def add_hydrogen(pdb_in, pdb_out, check_file_out=True, **reduce_options):
"""Add hydrogen to a pdb file using the ``reduce`` software:
:param pdb_in: pdb input
:type pdb_in: str
:param pdb_out: pdb output
:type pdb_out: str
:param check_file_out: flag to check or not if file has already been
created. If the file is present then the command break.
:type check_file_out: bool, optional, default=True
:param reduce_options: Optional arguments for ``reduce``
:Example:
>>> from pdb_manip_py import pdb_manip
>>> pdb_manip.show_log()
>>> TEST_OUT = getfixture('tmpdir')
>>> add_hydrogen(pdb_in=TEST_PATH+'/phenol.pdb',\
pdb_out=TEST_OUT+'/phenol_h.pdb') #doctest: +ELLIPSIS
reduce -build -nuclear .../phenol.pdb
>>> phenol_coor = pdb_manip.Coor(TEST_OUT+'/phenol_h.pdb') \
#doctest: +ELLIPSIS
Succeed to read file .../phenol_h.pdb , 13 atoms found
"""
# Check if output files exist:
if check_file_out and os.path.isfile(pdb_out):
logger.info("PDB files not created, {} already exist".format(pdb_out))
return
# Define reduce command:
cmd_reduce = os_command.Command([REDUCE_BIN, "-build", "-nuclear", pdb_in],
**reduce_options)
cmd_reduce.display()
return_code = cmd_reduce.run(display=False, out_data=True)
filout = open(pdb_out, 'w')
filout.write(return_code['stdout'])
logger.info("Succeed to save file %s" % os.path.relpath(pdb_out))
return
def acpype(pdb_in,
out_folder,
charge_model="bcc",
atom_type="gaff",
net_charge=None,
check_file_out=True,
**acpype_options):
"""Compute a molecule topologie using the ``antechamber`` software:
:param pdb_in: pdb input
:type pdb_in: str
:param out_folder: output folder
:type out_folder: str
:param charge_model: charge model
:type charge_model: str, default="bcc"
:param atom_type: atom_type model
:type atom_type: str, default="gaff"
:param check_file_out: flag to check or not if file has already been
created. If the file is present then the command break.
:type check_file_out: bool, optional, default=True
:param acpype_options: Optional arguments for ``acpype``
:Example:
>>> pdb_manip.show_log()
>>> TEST_OUT = getfixture('tmpdir')
>>> add_hydrogen(pdb_in=TEST_PATH+'/phenol.pdb',\
pdb_out=TEST_OUT+'/phenol_h.pdb') #doctest: +ELLIPSIS
reduce -build -nuclear .../phenol.pdb
>>> phenol_coor = pdb_manip.Coor(TEST_OUT+'/phenol_h.pdb') \
#doctest: +ELLIPSIS
Succeed to read file .../phenol_h.pdb , 13 atoms found
"""
# Check if output files exist:
if check_file_out and os.path.isfile(out_folder):
logger.info(
"MOL2 files not created, {} already exist".format(out_folder))
return
# Remove tha last char if == '/'
if out_folder[-1] == '/':
out_folder = out_folder[:-1]
name = out_folder.split('/')[-1]
cmd_list = [
ACPYPE_BIN, "-i", pdb_in, "-b", out_folder, "-c", charge_model, "-a",
atom_type, "-o", "gmx"
]
if net_charge is not None:
cmd_list += ["-n", str(net_charge)]
# Define reduce command:
cmd_acpype = os_command.Command(cmd_list, **acpype_options)
cmd_acpype.display()
cmd_acpype.run(display=False)
logger.info("Succeed to create topologie in %s" %
os.path.relpath(out_folder))
# Split the itp file atom_type part:
extract_itp_atomtypes(
'{}.acpype/{}_GMX.itp'.format(out_folder, name),
'{}.acpype/{}_GMX_atomtypes.itp'.format(out_folder, name))
sys_top = gmx.TopSys('{}.acpype/{}_GMX.top'.format(out_folder, name))
