#!/usr/bin/env python
# Copyright (C) 2019 The ProteinDF development team.
# see also AUTHORS and README if provided.
#
# This file is a part of the ProteinDF software package.
#
# The ProteinDF is free software: you can redistribute it and/or modify
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# The ProteinDF is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with ProteinDF. If not, see <http://www.gnu.org/licenses/>.
from .atomgroup import AtomGroup
from .atom import Atom
from .error import BrInputError
from .functions import load_msgpack, save_msgpack
from . import rs
import re
import logging
logger = logging.getLogger(__name__)
[docs]
class SimpleMmcif(object):
"""
"""
def __init__(self, file_path=None):
self._data = {}
if file_path:
self.load(file_path)
[docs]
def load(self, file_path):
rs_cif = rs.SimpleMmcif(str(file_path))
for block_name, (kv, tables) in rs_cif.data.items():
self._data[block_name] = (kv, tables)
[docs]
def load_msgpack(self, file_path):
self._data = load_msgpack(file_path)
[docs]
def save_msgpack(self, file_path):
save_msgpack(self._data, file_path)
[docs]
def get_molecule_names(self):
return list(self._data.keys())
[docs]
def get_atomgroup(self, name):
ag = AtomGroup()
mol_data = self._data[name]
try:
self._get_atomgroup_list(mol_data, ag)
self._get_atomgroup_bond_list(mol_data, ag)
except BrInputError as e:
raise BrInputError(
name, "Invalid mmcif data: name={}".format(name))
return ag
def _get_atomgroup_list(self, list_item, ag):
assert(isinstance(ag, AtomGroup))
try:
for item in list_item:
if isinstance(item, list):
self._get_atomgroup_list(item, ag)
elif isinstance(item, dict):
self._get_atomgroup_dict(item, ag)
except BrInputError as e:
raise e
def _get_atomgroup_dict(self, dict_item, output_atomgroup):
"""Write into output_atomgroup.
"""
assert(isinstance(output_atomgroup, AtomGroup))
assert(isinstance(dict_item, dict))
re_numbers = re.compile(r"^[\+\-]?\d*(\.\d+)?$")
# check input coordinates(x, y, z)
def get_coordinates(xyz, dict_item):
assert((xyz == "x") or (xyz == "y") or (xyz == "z"))
answer = None
ideal_key = "_chem_comp_atom.pdbx_model_Cartn_{}_ideal".format(xyz)
model_key = "_chem_comp_atom.model_Cartn_{}".format(xyz)
xyz_ideal = dict_item.get(ideal_key, "N/A")
xyz_model = dict_item.get(model_key, "N/A")
if re_numbers.match(xyz_ideal):
answer = float(xyz_ideal)
elif re_numbers.match(xyz_model):
answer = float(xyz_model)
else:
logger.warning("Invalid coordinate({}) [{}, {}]".format(
xyz, xyz_ideal, xyz_model))
# raise BrValueError([xyz_ideal, xyz_model], "Invalid coordinate({})".format(xyz))
return answer
# output key-value
#print(">" * 10)
# for key, value in dict_item.items():
# print("{}> {}".format(key, value))
#print("<" * 10)
if "_chem_comp.id" in dict_item:
output_atomgroup.name = dict_item["_chem_comp.id"]
if "_chem_comp_atom.atom_id" in dict_item:
atom = Atom()
id = dict_item["_chem_comp_atom.atom_id"]
atom.name = id
symbol = dict_item["_chem_comp_atom.type_symbol"]
if symbol == "D":
symbol = "H"
atom.symbol = symbol
x = get_coordinates("x", dict_item)
y = get_coordinates("y", dict_item)
z = get_coordinates("z", dict_item)
if (x != None) and (y != None) and (z != None):
atom.position = (x, y, z)
else:
update = False
charge = dict_item["_chem_comp_atom.charge"]
if charge != "?":
atom.charge = charge
output_atomgroup.set_atom(id, atom)
# if "_chem_comp_bond.comp_id" in dict_item:
# atom1_name = dict_item["_chem_comp_bond.atom_id_1"]
# atom2_name = dict_item["_chem_comp_bond.atom_id_2"]
# bond_order_str = dict_item["_chem_comp_bond.value_order"]
# bond_order = 0
# if bond_order_str == "SING":
# bond_order = 1
# elif bond_order_str == "DOUB":
# bond_order = 2
# elif bond_order_str == "TRIP":
# bond_order = 3
# else:
# print("illegal input: {}".format(bond_order_str))
# atom1 = output_atomgroup.get_atom(atom1_name)
# atom2 = output_atomgroup.get_atom(atom2_name)
# output_atomgroup.add_bond(atom1, atom2, bond_order)
def _get_atomgroup_bond_list(self, list_item, ag):
""" For bonds only.
"""
assert(isinstance(ag, AtomGroup))
try:
for item in list_item:
if isinstance(item, list):
self._get_atomgroup_bond_list(item, ag)
elif isinstance(item, dict):
self._get_atomgroup_bond_dict(item, ag)
except BrInputError as e:
raise e
def _get_atomgroup_bond_dict(self, dict_item, output_atomgroup):
""" For bonds only.
"""
assert(isinstance(output_atomgroup, AtomGroup))
assert(isinstance(dict_item, dict))
if "_chem_comp_bond.comp_id" in dict_item:
atom1_name = dict_item["_chem_comp_bond.atom_id_1"]
atom2_name = dict_item["_chem_comp_bond.atom_id_2"]
bond_order_str = dict_item["_chem_comp_bond.value_order"]
bond_order = 0
if bond_order_str == "SING":
bond_order = 1
elif bond_order_str == "DOUB":
bond_order = 2
elif bond_order_str == "TRIP":
bond_order = 3
else:
logger.warning("illegal input: {}".format(bond_order_str))
atom1 = output_atomgroup.get_atom(atom1_name)
atom2 = output_atomgroup.get_atom(atom2_name)
output_atomgroup.add_bond(atom1, atom2, bond_order)
def __str__(self):
answer = ""
for name in self._data.keys():
answer += "data: {}\n".format(name)
(kv, tables) = self._data[name]
for key, value in kv.items():
answer += " {key}: {value}\n".format(key=key, value=value)
for table in tables:
answer += " ----\n"
for row in range(len(table)):
for key, value in table[row].items():
answer += " [{id}]{key}: {value}\n".format(
id=row, key=key, value=value)
return answer