def test_intrachain_inter_residue_atomic_distance():
# A custom version of NTL9 is needed, since we want to have multiple protein chains
protein_groups_residues = [[0, 1, 2, 3, 4, 5, 6, 7, 8, 9],
[10, 11, 12, 13, 14, 15, 16, 17, 18, 19],
[20, 21, 22, 23, 24, 25, 26, 27, 28, 29],
[30, 31, 32, 33, 34, 35, 36, 37, 38, 39],
[40, 41, 42, 43, 44, 45, 46, 47, 48, 49]]
pdb_filename = os.path.join(soursop.get_data('test_data'), 'ntl9.pdb')
traj_filename = os.path.join(soursop.get_data('test_data'),
'ntl9.xtc') # ntl9 has 56 residues
trajectory = sstrajectory.SSTrajectory(
trajectory_filename=traj_filename,
pdb_filename=pdb_filename,
protein_grouping=protein_groups_residues)
for protein_group in itertools.combinations(range(
len(protein_groups_residues)),
r=2):
protein_a, protein_b = protein_group
a_residues = protein_groups_residues[protein_a]
b_residues = protein_groups_residues[protein_b]
residue_a = random.randint(0, len(a_residues) - 1)
residue_b = random.randint(0, len(b_residues) - 1)
distances = trajectory.get_interchain_distance(protein_a, protein_b,
residue_a, residue_b)
assert len(distances) == len(a_residues)
def test_get_intra_chain_distance_map_protein_groups_with_residue_indices():
# Note that the residues for the resID1 and resID2 indices are with respect to the residues of the protein chain
# and not the full protein itself.
protein_groups_residues = [[0, 1, 2, 3, 4, 5, 6, 7, 8],
[10, 11, 12, 13, 14, 15, 16, 17, 18],
[20, 21, 22, 23, 24, 25, 26, 27, 28],
[30, 31, 32, 33, 34, 35, 36, 37, 38],
[40, 41, 42, 43, 44, 45, 46, 47, 48]]
pdb_filename = os.path.join(soursop.get_data('test_data'), 'ntl9.pdb')
traj_filename = os.path.join(soursop.get_data('test_data'), 'ntl9.xtc') # ntl9 has 56 residues
trajectory = sstrajectory.SSTrajectory(trajectory_filename=traj_filename,
pdb_filename=pdb_filename,
protein_grouping=protein_groups_residues)
# select pairwise protein ids (no repetitions).
for protein_group in itertools.combinations(range(len(protein_groups_residues)), r=2):
protein_a, protein_b = protein_group
# now, let's randomly choose a set of residues to select for `protein_a` and `protein_b`
num_residues_a = random.randint(1, len(protein_groups_residues[protein_a]))
num_residues_b = random.randint(1, len(protein_groups_residues[protein_b]))
protein_a_residues = protein_groups_residues[protein_a]
a_residues = list(sorted(random.sample(protein_a_residues, num_residues_a)))
a_residues = [(r - protein_a_residues[0]) for r in a_residues] # offset by the starting residue number
protein_b_residues = protein_groups_residues[protein_b]
b_residues = list(sorted(random.sample(protein_b_residues, num_residues_b)))
b_residues = [(r - protein_b_residues[0]) for r in b_residues] # offset by the starting residue number
distance_map, stddev_map = trajectory.get_interchain_distance_map(protein_a, protein_b)
assert distance_map.shape == stddev_map.shape
def test_get_interchain_distance_failing_atom():
protein_groups = [[0, 1, 2, 3, 4], [5, 6, 7, 8, 9], [10, 11, 12, 13, 14]]
pdb_filename = os.path.join(soursop.get_data('test_data'), 'ntl9.pdb')
traj_filename = os.path.join(soursop.get_data('test_data'),
'ntl9.xtc') # ntl9 has 56 residues
trajectory = sstrajectory.SSTrajectory(trajectory_filename=traj_filename,
pdb_filename=pdb_filename,
protein_grouping=protein_groups)
mode = 'atom'
atoms1 = ['X', 'CA']
atoms2 = atoms1[::-1]
for protein_group in itertools.combinations(range(len(protein_groups)),
r=2):