fullname = '{}_GMX_atomtypes.itp'.format(name)
include = '{}_GMX_atomtypes'.format(name)
path = '{}.acpype/{}_GMX_atomtypes.itp'.format(out_folder, name)
atomtypes_itp = gmx.Itp(name=include, fullname=fullname, path=path)
sys_top.itp_list = [atomtypes_itp] + sys_top.itp_list
# Add position restraints
# Get heavy atoms name:
atom_list = []
for key, value in sys_top.itp_list[-1].top_mol_list[0].atom_dict.items():
if not value['atom_name'].startswith('H'):
atom_list.append(value['atom_name'])
sys_top.add_posre(posre_name="POSRES",
selec_dict={'atom_name': atom_list},
fc=[1000, 1000, 1000])
sys_top.add_posre(posre_name="POSRES_LIG",
selec_dict={'atom_name': atom_list},
fc=[1000, 1000, 1000])
sys_top.add_posre(posre_name="POSRES_CA",
selec_dict={'atom_name': atom_list},
fc=[1000, 1000, 1000])
sys_top.add_posre(posre_name="POSRES_CA_LOW",
selec_dict={'atom_name': atom_list},
fc=[100, 100, 100])
sys_top.write_file('{}.acpype/{}_GMX_split.top'.format(out_folder, name))
molecule = gmx.GmxSys(
name='mol',
coor_file='{}.acpype/{}_GMX.gro'.format(out_folder, name),
top_file='{}.acpype/{}_GMX_split.top'.format(out_folder, name))
return molecule
def antechamber(pdb_in,
mol2_out,
charge_model="bcc",
check_file_out=True,
**antechamber_options):
"""Compute a molecule topologie using the ``antechamber`` software:
:param pdb_in: pdb input
:type pdb_in: str
:param mol2_out: pdb output
:type mol2_out: str
:param charge_model: charge model
:type charge_model: str, default="bcc"
:param check_file_out: flag to check or not if file has already been
created. If the file is present then the command break.
:type check_file_out: bool, optional, default=True
:param reduce_options: Optional arguments for ``reduce``
Output files:
- mol2_out
- ANTECHAMBER_AM1BCC_PRE.AC
- ANTECHAMBER_BOND_TYPE.AC
- ANTECHAMBER_BOND_TYPE.AC0
- ANTECHAMBER_AC.AC
- ATOMTYPE.INF
- ANTECHAMBER_AC.AC0
- ANTECHAMBER_AM1BCC.AC
:Example:
>>> pdb_manip.show_log()
>>> TEST_OUT = getfixture('tmpdir')
>>> add_hydrogen(pdb_in=TEST_PATH+'/phenol.pdb',\
pdb_out=TEST_OUT+'/phenol_h.pdb') #doctest: +ELLIPSIS
reduce -build -nuclear .../phenol.pdb
>>> phenol_coor = pdb_manip.Coor(TEST_OUT+'/phenol_h.pdb') \
#doctest: +ELLIPSIS
Succeed to read file .../phenol_h.pdb , 13 atoms found
>>> antechamber(pdb_in=TEST_OUT+'/phenol_h.pdb',\
mol2_out=TEST_OUT+'/phenol_h.mol2') #doctest: +ELLIPSIS
antechamber -i phenol_h.pdb -fi pdb -o phenol_h.mol2 -fo \
mol2 -c bcc
"""
# Check if output files exist:
if check_file_out and os.path.isfile(mol2_out):
logger.info(
"MOL2 files not created, {} already exist".format(mol2_out))
return
start_dir = os.path.abspath(".")
# Create and go in out_folder:
out_folder = os_command.get_directory(mol2_out)
os_command.create_and_go_dir(out_folder)
# Define reduce command:
cmd_antechamber = os_command.Command([
ANTECHAMBER_BIN, "-i", pdb_in, "-fi",
str(pdb_in).split('.')[-1], "-o", mol2_out, "-fo", "mol2", "-c",
charge_model
], **antechamber_options)
cmd_antechamber.display()
cmd_antechamber.run(display=False)
logger.info("Succeed to save file %s" % os.path.relpath(mol2_out))
# Get absolute path:
os.chdir(start_dir)
return
def compute_pdb2pqr(pdb_in,
pdb_out,
ff="CHARMM",
method='propka',
ph=7.0,
check_file_out=True):
"""
Use pdb2pqr to define protonation state of each residue of a protein.
