def main(args):
geom_patt = re.compile("([A-Z][a-z]*)((?:\s+-?\d+\.?\d*){3})")
float_patt = re.compile("-?\d+\.?\d*")
all_names = []
atoms = []
name = None
for i, page in enumerate(extract_pages(args.infile)):
print("parsing page {: 4d} please wait...".format(i + 1), end="\r")
for element in page:
last_line = None
if hasattr(element, "get_text"):
for line in element:
text = line.get_text()
match = geom_patt.search(text)
if not match and last_line and atoms:
name_match = geom_patt.search(name)
if name_match:
geom = Geometry(all_names[-1] + ".xyz")
geom.atoms.extend(atoms)
else:
geom = Geometry(atoms)
geom.name = name
geom.comment = name
if args.directory != "CURRENTDIR":
geom.name = os.path.join(
args.directory, geom.name)
orig_name = geom.name
i = 2
while geom.name in all_names:
geom.name = "{}_{:03d}".format(orig_name, i)
i += 1
if args.sort:
geom.refresh_connected()
geom.refresh_ranks()
geom.atoms = geom.reorder()[0]
geom.write()
all_names.append(geom.name)
atoms = []
name = None
# print()
# print(geom.name, len(geom.atoms))
# print(geom)
if match:
if not name:
name = last_line
element = match.group(1)
coords = float_patt.findall(match.group(2))
atoms.append(Atom(element, [float(c) for c in coords]))
last_line = text.strip()
def save_aarontools(session, path, format_name, **kwargs):
"""
save XYZ file using AaronTools
kwargs may be:
comment - str
"""
from SEQCROW.residue_collection import ResidueCollection
from AaronTools.geometry import Geometry
from chimerax.atomic import AtomicStructure
accepted_kwargs = ['comment', 'models']
unknown_kwargs = [kw for kw in kwargs if kw not in accepted_kwargs]
if len(unknown_kwargs) > 0:
raise RuntimeWarning("unrecognized keyword%s %s?" %
("s" if len(unknown_kwargs) > 1 else "",
", ".join(unknown_kwargs)))
if 'models' in kwargs:
models = kwargs['models']
else:
models = None
if models is None:
models = session.models.list(type=AtomicStructure)
models = [m for m in models if isinstance(m, AtomicStructure)]
if len(models) < 1:
raise RuntimeError('nothing to save')
res_cols = [ResidueCollection(model) for model in models]
atoms = []
for res in res_cols:
atoms.extend(res.atoms)
geom = Geometry(atoms)
if 'comment' in kwargs:
geom.comment = kwargs[comment]
geom.write(outfile=path)
default=[''], \
required=False, \
dest='comment', \
help='comment line')
args = xyz_parser.parse_args()
for f in args.infile:
if isinstance(f, str):
if args.input_format is not None:
infile = FileReader((f, args.input_format[0], None))
else:
infile = FileReader(f)
else:
if args.input_format is not None:
infile = FileReader(('from stdin', args.input_format[0], f))
else:
if len(sys.argv) >= 1:
xyz_parser.print_help()
raise RuntimeError("when no input file is given, stdin is read and a format must be specified")
geom = Geometry(infile)
if args.comment[0]:
geom.comment = args.comment[0]
else:
geom.comment=f
s = FileWriter.write_xyz(geom, append=True, outfile=args.outfile[0])
if not args.outfile[0]:
print(s)
for t in ts:
dEdt = S.dE_func(t)*S.dE_func(t+dt)
if dEdt <= 0 and S.dE_func(t) > 0 and args.print_max:
max_n_min_ts.append(t)
if dEdt <= 0 and S.dE_func(t) < 0 and args.print_min:
max_n_min_ts.append(t)
for i, t in enumerate(max_n_min_ts):
E = S.E_func(t)
if args.print_E:
dE = S.dE_func(t)
nrg_out += "%f\t%f\t%f\n" % (t,E,dE)
else:
G = S.Geom_func(t)
comment = "E(%f) = %f" % (t, E)
G.comment = comment
write_geoms.append(G.copy())
if args.specific_ts:
#print structures for specified values of t
for i, t in enumerate(args.specific_ts):
