def test_read_field_error():
from pyxmolpp2.pdb import PdbFile, StandardPdbRecords, AlteredPdbRecords, RecordName, FieldName, PdbException
import glob
records = AlteredPdbRecords(StandardPdbRecords.instance())
records.alter_record(RecordName("ATOM"), FieldName("serial"), [4, 6])
#print(glob.glob("tests_dataset/pdb/rcsb/*.pdb"))
for filename in glob.glob("tests_dataset/pdb/rcsb/*.pdb"):
# print(filename)
with pytest.raises(PdbException):
PdbFile(filename, records).get_frame()
records = AlteredPdbRecords(StandardPdbRecords.instance())
records.alter_record(RecordName("ATOM"), FieldName("x"), [4, 4])
#print(glob.glob("tests_dataset/pdb/rcsb/*.pdb"))
for filename in glob.glob("tests_dataset/pdb/rcsb/*.pdb"):
# print(filename)
with pytest.raises(PdbException):
frame = PdbFile(filename, records).get_frame()
# print(frame)
records = AlteredPdbRecords(StandardPdbRecords.instance())
records.alter_record(RecordName("ATOM"), FieldName("resName"), [1, 85])
#print(glob.glob("tests_dataset/pdb/rcsb/*.pdb"))
for filename in glob.glob("tests_dataset/pdb/rcsb/*.pdb"):
# print(filename)
with pytest.raises(PdbException):
frame = PdbFile(filename, records).get_frame()
def test_traj_exceptions():
from pyxmolpp2.pdb import PdbFile, AlteredPdbRecords, StandardPdbRecords, RecordName, FieldName
from pyxmolpp2.polymer import AtomName
from pyxmolpp2.trjtool import DatFile
from pyxmolpp2.trajectory import Trajectory, TrajectoryException
records = AlteredPdbRecords(StandardPdbRecords.instance())
records.alter_record(RecordName("ATOM"), FieldName("serial"), [7, 12])
datfile1 = DatFile("tests_dataset/trjtool/GB1/run00001.dat")
with pytest.raises(TrajectoryException):
frame = PdbFile("tests_dataset/trjtool/GB1/run00001.pdb").get_frame(
records)
frame.asAtoms[0].name = AtomName("XX")
trj = Trajectory(frame, True)
trj.push_trajectory_portion(datfile1)
with pytest.raises(TrajectoryException):
frame = PdbFile("tests_dataset/trjtool/GB1/run00001.pdb").get_frame(
records)
frame.asAtoms[0].delete()
trj = Trajectory(frame, True)
trj.push_trajectory_portion(datfile1)
def test_traj_size():
from pyxmolpp2.pdb import PdbFile, AlteredPdbRecords, StandardPdbRecords, RecordName, FieldName
from pyxmolpp2.trjtool import DatFile
from pyxmolpp2.trajectory import Trajectory
records = AlteredPdbRecords(StandardPdbRecords.instance())
records.alter_record(RecordName("ATOM"), FieldName("serial"), [7, 12])
frame = PdbFile("tests_dataset/trjtool/GB1/run00001.pdb").get_frame(
records)
assert frame.asAtoms.size > 0
trj = Trajectory(frame, True)
trj.push_trajectory_portion(
DatFile("tests_dataset/trjtool/GB1/run00001.dat"))
assert len(trj[0:10]) == 10
assert len(trj[0:10:10]) == 1
assert len(trj[0:10:100]) == 1
assert len(trj[0:100:10]) == 10
assert len(trj[0:100:-10]) == 0
assert len(trj[100:0:-1]) == 100
assert len(trj[0:100:-1]) == 0
def test_calc_sasa():
from pyxmolpp2.pdb import PdbFile
from pyxmolpp2.geometry import calc_sasa
from timeit import default_timer as timer
import numpy as np
import glob
for filename in sorted(glob.glob("tests_dataset/pdb/rcsb/*.pdb")):
