def run_epik(input_file_path, output_file_path, max_structures=32, ph=7.4,
ph_tolerance=None, min_probability=None, tautomerize=True, extract_range=None):
"""Run Schrodinger's epik command line utility to enumerate protonation and
tautomeric states.
Parameters
----------
input_file_path : str
Path to input file describing the molecule.
output_file_path : str
Path to the output file created by epik.
max_structures : int, optional
Maximum number of generated structures (default is 32).
ph : float, optional
Target pH for generated states (default is 7.4).
ph_tolerance : float, optional
Equivalent of -pht option in Epik command (default is None).
min_probability: float, optional
Minimum probability for the generated states.
tautomerize : bool, optional
Whether or not tautomerize the input structure (default is True).
extract_range : int or list of ints, optional
If not None, the function uses the Schrodinger's utility maesubset to
extract only a subset of the generated structures. This is the 0-based
indices of the structures to extract from the input files.
"""
# Locate epik executable
epik_path = os.path.join(os.environ['SCHRODINGER'], 'epik')
# Normalize paths as we'll run in a different working directory
input_file_path = os.path.abspath(input_file_path)
output_file_path = os.path.abspath(output_file_path)
output_dir = os.path.dirname(output_file_path)
# Preparing epik command arguments for format()
epik_args = dict(ms=max_structures, ph=ph)
epik_args['pht'] = '-pht {}'.format(ph_tolerance) if ph_tolerance else ''
epik_args['nt'] = '' if tautomerize else '-nt'
epik_args['p'] = '-p {}'.format(min_probability) if min_probability else ''
# Determine if we need to convert input and/or output file
if extract_range is None:
epik_output = output_file_path
else:
epik_output = os.path.splitext(output_file_path)[0] + '-full.mae'
# Epik command. We need list in case there's a space in the paths
cmd = [epik_path, '-imae', input_file_path, '-omae', epik_output]
cmd += '-ms {ms} -ph {ph} {pht} {nt} {p} -pKa_atom -WAIT -NO_JOBCONTROL'.format(
**epik_args).split()
# We run with output_dir as working directory to save there the log file
with utils.temporary_cd(output_dir):
run_and_log_error(cmd)
# Check if we need to extract a range of structures
if extract_range is not None:
run_maesubset(epik_output, output_file_path, extract_range)
os.remove(epik_output)
def protein_prep(input_file_path, output_file_path, pdbid, pH=7.4, fillsidechains=True, fillloops=True, max_states=32, tolerance=0):
# Locate PrepWizard executable
prepwiz_path = os.path.join(os.environ['SCHRODINGER'], 'utilities', 'prepwizard')
# Normalize paths
input_file_path = os.path.abspath(input_file_path)
output_file_path = os.path.abspath(output_file_path)
output_dir = os.path.join(output_file_path, '%s-fixed' % pdbid)
output_file_name = '../%s-fixed.pdb' % pdbid
# Check for output file pathway
if not os.path.exists(output_dir):
os.makedirs(output_dir)
# Format arguments for PrepWizard command
wiz_args = dict(ms=max_states, ph=pH)
wiz_args['fillsidechains'] = '-fillsidechains' if fillsidechains else ''
wiz_args['fillloops'] = '-fillloops' if fillloops else ''
wiz_args['pht'] = tolerance
cmd = [prepwiz_path]
cmd += '-captermini -mse -propka_pH {ph} {fillsidechains} {fillloops} -keepfarwat -disulfides -ms {ms} -minimize_adj_h -epik_pH {ph} -epik_pHt {pht} -fix -NOJOBID'.format(**wiz_args).split()
cmd.append(input_file_path)
cmd.append(output_file_name)
with utils.temporary_cd(output_dir):
log = schrodinger.run_and_log_error(cmd)
write_file('%s.log' % pdbid, log)
