def test_get_residue_masks(array):
SAMPLE_SIZE = 100
np.random.seed(0)
indices = np.random.randint(0, array.array_length(), SAMPLE_SIZE)
masks = struc.get_residue_masks(array, indices)
for index, mask in zip(indices, masks):
ref_mask = array.res_id == array.res_id[index]
assert mask.tolist() == ref_mask.tolist()
def find_leaflets(structure,
head_atom_mask,
cutoff_distance=15.0,
periodic=False):
"""
Identify which lipids molecules belong to the same lipid bilayer
leaflet.
Parameters
----------
structure : AtomArray, shape=(n,)
The structure containing the membrane.
May also include other molecules, e.g. water or an embedded
protein.
head_atom_mask : ndarray, dtype=bool, shape=(n,)
A boolean mask that selects atoms from `structure` that
represent lipid head groups.
cutoff_distance : float, optional
When the distance of two head groups is larger than this value,
they are not (directly) connected in the same leaflet.
periodic : bool, optional,
If true, periodic boundary conditions are considered.
This requires that `structure` has an associated `box`.
Returns
-------
leaflets : ndarray, dtype=bool, shape=(m,n)
Multiple boolean masks, one for each identified leaflet.
Each masks indicates which atoms of the input `structure`
are in the leaflet.
"""
cell_list = struc.CellList(structure,
cell_size=cutoff_distance,
selection=head_atom_mask,
periodic=periodic)
adjacency_matrix = cell_list.create_adjacency_matrix(cutoff_distance)
graph = nx.Graph(adjacency_matrix)
head_leaflets = [
sorted(c) for c in nx.connected_components(graph)
# A leaflet cannot consist of a single lipid
# This also removes all entries
# for atoms not in 'head_atom_mask'
if len(c) > 1
]
# 'leaflets' contains indices to head atoms
# Broadcast each head atom index to all atoms in its corresponding
# residue
leaflet_masks = np.empty((len(head_leaflets), structure.array_length()),
dtype=bool)
for i, head_leaflet in enumerate(head_leaflets):
leaflet_masks[i] = struc.get_residue_masks(structure, head_leaflet) \
.any(axis=0)
return leaflet_masks
def test_get_residue_starts_for(array):
SAMPLE_SIZE = 100
np.random.seed(0)
indices = np.random.randint(0, array.array_length(), SAMPLE_SIZE)
ref_starts = np.array([
np.where(mask)[0][0]
for mask in struc.get_residue_masks(array, indices)
])
test_starts = struc.get_residue_starts_for(array, indices)
assert test_starts.tolist() == ref_starts.tolist()
import biotite.structure.io.mmtf as mmtf
import biotite.structure.graphics as graphics
import biotite.database.rcsb as rcsb
# Structure of a DNA double helix
mmtf_file = mmtf.MMTFFile.read(rcsb.fetch("1qxb", "mmtf"))
structure = mmtf.get_structure(mmtf_file, model=1, include_bonds=True)
nucleotides = structure[struc.filter_nucleotides(structure)]
# Choose one adenine-thymine and one guanine-cytosine base pair
base_pairs = struc.base_pairs(nucleotides)
for i, j in base_pairs:
if (nucleotides.res_name[i], nucleotides.res_name[j]) == ("DG", "DC"):
guanine, cytosine = [nucleotides[mask] for mask
in struc.get_residue_masks(nucleotides, [i, j])]
break
for i, j in base_pairs:
if (nucleotides.res_name[i], nucleotides.res_name[j]) == ("DA", "DT"):
adenine, thymine = [nucleotides[mask] for mask
in struc.get_residue_masks(nucleotides, [i, j])]
break
pairs = [(guanine, cytosine), (adenine, thymine)]
fig = plt.figure(figsize=(8.0, 8.0))
ax = fig.add_subplot(111, projection="3d")
# Arrange bases
for i, (purine, pyrimidine) in enumerate(pairs):
n1, n3, c5, c6 = [pyrimidine[pyrimidine.atom_name == name][0]
for name in ("N1", "N3", "C5", "C6")]