frame = PdbFile(filename).get_frame()
ats = frame.asAtoms
radii = np.array([1.0] * ats.size)
coords = ats.toCoords
t1 = timer()
assert calc_sasa(coords, radii, 0.0, np.array([0],
dtype=np.intc)).size == 1
t2 = timer()
assert calc_sasa(coords, radii, 0.0,
np.array([0, 1, 2, 3, 4], dtype=np.intc)).size == 5
t3 = timer()
assert calc_sasa(coords, radii, 0.0).size == radii.size
t4 = timer()
assert calc_sasa(coords, radii, 0.0, n_samples=1).size == radii.size
T1, T3 = t2 - t1, t4 - t3
assert T3 > T1
def test_trajectory_integer_indexing():
from pyxmolpp2.pdb import PdbFile, AlteredPdbRecords, StandardPdbRecords, RecordName, FieldName
from pyxmolpp2.trjtool import DatFile
from pyxmolpp2.trajectory import Trajectory
records = AlteredPdbRecords(StandardPdbRecords.instance())
records.alter_record(RecordName("ATOM"), FieldName("serial"), [7, 12])
frame = PdbFile("tests_dataset/trjtool/GB1/run00001.pdb",
records).get_frame()
trj = Trajectory(frame, True)
trj.push_trajectory_portion(
DatFile("tests_dataset/trjtool/GB1/run00001.dat"))
n = trj.size
trj[-n]
trj[n - 1]
with pytest.raises(IndexError):
trj[n]
with pytest.raises(IndexError):
trj[-n - 1]
frame1 = trj[0]
frame2 = trj[-n]
assert frame1.index == frame2.index
def test_torsions():
from pyxmolpp2.polymer import TorsionAngleFactory, OutOfRangeResidue
from pyxmolpp2.pdb import PdbFile
from pyxmolpp2.geometry import Degrees
import glob
filenames = sorted(glob.glob("tests_dataset/pdb/rcsb/*.pdb"))
for filename in filenames:
frame = PdbFile(filename).get_frame()
for r in frame.asResidues:
try:
angles = [
TorsionAngleFactory.phi(r),
TorsionAngleFactory.psi(r),
TorsionAngleFactory.omega(r),
TorsionAngleFactory.chi1(r),
TorsionAngleFactory.chi2(r),
TorsionAngleFactory.chi3(r),
TorsionAngleFactory.chi4(r),
TorsionAngleFactory.chi5(r),
]
for angle in angles:
if angle:
try:
value = angle.value()
angle.set(value + Degrees(30), Degrees(0))
except Exception:
pass
except OutOfRangeResidue:
pass
def test_read_frame():
from pyxmolpp2.pdb import PdbFile
import glob
for filename in glob.glob("tests_dataset/pdb/rcsb/*.pdb"):
frame = PdbFile(filename).get_frame()
assert frame.asAtoms.size > 0
def test_read_frames():
from pyxmolpp2.pdb import PdbFile
import glob
for filename in glob.glob("tests_dataset/pdb/rcsb/*.pdb"):
frames = PdbFile(filename).get_frames()
assert len(frames) > 0
print(len(frames))
def test_rmsd():
from pyxmolpp2.polymer import AtomName
from pyxmolpp2.pdb import PdbFile
from pyxmolpp2.geometry import calc_rmsd, calc_alignment, calc_geom_center
import glob
filenames = sorted(glob.glob("tests_dataset/pdb/rcsb/*.pdb"))
for i in range(len(filenames) - 1):
frame_1 = PdbFile(filenames[i]).get_frame()
residues_1 = [
a.rId for a in frame_1.asChains[0].asAtoms.filter(
lambda a: a.name.str == "CA")
]
for j in range(i + 1, len(filenames)):
frame_2 = PdbFile(filenames[j]).get_frame()
residues_2 = [
a.rId for a in frame_2.asChains[0].asAtoms.filter(
lambda a: a.name.str == "CA")
]
common = set(residues_1) & set(residues_2)
ats1 = frame_1.asChains[0].asAtoms.filter(lambda a: (
