本文整理汇总了Python中rdkit.Chem.AllChem.GetMorganFingerprintAsBitVect方法的典型用法代码示例。如果您正苦于以下问题:Python AllChem.GetMorganFingerprintAsBitVect方法的具体用法?Python AllChem.GetMorganFingerprintAsBitVect怎么用?Python AllChem.GetMorganFingerprintAsBitVect使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类rdkit.Chem.AllChem
的用法示例。
在下文中一共展示了AllChem.GetMorganFingerprintAsBitVect方法的15个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: compute_ecfp_features
# 需要导入模块: from rdkit.Chem import AllChem [as 别名]
# 或者: from rdkit.Chem.AllChem import GetMorganFingerprintAsBitVect [as 别名]
def compute_ecfp_features(mol, ecfp_degree=2, ecfp_power=11):
"""Computes ECFP features for provided rdkit molecule.
Parameters:
-----------
mol: rdkit molecule
Molecule to featurize.
ecfp_degree: int
ECFP radius
ecfp_power: int
Number of bits to store ECFP features (2^ecfp_power will be length of
ECFP array)
Returns:
--------
ecfp_array: np.ndarray
Returns an array of size 2^ecfp_power where array at index i has a 1 if
that ECFP fragment is found in the molecule and array at index j has a 0
if ECFP fragment not in molecule.
"""
from rdkit.Chem import AllChem
bv = AllChem.GetMorganFingerprintAsBitVect(
mol, ecfp_degree, nBits=2**ecfp_power)
return np.array(bv)
示例2: fingerprint_mols
# 需要导入模块: from rdkit.Chem import AllChem [as 别名]
# 或者: from rdkit.Chem.AllChem import GetMorganFingerprintAsBitVect [as 别名]
def fingerprint_mols(mols, fp_dim):
fps = []
for mol in mols:
mol = Chem.MolFromSmiles(mol)
# Necessary for fingerprinting
# Chem.GetSymmSSSR(mol)
# "When comparing the ECFP/FCFP fingerprints and
# the Morgan fingerprints generated by the RDKit,
# remember that the 4 in ECFP4 corresponds to the
# diameter of the atom environments considered,
# while the Morgan fingerprints take a radius parameter.
# So the examples above, with radius=2, are roughly
# equivalent to ECFP4 and FCFP4."
# <http://www.rdkit.org/docs/GettingStartedInPython.html>
fp = AllChem.GetMorganFingerprintAsBitVect(mol, 2, nBits=int(fp_dim))
# fold_factor = fp.GetNumBits()//fp_dim
# fp = DataStructs.FoldFingerprint(fp, fold_factor)
fps.append(fp)
return fps
示例3: highest_tanimoto_precalc_fps
# 需要导入模块: from rdkit.Chem import AllChem [as 别名]
# 或者: from rdkit.Chem.AllChem import GetMorganFingerprintAsBitVect [as 别名]
def highest_tanimoto_precalc_fps(mol, fps):
"""
Args:
mol: Rdkit molecule
fps: precalculated ECFP4 bitvectors
Returns:
"""
if fps is None or len(fps) == 0:
return 0
fp1 = AllChem.GetMorganFingerprintAsBitVect(mol, 2, 4096)
sims = np.array(DataStructs.BulkTanimotoSimilarity(fp1, fps))
return sims.max()
示例4: batch_mixed_diversity
# 需要导入模块: from rdkit.Chem import AllChem [as 别名]
# 或者: from rdkit.Chem.AllChem import GetMorganFingerprintAsBitVect [as 别名]
def batch_mixed_diversity(smiles, set_smiles):
# set smiles
rand_smiles = random.sample(set_smiles, 100)
rand_mols = [Chem.MolFromSmiles(s) for s in rand_smiles]
fps = [Chem.GetMorganFingerprintAsBitVect(
m, 4, nBits=2048) for m in rand_mols]
# gen smiles
rand_gen_smiles = random.sample(smiles, 500)
gen_mols = [Chem.MolFromSmiles(s) for s in smiles]
fps = [Chem.GetMorganFingerprintAsBitVect(
m, 4, nBits=2048) for m in gen_mols]
vals = [diversity(s, fps) + diversity(s, fps) if verify_sequence(s)
else 0.0 for s in smiles]
return vals
示例5: make_circular_fingerprint
# 需要导入模块: from rdkit.Chem import AllChem [as 别名]
# 或者: from rdkit.Chem.AllChem import GetMorganFingerprintAsBitVect [as 别名]
def make_circular_fingerprint(mol, circular_fp_key):
"""Returns circular fingerprint for a mol given its circular_fp_key.