:param pdb_in: path of input pdb file
:type pdb_in: str
:param pdb_out: path of output pdb file
:type pdb_out: str
:param ff: forcefield nomenclature for atom names
:type ff: str, optional, default="CHARMM"
:param method: Method used to calculate ph values (propka or pdb2pka).
:type method: str, optional, default="propka"
:param ph: pH value to define AA residue
:type ph: float, optional, default=7.0
:param check_file_out: flag to check or not if file has already
been created. If the file is present then the command break.
:type check_file_out: bool, optional, default=True
:Example:
>>> pdb_manip.show_log()
>>> TEST_OUT = str(getfixture('tmpdir'))
>>> # Compute protonation with pdb2pqr:
>>> compute_pdb2pqr(os.path.join(TEST_PATH,'4n1m.pdb'),
... os.path.join(TEST_OUT, '4n1m.pqr')) #doctest: +ELLIPSIS
Succeed to read file ...4n1m.pdb , 2530 atoms found
Succeed to save file ...tmp_pdb2pqr.pdb
pdb2pqr30... --ff CHARMM --ffout CHARMM --keep-chain \
--titration-state-method=propka --with-ph=7.00 \
...tmp_pdb2pqr.pdb ...4n1m.pqr
0
>>> prot_coor = pdb_manip.Coor()
>>> prot_coor.read_pdb(os.path.join(TEST_OUT, '4n1m.pqr'), \
pqr_format = True) #doctest: +ELLIPSIS
Succeed to read file ...4n1m.pqr , 2549 atoms found
>>> HSD_index = prot_coor.get_index_selection({'res_name' : ['HSD'],
... 'name':['CA']})
>>> print(len(HSD_index))
4
>>> HSE_index = prot_coor.get_index_selection({'res_name' : ['HSE'],
... 'name':['CA']})
>>> print(len(HSE_index))
0
>>> HSP_index = prot_coor.get_index_selection({'res_name' : ['HSP'],
... 'name':['CA']})
>>> print(len(HSP_index))
1
.. note::
Idealy I would need a pdb file with 3 different histidine protonation.
I couldn't find one.
"""
# print("Compute pdb2pqr on",pdb_in)
# Check if output files exist and create directory:
if check_file_out and os_command.check_file_and_create_path(pdb_out):
logger.info("pdb2pqr not launched %s already exist" % pdb_out)
return pdb_out
out_folder = os_command.get_directory(pdb_out)
# print("out_folder", out_folder)
# WARING :
# Many bugs are due to the REMARK field in pdb2pqr
# The 2 following steps remove the REMARK field of the pdb
tmp_coor = pdb_manip.Coor()
tmp_coor.read_pdb(pdb_in)
# Remove Nucleic acids:
# WARNING, that part might be removed, as pdb2pqr could compute
# protonation on nucleic acid in a near future
na_index = tmp_coor.get_index_selection({'res_name': pdb_manip.NA_DICT})
tmp_coor.del_atom_index(index_list=na_index)
# Remove HETATM
no_hetatm_pdb = tmp_coor.select_part_dict({'field': 'ATOM'})
if no_hetatm_pdb.num == 0:
logger.warning('No amino acids present in pdb file'
', no PD2PQR calculation')
tmp_coor = pdb_manip.Coor()
tmp_coor.read_pdb(pdb_in)
# To be coherent with the pdb2pqr calc., remove HETATOM :
no_hetatm_pdb = tmp_coor.select_part_dict({'field': 'ATOM'})
no_hetatm_pdb.write_pqr(pdb_out)
return
no_hetatm_pdb.write_pdb(os.path.join(out_folder + "/tmp_pdb2pqr.pdb"))
cmd_pdb2pqr = os_command.Command([
PDB2PQR_BIN, "--ff", ff, "--ffout", ff, "--keep-chain",
"--titration-state-method={}".format(method),
"--with-ph={:.2f}".format(ph),
os.path.join(out_folder + "/tmp_pdb2pqr.pdb"), pdb_out
])
cmd_pdb2pqr.display()
out_data = cmd_pdb2pqr.run()
os_command.delete_file(os.path.join(out_folder + "/tmp_pdb2pqr.pdb"))
return out_data