from rdkit.Chem import AllChem
if not "smiclean" in self.__dict__:
self.log = self.log + "No smiles prepared\n"
return 1
else:
self.mol = Chem.MolFromSmiles(self.smiclean)
#print self.smiclean
dFP = {}
if typeFP == "Mol" or typeFP == "All":
dFP["Mol"] = FingerprintMols.FingerprintMol(self.mol)
if typeFP == "MACCS" or typeFP == "All":
dFP["MACCS"] = MACCSkeys.GenMACCSKeys(self.mol)
if typeFP == "pairs" or typeFP == "All":
dFP["pairs"] = Pairs.GetAtomPairFingerprint(self.mol)
if typeFP == "Torsion" or typeFP == "All":
dFP["Torsion"] = Torsions.GetTopologicalTorsionFingerprint(
self.mol)
if typeFP == "Morgan" or typeFP == "All":
dFP["Morgan"] = AllChem.GetMorganFingerprint(self.mol, 2)
self.FP = dFP
return 0
def extract_atompair_fragments(molecule: object) -> list:
output = []
pairFps = Pairs.GetAtomPairFingerprint(molecule)
d = pairFps.GetNonzeroElements()
for pair in d:
atom1 = rdkit.Chem.AtomFromSmarts(Pairs.ExplainPairScore(pair)[0][0])
atom2 = rdkit.Chem.AtomFromSmarts(Pairs.ExplainPairScore(pair)[2][0])
smiles = (Pairs.ExplainPairScore(pair)[0][0] +
Pairs.ExplainPairScore(pair)[2][0])
atom1_type = atom1.GetAtomicNum()
atom2_type = atom2.GetAtomicNum()
atom1_num_pi_bonds = Pairs.ExplainPairScore(pair)[0][2]
atom2_num_pi_bonds = Pairs.ExplainPairScore(pair)[2][2]
atom1_num_neigh = Pairs.ExplainPairScore(pair)[0][1]
atom2_num_neigh = Pairs.ExplainPairScore(pair)[2][1]
atom1_property_value = 64 * atom1_type + 16 * atom1_num_pi_bonds + atom1_num_neigh
atom2_property_value = 64 * atom2_type + 16 * atom2_num_pi_bonds + atom2_num_neigh
dist = Pairs.ExplainPairScore(pair)[1] + 1
atom_pair_key = min(
atom1_property_value, atom2_property_value) + 1024 * (
max(atom1_property_value, atom2_property_value) + 1024 * dist)
num = (d[pair])
for i in range(num):
output.append({
"smiles": smiles,
"index": atom_pair_key,
"type": "AP",
"size": dist
})
return output
def atom_pairs():
""" Atom pair fingerprints, atom descriptor
"""
# Generate molecules
ms = [
Chem.MolFromSmiles('C1CCC1OCC'),
Chem.MolFromSmiles('CC(C)OCC'),
Chem.MolFromSmiles('CCOCC')
]
pairFps = [Pairs.GetAtomPairFingerprint(x) for x in ms]
# Get the list of bits and their counts for each fingerprint as a dictionary
d = pairFps[-1].GetNonzeroElements()
print(d)
# Explanation of the bitscore.
print(Pairs.ExplainPairScore(558115))
# Dice similarity; The usual metric for similarity between atom-pair fingerprints
print(DataStructs.DiceSimilarity(pairFps[0], pairFps[1]))
# Atom decriptor without count
pairFps = [Pairs.GetAtomPairFingerprintAsBitVect(x) for x in ms]
print(DataStructs.DiceSimilarity(pairFps[0], pairFps[1]))
def _atomsFingerprintsClustering(rdkit_mols):
"""
Returns the dice distance matrix based on atomsfingerprints method
Parameters
----------
rdkit_mols: list
The list of rdkit.Chem.rdchem.Mol objects
Returns
-------
dicematrix: np.array
The numpy array containing the dice matrix
"""
from rdkit.Chem.AtomPairs import Pairs # Atom pairs
fps = []
for m in tqdm(rdkit_mols):
fps.append(Pairs.GetAtomPairFingerprint(m))
aprun = ParallelExecutor(n_jobs=-1) # _config['ncpus'])
dice_matrix = aprun(total=len(fps), desc='AtomsFingerprints Distance') \
(delayed(DiceDistances)(fp1, fps) for fp1 in fps)
return np.array(dice_matrix)
def findCluster(self, smiles):
mol = Chem.MolFromSmiles(smiles)
if mol:
try:
scaffold = MurckoScaffold.GetScaffoldForMol(mol)
except:
return "", "", False
if scaffold:
cluster = Chem.MolToSmiles(scaffold, isomericSmiles=False)
else:
return "", "", False
else:
return "", "", False
fp = Pairs.GetAtomPairFingerprint(scaffold) # Change to Tanimoto?