Args:
mol : rdkit.Mol
circular_fp_key : A ms_constants.CircularFingerprintKey object
Returns:
np.array of len circular_fp_key.fp_len
"""
# A dictionary to record rdkit functions to base names
fp_methods_dict = {
fmap_constants.CIRCULAR_FP_BASENAME:
AllChem.GetMorganFingerprintAsBitVect,
fmap_constants.COUNTING_CIRCULAR_FP_BASENAME:
AllChem.GetHashedMorganFingerprint
}
fp = fp_methods_dict[circular_fp_key.fp_type](
mol, circular_fp_key.radius, nBits=circular_fp_key.fp_len)
fp_arr = np.zeros(1)
DataStructs.ConvertToNumpyArray(fp, fp_arr)
return fp_arr
示例6: ECFP_from_SMILES
# 需要导入模块: from rdkit.Chem import AllChem [as 别名]
# 或者: from rdkit.Chem.AllChem import GetMorganFingerprintAsBitVect [as 别名]
def ECFP_from_SMILES(cls, smiles, radius=3, bit_len=4096, scaffold=0, index=None):
fps = np.zeros((len(smiles), bit_len))
for i, smile in enumerate(smiles):
mol = Chem.MolFromSmiles(smile)
arr = np.zeros((1,))
try:
if scaffold == 1:
mol = MurckoScaffold.GetScaffoldForMol(mol)
elif scaffold == 2:
mol = MurckoScaffold.MakeScaffoldGeneric(mol)
fp = AllChem.GetMorganFingerprintAsBitVect(mol, radius, nBits=bit_len)
DataStructs.ConvertToNumpyArray(fp, arr)
fps[i, :] = arr
except:
print(smile)
fps[i, :] = [0] * bit_len
return pd.DataFrame(fps, index=(smiles if index is None else index))
示例7: morgan_fingerprint
# 需要导入模块: from rdkit.Chem import AllChem [as 别名]
# 或者: from rdkit.Chem.AllChem import GetMorganFingerprintAsBitVect [as 别名]
def morgan_fingerprint(smiles: str, radius: int = 2, num_bits: int = 2048, use_counts: bool = False) -> np.ndarray:
"""
Generates a morgan fingerprint for a smiles string.
:param smiles: A smiles string for a molecule.
:param radius: The radius of the fingerprint.
:param num_bits: The number of bits to use in the fingerprint.
:param use_counts: Whether to use counts or just a bit vector for the fingerprint
:return: A 1-D numpy array containing the morgan fingerprint.
"""
if type(smiles) == str:
mol = Chem.MolFromSmiles(smiles)
else:
mol = smiles
if use_counts:
fp_vect = AllChem.GetHashedMorganFingerprint(mol, radius, nBits=num_bits)
else:
fp_vect = AllChem.GetMorganFingerprintAsBitVect(mol, radius, nBits=num_bits)
fp = np.zeros((1,))
DataStructs.ConvertToNumpyArray(fp_vect, fp)
return fp
示例8: getMorganEnvironment
# 需要导入模块: from rdkit.Chem import AllChem [as 别名]
# 或者: from rdkit.Chem.AllChem import GetMorganFingerprintAsBitVect [as 别名]
def getMorganEnvironment(mol, bitInfo, fp=None, minRad=0):
"""
>>> m = Chem.MolFromSmiles('CC(O)C')
>>> bi = {}
>>> fp = AllChem.GetMorganFingerprintAsBitVect(m,2,2048,bitInfo=bi)
>>> getMorganEnvironment(m,bi)
defaultdict(<class 'list'>, {1057: [[], []], 227: [[1]], 709: [[0, 1, 2]], 1: [[]], 283: [[0], [2]], 807: [[]]})
>>> getMorganEnvironment(m,bi,minRad=1)
defaultdict(<class 'list'>, {283: [[0], [2]], 227: [[1]], 709: [[0, 1, 2]]})
>>> list(fp.GetOnBits())
[1, 227, 283, 709, 807, 1057]
>>> getMorganEnvironment(m,bi,minRad=1,fp=fp)
defaultdict(<class 'list'>, {283: [[0], [2]], 227: [[1]], 709: [[0, 1, 2]]})
>>> list(fp.GetOnBits())
[227, 283, 709]
"""
bitPaths=defaultdict(list)
for bit,info in bitInfo.items():
for atomID,radius in info:
if radius < minRad:
if fp != None:
fp[bit]=0
continue
env = Chem.FindAtomEnvironmentOfRadiusN(mol,radius,atomID)
bitPaths[bit].append(list(env))
return bitPaths
示例9: similarity
# 需要导入模块: from rdkit.Chem import AllChem [as 别名]
# 或者: from rdkit.Chem.AllChem import GetMorganFingerprintAsBitVect [as 别名]
def similarity(a, b):
if a is None or b is None:
return 0.0
amol = Chem.MolFromSmiles(a)
bmol = Chem.MolFromSmiles(b)
if amol is None or bmol is None:
return 0.0
fp1 = AllChem.GetMorganFingerprintAsBitVect(amol, 2, nBits=2048, useChirality=False)
fp2 = AllChem.GetMorganFingerprintAsBitVect(bmol, 2, nBits=2048, useChirality=False)
return DataStructs.TanimotoSimilarity(fp1, fp2)
示例10: similarity
# 需要导入模块: from rdkit.Chem import AllChem [as 别名]
# 或者: from rdkit.Chem.AllChem import GetMorganFingerprintAsBitVect [as 别名]
def similarity(a, b, chiral=False):
if a is None or b is None:
return 0.0
amol = Chem.MolFromSmiles(a)
bmol = Chem.MolFromSmiles(b)
if amol is None or bmol is None:
return 0.0
fp1 = AllChem.GetMorganFingerprintAsBitVect(amol, 2, nBits=2048, useChirality=chiral)
fp2 = AllChem.GetMorganFingerprintAsBitVect(bmol, 2, nBits=2048, useChirality=chiral)
return DataStructs.TanimotoSimilarity(fp1, fp2)
示例11: calcfingerprint
# 需要导入模块: from rdkit.Chem import AllChem [as 别名]
# 或者: from rdkit.Chem.AllChem import GetMorganFingerprintAsBitVect [as 别名]
def calcfingerprint(mol, args):
'''Return a list of the bits/cnts of the fingerprint of mol.
