def process_pdb(cfg, atom_num_dict, mol_num_dict, element_dict):
pdb_loc = cfg[PDB_FILE]
pdb_data = {HEAD_CONTENT: [], ATOMS_CONTENT: [], TAIL_CONTENT: []}
# to allow warning to be printed once and only once
missing_types = []
qmmm_elem_id_dict = {}
ca_res_atom_id_dict = {}
cb_res_atom_id_dict = {}
atoms_for_vmd = []
with open(pdb_loc) as f:
wat_count = 0
atom_count = 0
mol_count = 1
current_mol = None
last_mol_num = None
atoms_content = []
for line in f:
line = line.strip()
line_len = len(line)
if line_len == 0:
continue
line_head = line[:cfg[PDB_LINE_TYPE_LAST_CHAR]]
# head_content to contain Everything before 'Atoms' section
# also capture the number of atoms
if line_head == 'REMARK' or line_head == 'CRYST1':
pdb_data[HEAD_CONTENT].append(line)
# atoms_content to contain everything but the xyz
elif line_head == 'ATOM ':
# My template PDB has ***** after atom_count 99999. Thus, I'm renumbering. Otherwise, this this:
# atom_num = line[cfg[PDB_LINE_TYPE_LAST_CHAR]:cfg[PDB_ATOM_NUM_LAST_CHAR]]
# For renumbering, making sure prints in the correct format, including num of characters:
atom_count += 1
# For reordering atoms
if atom_count in atom_num_dict:
atom_id = atom_num_dict[atom_count]
else:
atom_id = atom_count
if atom_id > 99999:
atom_num = format(atom_id, 'x')
if len(atom_num) > 5:
warning("Hex representation of {} is {}, which is greater than 5 characters. This"
"will affect the PDB output formatting.".format(atom_id, atom_num))
else:
atom_num = '{:5d}'.format(atom_id)
atom_type = line[cfg[PDB_ATOM_NUM_LAST_CHAR]:cfg[PDB_ATOM_TYPE_LAST_CHAR]]
res_type = line[cfg[PDB_ATOM_TYPE_LAST_CHAR]:cfg[PDB_RES_TYPE_LAST_CHAR]]
mol_num = int(line[cfg[PDB_RES_TYPE_LAST_CHAR]:cfg[PDB_MOL_NUM_LAST_CHAR]])
pdb_x = float(line[cfg[PDB_MOL_NUM_LAST_CHAR]:cfg[PDB_X_LAST_CHAR]])
pdb_y = float(line[cfg[PDB_X_LAST_CHAR]:cfg[PDB_Y_LAST_CHAR]])
pdb_z = float(line[cfg[PDB_Y_LAST_CHAR]:cfg[PDB_Z_LAST_CHAR]])
occ_t = line[cfg[PDB_Z_LAST_CHAR]:cfg[PDB_LAST_T_CHAR]]
element = line[cfg[PDB_LAST_T_CHAR]:cfg[PDB_LAST_ELEM_CHAR]]
last_cols = line[cfg[PDB_LAST_ELEM_CHAR]:]
# For user-specified changing of molecule number
if mol_num in mol_num_dict:
mol_num = mol_num_dict[mol_num]
# If doing water molecule checking...
if cfg[FIRST_WAT_ID] <= atom_count <= cfg[LAST_WAT_ID]:
if (wat_count % 3) == 0:
current_mol = mol_num
if atom_type != ' OH2 ':
warning('Expected an OH2 atom to be the first atom of a water molecule. '
'Check line: {}'.format(line))
# last_cols = ' 0.00 0.00 S2 O'
else:
if current_mol != mol_num:
warning('Water not in order on line:', line)
if (wat_count % 3) == 1:
if atom_type != ' H1 ':
warning('Expected an H1 atom to be the second atom of a water molecule. '
'Check line: {}'.format(line))
else:
if atom_type != ' H2 ':
warning('Expected an H2 atom to be the second atom of a water molecule. '
'Check line: {}'.format(line))
wat_count += 1
if mol_num in cfg[RESID_QMMM] and atom_type not in SKIP_ATOM_TYPES:
if atom_type == C_ALPHA:
ca_res_atom_id_dict[mol_num] = atom_id
else:
if atom_type == C_BETA:
cb_res_atom_id_dict[mol_num] = atom_id
if atom_type in element_dict:
element = element_dict[atom_type]
else:
raise InvalidDataError("Did not find atom type '{}' in the element dictionary. Please "
"provide a new atom type, element dictionary (using keyword {} "
"in the configuration file) that includes all atom types in the "
"residues identified with the '{}' key."