if cluster in self.getFingerprints():
return cluster, fp, False
fps = list(self.getFingerprints().values())
sims = DataStructs.BulkTanimotoSimilarity(fp, fps)
if len(sims) == 0:
return cluster, fp, True
closest = np.argmax(sims)
if sims[closest] >= self.minsimilarity:
return list(self.getFingerprints().keys())[closest], fp, False
else:
return cluster, fp, True
def atom_pairs_similarity(active_molecules1, test_molecules):
similarity = []
active_molecules_pairfps = [
Pairs.GetAtomPairFingerprint(p) for p in active_molecules1
]
test_molecules_pairsfps = [
Pairs.GetAtomPairFingerprint(p) for p in test_molecules
]
for i in range(len(test_molecules_pairsfps)):
num_sim = 0
for j in range(len(active_molecules_pairfps)):
sim = DataStructs.DiceSimilarity(test_molecules_pairsfps[i],
active_molecules_pairfps[j])
if sim > num_sim:
num_sim = sim
similarity.append(num_sim)
return similarity
def testPairsRegression(self):
inF = gzip.open(os.path.join(self.testDataPath, 'mols1000.aps.pkl.gz'), 'rb')
atomPairs = cPickle.load(inF, encoding='bytes')
for i, m in enumerate(self.mols):
ap = Pairs.GetAtomPairFingerprint(m)
if ap != atomPairs[i]: # pragma: nocover
debugFingerprint(m, ap, atomPairs[i])
self.assertEqual(ap, atomPairs[i])
self.assertNotEqual(ap, atomPairs[i - 1])
def orng_sim_rdk_atompair_fps(smile_active, train_instance):
""" calculate the fingerprint similarity using the RDK atom pair fingerprints
input are a smiles string and a orange data instance
returned is a similaritie value
"""
smilesName = getSMILESAttr(train_instance)
if not smilesName: return None
smile_train = str(train_instance[smilesName].value)
molAct = getMolFromSmiles(smile_active)
molTrain = getMolFromSmiles(smile_train)
if not molAct: return None
if not molTrain: return None
fp_A = Pairs.GetAtomPairFingerprint(molAct)
fp_T = Pairs.GetAtomPairFingerprint(molTrain)
sim = DataStructs.DiceSimilarity(fp_A, fp_T)
return sim
def get_similarity(): # get similarities on the first molecule in compound group
# precalculate fingerprints for reference compound
ref_morgan2 = AllChem.GetMorganFingerprintAsBitVect(mols[0],radius,bit_size)
ref_cmorgan2 = AllChem.GetMorganFingerprint(mols[0],radius)
ref_fmorgan2 = AllChem.GetMorganFingerprintAsBitVect(mols[0], radius,bit_size, useFeatures = True)
ref_ap = Pairs.GetAtomPairFingerprint(mols[0])
# precalculate fingerprints and bit information for test molecules
total_sims = ''
fps_morgan2 = []
fps_cmorgan2 = []
fps_fmorgan2 = []
fps_ap = []
info_morgan2 = []
info_cmorgan2 = []
info_fmorgan2 = []
num_mols = len(mols) - 1
reference = compounds[0]
del compounds[0]
del mols[0] #remove reference cmp from list
for m in mols:
info = {}
fps_morgan2.append(AllChem.GetMorganFingerprintAsBitVect(m, radius, bit_size, bitInfo = info))
info_morgan2.append(info)
info = {}
fps_cmorgan2.append(AllChem.GetMorganFingerprint(m, radius, bitInfo=info))
info_cmorgan2.append(info)
info = {}
fps_fmorgan2.append(AllChem.GetMorganFingerprintAsBitVect(m, radius, bit_size, useFeatures=True, bitInfo=info))
info_fmorgan2.append(info)
fps_ap.append(Pairs.GetAtomPairFingerprint(m))
## calculate similarities
for i,m in enumerate(mols):
ap_simil = DataStructs.DiceSimilarity(ref_ap, fps_ap[i])
morgan2_simil = DataStructs.DiceSimilarity(ref_morgan2, fps_morgan2[i])
cmorgan2_simil = DataStructs.DiceSimilarity(ref_cmorgan2, fps_cmorgan2[i])
fmorgan2_simil = DataStructs.DiceSimilarity(ref_fmorgan2, fps_fmorgan2[i])
sims =str(reference)+' '+ str(compounds[i].rstrip())+' '+ str(ap_simil)+' '+str(morgan2_simil)+' '+str(cmorgan2_simil)+' '+str(fmorgan2_simil)+'\n'
total_sims += sims
return total_sims
def getCountInfo(m, fpType):
# m = Chem.MolFromSmiles(formula)
fp = None
if fpType == 'AtomPair' or fpType.lower() == 'atom':
