def mol_from_xyz(filepath, add_hs=True, compute_dist_centre=False):
"""Wrapper function for calling xyz2mol function."""
charged_fragments = True # alternatively radicals are made
# quick is faster for large systems but requires networkx
# if you don't want to install networkx set quick=False and
# uncomment 'import networkx as nx' at the top of the file
quick = True
atomicNumList, charge, xyz_coordinates = read_xyz_file(filepath)
mol, dMat = xyz2mol(atomicNumList, charge, xyz_coordinates,
charged_fragments, quick, check_chiral_stereo=False) #The molecular structure mol and distance matrix can be obtained by reading the XYZ file
return mol, np.array(xyz_coordinates), dMat
def test_smiles_from_xyz_files(filename, charge, answer):
atoms, charge_read, coordinates = x2m.read_xyz_file(filename)
mols = x2m.xyz2mol(atoms, coordinates, charge=charge)
smiles_list = []
for mol in mols:
mol = Chem.RemoveHs(mol)
smiles = Chem.MolToSmiles(mol)
smiles_list.append(smiles)
assert answer in smiles_list
def MolFromXYZ(filename):
charged_fragments = True
quick = True
cache_filename = filename.parent / f'{filename.stem}.pkl'
if cache_filename.exists():
return pickle.load(open(cache_filename, 'rb'))
else:
try:
atomicNumList, charge, xyz_coordinates = read_xyz_file(filename)
mol = xyz2mol(atomicNumList, charge, xyz_coordinates,
charged_fragments, quick)
pickle.dump(mol, open(cache_filename, 'wb'))
except:
print(filename)
return mol
def get_molecules():
"""
Constructs rdkit mol objects derrived from the .xyz files. Also returns:
- mol ids (unique numerical ids)
- set of molecule level features
- arrays of xyz coordinates
- euclidean distance matrices
- graph distance matrices.
All objects are returned in dictionaries with 'mol_name' as keys.
"""
mols, mol_ids, mol_feats = {}, {}, {}
xyzs, dist_matrices, graph_dist_matrices = {}, {}, {}
print('Create molecules and distance matrices.')
for i in range(C.N_MOLS):
print_progress(i, C.N_MOLS)
filepath = xyz_filepath_list[i]
mol_name = filepath.split('/')[-1][:-4]
mol, xyz, dist_matrix = mol_from_xyz(filepath) #读取XYZ文件获取结构mol和距离矩阵，坐标
mols[mol_name] = mol
xyzs[mol_name] = xyz
dist_matrices[mol_name] = dist_matrix
mol_ids[mol_name] = i # 数据集中分子序号作为分子的id
# make padded graph distance matrix dataframes
n_atoms = len(xyz)
graph_dist_matrix = pd.DataFrame(
np.pad(rdmolops.GetDistanceMatrix(mol),
[(0, 0), (0, C.MAX_N_ATOMS - n_atoms)],
'constant')) #通过ramolops.GetDistanceMatrix获取 图距离矩阵
graph_dist_matrix['molecule_id'] = n_atoms * [
i
] # eg: CH4 5 * [0] = [0, 0, 0, 0, 0] list数据可以为dataframe赋值
graph_dist_matrices[mol_name] = graph_dist_matrix #字典：value: dataframe
# compute molecule level features
adj_matrix = rdmolops.GetAdjacencyMatrix(
mol) #通过ramolops.GetDistanceMatrix获取 图邻接矩阵
atomic_num_list, _, _ = read_xyz_file(
filepath) #读取XYZ文件获取分子中各原子的原子序数和坐标
dists = dist_matrix.ravel()[np.tril(adj_matrix).ravel() ==
1] #通过邻接矩阵的下三角获取与相邻原子之间的距离
mol_feats[mol_name] = pd.Series(
[np.mean(dists),
np.std(dists),
np.mean(atomic_num_list)],
index=mol_feat_columns) #获取与领接原子之间距离均值和标准差、原子序数的均值(分子级特征)
return mols, mol_ids, mol_feats, xyzs, dist_matrices, graph_dist_matrices #返回训练集所有分子结构mol和分子ids,分子级特征,原子坐标,距离矩阵，图距离矩阵
def get_molecules():
"""
Constructs rdkit mol objects derrived from the .xyz files. Also returns:
- mol ids (unique numerical ids)
- set of molecule level features
- arrays of xyz coordinates
- euclidean distance matrices
- graph distance matrices.