"".format(atom_type, ELEMENT_DICT_FILE, RESID_QMMM))
if element in qmmm_elem_id_dict:
qmmm_elem_id_dict[element].append(atom_id)
else:
qmmm_elem_id_dict[element] = [atom_id]
atoms_for_vmd.append(atom_id - 1)
if cfg[ADD_ELEMENTS] and atom_count <= cfg[LAST_ADD_ELEM]:
if atom_type in element_dict:
element = element_dict[atom_type]
else:
if atom_type not in missing_types:
warning("Please add atom type '{}' to dictionary of elements. Will not write/overwrite "
"element type in the pdb output.".format(atom_type))
missing_types.append(atom_type)
# For numbering molecules from 1 to end
if cfg[RENUM_MOL]:
if last_mol_num is None:
last_mol_num = mol_num
if mol_num != last_mol_num:
last_mol_num = mol_num
mol_count += 1
if mol_count == 10000:
warning("Molecule numbers greater than 9999 will be printed in hex")
# Due to PDB format constraints, need to print in hex starting at 9999 molecules.
if mol_count > 9999:
mol_num = format(mol_count, 'x')
if len(mol_num) > 4:
warning("Hex representation of {} is {}, which is greater than 4 characters. This"
"will affect the PDB output formatting.".format(atom_id, atom_num))
else:
mol_num = '{:4d}'.format(mol_count)
line_struct = [line_head, atom_num, atom_type, res_type, mol_num, pdb_x, pdb_y, pdb_z,
occ_t, element, last_cols]
atoms_content.append(line_struct)
# tail_content to contain everything after the 'Atoms' section
else:
pdb_data[TAIL_CONTENT].append(line)
# Only sort if there is renumbering
if len(atom_num_dict) > 0:
pdb_data[ATOMS_CONTENT] = sorted(atoms_content, key=lambda entry: entry[1])
else:
pdb_data[ATOMS_CONTENT] = atoms_content
if cfg[PDB_NEW_FILE] is None:
f_name = create_out_fname(cfg[PDB_FILE], suffix="_new", base_dir=cfg[OUT_BASE_DIR])
else:
f_name = create_out_fname(cfg[PDB_NEW_FILE], base_dir=cfg[OUT_BASE_DIR])
print_pdb(pdb_data[HEAD_CONTENT], pdb_data[ATOMS_CONTENT], pdb_data[TAIL_CONTENT],
f_name, cfg[PDB_FORMAT])
if len(cfg[RESID_QMMM]) > 0:
f_name = create_out_fname('amino_id.dat', base_dir=cfg[OUT_BASE_DIR])
print_mode = "w"
for elem in qmmm_elem_id_dict:
print_qm_kind(qmmm_elem_id_dict[elem], elem, f_name, mode=print_mode)
print_mode = 'a'
print_qm_links(ca_res_atom_id_dict, cb_res_atom_id_dict, f_name, mode=print_mode)
f_name = create_out_fname('vmd_protein_atoms.dat', base_dir=cfg[OUT_BASE_DIR])
list_to_csv([atoms_for_vmd], f_name, delimiter=' ')
def process_pdb(cfg, atom_num_dict, mol_num_dict, element_dict):
pdb_loc = cfg[PDB_FILE]
pdb_data = {HEAD_CONTENT: [], ATOMS_CONTENT: [], TAIL_CONTENT: []}
# to allow warning to be printed once and only once
missing_types = []
qmmm_elem_id_dict = {}
ca_res_atom_id_dict = {}
cb_res_atom_id_dict = {}
atoms_for_vmd = []
with open(pdb_loc) as f:
wat_count = 0
atom_count = 0
mol_count = 1
current_mol = None
last_mol_num = None
atoms_content = []
for line in f:
line = line.strip()
line_len = len(line)
if line_len == 0:
continue