a.id == a.residue[AtomName("CA")].id) and a.rId in common)
ats2 = frame_2.asChains[0].asAtoms.filter(lambda a: (
a.id == a.residue[AtomName("CA")].id) and a.rId in common)
assert ats1.size == len(common)
assert ats2.size == len(common)
assert ats1.size == ats2.size
assert len(ats1) > 3
assert len(ats2) > 3
aligment = calc_alignment(ats1.toCoords, ats2.toCoords)
not_aligned_rmsd = calc_rmsd(ats1.toCoords, ats2.toCoords)
aligned_rmsd = calc_rmsd(ats1.toCoords, ats2.toCoords, aligment)
def test_read_trjtool():
from pyxmolpp2.pdb import PdbFile, AlteredPdbRecords, StandardPdbRecords, RecordName, FieldName
from pyxmolpp2.trjtool import DatFile
records = AlteredPdbRecords(StandardPdbRecords.instance())
records.alter_record(RecordName("ATOM"), FieldName("serial"), [7,12])
frame = PdbFile("tests_dataset/trjtool/GB1/run00001.pdb",records).get_frame()
assert frame.asAtoms.size > 0
datfile = DatFile("tests_dataset/trjtool/GB1/run00001.dat")
assert datfile.n_frames == 1000
assert datfile.match(frame.asAtoms)
assert datfile.n_atoms_per_frame == frame.asAtoms.size
datfile.set_coordinates(0, frame.asAtoms, list(range(frame.asAtoms.size)))
def test_read_trjtool():
from pyxmolpp2.pdb import PdbFile, AlteredPdbRecords, StandardPdbRecords, RecordName, FieldName
from pyxmolpp2.amber import NetCDFTrajectoryFile
records = AlteredPdbRecords(StandardPdbRecords.instance())
records.alter_record(RecordName("ATOM"), FieldName("serial"), [7, 12])
frame = PdbFile("tests_dataset/amber/GB1_F30C_MTSL/box.pdb",
records).get_frame()
assert frame.asAtoms.size > 0
datfile = NetCDFTrajectoryFile(
"tests_dataset/amber/GB1_F30C_MTSL/GB1_F30C_MTSL_10_frames.nc")
assert datfile.n_frames == 10
assert datfile.match(frame.asAtoms)
assert datfile.n_atoms_per_frame == frame.asAtoms.size
datfile.set_coordinates(0, frame.asAtoms, list(range(frame.asAtoms.size)))
def test_traj_iteration():
from pyxmolpp2.pdb import PdbFile, AlteredPdbRecords, StandardPdbRecords, RecordName, FieldName
from pyxmolpp2.trjtool import DatFile
from pyxmolpp2.trajectory import Trajectory
records = AlteredPdbRecords(StandardPdbRecords.instance())
records.alter_record(RecordName("ATOM"), FieldName("serial"), [7, 12])
frame = PdbFile("tests_dataset/trjtool/GB1/run00001.pdb").get_frame(
records)
assert frame.asAtoms.size > 0
datfile1 = DatFile("tests_dataset/trjtool/GB1/run00001.dat")
datfile2 = DatFile("tests_dataset/trjtool/GB1/run00002.dat")
trj = Trajectory(frame, True)
trj.push_trajectory_portion(datfile1)
trj.push_trajectory_portion(datfile2)
assert trj.size == datfile1.n_frames + datfile2.n_frames
n = 0
stride = 50
for f in trj[::stride]:
r = f.asAtoms[0].r
n += 1
assert trj.size // stride == n
n = 0
stride = 1
ats = frame.asResidues[0].asAtoms
trj.set_update_list(ats)
for f in trj[::stride]:
n += 1
assert trj.size // stride == n
def traj_from_dir(path: str,
reference_pdb: Union[str, None] = None,
stride: int = 1,
first: int = 1,
last: int = 1,
pattern: str = "run%05d",
subdir="5_run",
filetype: str = "dat") \
-> Tuple[pyxmolpp2.trajectory.Trajectory, pyxmolpp2.polymer.Frame]:
import os