fp = Pairs.GetAtomPairFingerprint(m)
return fp.GetNonzeroElements()
elif fpType.lower() == 'morgan' or fpType.lower() == 'circular':
fp = AllChem.GetMorganFingerprint(m, 2)
return fp.GetNonzeroElements()
elif fpType == 'Topological' or fpType.lower() == 'topo':
fp = Torsions.GetTopologicalTorsionFingerprint(m)
Dict = fp.GetNonzeroElements()
convertedDict = {}
for elem in Dict:
convertedDict[int(elem)] = Dict[elem]
return convertedDict
def Atompair_fp(mol, rc_names):
fp = [Pairs.GetAtomPairFingerprint(x) for x in mol]
tc_df = pd.DataFrame(index=rc_names, columns=rc_names).fillna(0)
for c1 in range(len(fp)):
tc_df[rc_names[c1]] = [
DataStructs.DiceSimilarity(fp[c1], fp[c2]) for c2 in range(len(fp))
]
clusters = linkage(tc_df.as_matrix(columns=None), "ward")
clust_tree = to_tree(clusters, rd=False)
d3Dendro = dict(children=[], name=" ")
add_node(clust_tree, d3Dendro)
label_tree(d3Dendro["children"][0], rc_names)
return d3Dendro
def computeFP(self, typeFP):
if not "mol" in self.__dict__:
self.log = self.log + "No smiles prepared\n"
self.err = 1
else:
d_FP = {}
if typeFP == "Mol" or typeFP == "All":
d_FP["Mol"] = FingerprintMols.FingerprintMol(self.mol)
if typeFP == "MACCS" or typeFP == "All":
d_FP["MACCS"] = MACCSkeys.GenMACCSKeys(self.mol)
if typeFP == "pairs" or typeFP == "All":
d_FP["pairs"] = Pairs.GetAtomPairFingerprint(self.mol)
if typeFP == "Torsion" or typeFP == "All":
d_FP["Torsion"] = Torsions.GetTopologicalTorsionFingerprint(self.mol)
if typeFP == "Morgan" or typeFP == "All":
d_FP["Morgan"] = AllChem.GetMorganFingerprint(self.mol, 2)
self.d_FP = d_FP
def compare_structure(smiles1, smiles2, fp_type="Morgan", sim_type="Dice"):
"""
Task: Compare structual similarity of two compound based on fingerprints.
Parameters:
smiles1: str, smiles of the compound 1
smiles2: str, smiles of the compound 2
fp_type: str, type of fingerprints
sim_type: str, method for calculating similarity
"""
if fp_type == "Morgan":
getfp = lambda smi: AllChem.GetMorganFingerprint(
Chem.MolFromSmiles(smi), 2, useFeatures=False)
elif fp_type == "MorganWithFeature":
getfp = lambda smi: AllChem.GetMorganFingerprint(
Chem.MolFromSmiles(smi), 2, useFeatures=True)
elif fp_type == "MACCS":
getfp = lambda smi: Chem.MACCSkeys.GenMACCSKeys(Chem.MolFromSmiles(smi)
)
elif fp_type == "Topological":
getfp = lambda smi: FingerprintMols.FingerprintMol(
Chem.MolFromSmiles(smi))
elif fp_type == "AtomPairs":
getfp = lambda smi: Pairs.GetAtomPairFingerprint(
Chem.MolFromSmiles(smi))
try:
fp1 = getfp(smiles1)
fp2 = getfp(smiles2)
if sim_type == "Dice":
sim_fp = DataStructs.DiceSimilarity(fp1, fp2)
elif sim_type == "Tanimoto":
sim_fp = DataStructs.TanimotoSimilarity(fp1, fp2)
elif sim_type == "Cosine":
sim_fp = DataStructs.CosineSimilarity(fp1, fp2)
elif sim_type == "Sokal":
sim_fp = DataStructs.SokalSimilarity(fp1, fp2)
elif sim_type == "Russel":
sim_fp = DataStructs.RusselSimilarity(fp1, fp2)
except Exception as e:
sim_fp = -1
return sim_fp
def testPairsRegression(self):
inF = gzip.open(os.path.join(self.testDataPath,'mols1000.aps.pkl.gz'),'rb')
atomPairs = cPickle.load(inF, encoding='bytes')
for i,m in enumerate(self.mols):
ap = Pairs.GetAtomPairFingerprint(m)
#if ap!=atomPairs[i]:
# print Chem.MolToSmiles(m)
# pd=ap.GetNonzeroElements()
# rd=atomPairs[i].GetNonzeroElements()
# for k,v in pd.iteritems():
# if rd.has_key(k):
# if rd[k]!=v: print '>>>1',k,v,rd[k]
# else:
# print '>>>2',k,v
# for k,v in rd.iteritems():
# if pd.has_key(k):
# if pd[k]!=v: print '>>>3',k,v,pd[k]
# else:
# print '>>>4',k,v
self.assertTrue(ap==atomPairs[i])
self.assertTrue(ap!=atomPairs[i-1])
def CalculateAtomPairsFingerprint(mol: Chem.Mol,
rtype: str = 'countstring',
bits: int = 2048) -> Tuple[str, dict, Any]:
"""Calculate atom pairs fingerprints.