line_head = line[:cfg[PDB_LINE_TYPE_LAST_CHAR]]
# head_content to contain Everything before 'Atoms' section
# also capture the number of atoms
if line_head == 'REMARK' or line_head == 'CRYST1':
pdb_data[HEAD_CONTENT].append(line)
# atoms_content to contain everything but the xyz
elif line_head == 'ATOM ':
# My template PDB has ***** after atom_count 99999. Thus, I'm renumbering. Otherwise, this this:
# atom_num = line[cfg[PDB_LINE_TYPE_LAST_CHAR]:cfg[PDB_ATOM_NUM_LAST_CHAR]]
# For renumbering, making sure prints in the correct format, including num of characters:
atom_count += 1
# For reordering atoms
if atom_count in atom_num_dict:
atom_id = atom_num_dict[atom_count]
else:
atom_id = atom_count
if atom_id > 99999:
atom_num = format(atom_id, 'x')
if len(atom_num) > 5:
warning("Hex representation of {} is {}, which is greater than 5 characters. This"
"will affect the PDB output formatting.".format(atom_id, atom_num))
else:
atom_num = '{:5d}'.format(atom_id)
atom_type = line[cfg[PDB_ATOM_NUM_LAST_CHAR]:cfg[PDB_ATOM_TYPE_LAST_CHAR]]
res_type = line[cfg[PDB_ATOM_TYPE_LAST_CHAR]:cfg[PDB_RES_TYPE_LAST_CHAR]]
mol_num = int(line[cfg[PDB_RES_TYPE_LAST_CHAR]:cfg[PDB_MOL_NUM_LAST_CHAR]])
pdb_x = float(line[cfg[PDB_MOL_NUM_LAST_CHAR]:cfg[PDB_X_LAST_CHAR]])
pdb_y = float(line[cfg[PDB_X_LAST_CHAR]:cfg[PDB_Y_LAST_CHAR]])
pdb_z = float(line[cfg[PDB_Y_LAST_CHAR]:cfg[PDB_Z_LAST_CHAR]])
occ_t = line[cfg[PDB_Z_LAST_CHAR]:cfg[PDB_LAST_T_CHAR]]
element = line[cfg[PDB_LAST_T_CHAR]:cfg[PDB_LAST_ELEM_CHAR]]
last_cols = line[cfg[PDB_LAST_ELEM_CHAR]:]
# For user-specified changing of molecule number
if mol_num in mol_num_dict:
mol_num = mol_num_dict[mol_num]
# If doing water molecule checking...
if cfg[FIRST_WAT_ID] <= atom_count <= cfg[LAST_WAT_ID]:
if (wat_count % 3) == 0:
current_mol = mol_num
if atom_type != ' OH2 ':
warning('Expected an OH2 atom to be the first atom of a water molecule. '
'Check line: {}'.format(line))
# last_cols = ' 0.00 0.00 S2 O'
else:
if current_mol != mol_num:
warning('Water not in order on line:', line)
if (wat_count % 3) == 1:
if atom_type != ' H1 ':
warning('Expected an H1 atom to be the second atom of a water molecule. '
'Check line: {}'.format(line))
else:
if atom_type != ' H2 ':
warning('Expected an H2 atom to be the second atom of a water molecule. '
'Check line: {}'.format(line))
wat_count += 1
if mol_num in cfg[RESID_QMMM] and atom_type not in SKIP_ATOM_TYPES:
if atom_type == C_ALPHA:
ca_res_atom_id_dict[mol_num] = atom_id
else:
if atom_type == C_BETA:
cb_res_atom_id_dict[mol_num] = atom_id
if atom_type in element_dict:
element = element_dict[atom_type]
else:
raise InvalidDataError("Did not find atom type '{}' in the element dictionary. Please "
"provide a new atom type, element dictionary (using keyword {} "
"in the configuration file) that includes all atom types in the "
"residues identified with the '{}' key."
