def test_pipes():
ref = PdbFile(os.environ["TEST_DATA_PATH"] +
"/trjtool/GB1/run00001.pdb").frames()[0]
traj = Trajectory(ref)
traj.extend(
TrjtoolDatFile(os.environ["TEST_DATA_PATH"] +
"/trjtool/GB1/run00001.dat"))
first_geom_center = XYZ(8.422286, 0.967190, -13.856332)
for frame in traj:
assert frame.coords.mean().distance(first_geom_center) < 0.001
break
del frame
for frame in traj | AngstromsToNanometers():
assert frame.coords.mean().distance(first_geom_center * 10) < 0.001
break
del frame
for frame in traj | Align(by=lambda a: True):
assert frame.coords.mean().distance(first_geom_center) < 0.001
del frame
for frame in traj[0:10] | Align(by=lambda a: True):
assert frame.coords.mean().distance(first_geom_center) < 0.001
del frame
for frame in traj[0:10] | Align(
by=lambda a: True) | AngstromsToNanometers():
assert frame.coords.mean().distance(first_geom_center * 10) < 0.001
del frame
def test_trajectory_integer_indexing():
from pyxmolpp2 import PdbFile, TrjtoolDatFile as DatFile, Trajectory
frame = PdbFile(os.environ["TEST_DATA_PATH"] +
"/trjtool/GB1/run00001.pdb").frames()[0]
trj = Trajectory(frame)
trj.extend(
DatFile(os.environ["TEST_DATA_PATH"] + "/trjtool/GB1/run00001.dat"))
n = trj.n_frames
trj[-n]
trj[n - 1]
with pytest.raises(IndexError):
trj[n]
with pytest.raises(IndexError):
trj[-n - 1]
frame1 = trj[0]
frame2 = trj[-n]
frame3 = trj[0]
assert frame1 != frame2
assert frame1 != frame3
def test_traj_iteration():
from pyxmolpp2 import PdbFile, TrjtoolDatFile as DatFile, Trajectory
frame = PdbFile(os.environ["TEST_DATA_PATH"] +
"/trjtool/GB1/run00001.pdb").frames()[0]
assert frame.atoms.size > 0
datfile1 = DatFile(os.environ["TEST_DATA_PATH"] +
"/trjtool/GB1/run00001.dat")
datfile2 = DatFile(os.environ["TEST_DATA_PATH"] +
"/trjtool/GB1/run00002.dat")
trj = Trajectory(frame)
trj.extend(datfile1)
trj.extend(datfile2)
assert trj.n_frames == datfile1.n_frames() + datfile2.n_frames()
n = 0
stride = 50
for f in trj[::stride]:
r = f.atoms[0].r
n += 1
assert trj.n_frames // stride == n
def test_read_frames():
from pyxmolpp2 import PdbFile
import glob
for filename in glob.glob(os.environ["TEST_DATA_PATH"] +
"/pdb/rcsb/*.pdb"):
frames = PdbFile(filename).frames()
assert len(frames) > 0
print(len(frames))
def test_trajectory_bad_n_atoms():
from pyxmolpp2 import PdbFile, TrjtoolDatFile as DatFile, Trajectory
frame = PdbFile(os.environ["TEST_DATA_PATH"] +
"/pdb/rcsb/1PGB.pdb").frames()[0]
trj = Trajectory(frame)
with pytest.raises(RuntimeError):
trj.extend(
DatFile(os.environ["TEST_DATA_PATH"] +
"/trjtool/GB1/run00001.dat"))
def test_writer():
from pyxmolpp2 import PdbFile, XtcWriter, Translation, XYZ
xtc_writer = XtcWriter("test.xtc", 1000)
frame = PdbFile(os.environ["TEST_DATA_PATH"] +
"/gromacs/xtc/1am7_protein.pdb").frames()[0]
for i in range(10):
frame.cell.scale_by(1.2)
frame.coords.apply(Translation(XYZ(1, 0, 0)))
xtc_writer.write(frame)
del xtc_writer
os.remove("test.xtc")
def test_traj_exceptions():
from pyxmolpp2 import PdbFile, TrjtoolDatFile as DatFile, Trajectory
datfile1 = DatFile(os.environ["TEST_DATA_PATH"] +
"/trjtool/GB1/run00001.dat")
# atom name is different
with pytest.raises(RuntimeError):
frame = PdbFile(os.environ["TEST_DATA_PATH"] +