:param rtype: Type of output, may either be:
countstring (default), returns a binary string
rdkit, return the native rdkit DataStructs
dict, for a dict of bits turned on
:param bits: Number of folded bits (ignored if rtype != 'countstring')
"""
res = Pairs.GetAtomPairFingerprint(mol)
if rtype == 'rdkit':
return res
counts = res.GetNonzeroElements()
if rtype == 'dict':
return {f'AtomPair_{k}': v for k, v in counts.items()}
folded = np.zeros(bits)
for k, v in counts.items():
folded[k % bits] += v
return ';'.join(folded.tolist())
def CalculateAtomPairsFingerprint(mol):
"""
#################################################################
Calculate atom pairs fingerprints
Usage:
result=CalculateAtomPairsFingerprint(mol)
Input: mol is a molecule object.
Output: result is a tuple form. The first is the number of
fingerprints. The second is a dict form whose keys are the
position which this molecule has some substructure. The third
is the DataStructs which is used for calculating the similarity.
#################################################################
"""
res = Pairs.GetAtomPairFingerprint(mol)
return res.GetLength(), res.GetNonzeroElements(), res
def get_smiles_similarity(smiles1, smiles2, similarity="fingerprint"):
from rdkit import DataStructs
from rdkit.Chem.Fingerprints import FingerprintMols
from rdkit.Chem.AtomPairs import Pairs
"""
fp_type: sim | sub
metric: tanimoto | tversky
"""
if len(smiles1) == 0 or len(smiles2) == 0:
return None
ms = [Chem.MolFromSmiles(smiles1), Chem.MolFromSmiles(smiles2)]
if similarity == "fingerprint":
fps = [FingerprintMols.FingerprintMol(x) for x in ms]
d = DataStructs.FingerprintSimilarity(fps[0],fps[1],metric=DataStructs.TanimotoSimilarity)
elif similarity == "atom":
pairFps = [Pairs.GetAtomPairFingerprint(x) for x in ms]
d = DataStructs.DiceSimilarity(pairFps[0], pairFps[1])
# d = DataStructs.TanimotoSimilarity(pairFps[0],pairFps[1])
# print(d)
return d
similarities_maccs[i][j] = 1
#for other similarity metrics use for example DataStructs.FingerprintSimilarity(fps[0],fps[1], metric=DataStructs.DiceSimilarity)
if i % 500 == 0:
print('running:', i / len(fps_maccs) * 100, '%')
# In[ ]:
df = pd.DataFrame(similarities_maccs)
df.to_csv('similarities_maccs.csv')
# ### Atom pairs fingerprints
# In[ ]:
from rdkit.Chem.AtomPairs import Pairs
fps_pairs = [Pairs.GetAtomPairFingerprint(x) for x in molecules]
similarities_pairs = np.zeros(shape=((len(fps_pairs), len(fps_pairs))))
# In[ ]:
#compute similarities. Comment this section if only the fingerprints are needed
for i in range(len(fps_pairs)):
for j in range(len(fps_pairs)):
if i > j:
similarities_pairs[i][j] = DataStructs.DiceSimilarity(
fps_pairs[i],
fps_pairs[j]) #default is the Dice similarity for these fps
similarities_pairs[j][i] = similarities_pairs[i][j]
elif i == j:
similarities_pairs[i][j] = 1
if i % 500 == 0:
m, 2, useFeatures=True, nBits=nbits)
FPDICT['fcfp6'] = lambda m: Chem.GetMorganFingerprintAsBitVect(
m, 3, useFeatures=True, nBits=nbits)
FPDICT['fcfc2'] = lambda m: Chem.GetMorganFingerprint(m, 1, useFeatures=True)
FPDICT['fcfc4'] = lambda m: Chem.GetMorganFingerprint(m, 2, useFeatures=True)
FPDICT['fcfc6'] = lambda m: Chem.GetMorganFingerprint(m, 3, useFeatures=True)
FPDICT['lecfp4'] = lambda m: Chem.GetMorganFingerprintAsBitVect(
m, 2, nBits=nbits_long)
FPDICT['lecfp6'] = lambda m: Chem.GetMorganFingerprintAsBitVect(
m, 3, nBits=nbits_long)
FPDICT['lfcfp4'] = lambda m: Chem.GetMorganFingerprintAsBitVect(
m, 2, useFeatures=True, nBits=nbits_long)