"".format(atom_type, ELEMENT_DICT_FILE, RESID_QMMM))
if element in qmmm_elem_id_dict:
qmmm_elem_id_dict[element].append(atom_id)
else:
qmmm_elem_id_dict[element] = [atom_id]
atoms_for_vmd.append(atom_id - 1)
if cfg[ADD_ELEMENTS] and atom_count <= cfg[LAST_ADD_ELEM]:
if atom_type in element_dict:
element = element_dict[atom_type]
else:
if atom_type not in missing_types:
warning("Please add atom type '{}' to dictionary of elements. Will not write/overwrite "
"element type in the pdb output.".format(atom_type))
missing_types.append(atom_type)
# For numbering molecules from 1 to end
if cfg[RENUM_MOL]:
if last_mol_num is None:
last_mol_num = mol_num
if mol_num != last_mol_num:
last_mol_num = mol_num
mol_count += 1
if mol_count == 10000:
warning("Molecule numbers greater than 9999 will be printed in hex")
# Due to PDB format constraints, need to print in hex starting at 9999 molecules.
if mol_count > 9999:
mol_num = format(mol_count, 'x')
if len(mol_num) > 4:
warning("Hex representation of {} is {}, which is greater than 4 characters. This"
"will affect the PDB output formatting.".format(atom_id, atom_num))
else:
mol_num = '{:4d}'.format(mol_count)
line_struct = [line_head, atom_num, atom_type, res_type, mol_num, pdb_x, pdb_y, pdb_z,
occ_t, element, last_cols]
atoms_content.append(line_struct)
# tail_content to contain everything after the 'Atoms' section
else:
pdb_data[TAIL_CONTENT].append(line)
# Only sort if there is renumbering
if len(atom_num_dict) > 0:
pdb_data[ATOMS_CONTENT] = sorted(atoms_content, key=lambda entry: entry[1])
else:
pdb_data[ATOMS_CONTENT] = atoms_content
if cfg[PDB_NEW_FILE] is None:
f_name = create_out_fname(cfg[PDB_FILE], suffix="_new", base_dir=cfg[OUT_BASE_DIR])
else:
f_name = create_out_fname(cfg[PDB_NEW_FILE], base_dir=cfg[OUT_BASE_DIR])
print_pdb(pdb_data[HEAD_CONTENT], pdb_data[ATOMS_CONTENT], pdb_data[TAIL_CONTENT],
f_name, cfg[PDB_FORMAT])
if len(cfg[RESID_QMMM]) > 0:
f_name = create_out_fname('amino_id.dat', base_dir=cfg[OUT_BASE_DIR])
print_mode = "w"
for elem in qmmm_elem_id_dict:
print_qm_kind(qmmm_elem_id_dict[elem], elem, f_name, mode=print_mode)
print_mode = 'a'
print_qm_links(ca_res_atom_id_dict, cb_res_atom_id_dict, f_name, mode=print_mode)
f_name = create_out_fname('vmd_protein_atoms.dat', base_dir=cfg[OUT_BASE_DIR])
list_to_csv([atoms_for_vmd], f_name, delimiter=' ')
def get_evb_atoms(cfg, chk_file):
with open(chk_file) as d:
chk_data = {HEAD_CONTENT: [], ATOMS_CONTENT: [], TAIL_CONTENT: []}
section = SEC_HEAD
o_ids = []
h_ids = []
for line in d:
line = line.strip()
# head_content to contain Everything before 'Atoms' section
# also capture the number of atoms
if section == SEC_HEAD:
chk_data[HEAD_CONTENT].append(line)
atoms_match = NUM_ATOMS_PAT.match(line)
if atoms_match:
# regex is 1-based
# print(atoms_match.group(1))
chk_data[NUM_ATOMS] = int(atoms_match.group(1))
section = SEC_ATOMS
elif section == SEC_ATOMS:
if len(line) == 0:
continue
split_line = line.split()
index = int(split_line[0])
atom_num = int(split_line[1])
x, y, z = map(float, split_line[2:5])
atom_type = split_line[5]
atom_struct = [index, atom_num, x, y, z, atom_type]
chk_data[ATOMS_CONTENT].append(atom_struct)
if atom_num > cfg[LAST_EXCLUDE_ID]:
if atom_type == 'O':
o_ids.append(atom_num)
elif atom_type == 'H':
h_ids.append(atom_num)
else:
raise InvalidDataError("Expected atom types are 'O' and 'H' (looking for water "
"molecules only). Found type '{}' for line:\n {}\n"
"Use the '{}' keyword to specify the last atom to exclude (i.e. "
"the last protein atom)."
