def _try_as_seq(self):
# XXX hack to avoid choking on CCP4 maps
assert (not self.file_name.endswith(".ccp4"))
# XXX hack to avoid choking on NCS files:
assert (not self.file_name.endswith(".ncs"))
assert (not self.file_name.endswith(".ncs_spec"))
from iotbx.bioinformatics import any_sequence_format
objects, non_compliant = any_sequence_format(self.file_name)
assert (objects is not None), "No sequence data found in file."
assert (len(non_compliant) == 0), "Misformatted data in file."
for seq_obj in objects:
assert (not "-" in seq_obj.sequence)
self._file_object = objects
# self._try_as_txt()
# assert len(self._file_object) != 0
# for _line in self._file_object.splitlines() :
# assert not _line.startswith(" ")
# line = re.sub(" ", "", _line)
# assert ((len(line) == 0) or
# (line[0] == ">") or
# (line == "*") or
# ((line[-1] == '*') and line[:-1].isalpha()) or
# line.isalpha())
self._file_type = "seq"
def run (args=(), params=None, out=sys.stdout) :
assert (params is not None)
seq_files = params.muscle.seq_file
output_file = params.muscle.output_file
if (output_file is None) or (output_file == "") :
output_file = os.path.join(os.getcwd(), "muscle.aln")
from iotbx import file_reader
from iotbx.bioinformatics import any_sequence_format, sequence
seqs = []
for file_name in seq_files :
if (file_name.endswith(".pdb") or file_name.endswith(".ent") or
file_name.endswith(".pdb.gz") or file_name.endswith(".ent.gz")) :
pdb_in = file_reader.any_file(file_name, force_type="pdb").file_object
hierarchy = pdb_in.hierarchy
first_model = hierarchy.models()[0]
found_protein = False
for chain in first_model.chains() :
if chain.is_protein() :
chain_seq = chain.as_padded_sequence()
base_name = os.path.basename(file_name)
seq_name = "%s_%s" % (os.path.splitext(base_name)[0], chain.id)
seqs.append(sequence(chain_seq, seq_name))
found_protein = True
if (not found_protein) :
raise Sorry(("The PDB file %s does not contain any recognizable "+
"protein chains.") % file_name)
else :
try :
seq_objects, non_compliant = any_sequence_format(file_name,
assign_name_if_not_defined=True)
seqs.extend(seq_objects)
except Exception, e :
raise Sorry(("Error parsing '%s' - not a recognizable sequence "+
"format. (Original message: %s)") % (file_name, str(e)))
def _try_as_seq (self) :
# XXX hack to avoid choking on CCP4 maps
assert (not self.file_name.endswith(".ccp4"))
# XXX hack to avoid choking on NCS files:
assert (not self.file_name.endswith(".ncs"))
assert (not self.file_name.endswith(".ncs_spec"))
from iotbx.bioinformatics import any_sequence_format
objects, non_compliant = any_sequence_format(self.file_name)
assert (objects is not None), "No sequence data found in file."
assert (len(non_compliant) == 0), "Misformatted data in file."