FPDICT['lfcfp6'] = lambda m: Chem.GetMorganFingerprintAsBitVect(
m, 3, useFeatures=True, nBits=nbits_long)
FPDICT['maccs'] = lambda m: MACCSkeys.GenMACCSKeys(m)
FPDICT['ap'] = lambda m: Pairs.GetAtomPairFingerprint(m)
FPDICT['tt'] = lambda m: Torsions.GetTopologicalTorsionFingerprintAsIntVect(m)
FPDICT['hashap'] = lambda m: Desc.GetHashedAtomPairFingerprintAsBitVect(
m, nBits=nbits)
FPDICT[
'hashtt'] = lambda m: Desc.GetHashedTopologicalTorsionFingerprintAsBitVect(
m, nBits=nbits)
FPDICT['rdk5'] = lambda m: Chem.RDKFingerprint(
m, maxPath=5, fpSize=nbits, nBitsPerHash=2)
FPDICT['rdk6'] = lambda m: Chem.RDKFingerprint(
m, maxPath=6, fpSize=nbits, nBitsPerHash=2)
FPDICT['rdk7'] = lambda m: Chem.RDKFingerprint(
m, maxPath=7, fpSize=nbits, nBitsPerHash=2)
if USE_AVALON:
FPDICT['avalon'] = lambda m: pyAv.GetAvalonFP(m, nbits)
FPDICT['avalon_l'] = lambda m: pyAv.GetAvalonFP(m, nbits_long)
def ClusterOnFingerprint(filename, mols=None, fingerprint=0, cutoff=0.8, metric='Tanimoto', outMatrix=False):
'''Clustering Structure based on Fingerprints in RDKit
filename: Smile format file saving molecules. If set to None, use given "mols"
mols: Input molecules. No use if set up "filename"
cutoff: Cutoff using for Butina Clustering
fingerprint: Fingerprint to use:
0 or else: RDKit Topological Fingerprint
1: MACCS Fingerprint
2: Atom Pair Fingerprint (AP)
3: Topological Torsion Fingerprint (TT)
4: Morgan Fingerprint similar to ECFP4 Fingerprint
5: Morgan Fingerprint similar to FCFP4 Fingerprint
metric: Available similarity metrics include:
Tanimoto, Dice, Cosine, Sokal, Russel, Kulczynski, McConnaughey, and Tversky.
outMatrix: Change output to a similarity matrix
Return: Default output "clusters, clusterOut":
clusters: Clusters containing molecule number.
clusterOut: Molecular Cluster Number in List.
'''
from rdkit import DataStructs
from rdkit.Chem.Draw import SimilarityMaps
from rdkit.Chem.Fingerprints import FingerprintMols
from rdkit.Chem import MACCSkeys
from rdkit.Chem.AtomPairs import Pairs, Torsions
if filename:
suppl = Chem.SmilesMolSupplier(filename)
mols=[]
for mol in suppl:
mols.append(mol)
molnums=len(mols)
### Calculate Molecular Fingerprint
## MACCS Fingerprint
if fingerprint==1:
fps = [MACCSkeys.GenMACCSKeys(mol) for mol in mols]
## Atom Pair Fingerprint (AP)
elif fingerprint == 2:
fps = [Pairs.GetAtomPairFingerprint(mol) for mol in mols]
## Topological Torsion Fingerprint (TT)
elif fingerprint == 3:
fps = [Torsions.GetTopologicalTorsionFingerprintAsIntVect(mol) for mol in mols]
## Morgan Fingerprint similar to ECFP4 Fingerprint
elif fingerprint == 4:
fps = [AllChem.GetMorganFingerprint(mol,2) for mol in mols]
## Morgan Fingerprint similar to FCFP4 Fingerprint
elif fingerprint == 5:
fps = [AllChem.GetMorganFingerprint(mol,2,useFeatures=True) for mol in mols]
## RDKit Topological Fingerprint
else: #fingerprint==0:
fps = [FingerprintMols.FingerprintMol(mol) for mol in mols]
if outMatrix:
### Output the Fingerprint similarity Matrix
metricsAvailable={'tanimoto':DataStructs.TanimotoSimilarity,"dice":DataStructs.DiceSimilarity,
"cosine": DataStructs.CosineSimilarity, "sokal": DataStructs.SokalSimilarity, "russel": DataStructs.RusselSimilarity,
"rogotGoldberg": DataStructs.RogotGoldbergSimilarity, "allbit": DataStructs.AllBitSimilarity,
"kulczynski": DataStructs.KulczynskiSimilarity, "mcconnaughey": DataStructs.McConnaugheySimilarity,
"asymmetric": DataStructs.AsymmetricSimilarity, "braunblanquet": DataStructs.BraunBlanquetSimilarity}
if metric.lower() not in metricsAvailable:
print "The given metric is unknown!"
