def draw_fingerprint_substructures(mol,
radius,
from_atoms=None,
im_size_x=250,
im_size_y=250):
""" Draws the fingerprint substructures of a molecule for a specified radius. """
# Check if the input molecule is given in SMILES or in the RDKit Mol format.
if isinstance(mol, str):
try:
# Generate the RDKit Mol object from the input SMILES string.
mol = AllChem.MolFromSmiles(mol)
# Sanitize the molecule.
AllChem.SanitizeMol(mol)
except:
print(
"Unable to sanitize generated molecule. Check the validity of the input SMILES string."
)
# Generate the full-length fingerprint of the molecule and collect the info about the active bits.
bit_info = {}
fp = rdMolDescriptors.GetMorganFingerprintAsBitVect(mol,
radius=radius,
fromAtoms=from_atoms,
bitInfo=bit_info)
on_bits = [(mol, x, bit_info) for x in fp.GetOnBits()]
# Create the drawer object only for active bits.
drawer = Draw.DrawMorganBits(on_bits,
molsPerRow=3,
subImgSize=(im_size_x, im_size_y),
legends=[str(x) for x in fp.GetOnBits()])
# Modify the .svg string.
svg = drawer.replace("svg:", "")
# Return the final Image object.
return Image.open(io.BytesIO(svg2png(svg)))
taxol = taxol[0]
type(taxol) ### pubchempy.Compound
taxol = Chem.MolFromSmiles(taxol.canonical_smiles)
type(taxol) ### rdkit.Chem.rdchem.Mol
### Morganフィンガープリント
bitI_morgan = {}
fp_morgan = AllChem.GetMorganFingerprintAsBitVect(taxol, 2, bitInfo=bitI_morgan)
### RDKitフィンガープリント
bitI_rdkit = {}
fp_rdkit = Chem.RDKFingerprint(taxol, bitInfo=bitI_rdkit)
print(fp_morgan.GetNumBits(),fp_morgan.GetNumOnBits()) ### 2048 86
print(len(bitI_morgan)) ### 86
print(len(fp_rdkit), len(bitI_rdkit.keys())) ### (2048, 1444)
for key in list(bitI_morgan.keys())[:5]:
print(bitI_morgan[key])
### Morgan可視化
morgan_turples = ((taxol, bit, bitI_morgan) for bit in list(bitI_morgan.keys())[:12])
Draw.DrawMorganBits(morgan_turples, molsPerRow=4, legends=['bit: '+str(x) for x in list(bitI_morgan.keys())[:12]])
### RDKit可視化
rdkit_turples = ((taxol, bit, bitI_rdkit) for bit in list(bitI_rdkit.keys())[:12])
Draw.DrawRDKitBits(rdkit_turples, molsPerRow=4, legends=['bit: '+str(x) for x in list(bitI_rdkit.keys())[:12]])
def displayingsinrow(imgs, col=4):
plt.figure(figsize=(20, 20))
columns = col
for i, image in enumerate(imgs):
ax = plt.subplot(len(imgs) / columns, columns, i)
ax.set_axis_off()
plt.imshow(image)
displayingsinrow(imgs)
bi_tuple = [(mol, bit, bi) for bit in list(bi.keys())]
img = Draw.DrawMorganBits(
bi_tuple,
molsPerRow=4,
subImgSize=(250, 250),
legends=list(
map(str, list(bi.keys()))
)
)
# 存储为图片
with open('/drug_development/studyRdkit/st_rdcit/img/mol26.svg', 'w+') as outf:
outf.write(img)
# 从上图我们可以看到对摩根指纹可视化的时候，不仅有片段结构，而且对原子用不同颜色进行了标注
# 1. 蓝色：说明该原子是中心原子
# 2. 黄色：说明该原子是芳香原子
# 3. 灰色：说明该原子是脂肪烃原子
# # 3.8 可视化拓扑指纹中的bit
# 拓扑指纹也称为RDKit指纹，其调用函数Chem.RDKFingerprint(mol)
mol = Chem.MolFromSmiles('c1cccnc1C')
rdkbi = {}