from tqdm import tqdm
from pyxmolpp2.trajectory import Trajectory
from pyxmolpp2.trjtool import DatFile
from pyxmolpp2.amber import NetCDFTrajectoryFile
from pyxmolpp2.pdb import PdbFile, \
AlteredPdbRecords, \
StandardPdbRecords, \
RecordName, \
FieldName
if reference_pdb is None:
for pdb in [
os.path.join(path, "5_run", "run00001.pdb"),
os.path.join(path, "5_run", "step-1.pdb"),
os.path.join(path, "ref", "ref.pdb")
]:
if os.path.isfile(pdb):
reference_pdb = pdb
break
if reference_pdb is None:
raise RuntimeError("Reference pdb is not specified")
if not os.path.isfile(reference_pdb):
if not os.path.isfile(os.path.join(path, reference_pdb)):
raise RuntimeError("Reference pdb is not found: `%s`" %
reference_pdb)
reference_pdb = os.path.join(path, reference_pdb)
altered_records = AlteredPdbRecords(StandardPdbRecords.instance())
altered_records.alter_record(RecordName("ATOM"), FieldName("serial"),
[7, 12])
ref_frame = PdbFile(reference_pdb, altered_records).get_frame()
coordinate_files = [
os.path.join(path, subdir, "%s.%s" % ((pattern % i), filetype))
for i in range(first, last + 1, stride)
]
traj = Trajectory(ref_frame, check_portions_to_match_reference=True)
if filetype == "dat":
portion_type = DatFile # type: Callable[[str], pyxmolpp2.trajectory.TrajectoryPortion]
elif filetype == "pdb":
portion_type = lambda filename: PdbFile(filename, altered_records
) # noqa: E731
elif filetype == "nc":
portion_type = NetCDFTrajectoryFile
else:
raise RuntimeError("Unknown trajectory coordinate file type `%s`" %
filetype)
for coordinate_file in tqdm(coordinate_files,
leave=False,
desc="checking input files"):
if not os.access(coordinate_file, os.O_RDONLY):
raise RuntimeError("Can't access file `%s`" % coordinate_file)
traj.push_trajectory_portion(portion_type(coordinate_file))
return traj, ref_frame
def test_read_empty_file():
from pyxmolpp2.pdb import PdbFile
import os
assert PdbFile(os.devnull).get_frame().asChains.size == 0
def test_read_non_existent_file():
from pyxmolpp2.pdb import PdbFile, PdbException
with pytest.raises(PdbException):
PdbFile("does_not_exists.pdb")
"""
import pyxmolpp2
from pyxmolpp2.pdb import AlteredPdbRecords, StandardPdbRecords, FieldName, RecordName, PdbFile
import os
# Create PDB records description based on standard records
altered_records = AlteredPdbRecords(
pyxmolpp2.pdb.StandardPdbRecords.instance())
# Expand ATOM.serial record to columns 7-12
altered_records.alter_record(RecordName("ATOM"), FieldName("serial"), [7, 12])
pdb_filename = os.path.join(os.environ["TEST_DATA_PATH"],
"trjtool/GB1/run00001.pdb")
# Define a PDB file with altered records fields layout
pdb_file = PdbFile(pdb_filename, altered_records)
# Read all frames (i.e. MODELS) from PDB
frames = pdb_file.get_frames()
# Print some info about frames
print("PDB contains %d MODELS: " % len(frames))
for frame in frames:
print("\tMODEL #%d contains %d molecules, total %d atoms" %
(frame.index, frame.asChains.size, frame.asAtoms.size))
# Write first model to PDB file using altered records
frames[0].to_pdb("out.pdb", altered_records)