metric='Tanimoto'
simMetrics=metricsAvailable[metric.lower()]
### Calculate Fingerprint similarity Matrix
simdm=[[0.0]*molnums]*molnums
for i in range(molnums):
simdm[i,i]=1.0
for j in range(i+1,molnums):
simdm[i,j]=DataStructs.FingerprintSimilarity(fps[i],fps[j],metric=simMetrics)
simdm[j,i]=DataStructs.FingerprintSimilarity(fps[j],fps[i],metric=simMetrics)
for i in range(molnums):
print
for j in range(molnums):
print '%3.2f' % simdm[i,j],
return simdm
else:
clusters=ClusterFps(fps, cutoff=1-cutoff, metric='Tanimoto')
clusterID=0
clusterOut=[0]*len(mols)
for cluster in clusters:
clusterID+=1
for idx in cluster:
clusterOut[idx]=clusterID
## To depict cluster molecule
if False:
if len(cluster)>1:
print "Cluster: "
for idx in cluster:
mol2mpl(mols[idx])
return clusters, clusterOut
def smiles2bob2(smiles):
m = chem.MolFromSmiles(smiles)
m = chem.AddHs(m)
fp = Pairs.GetAtomPairFingerprint(m)
return fp.GetNonzeroElements()
def eval_similarity(fp_list, dim, evaluator):
s_list = []
for i in range(len(fp_list) - 1):
for j in range(i + 1, len(fp_list)):
s_list.append(evaluator(fp_list[i][dim], fp_list[j][dim]))
s_list = np.array(s_list)
return np.mean(s_list), np.std(s_list)
if __name__ == '__main__':
f = sys.argv[1]
fp_func_list = [
lambda x: AllChem.GetMorganFingerprint(x, 2),
lambda x: MACCSkeys.GenMACCSKeys(x),
lambda x: Pairs.GetAtomPairFingerprint(x),
lambda x: FingerprintMols.FingerprintMol(x)
]
evaluators = [
lambda x, y: DataStructs.DiceSimilarity(x, y),
lambda x, y: DataStructs.FingerprintSimilarity(x, y),
lambda x, y: DataStructs.DiceSimilarity(x, y),
lambda x, y: DataStructs.FingerprintSimilarity(x, y)
]
fp_list = get_fp_list(f, fp_func_list)
for i in range(len(fp_func_list)):
m, s = eval_similarity(fp_list, i, evaluators[i])
print(1 - m, s)
def smiles2bob(listofsmiles):
for smiles in listofsmiles:
m = chem.MolFromSmiles(smiles)
m = chem.AddHs(m)
fp = Pairs.GetAtomPairFingerprint(m)
yield fp.GetNonzeroElements()
def sim_two_serial():
#Load Data-----------------------------------------------------------------------
path1 = input("Path for list 1: ")
path2 = input("Path for list 2: ")
smis1 = pd.read_csv(path1)
smis1 = smis1["smiles"]
smis2 = pd.read_csv(path2)
smis2 = smis2["smiles"]
l1 = len(smis1)
l2 = len(smis2)
l = l1 * l2
lp = round(l / 20)
#Get molecules from smiles-----------------------------------------------------------------------
bad1 = []
molecules1 = []
for i, smi in enumerate(smis1):
m = Chem.MolFromSmiles(smi)
if m is None:
print('smile with number:', i,
'in list 1 could not be converted to molecule')
bad1.append(i)
continue
molecules1.append(m)
bad2 = []
molecules2 = []
for i, smi in enumerate(smis2):
m = Chem.MolFromSmiles(smi)
if m is None:
print('smile with number:', i,
'in list 2 could not be converted to molecule')
bad2.append(i)
continue
molecules2.append(m)
#can1=[Chem.MolToSmiles(x) for x in molecules1]
#can2=[Chem.MolToSmiles(x) for x in molecules2]
#for j in bad1:
#can1.insert(j,"bad1")
#for j in bad2:
#can2.insert(j,"bad2")
smis1 = []
smis2 = []
#Final output matrix-----------------------------------------------------------------------
similarity = np.zeros(shape=(l1, l2), dtype=np.float32)
from rdkit.Chem import MACCSkeys
from rdkit.Chem.AtomPairs import Pairs
from rdkit.Chem.AtomPairs import Torsions
from rdkit.Chem import AllChem
print('Begining fingerprint calculation...wait')
fps_topol1 = [FingerprintMols.FingerprintMol(x) for x in molecules1]
fps_maccs1 = [MACCSkeys.GenMACCSKeys(x) for x in molecules1]
fps_pairs1 = [Pairs.GetAtomPairFingerprint(x) for x in molecules1]
fps_tts1 = [
Torsions.GetTopologicalTorsionFingerprintAsIntVect(x)
for x in molecules1
]
fps_ecfp4_1 = [
AllChem.GetMorganFingerprintAsBitVect(x, 2, nBits=1024)
for x in molecules1
]
fps_ecfp6_1 = [
AllChem.GetMorganFingerprintAsBitVect(x, 3, nBits=1024)