"/trjtool/GB1/run00001.pdb").frames()[0]
frame.atoms[0].name = "XX"
trj = Trajectory(frame)
trj.extend(datfile1)
# atom number of atoms is different
with pytest.raises(RuntimeError):
frame = PdbFile(os.environ["TEST_DATA_PATH"] +
"/trjtool/GB1/run00001.pdb").frames()[0]
frame.atoms[0].erase()
trj = Trajectory(frame)
trj.extend(datfile1)
def test_read_trjtool():
from pyxmolpp2 import PdbFile, TrjtoolDatFile
frame = PdbFile(os.environ["TEST_DATA_PATH"] + "/trjtool/GB1/run00001.pdb").frames()[0]
assert frame.atoms.size > 0
datfile = TrjtoolDatFile(os.environ["TEST_DATA_PATH"] + "/trjtool/GB1/run00001.dat")
assert datfile.n_frames() == 1000
assert datfile.n_atoms() == frame.atoms.size
datfile.advance(0)
datfile.read_frame(0, frame)
def test_read_netcdf():
from pyxmolpp2 import PdbFile, AmberNetCDF
frame = PdbFile(os.environ["TEST_DATA_PATH"] +
"/amber/GB1_F30C_MTSL/box.pdb").frames()[0]
assert frame.atoms.size > 0
datfile = AmberNetCDF(os.environ["TEST_DATA_PATH"] +
"/amber/GB1_F30C_MTSL/GB1_F30C_MTSL_10_frames.nc")
assert datfile.n_frames() == 10
assert datfile.n_atoms() == frame.atoms.size
datfile.read_frame(0, frame)
def test_read_one_file():
from pyxmolpp2 import PdbFile, GromacsXtcFile
frame = PdbFile(os.environ["TEST_DATA_PATH"] +
"/gromacs/xtc/1am7_protein.pdb").frames()[0]
assert frame.atoms.size > 0
inp = GromacsXtcFile(
os.environ["TEST_DATA_PATH"] + "/gromacs/xtc/1am7_corrected.xtc", 51)
assert inp.n_frames() == 51
assert inp.n_atoms() == frame.atoms.size
inp.advance(0)
inp.read_frame(0, frame)
def test_tqdm():
from tqdm import tqdm
ref = PdbFile(os.environ["TEST_DATA_PATH"] +
"/trjtool/GB1/run00001.pdb").frames()[0]
traj = Trajectory(ref)
traj.extend(
TrjtoolDatFile(os.environ["TEST_DATA_PATH"] +
"/trjtool/GB1/run00001.dat"))
for _ in tqdm(traj):
pass
del _
for _ in tqdm(traj[::2]):
pass
del _
def test_unit_cell_scale():
ref = PdbFile(os.environ["TEST_DATA_PATH"] +
"/trjtool/GB1/run00001.pdb").frames()[0]
traj = Trajectory(ref)
traj.extend(
TrjtoolDatFile(os.environ["TEST_DATA_PATH"] +
"/trjtool/GB1/run00002.dat"))
volumes = []
for frame in traj[::100] | ScaleUnitCell(
os.environ["TEST_DATA_PATH"] +
"/trjtool/GB1/summary/summary.VOLUME"):
volumes += [frame.cell.volume]
assert np.allclose(volumes, [
112190.6817, 111667.0223, 112060.3447, 112010.4530, 111899.7620,
112420.6936, 111794.6408, 112093.9081, 111655.2990, 111978.6604
])
def test_read_frame():
from pyxmolpp2 import PdbFile, UnitCell, Degrees
cells = [
UnitCell(36.633, 36.633, 79.254, Degrees(90), Degrees(90),
Degrees(120.00)),
UnitCell(50.840, 42.770, 28.950, Degrees(90), Degrees(90.00),
Degrees(90.00)),
UnitCell(52.323, 79.498, 52.406, Degrees(90), Degrees(90.14),
Degrees(90.00)),
UnitCell(25.037, 37.194, 49.217, Degrees(90), Degrees(90.00),
Degrees(90.00)),
]
for pdb_code, cell in zip(['1PGB', '1UBQ', '5BMG', '5BMH'], cells):
frames = PdbFile(os.environ["TEST_DATA_PATH"] +
f"/pdb/rcsb/{pdb_code}.pdb").frames()
for frame in frames:
for i in range(3):
assert cell[i].distance(frame.cell[i]) == pytest.approx(0)
assert frame.atoms.size > 0
def test_traj_size():
from pyxmolpp2 import PdbFile, TrjtoolDatFile as DatFile, Trajectory
frame = PdbFile(os.environ["TEST_DATA_PATH"] +