Uses fingerprint settings from args which should have been the result
of a parse of addfpargs'''
if args.fp == 'rdkit':
fp = Chem.RDKFingerprint(mol,fpSize=args.fpbits)
return [int(x) for x in fp.ToBitString()]
elif args.fp.startswith('ecfp'):
diameter = int(args.fp.replace('ecfp',''))
r = diameter/2
fp = Chem.GetMorganFingerprintAsBitVect(mol,r,nBits=args.fpbits)
return [int(x) for x in fp.ToBitString()]
elif args.fp == 'maccs':
fp = MACCSkeys.GenMACCSKeys(mol)
return [int(x) for x in fp.ToBitString()]
elif args.fp == 'smarts':
if args.smartsfile:
smarts = args.smartsfile
ret = [0]*len(smarts)
for (i,smart) in enumerate(smarts):
if mol.HasSubstructMatch(smart):
ret[i] = 1
return ret
else:
sys.stderr.write("ERROR: Must provide SMARTS file with --smarts\n")
sys.exit(-1)
elif args.fp == 'fp2':
smi = Chem.MolToSmiles(mol)
obmol = pybel.readstring('smi',smi)
fp = obmol.calcfp(fptype='FP2')
ret = [0]*1021 #FP2 are mod 1021
for setbit in fp.bits:
#but pybel makes the bits start at 1 for some reason
assert(setbit>0)
ret[setbit-1] = 1
return ret
else:
return []
示例12: calcFingerprints
# 需要导入模块: from rdkit.Chem import AllChem [as 别名]
# 或者: from rdkit.Chem.AllChem import GetMorganFingerprintAsBitVect [as 别名]
def calcFingerprints(smiles):
m1 = Chem.MolFromSmiles(smiles)
fp = AllChem.GetMorganFingerprintAsBitVect(m1,2, nBits=2048)
binary = fp.ToBitString()
return list(binary)
#calculate fingerprints for chunked array of smiles
示例13: calcFingerprints
# 需要导入模块: from rdkit.Chem import AllChem [as 别名]
# 或者: from rdkit.Chem.AllChem import GetMorganFingerprintAsBitVect [as 别名]
def calcFingerprints(smiles):
m1 = Chem.MolFromSmiles(smiles)
fp = AllChem.GetMorganFingerprintAsBitVect(m1,2, nBits=2048)
return fp
#calculate fingerprints for chunked array of smiles
示例14: test_pkl_io
# 需要导入模块: from rdkit.Chem import AllChem [as 别名]
# 或者: from rdkit.Chem.AllChem import GetMorganFingerprintAsBitVect [as 别名]
def test_pkl_io(self):
bfps = {}
for smiles in SMILES_SAMPLE:
mol = Chem.MolFromSmiles(smiles)
bfp = Chem.GetMorganFingerprintAsBitVect(mol, 2, 512)
obj = BfpModel.objects.create(bfp=bfp)
bfps[obj.pk] = bfp
for obj in BfpModel.objects.all():
self.assertTrue(obj.pk in bfps)
ibfp = bfps[obj.pk]
obfp = obj.bfp
self.assertEqual(list(ibfp.GetOnBits()),
list(obfp.GetOnBits()))
示例15: transform_mol
# 需要导入模块: from rdkit.Chem import AllChem [as 别名]
# 或者: from rdkit.Chem.AllChem import GetMorganFingerprintAsBitVect [as 别名]
def transform_mol(self, mol):
""" transforms the molecule into a numpy bit array with the morgan bits
:parameter mol: the RDKit molecule to be transformed
"""
fp = AllChem.GetMorganFingerprintAsBitVect(mol,self.radius,nBits=self.bits)
arr = np.zeros((self.bits,))
DataStructs.ConvertToNumpyArray(fp, arr)
return arr