for x in molecules1
]
fps_fcfp4_1 = [
AllChem.GetMorganFingerprintAsBitVect(x,
2,
nBits=1024,
useFeatures=True)
for x in molecules1
]
fps_fcfp6_1 = [
AllChem.GetMorganFingerprintAsBitVect(x,
3,
nBits=1024,
useFeatures=True)
for x in molecules1
]
print('Begining fingerprint calculation...50%')
fps_topol2 = [FingerprintMols.FingerprintMol(x) for x in molecules2]
fps_maccs2 = [MACCSkeys.GenMACCSKeys(x) for x in molecules2]
fps_pairs2 = [Pairs.GetAtomPairFingerprint(x) for x in molecules2]
fps_tts2 = [
Torsions.GetTopologicalTorsionFingerprintAsIntVect(x)
for x in molecules2
]
fps_ecfp4_2 = [
AllChem.GetMorganFingerprintAsBitVect(x, 2, nBits=1024)
for x in molecules2
]
fps_ecfp6_2 = [
AllChem.GetMorganFingerprintAsBitVect(x, 3, nBits=1024)
for x in molecules2
]
fps_fcfp4_2 = [
AllChem.GetMorganFingerprintAsBitVect(x,
2,
nBits=1024,
useFeatures=True)
for x in molecules2
]
fps_fcfp6_2 = [
AllChem.GetMorganFingerprintAsBitVect(x,
3,
nBits=1024,
useFeatures=True)
for x in molecules2
]
print('Begining fingerprint calculation...done\n')
for j in bad1:
fps_topol1.insert(j, 1)
fps_maccs1.insert(j, 1)
fps_pairs1.insert(j, 1)
fps_tts1.insert(j, 1)
fps_ecfp4_1.insert(j, 1)
fps_ecfp6_1.insert(j, 1)
fps_fcfp4_1.insert(j, 1)
fps_fcfp6_1.insert(j, 1)
for j in bad2:
fps_topol2.insert(j, 1)
fps_maccs2.insert(j, 1)
fps_pairs2.insert(j, 1)
fps_tts2.insert(j, 1)
fps_ecfp4_2.insert(j, 1)
fps_ecfp6_2.insert(j, 1)
fps_fcfp4_2.insert(j, 1)
fps_fcfp6_2.insert(j, 1)
print('Begining of fingerprints similarity calculation\n')
molecules1 = []
molecules2 = []
k = 0
maxs = 2 / (0.65 * 10) + 2 / (0.6 * 10) + 2 / (0.7 * 10) + 1 / (
0.75 * 5) + 1 / (0.85 * 5)
for i in range(l1):
for j in range(l2):
if not ((i in bad1) or (j in bad2)):
similarities_topol = DataStructs.FingerprintSimilarity(
fps_topol1[i], fps_topol2[j])
similarities_maccs = DataStructs.FingerprintSimilarity(
fps_maccs1[i], fps_maccs2[j])
similarities_pairs = DataStructs.DiceSimilarity(
fps_pairs1[i], fps_pairs2[j])
similarities_tts = DataStructs.DiceSimilarity(
fps_tts1[i], fps_tts2[j])
similarities_ecfp4 = DataStructs.FingerprintSimilarity(
fps_ecfp4_1[i], fps_ecfp4_2[j])
similarities_ecfp6 = DataStructs.FingerprintSimilarity(
fps_ecfp6_1[i], fps_ecfp6_2[j])
similarities_fcfp4 = DataStructs.FingerprintSimilarity(
fps_fcfp4_1[i], fps_fcfp4_2[j])
similarities_fcfp6 = DataStructs.FingerprintSimilarity(
fps_fcfp6_1[i], fps_fcfp6_2[j])
similarity[i][j] = (
0.5 *
(similarities_ecfp4 / 0.65 + similarities_ecfp6 / 0.6) +
0.5 *
(similarities_fcfp4 / 0.65 + similarities_fcfp6 / 0.6) +
0.5 * (similarities_tts / 0.7 + similarities_pairs / 0.7) +
similarities_maccs / 0.85 + similarities_topol / 0.75) / 5
k = k + 1
if k % lp == 0:
print('running:', (k / l) * 100, '%')
#for other similarity metrics use for example DataStructs.FingerprintSimilarity(fps[0],fps[1], metric=DataStructs.DiceSimilarity)
similarity = similarity / maxs
similarity[bad1, :] = 10
similarity[:, bad2] = 10
print('End of fingerprints similarity calculation')
bad1 = []
bad2 = []
df_similarity = pd.DataFrame(similarity)
similarity = []
return df_similarity
def sim_one_serial():
#Load Data-----------------------------------------------------------------------
path = input("Path for list : ")
smis = pd.read_csv(path)
smis = smis["smiles"]
l = len(smis)
lp = round(l * l / 20)
#Get molecules from smiles-----------------------------------------------------------------------
bad = []
molecules = []
for i, smi in enumerate(smis):
m = Chem.MolFromSmiles(smi)
if m is None:
print('smile with number:', i,
'in list could not be converted to molecule')
bad.append(i)
continue
molecules.append(m)
#can=[Chem.MolToSmiles(x) for x in molecules]
#for j in bad:
#can.insert(j,"bad")
smis = []
#Final output matrix-----------------------------------------------------------------------
