def __coo_atom(self, comp, m_ele):
'''
Given a molecule<ccdc.molecule.Molecule> and a metal symbol<str>
Return a dict about the metal with its coordinated atoms
:param comp: <ccdc.molecule.Molecule>molecule
:param m_ele: <str>metal elements symbol
:param label: <bool>return atom label or atom entity
:return:<dict>{<str>metal label: <set>{<str> coordinated atoms label}
'''
dict_coo_atoms = dict(
) # dict for storing the coordination atom around the target metal ie.atoms one by one
qm = QueryAtom(m_ele)
qs = search.QuerySubstructure()
qs.add_atom(qm)
sub_search = search.SubstructureSearch()
sub_search.add_substructure(qs)
mol_metals = sub_search.search(comp)
for mol_metal in mol_metals:
set_atom = set()
metal = mol_metal.match_atoms()
set_atom.update([N_atom.label for N_atom in metal[0].neighbours])
metal_label = metal[0].label
dict_coo_atoms[metal_label] = set_atom
return dict_coo_atoms
def delete_anion(self, path_anion):
'''
removing anions which are defined by mol2 file in a entry
:param path_anion: the defined anions files
:return: None
'''
if os.path.isdir(path_anion):
anion_list = [
search.MoleculeSubstructure(
io.MoleculeReader(f)[0].components[0])
for f in glob.glob(os.path.join(path_anion, '*.mol2'))
]
else:
raise FileExistsError('do not find the path!')
list_crystals_remove_anion = []
p_bar = tqdm(self.entry_reader)
for entry in p_bar:
if entry.has_3d_structure:
# Ensure labels are unique
mol = entry.molecule
mol.normalise_labels()
# Use a copy
clone = mol.copy()
# Remove all metal atoms
clone.remove_atoms(a for a in clone.atoms
if a.is_metal or not a.bonds)
for c in clone.components:
for anion in anion_list:
ani_search = search.SubstructureSearch()
ani_search.add_substructure(anion)
hits = ani_search.search(c)
for hit in hits:
hit_atoms = hit.match_atoms()
if len(hit_atoms) == len(c.atoms):
mol.remove_atoms(
mol.atom(a.label) for a in hit_atoms)
entry.crystal.molecule = self.__delete_isolated_atoms(mol)
list_crystals_remove_anion.append(entry)
p_bar.set_description('Anions removing...')
self.entry_reader = list_crystals_remove_anion
def get_all_function_groups(path_mols, path_con):
"""从*.mol2文件中找到指定基团的类型及数量
:param path_cifs:
:param path_con:
:return:
"""
# 确定每个已经去除了溶剂的*.mol2文件的名称和绝对路径
list_mol_names = os.listdir(path_mols)
list_path_mols = glob.glob(os.path.join(path_mols, '*.mol2'))
# 通过con定义功能基团
list_con_names = os.listdir(path_con)
path_conner_list = glob.glob(os.path.join(path_con, '*.con'))
list_connser_substructure = []
for path in path_conner_list:
connser_substructure = search.ConnserSubstructure(path)
list_connser_substructure.append(connser_substructure)
# 读取mol2文件中
dict_result = dict()
count = 0
pbar = tqdm(list_path_mols)
for path_cif_temp in pbar:
list_temp = [
] # 维度为len(list_connser_substructure)，即维度为定义的官能团个数；该列表用于储存当前cif文件中包含基团的数目
mol_temp = io.MoleculeReader(path_cif_temp)[0] # 读取cif文件
for func_group in list_connser_substructure:
substructure_search = search.SubstructureSearch()
_ = substructure_search.add_substructure(func_group)
hits = substructure_search.search(mol_temp)
list_temp.append(len(hits))
dict_result[list_mol_names[count]] = list_temp
count += 1
pbar.set_description('正在统计所有的指定基团：')
return dict_result, list_con_names
def get_neighbor_function_groups(path_mols, path_con, query_atom):
# 确定每个已经去除了溶剂的*.mol2文件的名称和绝对路径
list_mol_names = os.listdir(path_mols)
list_path_mols = glob.glob(os.path.join(path_mols, '*.mol2'))
# 通过con定义功能基团
list_con_names = os.listdir(path_con)
path_conner_list = glob.glob(os.path.join(path_con, '*.con'))
list_connser_substructure = []
for path in path_conner_list:
connser_substructure = search.ConnserSubstructure(path)
list_connser_substructure.append(connser_substructure)
# 统计配位基团的类型及数量
dict_result = dict()
pbar = tqdm(range(len(list_path_mols)))
for i in pbar:
# 读取分子，并且读取出其中的components
path_mol = list_path_mols[i]
mol = io.MoleculeReader(path_mol)[0]
list_components = mol.components
mol.normalise_labels()
# 统计每个基团在分子中出现的次数
list_temp = [] # 储存每个mol2文件中匹配到的配位基团的数量
for con in list_connser_substructure:
count_temp = 0 # 基团出现数量
for component in list_components:
set_temp = set() # 用于存放出现的基团的字符串
# 查询金属原子
m = QueryAtom(query_atom)
s = search.QuerySubstructure()
s.add_atom(m)
sub_search = search.SubstructureSearch()
sub_search.add_substructure(s)
mol_metals = sub_search.search(component)
if len(mol_metals) > 0:
substructure_search = search.SubstructureSearch()
substructure_search.add_substructure(con)
hits = substructure_search.search(component)
if len(hits) > 0:
for hit in hits:
temp_hit_atoms = hit.match_atoms() # 匹配到的基团的原子
for temp_metal in mol_metals:
temp_metal = temp_metal.match_atoms()[0]
common_elements = set(