def protein_prep(input_file,
output_file,
cap,
pH=7.4,
fillsidechains=True,
fillloops=True,
noepik=False,
rehtreat=True,
max_states=32,
tolerance=0):
# Locate PrepWizard executable
prepwiz_path = os.path.join(os.environ['SCHRODINGER'], 'utilities',
'prepwizard')
# Normalize paths
input_file_path = os.path.abspath(input_file)
input_file_dir, input_name = os.path.split(input_file_path)
output_file_name = os.path.join(input_file_dir,
output_file + '-prepped.pdb')
working_dir = os.path.join(input_file_dir, '%s-prepped' % input_name)
# Check for output file pathway
if not os.path.exists(working_dir):
os.makedirs(working_dir)
# Format arguments for PrepWizard command
wiz_args = dict(ms=max_states, ph=pH)
wiz_args['fillsidechains'] = '-fillsidechains' if fillsidechains else ''
wiz_args['fillloops'] = '-fillloops' if fillloops else ''
wiz_args['pht'] = tolerance
wiz_args['rehtreat'] = '-rehtreat' if rehtreat else ''
wiz_args['water_hbond_cutoff'] = 0
wiz_args['noepik'] = '-noepik' if noepik else ''
wiz_args['captermini'] = '-captermini' if cap else ''
cmd = [prepwiz_path]
cmd += '{captermini} -mse -propka_pH {ph} {fillsidechains} {fillloops} {rehtreat} {noepik} -delwater_hbond_cutoff {water_hbond_cutoff} ' \
'-keepfarwat -disulfides -ms {ms} -minimize_adj_h -epik_pH {ph} -epik_pHt {pht} -fix -NOJOBID'.format(**wiz_args).split()
cmd.append(input_file_path)
cmd.append(output_file_name)
with utils.temporary_cd(working_dir):
log = schrodinger.run_and_log_error(cmd)
write_file('protein_prep.log', log)
def protein_prep(input_file, output_file, cap, pH=7.4, fillsidechains=True, fillloops=True,
noepik=False, rehtreat=True, max_states=32, tolerance=0):
# Locate PrepWizard executable
prepwiz_path = os.path.join(os.environ['SCHRODINGER'], 'utilities', 'prepwizard')
# Normalize paths
input_file_path = os.path.abspath(input_file)
input_file_dir, input_name = os.path.split(input_file_path)
output_file_name = os.path.join(input_file_dir, output_file + '-prepped.pdb')
working_dir = os.path.join(input_file_dir, '%s-prepped' % input_name)
# Check for output file pathway
if not os.path.exists(working_dir):
os.makedirs(working_dir)
# Format arguments for PrepWizard command
wiz_args = dict(ms=max_states, ph=pH)
wiz_args['fillsidechains'] = '-fillsidechains' if fillsidechains else ''
wiz_args['fillloops'] = '-fillloops' if fillloops else ''
wiz_args['pht'] = tolerance
wiz_args['rehtreat'] = '-rehtreat' if rehtreat else ''
wiz_args['water_hbond_cutoff'] = 0
wiz_args['noepik'] = '-noepik' if noepik else ''
wiz_args['captermini'] = '-captermini' if cap else ''
cmd = [prepwiz_path]
cmd += '{captermini} -mse -propka_pH {ph} {fillsidechains} {fillloops} {rehtreat} {noepik} -delwater_hbond_cutoff {water_hbond_cutoff} ' \
'-keepfarwat -disulfides -ms {ms} -minimize_adj_h -epik_pH {ph} -epik_pHt {pht} -fix -NOJOBID'.format(**wiz_args).split()
cmd.append(input_file_path)
cmd.append(output_file_name)
with utils.temporary_cd(working_dir):
log = schrodinger.run_and_log_error(cmd)
write_file('protein_prep.log', log)
def run_ligprep(input_file_path, output_file_path, max_stereo_isomers=1, ionization_treatment=1):
"""
Run Schrodinger's ligprep command line utility to clean up a structure.
Parameters
----------
input_file_path : str
Path to input file describing the molecule.
output_file_path : str
Path to the output file created by epik.
max_stereo_isomers : int, optional
Maximum number of generated structures (default is 32).
ionization_treatment : int, default 1
0 do not neutralize or ionize, 1 neutralize, 2 neutralize and ionize.