All objects are returned in dictionaries with 'mol_name' as keys.
"""
mols, mol_ids, mol_feats = {}, {}, {}
xyzs, dist_matrices, graph_dist_matrices = {}, {}, {}
print('Create molecules and distance matrices.')
for i in range(C.N_MOLS):
print_progress(i, C.N_MOLS)
filepath = xyz_filepath_list[i]
mol_name = filepath.split('/')[-1][:-4]
mol, xyz, dist_matrix = mol_from_xyz(filepath)
mols[mol_name] = mol
xyzs[mol_name] = xyz
dist_matrices[mol_name] = dist_matrix
mol_ids[mol_name] = i
# make padded graph distance matrix dataframes
n_atoms = len(xyz)
graph_dist_matrix = pd.DataFrame(
np.pad(rdmolops.GetDistanceMatrix(mol),
[(0, 0), (0, C.MAX_N_ATOMS - n_atoms)], 'constant'))
graph_dist_matrix['molecule_id'] = n_atoms * [i]
graph_dist_matrices[mol_name] = graph_dist_matrix
# compute molecule level features
adj_matrix = rdmolops.GetAdjacencyMatrix(mol)
atomic_num_list, _, _ = read_xyz_file(filepath)
dists = dist_matrix.ravel()[np.tril(adj_matrix).ravel() == 1]
mol_feats[mol_name] = pd.Series(
[np.mean(dists),
np.std(dists),
np.mean(atomic_num_list)],
index=mol_feat_columns)
return mols, mol_ids, mol_feats, xyzs, dist_matrices, graph_dist_matrices
import xyz2mol as x2m
if __name__ == "__main__":
#print(rdBase.rdkitVersion)
filename = "ethane.xyz"
filename = "acetate.xyz"
filename = "chiral_stereo_test.xyz"
charged_fragments = True
quick = True
huckel = True
atomicNumList,charge,xyz_coordinates = x2m.read_xyz_file(filename)
mol = x2m.xyz2mol(atomicNumList,charge,xyz_coordinates,charged_fragments,quick,huckel)
print(Chem.MolToSmiles(mol, isomericSmiles=True))
# code to test using SMILES instead of xyz file
smiles_list = ['C=C([O-])CC','C=C([NH3+])CC','CC(=O)[O-]','C[N+](=O)[O-]','CS(CC)(=O)=O','CS([O-])(=O)=O',
'C=C(C)CC', 'CC(C)CC','C=C(N)CC','C=C(C)C=C','C#CC=C','c1ccccc1','c1ccccc1c1ccccc1',
'[NH3+]CS([O-])(=O)=O','CC(NC)=O','[O-]c1ccccc1','O=C(C=C1)C=CC1=CCC([O-])=O',
'C#CC#C','Cc1ccc(cc1)C1C=CC2C(C=CC2(C#N)C#N)=CC=1']
#smiles_list = ['C[NH+]=C([O-])CC[NH+]=C([O-])C','C[NH+]=CC=C([O-])C',
# "[C+](C)(C)CC[C-](C)(C)",'O=C(C=C1)C=CC1=CCC([O-])=O',
# 'O=C([CH-]C=CC(C([O-])=O)=O)[O-]','[O-]c1ccccc1','CNC(C(C)=[NH+][CH-]CC(O)=O)=O',"[CH2][CH2][CH]=[CH][CH2]"]
#smiles_list = ['Cc1ccc(cc1)C1C=CC2C(C=CC2(C#N)C#N)=CC=1']
#smiles_list = ['CC1C=CC2C(C=CC2(C)C)=CC=1']
#smiles_list = ['CC1=CC=C(C=CC2)C2C=C1']