temp_metal.neighbours) & set(
temp_hit_atoms)
if len(common_elements) > 0:
set_temp.add(str(temp_hit_atoms))
# for num in range(len(mol_metals)):
# metal_label = query_atom + str(num + 1)
# temp_metal = component.atom(metal_label)
# common_elements = set(temp_metal.neighbours) & set(temp_hit_atoms)
# if len(common_elements) > 0:
# set_temp.add(str(temp_hit_atoms))
count_temp += len(set_temp)
list_temp.append(count_temp)
dict_result[list_mol_names[i]] = list_temp
return dict_result, list_con_names
def coordination_bond_length(self, element=None):
'''
:param dict_coo_sub:
:param element:
:return:
'''
p_bar = tqdm(self.entry_reader)
# {bond type: [bond type, ideal bond length, bond length, substructure,
# The main of substructure connection, Connection with ligands
# metal, coordinated atom, identifier]
dict_bond = dict()
for entry in p_bar:
# Getting molecule
mol = entry.molecule
# Remove all of hydrogen
mol.remove_hydrogens()
# Ensure labels are unique
mol.normalise_labels()
# remove single_atoms
mol.remove_atoms([
single_atom for single_atom in mol.atoms
if not single_atom.bonds
])
# dict to save coordinated bonds information
dict_mol_bonds = dict()
for comp in mol.components:
dict_coo_atoms = self.__coo_atom(comp, element)
# Getting the bond length
dict_bond_length = self.__measurement_bond_length(
comp, element)
# Get coordinate substructures which the coordinated atoms belong to
for metal in dict_coo_atoms:
# Set of atoms in the matched substructure in the molecule
set_sub_atoms = set()
set_coo_atoms_label = dict_coo_atoms[metal]
# Set of coordinated atoms in defined substructures
set_coo_atoms_label_in_sub = set()
'''
Get information of coordinated atoms about which substructure belongs to
'''
list_sub_name = sorted(self.dict_substructure,
reverse=True)
for sub_name in list_sub_name:
# Defining method of substructure searching
substructure_search = search.SubstructureSearch()
substructure_search.add_substructure(
self.dict_substructure[sub_name])
# Searching
hits = substructure_search.search(comp)
if not not hits:
for hit in hits:
hit_atoms_label = set(
atom.label for atom in hit.match_atoms())
if not any(atom_label in set_sub_atoms
for atom_label in hit_atoms_label):
set_sub_atoms.update([
atom.label
for atom in hit.match_atoms()
if atom.atomic_symbol != 'C'
])
coo_atoms_in_sub_label = set_coo_atoms_label & hit_atoms_label
if not not coo_atoms_in_sub_label:
set_coo_atoms_label_in_sub.update(
coo_atoms_in_sub_label)
# Add the substructures type to bond information
# Add the type of the main that the substructure connects with
for coo_atom_in_sub_label in coo_atoms_in_sub_label:
if len(dict_bond_length[
metal + '-' +
coo_atom_in_sub_label]
) < 4:
dict_bond_length[metal + '-' + coo_atom_in_sub_label]. \
extend([sub_name, self.__main_type_sub_connect(hit)])
# Set of coordinated atoms out defined substructures
set_coo_atoms_label_out_sub = set_coo_atoms_label - set_coo_atoms_label_in_sub
# Filling coordination atoms with Nan that do not belong to any defined substructure
for coo_atom_out_sub_label in set_coo_atoms_label_out_sub:
dict_bond_length[metal + '-' + coo_atom_out_sub_label]. \
extend(['NaN', 'NaN'])
'''
Get information of Connection of metal with ligands
'''
c_comp = comp.copy()
c_comp.remove_atoms(atom for atom in c_comp.atoms
if atom.atomic_symbol == element)
set_coo_atoms_label_in_comp = set()
for sub_c_comp in c_comp.components:
set_sub_c_comp_atoms = set(
atom.label for atom in sub_c_comp.atoms)
common_coo_atoms = set_sub_c_comp_atoms & set_coo_atoms_label
set_coo_atoms_label_in_comp.update(common_coo_atoms)
len_common_coo_atoms = len(common_coo_atoms)
if len_common_coo_atoms != 0:
for common_coo_atom in common_coo_atoms:
dict_bond_length[metal + '-' +
common_coo_atom].append(
len_common_coo_atoms)
set_coo_atoms_label_out_comp = set_coo_atoms_label - set_coo_atoms_label_in_comp
for common_coo_atom in set_coo_atoms_label_out_comp:
dict_bond_length[metal + '-' +
common_coo_atom].append(0)
# Setting basic information for bonds
for metal in dict_coo_atoms:
for coo_atom in dict_coo_atoms[metal]:
dict_bond_length[metal + '-' + coo_atom].extend(
[metal, coo_atom, entry])
dict_bond_length[metal + '-' + coo_atom].insert(
0, metal + '-' + coo_atom)
dict_bond_length[metal + '-' + coo_atom].insert(
0,
element + '-' + mol.atom(coo_atom).atomic_symbol)
# Save information of bond length
dict_mol_bonds.update(dict_bond_length)
# Save results
for bond in dict_mol_bonds:
if dict_mol_bonds[bond][0] in dict_bond:
dict_bond[dict_mol_bonds[bond][0]].append(
dict_mol_bonds[bond])
else:
dict_bond[dict_mol_bonds[bond][0]] = []
dict_bond[dict_mol_bonds[bond][0]].append(
dict_mol_bonds[bond])
return dict_bond