protein_a, protein_b = protein_group
# There appears to be an issue where R1 > R2 - the calculation crashes for sidechain-heavy.
# See `test_get_interchain_distance`
R1 = 0 #random.choice(range(len(protein_groups[protein_a])))
R2 = 1 #random.choice(range(len(protein_groups[protein_b])))
for A1, A2 in zip(atoms1, atoms2):
with pytest.raises(SSException):
trajectory.get_interchain_distance(protein_a, protein_b, R1,
R2, A1, A2, mode)
def test_read_in_compare_trajectories(GS6_CO):
pdb_filename = os.path.join(soursop.get_data('test_data'), 'gs6.pdb')
traj_filename = os.path.join(soursop.get_data('test_data'), 'gs6.xtc')
trajectory = sstrajectory.SSTrajectory(trajectory_filename=traj_filename,
pdb_filename=pdb_filename)
assert np.allclose(trajectory.traj.xyz, GS6_CO.traj.xyz)
def test_read_in_trajectory_pdblead(GS6_CO):
pdb_filename = os.path.join(soursop.get_data('test_data'), 'gs6.pdb')
traj_filename = os.path.join(soursop.get_data('test_data'), 'gs6.xtc')
traj = sstrajectory.SSTrajectory(pdb_filename=pdb_filename, trajectory_filename=traj_filename, pdblead=True)
# Since we're using the PDB as an initial frame, the number of frames should have increased by 1.
assert len(traj) == len(GS6_CO) + 1
def test_cap_DSSP():
"""
Tests DSSP (and hence R1/R2 selection) works
"""
test_data_dir = soursop.get_data('test_data')
pdb_files = ['ACE_NME_multichain', 'ACE_NME_start_at_5']
for cap_name in pdb_files:
cap_path = os.path.join(test_data_dir, 'cap_tests', '{}.pdb'.format(cap_name))
cap_trajectory = sstrajectory.SSTrajectory(cap_path, cap_path)
def test_read_in_protein_grouping_multiple():
protein_groups = [[0, 1, 2], [3, 4, 5], [6, 7, 8]]
pdb_filename = os.path.join(soursop.get_data('test_data'), 'ntl9.pdb')
traj_filename = os.path.join(soursop.get_data('test_data'), 'ntl9.xtc') # ntl9 has 56 residues
trajectory = sstrajectory.SSTrajectory(trajectory_filename=traj_filename,
pdb_filename=pdb_filename,
protein_grouping=protein_groups)
# verify that we have loaded the number of proteins expected
assert trajectory.n_proteins == len(protein_groups)
def test_read_in_protein_grouping_simple():
protein_groups = [[0]]
pdb_filename = os.path.join(soursop.get_data('test_data'), 'gs6.pdb')
traj_filename = os.path.join(soursop.get_data('test_data'), 'gs6.xtc')
trajectory = sstrajectory.SSTrajectory(trajectory_filename=traj_filename,
pdb_filename=pdb_filename,
protein_grouping=protein_groups)
# verify that we have loaded the number of proteins expected
assert trajectory.num_proteins == len(protein_groups)
def test_read_in_protein_grouping_invalid_residues():
protein_groups = [[1000, 1001, 1002], [1003, 1004, 1005], [1006, 1007, 1008]]
pdb_filename = os.path.join(soursop.get_data('test_data'), 'ntl9.pdb')
traj_filename = os.path.join(soursop.get_data('test_data'), 'ntl9.xtc') # ntl9 has 56 residues
trajectory = sstrajectory.SSTrajectory(trajectory_filename=traj_filename,
pdb_filename=pdb_filename,
protein_grouping=protein_groups)
# Since this is a failing but non-disruptive test (i.e. no Exceptions), we
# check the number of proteins which should be 0.
assert trajectory.n_proteins == 0
def test_read_in_protein_grouping_multiple_mixed_order():
