def run(pdb_filename=None,
pdb_hierarchy=None,
crystal_symmetry=None,
model_completion=True,
original_pdb_filename=None,
append_to_end_of_model=True,
):
#
# function as be used in two main modes
# 1. completing a model with hydrogens in a protein-like manner
# 2. completing a cluster with hydrogens in a QM-sensible manner
#
if pdb_hierarchy:
assert crystal_symmetry
assert pdb_filename is None
if model_completion:
use_capping_hydrogens=False
fname = 'complete'
else:
use_capping_hydrogens=True
fname = 'capping'
#assert 0 # model has H
params=None
if use_capping_hydrogens:
params = hierarchy_utils.get_pdb_interpretation_params()
params.link_distance_cutoff=1.8
if pdb_hierarchy:
raw_records = hierarchy_utils.get_raw_records(
pdb_inp=None,
pdb_hierarchy=pdb_hierarchy,
crystal_symmetry=crystal_symmetry,
)
ppf = hierarchy_utils.get_processed_pdb(raw_records=raw_records)
sites_cart = pdb_hierarchy.atoms().extract_xyz()
ppf.all_chain_proxies.pdb_hierarchy.atoms().set_xyz(sites_cart)
else:
ppf = hierarchy_utils.get_processed_pdb(pdb_filename=pdb_filename,
params=params,
)
ppf = complete_pdb_hierarchy(
ppf.all_chain_proxies.pdb_hierarchy,
ppf.geometry_restraints_manager(),
use_capping_hydrogens=use_capping_hydrogens,
append_to_end_of_model=append_to_end_of_model, # needed for clustering
# code and Molprobity
pdb_filename=pdb_filename, # used just for naming of debug output
pdb_inp=ppf.all_chain_proxies.pdb_inp, # used in get_raw_records. why?
original_pdb_filename=original_pdb_filename, # used to define breaks in
# main chain for capping
verbose=False,
)
if pdb_filename:
output = hierarchy_utils.write_hierarchy(
pdb_filename,
ppf.all_chain_proxies.pdb_inp,
ppf.all_chain_proxies.pdb_hierarchy,
fname,
)
return ppf.all_chain_proxies.pdb_hierarchy
def complete_pdb_hierarchy(
hierarchy,
geometry_restraints_manager,
use_capping_hydrogens=False,
append_to_end_of_model=False,
pdb_filename=None,
pdb_inp=None,
original_pdb_filename=None,
verbose=False,
debug=False,
):
for ag in hierarchy.atom_groups():
if get_class(ag.resname) in ['common_rna_dna']:
raise Sorry('')
from mmtbx.building import extend_sidechains
params = None
original_hierarchy = None
if use_capping_hydrogens:
params = hierarchy_utils.get_pdb_interpretation_params()
params.link_distance_cutoff = 1.8 # avoid linking across a single missing AA
if original_pdb_filename:
original_pdb_inp = iotbx.pdb.input(original_pdb_filename)
original_hierarchy = original_pdb_inp.construct_hierarchy()
if debug:
output = hierarchy_utils.write_hierarchy(
pdb_filename,
pdb_inp,
hierarchy,
'temp1',
)
#
# assume model is heavy-atom complete
#
if not use_capping_hydrogens:
if debug:
ppf = hierarchy_utils.get_processed_pdb(pdb_filename=output)
else:
raw_records = hierarchy_utils.get_raw_records(pdb_inp, hierarchy)
ppf = hierarchy_utils.get_processed_pdb(
raw_records=raw_records,
params=params,
)
sites_cart = hierarchy.atoms().extract_xyz()
ppf.all_chain_proxies.pdb_hierarchy.atoms().set_xyz(sites_cart)
n_changed = extend_sidechains.extend_protein_model(
ppf.all_chain_proxies.pdb_hierarchy,
mon_lib_server,
add_hydrogens=False,
)
if debug:
print 'number of side chains changed', n_changed
output = hierarchy_utils.write_hierarchy(
pdb_filename,
pdb_inp,
ppf.all_chain_proxies.pdb_hierarchy,
'temp2',
)
#
# need to use Reduce/ReadySet! to add hydrogens
#
if not use_capping_hydrogens:
output = hierarchy_utils.write_hierarchy(
pdb_filename,
pdb_inp,
ppf.all_chain_proxies.pdb_hierarchy,
'readyset_input',
)
hierarchy = hierarchy_utils.add_hydrogens_using_ReadySet(output)
#
# remove side chain acid hydrogens - maybe not required since recent changes
#
if debug:
ppf = hierarchy_utils.get_processed_pdb(
pdb_filename=output,
params=params,
)
else:
raw_records = hierarchy_utils.get_raw_records(pdb_inp, hierarchy)
ppf = hierarchy_utils.get_processed_pdb(
raw_records=raw_records,
params=params,
)
sites_cart = hierarchy.atoms().extract_xyz()
ppf.all_chain_proxies.pdb_hierarchy.atoms().set_xyz(sites_cart)
remove_acid_side_chain_hydrogens(ppf.all_chain_proxies.pdb_hierarchy)
#
# add hydrogens in special cases
# eg ETA
# eg N - H, H2
#
if debug:
ppf = hierarchy_utils.get_processed_pdb(
pdb_filename=output,
params=params,
)
else:
hierarchy = ppf.all_chain_proxies.pdb_hierarchy
raw_records = hierarchy_utils.get_raw_records(pdb_inp, hierarchy)
ppf = hierarchy_utils.get_processed_pdb(
raw_records=raw_records,
params=params,
)
sites_cart = hierarchy.atoms().extract_xyz()
ppf.all_chain_proxies.pdb_hierarchy.atoms().set_xyz(sites_cart)
special_case_hydrogens(
ppf.all_chain_proxies.pdb_hierarchy,
ppf.geometry_restraints_manager(),
#use_capping_hydrogens=use_capping_hydrogens,
#append_to_end_of_model=append_to_end_of_model,
#original_hierarchy=original_hierarchy,
verbose=verbose,
)
#
# add terminals atoms including hydrogens and OXT - more docs here...
#
if debug:
output = hierarchy_utils.write_hierarchy(
pdb_filename,
pdb_inp,
ppf.all_chain_proxies.pdb_hierarchy,
'temp3',
)
ppf = hierarchy_utils.get_processed_pdb(
pdb_filename=output,
params=params,
)
else:
hierarchy = ppf.all_chain_proxies.pdb_hierarchy
raw_records = hierarchy_utils.get_raw_records(pdb_inp, hierarchy)
ppf = hierarchy_utils.get_processed_pdb(
raw_records=raw_records,
params=params,
)
sites_cart = hierarchy.atoms().extract_xyz()
ppf.all_chain_proxies.pdb_hierarchy.atoms().set_xyz(sites_cart)
add_terminal_hydrogens(
ppf.all_chain_proxies.pdb_hierarchy,
ppf.geometry_restraints_manager(),
use_capping_hydrogens=use_capping_hydrogens,
append_to_end_of_model=append_to_end_of_model,
original_hierarchy=original_hierarchy,
verbose=verbose,
) # in place
ppf.all_chain_proxies.pdb_hierarchy.atoms(
).set_chemical_element_simple_if_necessary()
ppf.all_chain_proxies.pdb_hierarchy.sort_atoms_in_place()
#display_hierarchy_atoms(ppf.all_chain_proxies.pdb_hierarchy)
#ppf.all_chain_proxies.pdb_hierarchy.atoms_reset_serial()
#ppf.all_chain_proxies.pdb_hierarchy.atoms().reset_i_seq()
return ppf