def calculate_mol_similarity(molA, molB):
"""
Function to calculate the similarity between two oemol objects
should be used to utils/openeye.py or openmoltools
:param molA: oemol object of molecule A
:param molB: oemol object of molecule B
:return: float, tanimoto score of the two molecules, between 0 and 1
"""
fpA = oegraphsim.OEFingerPrint()
fpB = oegraphsim.OEFingerPrint()
oegraphsim.OEMakeFP(fpA, molA, oegraphsim.OEFPType_MACCS166)
oegraphsim.OEMakeFP(fpB, molB, oegraphsim.OEFPType_MACCS166)
return oegraphsim.OETanimoto(fpA, fpB)
def calculate_fp(self):
for mol in self.act_list:
fp = oegraphsim.OEFingerPrint()
oegraphsim.OEMakeFP(fp, mol, self.args.fptype)
self.fp_list.append(fp)
# Customer is hereby permitted to use, copy, and modify the Sample Code,
# subject to these terms. OpenEye claims no rights to Customer's
# modifications. Modification of Sample Code is at Customer's sole and
# exclusive risk. Sample Code may require Customer to have a then
# current license or subscription to the applicable OpenEye offering.
# THE SAMPLE CODE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
# EXPRESS OR IMPLIED. OPENEYE DISCLAIMS ALL WARRANTIES, INCLUDING, BUT
# NOT LIMITED TO, WARRANTIES OF MERCHANTABILITY, FITNESS FOR A
# PARTICULAR PURPOSE AND NONINFRINGEMENT. In no event shall OpenEye be
# liable for any damages or liability in connection with the Sample Code
# or its use.
from openeye import oechem
from openeye import oegraphsim
mol = oechem.OEGraphMol()
oechem.OESmilesToMol(mol, "c1ccccc1")
# @ <SNIPPET-MAKE-FP>
fpA = oegraphsim.OEFingerPrint()
oegraphsim.OEMakePathFP(fpA, mol)
fpB = oegraphsim.OEFingerPrint()
oegraphsim.OEMakeFP(fpB, mol, fpA.GetFPTypeBase())
# @ </SNIPPET-MAKE-FP>
if oegraphsim.OEIsSameFPType(fpA, fpB):
print("same fingerprint types")
else:
print("different fingerprint types")
from openeye import oechem
from openeye import oegraphsim
mol = oechem.OEGraphMol()
oechem.OESmilesToMol(mol, "c1ccccc1")
# @ <SNIPPET-MAKE-PATH-1>
fp = oegraphsim.OEFingerPrint()
oegraphsim.OEMakePathFP(fp, mol)
# @ </SNIPPET-MAKE-PATH-1>
print(fp.GetFPTypeBase().GetFPTypeString())
# @ <SNIPPET-MAKE-PATH-2>
oegraphsim.OEMakeFP(fp, mol, oegraphsim.OEFPType_Path)
# @ </SNIPPET-MAKE-PATH-2>
print(fp.GetFPTypeBase().GetFPTypeString())
# @ <SNIPPET-MAKE-PATH-3>
numbits = 1024
minbonds = 0
maxbonds = 5
oegraphsim.OEMakePathFP(fp, mol, numbits, minbonds, maxbonds,
oegraphsim.OEFPAtomType_DefaultPathAtom,
oegraphsim.OEFPBondType_DefaultPathBond)
# @ </SNIPPET-MAKE-PATH-3>
print(fp.GetFPTypeBase().GetFPTypeString())