# TODO: This test passes - it shouldn't. Look into this further.
protein_groups = [[1, 2, 0], [10, 3, 7], [11, 1, 3]]
pdb_filename = os.path.join(soursop.get_data('test_data'), 'ntl9.pdb')
traj_filename = os.path.join(soursop.get_data('test_data'), 'ntl9.xtc') # ntl9 has 56 residues
trajectory = sstrajectory.SSTrajectory(trajectory_filename=traj_filename,
pdb_filename=pdb_filename,
protein_grouping=protein_groups)
# verify that we have loaded the number of proteins expected
assert trajectory.n_proteins == len(protein_groups)
def test_cap_BBSEG():
"""
Tests DSSP (and hence R1/R2 selection) works
"""
for CN in CAPNAMES:
CT = sstrajectory.SSTrajectory(
"%s/cap_tests/%s.pdb" % (test_data_dir, CN),
"%s/cap_tests/%s.pdb" % (test_data_dir, CN))
for CP in CT.proteinTrajectoryList:
assert len(CP.get_secondary_structure_DSSP()[0]) == 6
def test_get_intra_chain_distance_map_protein_groups():
protein_groups = [[0, 1, 2, 3, 4], [5, 6, 7, 8, 9], [10, 11, 12, 13, 14]]
pdb_filename = os.path.join(soursop.get_data('test_data'), 'ntl9.pdb')
traj_filename = os.path.join(soursop.get_data('test_data'), 'ntl9.xtc') # ntl9 has 56 residues
trajectory = sstrajectory.SSTrajectory(trajectory_filename=traj_filename,
pdb_filename=pdb_filename,
protein_grouping=protein_groups)
for protein_group in itertools.combinations(range(len(protein_groups)), r=2):
protein_a, protein_b = protein_group
distance_map, stddev_map = trajectory.get_interchain_distance_map(protein_a, protein_b)
assert distance_map.shape == stddev_map.shape
assert np.count_nonzero(distance_map) == len(distance_map.flatten()) # since the residue indices are unique
def test_cap():
"""
Test caps assignment works
"""
for CN in CAPNAMES:
CT = sstrajectory.SSTrajectory(
"%s/cap_tests/%s.pdb" % (test_data_dir, CN),
"%s/cap_tests/%s.pdb" % (test_data_dir, CN))
for CP in CT.proteinTrajectoryList:
if CP.ccap:
assert CN in CCAP
if CP.ncap:
assert CN in NCAP
def test_get_interchain_distance_invalid_protein_ids():
protein_groups = [[0, 1, 2, 3, 4], [5, 6, 7, 8, 9], [10, 11, 12, 13, 14]]
pdb_filename = os.path.join(soursop.get_data('test_data'), 'ntl9.pdb')
traj_filename = os.path.join(soursop.get_data('test_data'), 'ntl9.xtc') # ntl9 has 56 residues
trajectory = sstrajectory.SSTrajectory(trajectory_filename=traj_filename,
pdb_filename=pdb_filename,
protein_grouping=protein_groups)
R1 = 0
R2 = 1
A1 = 'CA'
A2 = 'CA'
modes = 'atom,ca,closest,closest-heavy,sidechain,sidechain-heavy'.split(',')
protein_a = 100
protein_b = 101
for mode in modes:
with pytest.raises(SSException):
trajectory.get_interchain_distance(protein_a, protein_b, R1, R2, A1, A2, mode)
def test_get_interchain_distance():
protein_groups = [[0, 1, 2, 3, 4], [5, 6, 7, 8, 9], [10, 11, 12, 13, 14]]
pdb_filename = os.path.join(soursop.get_data('test_data'), 'ntl9.pdb')
traj_filename = os.path.join(soursop.get_data('test_data'), 'ntl9.xtc') # ntl9 has 56 residues
trajectory = sstrajectory.SSTrajectory(trajectory_filename=traj_filename,
pdb_filename=pdb_filename,
protein_grouping=protein_groups)
for protein_group in itertools.combinations(range(len(protein_groups)), r=2):
protein_a, protein_b = protein_group
# There appears to be an issue where R1 > R2 - the calculation crashes for sidechain-heavy.
R1 = 0 #random.choice(range(len(protein_groups[protein_a])))
R2 = 1 #random.choice(range(len(protein_groups[protein_b])))
A1 = 'CA'
A2 = 'CA'
modes = 'atom,ca,closest,closest-heavy,sidechain,sidechain-heavy'.split(',')
for mode in modes:
distances = trajectory.get_interchain_distance(protein_a, protein_b, R1, R2, A1, A2, mode)
assert len(distances) > 0
def test_get_interchain_distance_invalid_mode():
protein_groups = [[0, 1, 2, 3, 4], [5, 6, 7, 8, 9], [10, 11, 12, 13, 14]]
pdb_filename = os.path.join(soursop.get_data('test_data'), 'ntl9.pdb')
traj_filename = os.path.join(soursop.get_data('test_data'), 'ntl9.xtc') # ntl9 has 56 residues
trajectory = sstrajectory.SSTrajectory(trajectory_filename=traj_filename,
pdb_filename=pdb_filename,
protein_grouping=protein_groups)
mode = 'unknown'
for protein_group in itertools.combinations(range(len(protein_groups)), r=2):