for seq_obj in objects :
assert (not "-" in seq_obj.sequence)
self._file_object = objects
# self._try_as_txt()
# assert len(self._file_object) != 0
# for _line in self._file_object.splitlines() :
# assert not _line.startswith(" ")
# line = re.sub(" ", "", _line)
# assert ((len(line) == 0) or
# (line[0] == ">") or
# (line == "*") or
# ((line[-1] == '*') and line[:-1].isalpha()) or
# line.isalpha())
self._file_type = "seq"
def run (args=(), params=None, out=sys.stdout) :
assert (params is not None)
seq_files = params.muscle.seq_file
output_file = params.muscle.output_file
if (output_file is None) or (output_file == "") :
output_file = os.path.join(os.getcwd(), "muscle.aln")
from iotbx import file_reader
from iotbx.bioinformatics import any_sequence_format, sequence
seqs = []
for file_name in seq_files :
if (file_name.endswith(".pdb") or file_name.endswith(".ent") or
file_name.endswith(".pdb.gz") or file_name.endswith(".ent.gz")) :
pdb_in = file_reader.any_file(file_name, force_type="pdb").file_object
hierarchy = pdb_in.hierarchy
first_model = hierarchy.models()[0]
found_protein = False
for chain in first_model.chains() :
if chain.is_protein() :
chain_seq = chain.as_padded_sequence()
base_name = os.path.basename(file_name)
seq_name = "%s_%s" % (os.path.splitext(base_name)[0], chain.id)
seqs.append(sequence(chain_seq, seq_name))
found_protein = True
if (not found_protein) :
raise Sorry(("The PDB file %s does not contain any recognizable "+
"protein chains.") % file_name)
else :
try :
seq_objects, non_compliant = any_sequence_format(file_name,
assign_name_if_not_defined=True)
seqs.extend(seq_objects)
except Exception, e :
raise Sorry(("Error parsing '%s' - not a recognizable sequence "+
"format. (Original message: %s)") % (file_name, str(e)))
def run (args, out=sys.stdout, verbose=True) :
import mmtbx.building.extend_sidechains
import mmtbx.command_line
input_out = out
if (not verbose) :
input_out = null_out()
cmdline = mmtbx.command_line.load_model_and_data(
args=args,
master_phil=get_master_phil(),
process_pdb_file=False,
out=input_out,
usage_string="""\
mmtbx.extend_sidechains model.pdb data.mtz [restraints.cif] [options]
Rebuild sidechains with missing non-hydrogen atoms. Includes real-space
refinement (but needs work).""")
params = cmdline.params
prefix = os.path.splitext(os.path.basename(params.input.pdb.file_name[0]))[0]
pdb_hierarchy = cmdline.pdb_hierarchy
xray_structure = cmdline.xray_structure
if (cmdline.params.input.sequence is not None) :
from iotbx.bioinformatics import any_sequence_format
sequences, nc = any_sequence_format(cmdline.params.input.sequence)
make_sub_header("Correcting model sequence", out=out)
n_changed = mmtbx.building.extend_sidechains.correct_sequence(
pdb_hierarchy=pdb_hierarchy,
sequences=sequences,
out=out)
if (n_changed == 0) :
print >> out, " No modifications required."
else :
xray_structure = pdb_hierarchy.extract_xray_structure(
crystal_symmetry=xray_structure.crystal_symmetry())
cmdline.fmodel.update_xray_structure(xray_structure,
update_f_calc=True)
return mmtbx.building.extend_sidechains.extend_and_refine(
pdb_hierarchy=pdb_hierarchy,
xray_structure=xray_structure,
fmodel=cmdline.fmodel,
params=params,
prefix=prefix,
cif_objects=[ co for fn, co in cmdline.cif_objects ],
out=out,
verbose=verbose,
output_model=params.output_model,
output_map_coeffs=params.output_map_coeffs)
def run(args, out=sys.stdout, verbose=True):
import mmtbx.building.extend_sidechains
import mmtbx.command_line
input_out = out
if (not verbose):
input_out = null_out()
cmdline = mmtbx.command_line.load_model_and_data(
args=args,
master_phil=get_master_phil(),
process_pdb_file=False,
out=input_out,
usage_string="""\
mmtbx.extend_sidechains model.pdb data.mtz [restraints.cif] [options]
Rebuild sidechains with missing non-hydrogen atoms. Includes real-space
refinement (but needs work).""")
params = cmdline.params
prefix = os.path.splitext(os.path.basename(
params.input.pdb.file_name[0]))[0]
pdb_hierarchy = cmdline.pdb_hierarchy
xray_structure = cmdline.xray_structure
if (cmdline.params.input.sequence is not None):
from iotbx.bioinformatics import any_sequence_format
sequences, nc = any_sequence_format(cmdline.params.input.sequence)
make_sub_header("Correcting model sequence", out=out)
n_changed = mmtbx.building.extend_sidechains.correct_sequence(
pdb_hierarchy=pdb_hierarchy, sequences=sequences, out=out)
if (n_changed == 0):
print >> out, " No modifications required."