"""
# Locate executable
exe_path = os.path.join(os.environ['SCHRODINGER'], 'ligprep')
# Normalize paths as we'll run in a different working directory
input_file_path = os.path.abspath(input_file_path)
output_file_path = os.path.abspath(output_file_path)
output_dir = os.path.dirname(output_file_path)
# Preparing epik command arguments for format()
prep_args = dict(s=max_stereo_isomers, i=ionization_treatment)
prep_output = os.path.splitext(output_file_path)[0] + '.mae'
# ligprep command. We need list in case there's a space in the paths
cmd = [exe_path, '-imae', input_file_path, '-omae', prep_output]
cmd += '-s {s} -i {i} -WAIT'.format(
**prep_args).split()
# We run with output_dir as working directory to save there the log file
with utils.temporary_cd(output_dir):
run_and_log_error(cmd)
def run_epik(input_file_path,
output_file_path,
max_structures=32,
ph=7.4,
ph_tolerance=None,
min_probability=None,
tautomerize=True,
extract_range=None,
max_atoms=150):
"""Run Schrodinger's epik command line utility to enumerate protonation and
tautomeric states.
Parameters
----------
input_file_path : str
Path to input file describing the molecule.
output_file_path : str
Path to the output file created by epik.
max_structures : int, optional
Maximum number of generated structures (default is 32).
ph : float, optional
Target pH for generated states (default is 7.4).
ph_tolerance : float, optional
Equivalent of -pht option in Epik command (default is None).
min_probability: float, optional
Minimum probability for the generated states.
tautomerize : bool, optional
Whether or not tautomerize the input structure (default is True).
extract_range : int or list of ints, optional
If not None, the function uses the Schrodinger's utility maesubset to
extract only a subset of the generated structures. This is the 0-based
indices of the structures to extract from the input files.
max_atoms : int, optional
Structures containing more than max_atoms atoms will not be adjusted. (default is 150)
"""
# Locate epik executable
epik_path = os.path.join(os.environ['SCHRODINGER'], 'epik')
# Normalize paths as we'll run in a different working directory
input_file_path = os.path.abspath(input_file_path)
output_file_path = os.path.abspath(output_file_path)
output_dir = os.path.dirname(output_file_path)
# Preparing epik command arguments for format()
epik_args = dict(ms=max_structures, ph=ph)
epik_args['pht'] = '-pht {}'.format(ph_tolerance) if ph_tolerance else ''
epik_args['nt'] = '' if tautomerize else '-nt'
epik_args['p'] = '-p {}'.format(min_probability) if min_probability else ''
epik_args['ma'] = '-ma {}'.format(max_atoms)
# Determine if we need to convert input and/or output file
if extract_range is None:
epik_output = output_file_path
else:
epik_output = os.path.splitext(output_file_path)[0] + '-full.mae'
# Epik command. We need list in case there's a space in the paths
cmd = [epik_path, '-imae', input_file_path, '-omae', epik_output]
cmd += '-ms {ms} -ph {ph} {ma} {pht} {nt} {p} -pKa_atom -WAIT -NO_JOBCONTROL'.format(
**epik_args).split()
# We run with output_dir as working directory to save there the log file
with utils.temporary_cd(output_dir):
run_and_log_error(cmd)
# Check if we need to extract a range of structures
if extract_range is not None:
run_maesubset(epik_output, output_file_path, extract_range)
os.remove(epik_output)
def test_temp_cd_context():
"""Test the context temporary_cd()."""
with utils.temporary_directory() as tmp_dir:
with utils.temporary_cd(tmp_dir):
assert os.getcwd() == os.path.realpath(tmp_dir)
assert os.getcwd() != os.path.realpath(tmp_dir)
def test_temp_cd_context():
"""Test the context temporary_cd()."""
with utils.temporary_directory() as tmp_dir:
with utils.temporary_cd(tmp_dir):
assert os.getcwd() == os.path.realpath(tmp_dir)
assert os.getcwd() != os.path.realpath(tmp_dir)