protein_a, protein_b = protein_group
# There appears to be an issue where R1 > R2 - the calculation crashes for sidechain-heavy.
R1 = 0 #random.choice(range(len(protein_groups[protein_a])))
R2 = 1 #random.choice(range(len(protein_groups[protein_b])))
A1 = 'CA'
A2 = 'CA'
with pytest.raises(SSException):
trajectory.get_interchain_distance(protein_a, protein_b, R1, R2, A1, A2, mode)
def test_get_interchain_distance_failing_residues():
protein_groups = [[0, 1, 2, 3, 4], [5, 6, 7, 8, 9], [10, 11, 12, 13, 14]]
pdb_filename = os.path.join(soursop.get_data('test_data'), 'ntl9.pdb')
traj_filename = os.path.join(soursop.get_data('test_data'), 'ntl9.xtc') # ntl9 has 56 residues
trajectory = sstrajectory.SSTrajectory(trajectory_filename=traj_filename,
pdb_filename=pdb_filename,
protein_grouping=protein_groups)
residues1 = [0, 100]
residues2 = residues1[::-1]
A1 = 'CA'
A2 = 'CA'
modes = 'atom,ca,closest,closest-heavy,sidechain,sidechain-heavy'.split(',')
for protein_group in itertools.combinations(range(len(protein_groups)), r=2):
protein_a, protein_b = protein_group
for mode in modes:
for R1, R2 in zip(residues1, residues2):
with pytest.raises(SSException):
trajectory.get_interchain_distance(protein_a, protein_b, R1, R2, A1, A2, mode)
def GMX_2CHAINS(request):
GMX_2CHAINS = sstrajectory.SSTrajectory(
"%s/%s" % (test_data_dir, GROMACS_2_CHAINS[1]),
"%s/%s" % (test_data_dir, GROMACS_2_CHAINS[0]))
return GMX_2CHAINS
def test_read_in_no_topology_xtc():
traj_filename = os.path.join(soursop.get_data('test_data'), 'gs6.xtc')
with pytest.raises(SSException):
sstrajectory.SSTrajectory(trajectory_filename=traj_filename)
def NTL9_CO(request):
topology_path = os.path.join(test_data_dir, NTL9_FILES[0])
trajectory_path = os.path.join(test_data_dir, NTL9_FILES[1])
NTL9_CO = sstrajectory.SSTrajectory(trajectory_path, topology_path)
return NTL9_CO
def NTL9_CP(request):
topology_path = os.path.join(test_data_dir, NTL9_FILES[0])
trajectory_path = os.path.join(test_data_dir, NTL9_FILES[1])
NTL9_CO = sstrajectory.SSTrajectory(trajectory_path, topology_path)
NTL9_CP = NTL9_CO.proteinTrajectoryList[0]
return NTL9_CP
def GS6_CP(request):
topology_path = os.path.join(test_data_dir, GS6_FILES[0])
trajectory_path = os.path.join(test_data_dir, GS6_FILES[1])
GS6_CO = sstrajectory.SSTrajectory(trajectory_path, topology_path)
GS6_CP = GS6_CO.proteinTrajectoryList[0]
return GS6_CP
def GS6_CO(request):
topology_path = os.path.join(test_data_dir, GS6_FILES[0])
trajectory_path = os.path.join(test_data_dir, GS6_FILES[1])
GS6_CO = sstrajectory.SSTrajectory(trajectory_path, topology_path)
return GS6_CO
def test_read_in_no_trajectory_and_no_topology():
with pytest.raises(SSException):
sstrajectory.SSTrajectory()
def test_read_in_no_trajectory_and_no_topology_but_use_custom_trajectory(
GS6_CO):
trajectory = GS6_CO.traj
sstrajectory.SSTrajectory(TRJ=trajectory)
def test_trajectory_initialization_debug():
pdb_filename = os.path.join(soursop.get_data('test_data'), 'gs6.pdb')
traj_filename = os.path.join(soursop.get_data('test_data'), 'gs6.xtc')
sstrajectory.SSTrajectory(pdb_filename=pdb_filename,
trajectory_filename=traj_filename,
debug=True)
def test_read_in_no_trajectory():
pdb_filename = os.path.join(soursop.get_data('test_data'), 'gs6.pdb')
with pytest.raises(SSException):
sstrajectory.SSTrajectory(pdb_filename=pdb_filename)
def test_read_in_no_topology_dcd():
"""The `SSTrajectory.__init__` references that `.dcd` files are supported too."""
traj_filename = os.path.join(soursop.get_data('test_data'), 'gs6.dcd')
with pytest.raises(SSException):
sstrajectory.SSTrajectory(trajectory_filename=traj_filename)
