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]))
ms,
molsPerRow=3,
subImgSize=(200, 200),
legends=['' for x in ms]
)
img.save(
'/drug_development/studyRdkit/st_rdcit/img/mol21.jpg'
)
pairFps = [Pairs.GetAtomPairFingerprint(x) for x in ms]
print(pairFps)
# 由于包含在原子对指纹中的位空间很大，因此他们以稀疏的方式存储为字典形式
d = pairFps[-1].GetNonzeroElements()
print(d) # {541732: 1, 558113: 2, 558115: 2, 558146: 1, 1606690: 2, 1606721: 2}
print(d[541732]) # 1
# 位描述也可以像如下所示展示
de = Pairs.ExplainPairScore(558115)
print(de) # (('C', 1, 0), 3, ('C', 2, 0))
# The above means: C with 1 neighbor and 0 pi electrons which is 3 bonds from a C with 2 neighbors and 0 pi electrons
# 碳带有一个邻位孤电子和0个π电子，这是因为碳与两个邻位原子和氧原子形成3个化学键。
# # 2.4 拓扑扭曲topological torsions
tts = [Torsions.GetTopologicalTorsionFingerprintAsIntVect(x) for x in ms]
d_ds = DataStructs.DiceSimilarity(tts[0], tts[1])
print(d_ds) # 0.16666666666666666
# # 2.5 摩根指纹（圆圈指纹）AllChem.GetMorganFingerprint(mol,2)
# 通过将Morgan算法应用于一组用户提供的原子不变式，可以构建这一系列的指纹。生成Morgan指纹时，还必须提供指纹的半径
m1 = Chem.MolFromSmiles('Cc1ccccc1')
m2 = Chem.MolFromSmiles('Cc1ncccc1')
fp1 = AllChem.GetMorganFingerprint(m1, 2)
fp2 = AllChem.GetMorganFingerprint(m2, 2)