"/trjtool/GB1/run00001.pdb").frames()[0]
assert frame.atoms.size > 0
trj = Trajectory(frame)
trj.extend(
DatFile(os.environ["TEST_DATA_PATH"] + "/trjtool/GB1/run00001.dat"))
assert sum([1 for _ in trj[0:10]]) == 10
assert sum([1 for _ in trj[0:10:10]]) == 1
assert sum([1 for _ in trj[0:10:100]]) == 1
assert sum([1 for _ in trj[0:100:10]]) == 10
assert sum([1 for _ in trj[0:-1000]]) == 0
assert sum([1 for _ in trj[-100:]]) == 100
assert sum([1 for _ in trj[:-100]]) == 900
with pytest.raises(TypeError):
trj[::-1]
def test_calc_sasa():
from pyxmolpp2 import PdbFile, calc_sasa
from timeit import default_timer as timer
import numpy as np
import glob
for filename in sorted(glob.glob(os.environ["TEST_DATA_PATH"] + "/pdb/rcsb/*.pdb")):
frame = PdbFile(filename).frames()[0]
coords = frame.coords.values
radii = np.array([1.0] * frame.atoms.size)
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_read_non_existent_file():
from pyxmolpp2 import PdbFile
with pytest.raises(RuntimeError):
PdbFile("does_not_exists.pdb")
from ccr_scripts.save_utils import fit_and_save_crosscorr_func
from ccr_scripts.process_utils.fit import fit_corrfunc_amp_unfixed
if __name__ == '__main__':
parser = argparse.ArgumentParser(description='fit crosscorr')
parser.add_argument(
'--path-to-crosscorr-csv',
required=True,
)
parser.add_argument('--limit', default=None, type=int)
parser.add_argument('--path-to-reference-pdb')
parser.add_argument('--output-directory', default="./")
args = parser.parse_args()
bounds = [
([[0, 0.001, 0, 0.01, 0, 0.1, 0, 1], [1, 0.01, 1, 0.1, 1, 1, 1, 10]]),
]
scales = [1]
ref = PdbFile(args.path_to_reference_pdb).frames()[0]
residue_name_map = {r.id.serial: r.name for r in ref.residues}
fit_and_save_crosscorr_func(args.path_to_crosscorr_csv,
bounds=bounds,
scales=scales,
residue_name_map=residue_name_map,
limit=args.limit,
output_directory=args.output_directory,
fit_func=fit_corrfunc_amp_unfixed)
parser.add_argument('--trajectory-length', required=True, type=int)
parser.add_argument('--frames-per-trajectory-file', type=int, default=1000)
parser.add_argument('--vectors', required=True)
parser.add_argument('--output-directory', default=".")
args = parser.parse_args()
trj_reader_dict = {
"dat": TrjtoolDatFile,
"nc": AmberNetCDF,
"xtc": XtcFileReaderWrapper(args.frames_per_trajectory_file)
}
subdir_prefix = {"one_residue": "", "next_residue": "p1"}
# load trajectory
traj = Trajectory(PdbFile(args.path_to_reference_pdb).frames()[0])
for ind in tqdm(range(1, args.trajectory_length + 1), desc="traj_reading"):
fname = "{pattern}.{filetype}".format(pattern=args.pattern,
filetype=args.filetype)
traj.extend(trj_reader_dict[args.filetype](os.path.join(
args.path_to_trajectory, fname % (ind))))
# define processes for writing of vectors coordinates
processes = []
for vector in args.vectors.split(","):
atom_pair, residue_mode = vector.split("_", 1)
atom_1, atom_2 = atom_pair.split("-")
subdir = f"{vector_name_to_basename(atom_pair)}{subdir_prefix[residue_mode]}"
processes.append(
WriteVectorsToCsvWithMetadata(
atom_pairs_selector(atom_1.split("|"),
def test_read_empty_file():
from pyxmolpp2 import PdbFile
import os
assert len(PdbFile(os.devnull).frames()) == 0