else:
xray_structure = pdb_hierarchy.extract_xray_structure(
crystal_symmetry=xray_structure.crystal_symmetry())
cmdline.fmodel.update_xray_structure(xray_structure,
update_f_calc=True)
return mmtbx.building.extend_sidechains.extend_and_refine(
pdb_hierarchy=pdb_hierarchy,
xray_structure=xray_structure,
fmodel=cmdline.fmodel,
params=params,
prefix=prefix,
cif_objects=[co for fn, co in cmdline.cif_objects],
out=out,
verbose=verbose,
output_model=params.output_model,
output_map_coeffs=params.output_map_coeffs)
def get_residues_and_ha(
seq_file=None, atom_type=None, chain_type=None, data=None, solvent_fraction=None, ncs_copies=None, out=sys.stdout
):
if not seq_file or not os.path.isfile(seq_file):
raise Sorry("Please supply number of residues or a sequence file")
objects, non_compliant = any_sequence_format(seq_file)
if non_compliant:
raise Sorry("Sorry, unable to read the sequence file %s" % (seq_file))
n_aa, n_met, n_cys = 0, 0, 0
for seq_obj in objects:
n_aa_, n_met_, n_cys_ = get_aa_and_met(sequence=seq_obj.sequence)
n_aa += n_aa_
n_met += n_met_
n_cys += n_cys_
number_of_s = n_met + n_cys
number_of_sites, number_of_sites_lowres = get_number_of_sites(
atom_type=atom_type, n_met=n_met, n_cys=n_cys, n_aa=n_aa, ncs_copies=1, out=null_out()
)
# if data file is specified, use it to get crystal_symmetry and then estimate
# residues and ha using that information and seq_file. Otherwise guess
if data and os.path.isfile(data):
from phenix.command_line.ncs_and_number_of_ha import ncs_and_number_of_ha
args = ["data=%s" % (data)]
if seq_file:
args.append("seq_file=%s" % (seq_file))
if atom_type:
args.append("atom_type=%s" % (atom_type))
if chain_type:
args.append("chain_type=%s" % (chain_type))
if ncs_copies:
args.append("ncs_copies=%s" % (ncs_copies))
args.append("log=None")
args.append("params_out=None")
na = ncs_and_number_of_ha(args=args, out=null_out())
return na.ncs_copies * n_aa, na.number_of_sites, na.ncs_copies * number_of_s, na.solvent_fraction, na.ncs_copies
else:
return n_aa, number_of_sites, number_of_s, solvent_fraction, ncs_copies
def get_residues_and_ha(seq_file=None,atom_type=None,
chain_type=None,data=None,solvent_fraction=None,
ncs_copies=None,out=sys.stdout):
if not seq_file or not os.path.isfile(seq_file):
raise Sorry("Please supply number of residues or a sequence file")
objects, non_compliant = any_sequence_format(seq_file)
if non_compliant:
raise Sorry("Sorry, unable to read the sequence file %s" %(seq_file))
n_aa, n_met, n_cys = 0, 0, 0
for seq_obj in objects :
n_aa_,n_met_,n_cys_ = get_aa_and_met(sequence=seq_obj.sequence)
n_aa += n_aa_
n_met += n_met_
n_cys += n_cys_
number_of_s=n_met+n_cys
number_of_sites,number_of_sites_lowres=get_number_of_sites(
atom_type=atom_type,n_met=n_met,n_cys=n_cys,
n_aa=n_aa,ncs_copies=1,out=null_out())
# if data file is specified, use it to get crystal_symmetry and then estimate
# residues and ha using that information and seq_file. Otherwise guess
if data and os.path.isfile(data):
from phenix.command_line.ncs_and_number_of_ha import ncs_and_number_of_ha
args=["data=%s" %(data)]
if seq_file: args.append("seq_file=%s" %(seq_file))
if atom_type: args.append("atom_type=%s" %(atom_type))
if chain_type: args.append("chain_type=%s" %(chain_type))
if ncs_copies: args.append("ncs_copies=%s" %(ncs_copies))
args.append("log=None")
args.append("params_out=None")
na=ncs_and_number_of_ha(args=args,out=null_out())
return na.ncs_copies*n_aa,na.number_of_sites,na.ncs_copies*number_of_s,\
na.solvent_fraction,na.ncs_copies
else:
return n_aa,number_of_sites,number_of_s,solvent_fraction,ncs_copies