if args.print_E:
E = S.E_func(t)
dE = S.dE_func(t)
nrg_out += "%f\t%f\t%f\n" % (t,E,dE)
else:
G = S.Geom_func(t)
E = S.E_func(t)
comment = "E(%f) = %f" % (t, E)
G.comment = comment
write_geoms.append(G.copy())
if args.input_format is not None:
infile = FileReader(("from stdin", args.input_format, f))
else:
infile = FileReader(("from stdin", "xyz", f))
geom = Geometry(infile)
# align
rmsd = geom.RMSD(ref_geom,
align=True,
targets=args.in_target,
ref_targets=args.ref_target,
heavy_only=args.heavy,
sort=args.sort)
geom.comment = "rmsd = %f" % rmsd
if not args.value_only and not args.csv:
if args.outfile:
outfile = args.outfile
if "$INFILE" in outfile:
outfile = outfile.replace("$INFILE", get_filename(f))
geom.write(append=True, outfile=outfile)
else:
print(geom.write(outfile=False))
elif args.value_only:
if args.outfile:
outfile = args.outfile
if "$INFILE" in outfile:
outfile = outfile.replace("$INFILE", get_filename(f))
for t in ts:
dnrg_dt = pathway.dvar_func_dt["energy"](t) * pathway.dvar_func_dt["energy"](t + dt)
if dnrg_dt <= 0 and pathway.dvar_func_dt["energy"](t) > 0 and args.print_max:
max_n_min_ts.append(t)
elif dnrg_dt <= 0 and pathway.dvar_func_dt["energy"](t) < 0 and args.print_min:
max_n_min_ts.append(t)
for i, t in enumerate(max_n_min_ts):
nrg = pathway.var_func["energy"](t)
if args.print_E:
d_nrg = pathway.dvar_func_dt["energy"](t)
nrg_out += "%f\t%f\t%f\n" % (t, nrg, d_nrg)
else:
geom = pathway.geom_func(t)
comment = "E(%f) = %f" % (t, nrg)
geom.comment = comment
write_geoms.append(geom)
if args.specific_ts:
#print structures for specified values of t
for i, t in enumerate(args.specific_ts):
if args.print_E:
nrg = pathway.var_func["energy"](t)
d_nrg = pathway.dvar_func_dt["energy"](t)
nrg_out += "%f\t%f\t%f\n" % (t, nrg, d_nrg)
else:
geom = pathway.geom_func(t)
nrg = pathway.var_func["energy"](t)
comment = "E(%f) = %f" % (t, nrg)
geom.comment = comment
write_geoms.append(geom)
s += "%s\n" % formula
for group in structures[n_atoms][formula]:
total += len(group)
if args.directory:
dir_name = os.path.join(
args.directory,
formula,
get_filename(group[0][0].name, include_parent_dir=False),
)
if not os.path.exists(dir_name):
os.makedirs(dir_name)
for geom, rmsd, _ in group:
geom.comment = "RMSD from %s = %.4f" % (
get_filename(group[0][0].name,
include_parent_dir=False),
rmsd,
)
if args.energy_filter and all(
"energy" in g.other for g in [geom, group[0][0]]):
d_nrg = UNIT.HART_TO_KCAL * (
geom.other["energy"] - group[0][0].other["energy"])
geom.comment += " energy from %s = %.1f kcal/mol" % (
get_filename(group[0][0].name,
include_parent_dir=False),
d_nrg,
)
geom.write(outfile=os.path.join(
args.directory, formula,
get_filename(group[0][0].name,
include_parent_dir=False),
args = xyz_parser.parse_args()
for f in glob_files(args.infile, parser=xyz_parser):
if isinstance(f, str):
if args.input_format is not None:
infile = FileReader((f, args.input_format, None))
else:
infile = FileReader(f)
else:
if args.input_format is not None:
infile = FileReader(("from stdin", args.input_format, f))
else:
if len(sys.argv) >= 1:
infile = FileReader(("from stdin", "xyz", f))
geom = Geometry(infile, refresh_connected=False, refresh_ranks=False)
if args.comment:
geom.comment = args.comment
else:
geom.comment = f
if not args.outfile:
print(geom.write(outfile=False))
else:
outfile = args.outfile
if "$INFILE" in outfile:
outfile = outfile.replace("$INFILE", get_filename(f))
geom.write(append=args.append, outfile=outfile)