"".format(atom_type, line, LAST_EXCLUDE_ID))
if len(chk_data[ATOMS_CONTENT]) == chk_data[NUM_ATOMS]:
section = SEC_TAIL
# tail_content to contain everything after the 'Atoms' section
elif section == SEC_TAIL:
break
# Data validation: checking total charge
num_o = len(o_ids)
num_h = len(h_ids)
total_charge = num_h - 2 * num_o
if cfg[EXPECTED_CHARGE] is None:
print("Found {} oxygen atoms and {} hydrogen atoms for a total charge of {}."
"".format(num_o, num_h, add_sign(total_charge)))
else:
if total_charge != cfg[EXPECTED_CHARGE]:
raise InvalidDataError("Expected a total charge of {} but found {} for file: {}"
"".format(add_sign(cfg[EXPECTED_CHARGE]), add_sign(total_charge), chk_file))
# printing!
f_name = create_out_fname(chk_file, prefix='water_', ext='.dat', base_dir=cfg[OUT_BASE_DIR],
remove_prefix='CHK_')
print_qm_kind(h_ids, 'H', f_name)
print_qm_kind(o_ids, 'O', f_name, mode='a')
f_name = create_out_fname(chk_file, prefix='vmd_water_', ext='.dat', base_dir=cfg[OUT_BASE_DIR],
remove_prefix='CHK_')
print_vmd_list(o_ids+h_ids, f_name)
def process_psf(cfg, atom_num_dict, mol_num_dict, element_dict, radii_dict):
with open(cfg[PSF_FILE]) as f:
psf_data = {HEAD_CONTENT: [], ATOMS_CONTENT: [], TAIL_CONTENT: []}
num_atoms_pat = re.compile(r"(\d+).*NATOM$")
num_atoms = 1
section = SEC_HEAD
# for printing qmmm info
qmmm_elem_id_dict = {}
ca_res_atom_id_dict = {}
cb_res_atom_id_dict = {}
atoms_for_vmd = []
types_for_mm_kind = set()
qmmm_charge = 0
# for RENUM_MOL
last_resid = None
cur_mol_num = 0
for line in f.readlines():
s_line = line.strip()
# head_content to contain Everything before 'Atoms' section
# also capture the number of atoms
if section == SEC_HEAD:
psf_data[HEAD_CONTENT].append(line.rstrip())
atoms_match = num_atoms_pat.match(s_line)
if atoms_match:
# regex is 1-based
num_atoms = int(atoms_match.group(1))
section = SEC_ATOMS
elif section == SEC_ATOMS:
if len(s_line) == 0:
continue
split_line = s_line.split()
atom_num = int(split_line[0])
segid = split_line[1]
resid = int(split_line[2])
resname = split_line[3]
atom_type = split_line[4]
charmm_type = split_line[5]
charge = float(split_line[6])
atom_wt = float(split_line[7])
zero = split_line[8]
# For reordering atoms
if atom_num in atom_num_dict:
atom_num = atom_num_dict[atom_num]
# For user-specified changing of molecule number
if resid in mol_num_dict:
resid = mol_num_dict[resid]
if cfg[RENUM_MOL]:
if resid != last_resid:
last_resid = resid
cur_mol_num += 1
resid = cur_mol_num
atom_struct = [
atom_num, segid, resid, resname, atom_type, charmm_type,
charge, atom_wt, zero
]
psf_data[ATOMS_CONTENT].append(atom_struct)
if resid in cfg[RESID_QM] or resid in cfg[
RESID_QMMM] and atom_type not in cfg[SKIP_ATOM_TYPES]:
if resid in cfg[RESID_QMMM]:
if atom_type == C_ALPHA:
ca_res_atom_id_dict[resid] = atom_num
if resid in cfg[RESID_QMMM] and atom_type == C_ALPHA:
ca_res_atom_id_dict[resid] = atom_num
else:
if resid in cfg[RESID_QMMM] and atom_type == C_BETA:
cb_res_atom_id_dict[resid] = atom_num
if atom_type in element_dict:
element = element_dict[atom_type]
else:
raise InvalidDataError(
"Did not find atom type '{}' in the element dictionary. Please "
"provide a new atom type, element dictionary (using keyword {} "
"in the configuration file) that includes all atom types in the "
"residues identified with the '{}' key."
