RDkit介绍¶

def generate_morgan_fingerprint(smiles, radius=2, nBits=2048):
    # Initialize a list to count substructure occurrences
    substructCnt = {}

    # Loop over all possible substructures of length 1 to radius
    for i in range(1, radius + 1):
        for j in range(len(smiles) - i + 1):
            substruct = smiles[j:j + i]

            if substruct in substructCnt:
                substructCnt[substruct] += 1
            else:
                substructCnt[substruct] = 1

# Initialize the fingerprint
    fingerprint = []

    # For each substructure, convert the count to a 16-bit binary representation
    for substruct in sortedSubstruct:
        substructBinary = [int(bit) for bit in bin(substructCnt[substruct])[2:].zfill(16)]
        fingerprint.extend(substructBinary)

    if len(fingerprint) >= nBits:
        fingerprint = fingerprint[:nBits]
    else:
        fingerprint.extend([0] * (nBits - len(fingerprint)))
    return np.array(fingerprint)

from rdkit import Chem
from rdkit.Chem import AllChem
def generate_rdkit_morgan_fingerprint(smiles, radius=2, nBits=2048):
    mol=Chem.MolFromSmiles(smiles)
    if not mol:
        raise ValueError(f"Invalid SMILES: {smiles}")
    fp = AllChem.GetMorganFingerprintAsBitVect(mol, radius, nBits=nBits)
    return np.array(fp)

smiles = "CC(C)c4nc(CN(C)C(=O)N[C@@H](C(C)C)C(=O)N[C@@H](Cc1ccccc1)C[C@H](O)[C@H](Cc2ccccc2)NC(=O)OCc3cncs3)cs4"  # Example SMILES string
mol = Chem.MolFromSmiles(smiles)
from rdkit.Chem import Draw

# 创建高清图像
img = Draw.MolToImage(mol, 
                     size=(500,500),  # 更大的尺寸
                     dpi=300,  # 更高的DPI
                     )

# 如果要保存高清图像
img.save('molecule_hd.png', dpi=(300,300))

from rdkit import Chem
from rdkit.Chem import Draw

# Create a molecule from SMILES (ethylbenzene)
smiles = "CCc1ccccc1"
mol = Chem.MolFromSmiles(smiles)

# Define atom indices to highlight.
# For ethylbenzene, we choose the benzene ring atoms.
# Typically, for ethylbenzene the benzene ring is represented by indices 2 to 7.
highlight_atoms = [2, 3, 4, 5, 6, 7]

# Find bonds connecting these highlighted atoms.
highlight_bonds = []
for bond in mol.GetBonds():
    begin_idx = bond.GetBeginAtomIdx()
    end_idx = bond.GetEndAtomIdx()
    # Check if both atoms in the bond are part of the highlight_atoms list.
    if begin_idx in highlight_atoms and end_idx in highlight_atoms:
        highlight_bonds.append(bond.GetIdx())

# Draw the molecule with the specified atoms and bonds highlighted.
img = Draw.MolToImage(mol,
                      size=(300, 300),
                      highlightAtoms=highlight_atoms,
                      highlightBonds=highlight_bonds)
print(highlight_bonds)

from rdkit import Chem
from rdkit.Chem import AllChem

# Example complex molecule containing a benzene ring.
# Replace this with your molecule's SMILES.
smiles = "c1ccccc1CC(=O)O"  # for instance, a benzoic acid derivative
mol = Chem.MolFromSmiles(smiles)
Chem.SanitizeMol(mol)   # 检查分子是否合法
# Define a benzene ring pattern (SMARTS)
benzene_pattern = Chem.MolFromSmarts("c1ccccc1")

# Find benzene substructure matches in the molecule
matches = mol.GetSubstructMatches(benzene_pattern)
print(matches)
if matches:
    # Choose the first match; this returns a tuple of atom indices (one per ring atom)
    match = matches[0]
    print(match)
    # Replace one carbon with nitrogen.
    # Here, we choose the first atom in the match.
    atom_to_replace = match[1]
    mol.GetAtomWithIdx(atom_to_replace).SetAtomicNum(14)  # 7 is nitrogen

    # Resanitize the molecule to update aromaticity and valence
    Chem.SanitizeMol(mol)
    new_smiles_direct = Chem.MolToSmiles(mol)
    print("Modified molecule (atom replacement):", new_smiles_direct)
else:
    print("No benzene ring found using the SMARTS pattern.")

from rdkit.Chem import Crippen,Descriptors

def get_common_descriptors(mol):
    return {
        'MW': Descriptors.ExactMolWt(mol),
        'LogP': Crippen.MolLogP(mol),
        'TPSA': Descriptors.TPSA(mol),
        'HBA': Descriptors.NumHAcceptors(mol),
        'HBD': Descriptors.NumHDonors(mol),
        'Rotatable_Bonds': Descriptors.NumRotatableBonds(mol),
        'Rings': Descriptors.RingCount(mol),
        'Aromatic_Rings': Descriptors.NumAromaticRings(mol)
    }

# 使用示例
mol = Chem.MolFromSmiles("CC(=O)OC1=CC=CC=C1C(=O)O")
common_desc = get_common_descriptors(mol)
for name, value in common_desc.items():
    print(f"{name}: {value}")

matches = mol.GetSubstructMatches(benzene)