def __call__(self, smiles: List[str]) -> dict:
mols = [Chem.MolFromSmiles(smile) for smile in smiles]
valid = [1 if mol is not None else 0 for mol in mols]
valid_idxs = [idx for idx, boolean in enumerate(valid) if boolean == 1]
valid_mols = [mols[idx] for idx in valid_idxs]
fps = [
AllChem.GetMorganFingerprint(mol,
3,
useCounts=True,
useFeatures=False)
for mol in valid_mols
]
tanimoto = np.array([
np.max(DataStructs.BulkTanimotoSimilarity(fp, self.ref_fps))
for fp in fps
])
tanimoto = np.maximum((1 - 2 * np.absolute(0.5 - tanimoto)), 0)
score = np.full(len(smiles), 0, dtype=np.float32)
for idx, value in zip(valid_idxs, tanimoto):
score[idx] = value
return {"total_score": np.array(score, dtype=np.float32)}
def ClusterFps(fps, similaridad):
cutoff = 1-similaridad
# first generate the distance matrix:
dists = []
nfps = len(fps)
for i in range(1,nfps):
sims = DataStructs.BulkTanimotoSimilarity(fps[i],fps[:i])
dists.extend([1-x for x in sims])
# now cluster the data:
cs = Butina.ClusterData(dists,nfps,cutoff,isDistData=True)
return cs
def Tanimotosimilarity():
out = open("hogehoge.txt", "w")
fps = [AllChem.GetMorganFingerprint(m, 2) for m in mols]
simmat = []
for i in range(len(fps)):
tsims = DataStructs.BulkTanimotoSimilarity(fps[i], fps[:i])
simmat.append(tsims)
if tsims >= 0.7:
out.write("%s\tsim\t%s\n" %
(mols[i].GetProp("ID"), mols[j].GetProp("ID")))
out.close()
def calcDistMatrix(df, distMeasure):
# calculates the distance matrix between all paris of molecules, standard: Tanimoto and Morgan2 FPs
dists=np.zeros([len(df),len(df)])
if distMeasure=='Tanimoto':
for i in range(1,len(df)):
ds = DataStructs.BulkTanimotoSimilarity(df.FP.iloc[i],list(df.FP.iloc[:i]),returnDistance=1)
for j in range(i):
dists[i,j] = ds[j]
dists[j,i] = ds[j]
else:
print(distMeasure, 'distance metric not implemented.')
return
return dists
def ClusterFps(fps, cutoff=0.2):
# Function to group molecules based on their similarity to other compounds in the HERG set.
# This is an attempt to overcome some of the problems associated with not
# having a single series of related compounds
# first generate the distance matrix:
dists = []
nfps = len(fps)
for i in range(1, nfps):
sims = DataStructs.BulkTanimotoSimilarity(fps[i], fps[:i])
dists.extend([1 - x for x in sims])
# now cluster the data:
cs = Butina.ClusterData(dists, nfps, cutoff, isDistData=True)
return cs
def cluster_mols(
mols: List[Chem.rdchem.Mol],
cutoff: float = 0.2,
feature_fn: Callable = None,
n_jobs: Optional[int] = 1,
):
"""Cluster a set of molecules using the butina clustering algorithm and a given threshold.
Args:
mols: a list of molecules.
cutoff: Cuttoff for the clustering. Default to 0.2.
feature_fn: A feature function that takes a Chem.rdchem.Mol object
and return molecular features. By default, the `dm.to_fp()` is used.
Default to None.
n_jobs: Number of jobs for parallelization. Let to 1 for no
parallelization. Set to None to use all available cores.
"""
if feature_fn is None:
feature_fn = functools.partial(dm.to_fp, as_array=False)
features = dm.parallelized(feature_fn, mols, n_jobs=n_jobs)
dists = []
n_mols = len(mols)
for i in range(1, n_mols):
dist = DataStructs.BulkTanimotoSimilarity(features[i],
features[:i],
returnDistance=True)
dists.extend([x for x in dist])
# now cluster the data
cluster_indices = Butina.ClusterData(dists,
n_mols,
cutoff,
isDistData=True)
cluster_mols = [
operator.itemgetter(*cluster)(mols) for cluster in cluster_indices
]
# Make single mol cluster a list
cluster_mols = [[c] if isinstance(c, Chem.rdchem.Mol) else c
for c in cluster_mols]
return cluster_indices, cluster_mols
def tanimoto(mol, lib_in):
return DataStructs.BulkTanimotoSimilarity(mol, lib_in)
def _calculate_tanimoto(self, query_fps, ref_fingerprints) -> np.array:
return np.array([
np.max(DataStructs.BulkTanimotoSimilarity(fp, ref_fingerprints))
for fp in query_fps
])
fp_bulk.append(fp1)
for idy, parms_y in dataset2.iterrows():
try:
smi_y = parms_y['SMILES']
exp_solb = parms_y['measured']
mol_y = Chem.MolFromSmiles(smi_y)
AllChem.Compute2DCoords(mol_y)
# fp2 = Chem.RDKFingerprint(mol_y)
fp2 = AllChem.GetMorganFingerprintAsBitVect(mol_y, 2, 2048)
except:
print(smi_y + "was not valid SMILES\n")
continue
else:
Tan = DataStructs.BulkTanimotoSimilarity(fp2, fp_bulk)
Tan = np.asarray(Tan)
Tan_mean = Tan.mean()
Tan_min = Tan.min()
Tan_max = Tan.max()
Tan_bulk.append([smi_y, exp_solb, Tan_mean, Tan_min, Tan_max])
print("Tan= %s" % (Tan))
Tan_pd = pd.DataFrame(Tan_bulk,
columns=[
'smi', 'experimental_solubilty', 'smlty_mean',
'smlty_min', 'smlty_max'
])
pd_file = '%s_%s_smlty.csv' % (args.dataset1, args.dataset2)
Tan_pd.to_csv(pd_file, index=False)
print('mean= %s' % (Tan_pd['smlty_mean'].mean()))