"".format(atom_type, ELEMENT_DICT_FILE,
RESID_QMMM))
if element in qmmm_elem_id_dict:
qmmm_elem_id_dict[element].append(atom_num)
else:
qmmm_elem_id_dict[element] = [atom_num]
qmmm_charge += charge
atoms_for_vmd.append(atom_num - 1)
if cfg[PRINT_FOR_CP2K]:
types_for_mm_kind.add(atom_type)
if len(psf_data[ATOMS_CONTENT]) == num_atoms:
section = SEC_TAIL
# tail_content to contain everything after the 'Atoms' section
elif section == SEC_TAIL:
psf_data[TAIL_CONTENT].append(line.rstrip())
if len(atom_num_dict) > 0:
warning(
"This program does not yet edit any sections other than the atoms section."
"If you are renumbering atoms, the bonds, angles, dihedrals, impropers, and"
"cross-terms sections will not match.")
psf_data[ATOMS_CONTENT] = sorted(psf_data[ATOMS_CONTENT],
key=lambda entry: entry[0])
if cfg[RENUM_MOL] or len(atom_num_dict) + len(mol_num_dict) > 0:
if cfg[PSF_NEW_FILE] is None:
f_name = create_out_fname(cfg[PSF_FILE],
suffix="_new",
base_dir=cfg[OUT_BASE_DIR])
else:
f_name = cfg[PSF_NEW_FILE]
list_to_file(psf_data[HEAD_CONTENT] + psf_data[ATOMS_CONTENT] +
psf_data[TAIL_CONTENT],
f_name,
list_format=cfg[PSF_FORMAT])
if cfg[PRINT_FOR_CP2K]:
print("Total charge from QM atoms: {:.2f}".format(qmmm_charge))
# create CP2K input listing amino atom ids
f_name = create_out_fname('amino_id.dat', base_dir=cfg[OUT_BASE_DIR])
print_mode = "w"
for elem in qmmm_elem_id_dict:
print_qm_kind(qmmm_elem_id_dict[elem],
elem,
f_name,
mode=print_mode)
print_mode = 'a'
print_qm_links(ca_res_atom_id_dict,
cb_res_atom_id_dict,
f_name,
mode=print_mode)
# create CP2K input listing MM atom type radii
f_name = create_out_fname('mm_kinds.dat', base_dir=cfg[OUT_BASE_DIR])
print_mode = "w"
for atom_type in types_for_mm_kind:
try:
print_mm_kind(atom_type,
radii_dict[atom_type],
f_name,
mode=print_mode)
print_mode = 'a'
except KeyError:
warning(
"Did not find atom type '{}' in the atom_type to radius dictionary: {}\n"
" '{}' printed without this type; user may manually add its radius specification.\n"
" To print this file with all MM types, use the keyword '{}' in the configuration file \n"
" to identify a file with atom_type,radius (one per line, comma-separated) with all "
"MM types in the psf".format(atom_type,
cfg[RADII_DICT_FILE],
'mm_kinds.dat',
RADII_DICT_FILE))
# create VMD input listing amino atom indexes (base-zero counting)
f_name = create_out_fname('vmd_protein_atoms.dat',
base_dir=cfg[OUT_BASE_DIR])
list_to_csv([atoms_for_vmd], f_name, delimiter=' ')
def process_file(cfg):
chk_list_loc = cfg[CHK_FILE_LIST]
num_atoms_pat = re.compile(r"^ATOMS (\d+).*")
last_exclude_id = cfg[LAST_EXCLUDE_ID]
with open(chk_list_loc) as f:
for chk_file in f:
chk_file = chk_file.strip()
with open(chk_file) as d:
chk_data = {HEAD_CONTENT: [], ATOMS_CONTENT: [], TAIL_CONTENT: []}
section = SEC_HEAD
o_ids = []
h_ids = []
for line in d:
line = line.strip()
# head_content to contain Everything before 'Atoms' section
# also capture the number of atoms
if section == SEC_HEAD:
chk_data[HEAD_CONTENT].append(line)
atoms_match = num_atoms_pat.match(line)
if atoms_match:
# regex is 1-based
# print(atoms_match.group(1))
chk_data[NUM_ATOMS] = int(atoms_match.group(1))
section = SEC_ATOMS
elif section == SEC_ATOMS:
if len(line) == 0:
continue
split_line = line.split()
index = int(split_line[0])
atom_num = int(split_line[1])
x, y, z = map(float, split_line[2:5])
atom_type = split_line[5]
atom_struct = [index, atom_num, x, y, z, atom_type]
chk_data[ATOMS_CONTENT].append(atom_struct)
if atom_num > last_exclude_id:
if atom_type == 'O':
o_ids.append(atom_num)
elif atom_type == 'H':
h_ids.append(atom_num)
else:
raise InvalidDataError("Expected atom types are 'O' and 'H' (looking for water "
"molecules only). Found type '{}' for line:\n {}\n"
"Use the '{}' keyword to specify the last atom to exclude (i.e. "
"the last protein atom)."