# liable for any damages or liability in connection with the Sample Code
# or its use.
from openeye import oechem
from openeye import oegraphsim
import sys
if len(sys.argv) != 3:
oechem.OEThrow.Usage("%s <queryfile> <targetfile>" % sys.argv[0])
ifs = oechem.oemolistream()
if not ifs.open(sys.argv[1]):
oechem.OEThrow.Fatal("Unable to open %s for reading" % sys.argv[1])
qmol = oechem.OEGraphMol()
oechem.OEReadMolecule(ifs, qmol)
qfp = oegraphsim.OEFingerPrint()
oegraphsim.OEMakeFP(qfp, qmol, oegraphsim.OEFPType_Path)
if not ifs.open(sys.argv[2]):
oechem.OEThrow.Fatal("Unable to open %s for reading" % sys.argv[2])
# @ <SNIPPET-DB-SIM-CALC-FROM-FILE>
fpdb = oegraphsim.OEFPDatabase(qfp.GetFPTypeBase())
for tmol in ifs.GetOEGraphMols():
fpdb.AddFP(tmol)
for score in fpdb.GetScores(qfp):
print("%.3f" % score.GetScore())
# @ </SNIPPET-DB-SIM-CALC-FROM-FILE>
# Customer is hereby permitted to use, copy, and modify the Sample Code, # subject to these terms. OpenEye claims no rights to Customer's # modifications. Modification of Sample Code is at Customer's sole and # exclusive risk. Sample Code may require Customer to have a then # current license or subscription to the applicable OpenEye offering. # THE SAMPLE CODE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, # EXPRESS OR IMPLIED. OPENEYE DISCLAIMS ALL WARRANTIES, INCLUDING, BUT # NOT LIMITED TO, WARRANTIES OF MERCHANTABILITY, FITNESS FOR A # PARTICULAR PURPOSE AND NONINFRINGEMENT. In no event shall OpenEye be # liable for any damages or liability in connection with the Sample Code # or its use. from openeye import oechem from openeye import oegraphsim mol = oechem.OEGraphMol() oechem.OESmilesToMol(mol, "c1ccccc1") # @ <SNIPPET-MAKE-LINGO-1> fp = oegraphsim.OEFingerPrint() oegraphsim.OEMakeLingoFP(fp, mol) # @ </SNIPPET-MAKE-LINGO-1> print(fp.GetFPTypeBase().GetFPTypeString()) # @ <SNIPPET-MAKE-LINGO-2> oegraphsim.OEMakeFP(fp, mol, oegraphsim.OEFPType_Lingo) # @ </SNIPPET-MAKE-LINGO-2> print(fp.GetFPTypeBase().GetFPTypeString())
# THE SAMPLE CODE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
# EXPRESS OR IMPLIED. OPENEYE DISCLAIMS ALL WARRANTIES, INCLUDING, BUT
# NOT LIMITED TO, WARRANTIES OF MERCHANTABILITY, FITNESS FOR A
# PARTICULAR PURPOSE AND NONINFRINGEMENT. In no event shall OpenEye be
# liable for any damages or liability in connection with the Sample Code
# or its use.
from openeye import oechem
from openeye import oegraphsim
# @ <SNIPPET-BIT-STRING>
def GetBitString(fp):
bitstring = ''
for b in range(0, fp.GetSize()):
if fp.IsBitOn(b):
bitstring += '1'
else:
bitstring += '0'
return bitstring
# @ </SNIPPET-BIT-STRING>
mol = oechem.OEGraphMol()
oechem.OESmilesToMol(mol, "c1ccncc1")
fp = oegraphsim.OEFingerPrint()
oegraphsim.OEMakeFP(fp, mol, oegraphsim.OEFPType_MACCS166)
print(GetBitString(fp))
def cluster_similar_molecules(
smiles, fingerprint_type=oegraphsim.OEFPType_Tree, eps=0.5, min_samples=2
):
"""The method attempts to cluster a sets of molecules based on their
similarity using a Tanimoto distance metric and the `sklearn` DBSCAN
clustering code.
Notes
-----
This is based on the code by David Mobley:
https://github.com/openforcefield/release-1-benchmarking/blob/master/QM_molecule_selection/divide_sets.ipynb
Parameters
----------
smiles: list of str
The SMILES representations of the molecules to cluster.
fingerprint_type
The type of molecular fingerprint to use.
eps: float
The `eps` parameter to pass as an argument to DBSCAN while clustering.
min_samples: int
The `min_samples` parameter to pass as an argument to DBSCAN while
clustering.
Returns
-------
dict of str and list of str
The clustered SMILES patterns.