similarity = np.zeros(shape=(l, l), dtype=np.float32)
from rdkit.Chem import MACCSkeys
from rdkit.Chem.AtomPairs import Pairs
from rdkit.Chem.AtomPairs import Torsions
from rdkit.Chem import AllChem
print('Begining fingerprint calculation...wait')
fps_topol = [FingerprintMols.FingerprintMol(x) for x in molecules]
fps_maccs = [MACCSkeys.GenMACCSKeys(x) for x in molecules]
fps_pairs = [Pairs.GetAtomPairFingerprint(x) for x in molecules]
fps_tts = [
Torsions.GetTopologicalTorsionFingerprintAsIntVect(x)
for x in molecules
]
fps_ecfp4 = [
AllChem.GetMorganFingerprintAsBitVect(x, 2, nBits=1024)
for x in molecules
]
fps_ecfp6 = [
AllChem.GetMorganFingerprintAsBitVect(x, 3, nBits=1024)
for x in molecules
]
fps_fcfp4 = [
AllChem.GetMorganFingerprintAsBitVect(x,
2,
nBits=1024,
useFeatures=True)
for x in molecules
]
fps_fcfp6 = [
AllChem.GetMorganFingerprintAsBitVect(x,
3,
nBits=1024,
useFeatures=True)
for x in molecules
]
print('Begining fingerprint calculation...done\n')
for j in bad:
fps_topol.insert(j, 1)
fps_maccs.insert(j, 1)
fps_pairs.insert(j, 1)
fps_tts.insert(j, 1)
fps_ecfp4.insert(j, 1)
fps_ecfp6.insert(j, 1)
fps_fcfp4.insert(j, 1)
fps_fcfp6.insert(j, 1)
#molecules=[]
print('Begining of fingerprints similarity calculation\n')
k = 0
maxs = 2 / (0.65 * 10) + 2 / (0.6 * 10) + 2 / (0.7 * 10) + 1 / (
0.75 * 5) + 1 / (0.85 * 5)
for i in range(l):
for j in range(l):
if i >= j:
if not ((i in bad) or (j in bad)):
similarities_topol = DataStructs.FingerprintSimilarity(
fps_topol[i], fps_topol[j])
similarities_maccs = DataStructs.FingerprintSimilarity(
fps_maccs[i], fps_maccs[j])
similarities_pairs = DataStructs.DiceSimilarity(
fps_pairs[i], fps_pairs[j])
similarities_tts = DataStructs.DiceSimilarity(
fps_tts[i], fps_tts[j])
similarities_ecfp4 = DataStructs.FingerprintSimilarity(
fps_ecfp4[i], fps_ecfp4[j])
similarities_ecfp6 = DataStructs.FingerprintSimilarity(
fps_ecfp6[i], fps_ecfp6[j])
similarities_fcfp4 = DataStructs.FingerprintSimilarity(
fps_fcfp4[i], fps_fcfp4[j])
similarities_fcfp6 = DataStructs.FingerprintSimilarity(
fps_fcfp6[i], fps_fcfp6[j])
similarity[i][j] = (
0.5 *
(similarities_ecfp4 / 0.65 + similarities_ecfp6 / 0.6)
+ 0.5 *
(similarities_fcfp4 / 0.65 + similarities_fcfp6 / 0.6)
+ 0.5 *
(similarities_tts / 0.7 + similarities_pairs / 0.7) +
similarities_maccs / 0.85 +
similarities_topol / 0.75) / 5
similarity[j][i] = similarity[i][j]
k = k + 1
if k % lp == 0:
print('running:', (k / (l * l / 2)) * 100, '%')
#for other similarity metrics use for example DataStructs.FingerprintSimilarity(fps[0],fps[1], metric=DataStructs.DiceSimilarity)
similarity = similarity / maxs
similarity[bad, :] = 10
similarity[:, bad] = 10
print('End of fingerprints similarity calculation')
bad = []
df_similarity = pd.DataFrame(similarity)
similarity = []
return df_similarity
m, 3, useFeatures=True
)
fpdict["lecfp4"] = lambda m: AllChem.GetMorganFingerprintAsBitVect(
m, 2, nBits=longbits
)
fpdict["lecfp6"] = lambda m: AllChem.GetMorganFingerprintAsBitVect(
m, 3, nBits=longbits
)
fpdict["lfcfp4"] = lambda m: AllChem.GetMorganFingerprintAsBitVect(
m, 2, useFeatures=True, nBits=longbits
)
fpdict["lfcfp6"] = lambda m: AllChem.GetMorganFingerprintAsBitVect(
m, 3, useFeatures=True, nBits=longbits
)
fpdict["maccs"] = lambda m: MACCSkeys.GenMACCSKeys(m)
fpdict["ap"] = lambda m: Pairs.GetAtomPairFingerprint(m)
fpdict["tt"] = lambda m: Torsions.GetTopologicalTorsionFingerprintAsIntVect(m)
fpdict[
"hashap"
] = lambda m: rdMolDescriptors.GetHashedAtomPairFingerprintAsBitVect(
m, nBits=nbits
)
fpdict[
"hashap_cas_length"
] = lambda m: rdMolDescriptors.GetHashedAtomPairFingerprintAsBitVect(
m, nBits=n_cas_bits
)
fpdict[
"hashtt"
] = lambda m: rdMolDescriptors.GetHashedTopologicalTorsionFingerprintAsBitVect(
m, nBits=nbits