"".format(atom_type, line, LAST_EXCLUDE_ID))
if len(chk_data[ATOMS_CONTENT]) == chk_data[NUM_ATOMS]:
section = SEC_TAIL
# tail_content to contain everything after the 'Atoms' section
elif section == SEC_TAIL:
break
# Data validation: checking total charge
num_o = len(o_ids)
num_h = len(h_ids)
total_charge = num_h - 2 * num_o
if cfg[EXPECTED_CHARGE] is None:
print("Found {} oxygen atoms and {} hydrogen atoms for a total charge of {}."
"".format(num_o, num_h, add_sign(total_charge)))
else:
if total_charge != cfg[EXPECTED_CHARGE]:
raise InvalidDataError("Expected a total charge of {} but found {} for file: {}"
"".format(add_sign(cfg[EXPECTED_CHARGE]), add_sign(total_charge), chk_file))
# printing!
f_name = create_out_fname(chk_file, prefix='water_', ext='.dat', base_dir=cfg[OUT_BASE_DIR],
remove_prefix='CHK_')
print_qm_kind(h_ids, 'H', f_name)
print_qm_kind(o_ids, 'O', f_name, mode='a')
f_name = create_out_fname(chk_file, prefix='vmd_water_', ext='.dat', base_dir=cfg[OUT_BASE_DIR],
remove_prefix='CHK_')
print_vmd_list(o_ids+h_ids, f_name)
def process_psf(cfg, atom_num_dict, mol_num_dict, element_dict, radii_dict):
with open(cfg[PSF_FILE]) as f:
psf_data = {HEAD_CONTENT: [], ATOMS_CONTENT: [], TAIL_CONTENT: []}
num_atoms_pat = re.compile(r"(\d+).*NATOM$")
num_atoms = 1
section = SEC_HEAD
# for printing qmmm info
qmmm_elem_id_dict = {}
ca_res_atom_id_dict = {}
cb_res_atom_id_dict = {}
atoms_for_vmd = []
types_for_mm_kind = set()
qmmm_charge = 0
# for RENUM_MOL
last_resid = None
cur_mol_num = 0
for line in f.readlines():
s_line = line.strip()
# head_content to contain Everything before 'Atoms' section
# also capture the number of atoms
if section == SEC_HEAD:
psf_data[HEAD_CONTENT].append(line.rstrip())
atoms_match = num_atoms_pat.match(s_line)
if atoms_match:
# regex is 1-based
num_atoms = int(atoms_match.group(1))
section = SEC_ATOMS
elif section == SEC_ATOMS:
if len(s_line) == 0:
continue
split_line = s_line.split()
atom_num = int(split_line[0])
segid = split_line[1]
resid = int(split_line[2])
resname = split_line[3]
atom_type = split_line[4]
charmm_type = split_line[5]
charge = float(split_line[6])
atom_wt = float(split_line[7])
zero = split_line[8]
# For reordering atoms
if atom_num in atom_num_dict:
atom_num = atom_num_dict[atom_num]
# For user-specified changing of molecule number
if resid in mol_num_dict:
resid = mol_num_dict[resid]
if cfg[RENUM_MOL]:
if resid != last_resid:
last_resid = resid
cur_mol_num += 1
resid = cur_mol_num
atom_struct = [atom_num, segid, resid, resname, atom_type, charmm_type, charge, atom_wt, zero]
psf_data[ATOMS_CONTENT].append(atom_struct)
if resid in cfg[RESID_QM] or resid in cfg[RESID_QMMM] and atom_type not in cfg[SKIP_ATOM_TYPES]:
if resid in cfg[RESID_QMMM]:
if atom_type == C_ALPHA:
ca_res_atom_id_dict[resid] = atom_num
if resid in cfg[RESID_QMMM] and atom_type == C_ALPHA:
ca_res_atom_id_dict[resid] = atom_num
else:
if resid in cfg[RESID_QMMM] and atom_type == C_BETA:
cb_res_atom_id_dict[resid] = atom_num
if atom_type in element_dict:
element = element_dict[atom_type]
else:
raise InvalidDataError(
"Did not find atom type '{}' in the element dictionary. Please "
"provide a new atom type, element dictionary (using keyword {} "
"in the configuration file) that includes all atom types in the "
"residues identified with the '{}' key."