"""
assert isinstance(smiles, list)
# Build fingerprints
fingerprints = {}
for smiles_pattern in smiles:
oe_molecule = oechem.OEMol()
oechem.OEParseSmiles(oe_molecule, smiles_pattern)
fingerprint = oegraphsim.OEFingerPrint()
oegraphsim.OEMakeFP(fingerprint, oe_molecule, fingerprint_type)
fingerprints[smiles_pattern] = fingerprint
# Build a similarity matrix
distance_matrix = np.zeros((len(smiles), len(smiles)))
for i, smiles_i in enumerate(smiles):
for j, smiles_j in enumerate(smiles):
if i == j:
continue
distance_matrix[i, j] = 1.0 - oegraphsim.OETanimoto(
fingerprints[smiles_i], fingerprints[smiles_j]
)
# Cluster the data
clustering = DBSCAN(eps=eps, min_samples=min_samples, metric="precomputed")
clustered_smiles = clustering.fit(distance_matrix)
labels = clustered_smiles.labels_
smiles_by_cluster = {}
for label in set(labels):
smiles_by_cluster[label] = [
smiles[i] for i, x in enumerate(labels) if x == label
]
return smiles_by_cluster
fpA = oegraphsim.OEFingerPrint()
molB = oechem.OEGraphMol()
oechem.OESmilesToMol(molB, "COc1cc2ccc(cc2c(=O)o1)NC(=N)N")
fpB = oegraphsim.OEFingerPrint()
molC = oechem.OEGraphMol()
oechem.OESmilesToMol(molC, "COc1c(c2ccc(cc2c(=O)o1)NC(=N)N)Cl")
fpC = oegraphsim.OEFingerPrint()
# @ <SNIPPET-FP-YULE-1>
def CalculateYule(fpA, fpB):
onlyA, onlyB, bothAB, neitherAB = oechem.OEGetBitCounts(fpA, fpB)
yule = float(bothAB * neitherAB - onlyA * onlyB)
yule /= float(bothAB * neitherAB + onlyA * onlyB)
return yule
# @ </SNIPPET-FP-YULE-1>
# @ <SNIPPET-FP-YULE-2>
oegraphsim.OEMakeFP(fpA, molA, oegraphsim.OEFPType_Path)
oegraphsim.OEMakeFP(fpB, molB, oegraphsim.OEFPType_Path)
oegraphsim.OEMakeFP(fpC, molC, oegraphsim.OEFPType_Path)
print("Yule(A,B) = %.3f" % CalculateYule(fpA, fpB))
print("Yule(A,C) = %.3f" % CalculateYule(fpA, fpC))
print("Yule(B,C) = %.3f" % CalculateYule(fpB, fpC))