"".format(atom_type, ELEMENT_DICT_FILE, RESID_QMMM)
)
if element in qmmm_elem_id_dict:
qmmm_elem_id_dict[element].append(atom_num)
else:
qmmm_elem_id_dict[element] = [atom_num]
qmmm_charge += charge
atoms_for_vmd.append(atom_num - 1)
if cfg[PRINT_FOR_CP2K]:
types_for_mm_kind.add(atom_type)
if len(psf_data[ATOMS_CONTENT]) == num_atoms:
section = SEC_TAIL
# tail_content to contain everything after the 'Atoms' section
elif section == SEC_TAIL:
psf_data[TAIL_CONTENT].append(line.rstrip())
if len(atom_num_dict) > 0:
warning(
"This program does not yet edit any sections other than the atoms section."
"If you are renumbering atoms, the bonds, angles, dihedrals, impropers, and"
"cross-terms sections will not match."
)
psf_data[ATOMS_CONTENT] = sorted(psf_data[ATOMS_CONTENT], key=lambda entry: entry[0])
if cfg[RENUM_MOL] or len(atom_num_dict) + len(mol_num_dict) > 0:
if cfg[PSF_NEW_FILE] is None:
f_name = create_out_fname(cfg[PSF_FILE], suffix="_new", base_dir=cfg[OUT_BASE_DIR])
else:
f_name = cfg[PSF_NEW_FILE]
list_to_file(
psf_data[HEAD_CONTENT] + psf_data[ATOMS_CONTENT] + psf_data[TAIL_CONTENT],
f_name,
list_format=cfg[PSF_FORMAT],
)
if cfg[PRINT_FOR_CP2K]:
print("Total charge from QM atoms: {:.2f}".format(qmmm_charge))
# create CP2K input listing amino atom ids
f_name = create_out_fname("amino_id.dat", base_dir=cfg[OUT_BASE_DIR])
print_mode = "w"
for elem in qmmm_elem_id_dict:
print_qm_kind(qmmm_elem_id_dict[elem], elem, f_name, mode=print_mode)
print_mode = "a"
print_qm_links(ca_res_atom_id_dict, cb_res_atom_id_dict, f_name, mode=print_mode)
# create CP2K input listing MM atom type radii
f_name = create_out_fname("mm_kinds.dat", base_dir=cfg[OUT_BASE_DIR])
print_mode = "w"
for atom_type in types_for_mm_kind:
try:
print_mm_kind(atom_type, radii_dict[atom_type], f_name, mode=print_mode)
print_mode = "a"
except KeyError:
warning(
"Did not find atom type '{}' in the atom_type to radius dictionary: {}\n"
" '{}' printed without this type; user may manually add its radius specification.\n"
" To print this file with all MM types, use the keyword '{}' in the configuration file \n"
" to identify a file with atom_type,radius (one per line, comma-separated) with all "
"MM types in the psf".format(atom_type, cfg[RADII_DICT_FILE], "mm_kinds.dat", RADII_DICT_FILE)
)
# create VMD input listing amino atom indexes (base-zero counting)
f_name = create_out_fname("vmd_protein_atoms.dat", base_dir=cfg[OUT_BASE_DIR])
list_to_csv([atoms_for_vmd], f_name, delimiter=" ")