# @ </SNIPPET-FP-YULE-2>
# Customer is hereby permitted to use, copy, and modify the Sample Code,
# subject to these terms. OpenEye claims no rights to Customer's
# modifications. Modification of Sample Code is at Customer's sole and
# exclusive risk. Sample Code may require Customer to have a then
# current license or subscription to the applicable OpenEye offering.
# THE SAMPLE CODE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
# EXPRESS OR IMPLIED. OPENEYE DISCLAIMS ALL WARRANTIES, INCLUDING, BUT
# NOT LIMITED TO, WARRANTIES OF MERCHANTABILITY, FITNESS FOR A
# PARTICULAR PURPOSE AND NONINFRINGEMENT. In no event shall OpenEye be
# liable for any damages or liability in connection with the Sample Code
# or its use.
from openeye import oechem
from openeye import oegraphsim
mol = oechem.OEGraphMol()
oechem.OESmilesToMol(mol, "c1ccccc1")
fpA = oegraphsim.OEFingerPrint()
fpB = oegraphsim.OEFingerPrint()
oegraphsim.OEMakeFP(fpA, mol, oegraphsim.OEFPType_Path)
oegraphsim.OEMakeFP(fpB, mol, oegraphsim.OEFPType_Path)
# @ <SNIPPET-FP-COMPARE>
if fpA == fpB:
print("same fingerprints")
else:
print("different fingerprints")
# @ </SNIPPET-FP-COMPARE>
from openeye import oechem
from openeye import oegraphsim
mol = oechem.OEGraphMol()
oechem.OESmilesToMol(mol, "c1ccccc1")
# @ <SNIPPET-MAKE-CIRCULAR-1>
fp = oegraphsim.OEFingerPrint()
oegraphsim.OEMakeCircularFP(fp, mol)
# @ </SNIPPET-MAKE-CIRCULAR-1>
print(fp.GetFPTypeBase().GetFPTypeString())
# @ <SNIPPET-MAKE-CIRCULAR-2>
oegraphsim.OEMakeFP(fp, mol, oegraphsim.OEFPType_Circular)
# @ </SNIPPET-MAKE-CIRCULAR-2>
print(fp.GetFPTypeBase().GetFPTypeString())
# @ <SNIPPET-MAKE-CIRCULAR-3>
numbits = 1024
minradius = 0
maxradius = 3
oegraphsim.OEMakeCircularFP(fp, mol, numbits, minradius, maxradius,
oegraphsim.OEFPAtomType_DefaultCircularAtom,
oegraphsim.OEFPBondType_DefaultCircularBond)
# @ </SNIPPET-MAKE-CIRCULAR-3>
print(fp.GetFPTypeBase().GetFPTypeString())
from openeye import oechem
from openeye import oegraphsim
mol = oechem.OEGraphMol()
oechem.OESmilesToMol(mol, "c1ccccc1")
# @ <SNIPPET-MAKE-TREE-1>
fp = oegraphsim.OEFingerPrint()
oegraphsim.OEMakeTreeFP(fp, mol)
# @ </SNIPPET-MAKE-TREE-1>
print(fp.GetFPTypeBase().GetFPTypeString())
# @ <SNIPPET-MAKE-TREE-2>
oegraphsim.OEMakeFP(fp, mol, oegraphsim.OEFPType_Tree)
# @ </SNIPPET-MAKE-TREE-2>
print(fp.GetFPTypeBase().GetFPTypeString())
# @ <SNIPPET-MAKE-TREE-3>
numbits = 1024
minbonds = 0
maxbonds = 5
oegraphsim.OEMakeTreeFP(fp, mol, numbits, minbonds, maxbonds,
oegraphsim.OEFPAtomType_DefaultTreeAtom,
oegraphsim.OEFPBondType_DefaultTreeBond)
# @ </SNIPPET-MAKE-TREE-3>
print(fp.GetFPTypeBase().GetFPTypeString())
# current license or subscription to the applicable OpenEye offering.
# THE SAMPLE CODE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
# EXPRESS OR IMPLIED. OPENEYE DISCLAIMS ALL WARRANTIES, INCLUDING, BUT
# NOT LIMITED TO, WARRANTIES OF MERCHANTABILITY, FITNESS FOR A
# PARTICULAR PURPOSE AND NONINFRINGEMENT. In no event shall OpenEye be
# liable for any damages or liability in connection with the Sample Code
# or its use.
from openeye import oechem
from openeye import oegraphsim
# @ <SNIPPET-FP-TANIMOTO>
molA = oechem.OEGraphMol()
oechem.OESmilesToMol(molA, "c1ccc2c(c1)c(c(oc2=O)OCCSC(=N)N)Cl")
fpA = oegraphsim.OEFingerPrint()
oegraphsim.OEMakeFP(fpA, molA, oegraphsim.OEFPType_MACCS166)
molB = oechem.OEGraphMol()
oechem.OESmilesToMol(molB, "COc1cc2ccc(cc2c(=O)o1)NC(=N)N")
fpB = oegraphsim.OEFingerPrint()
oegraphsim.OEMakeFP(fpB, molB, oegraphsim.OEFPType_MACCS166)
molC = oechem.OEGraphMol()
oechem.OESmilesToMol(molC, "COc1c(c2ccc(cc2c(=O)o1)NC(=N)N)Cl")
fpC = oegraphsim.OEFingerPrint()
oegraphsim.OEMakeFP(fpC, molC, oegraphsim.OEFPType_MACCS166)
print("Tanimoto(A,B) = %.3f" % oegraphsim.OETanimoto(fpA, fpB))
print("Tanimoto(A,C) = %.3f" % oegraphsim.OETanimoto(fpA, fpC))
print("Tanimoto(B,C) = %.3f" % oegraphsim.OETanimoto(fpB, fpC))
# @ </SNIPPET-FP-TANIMOTO>