def test_dssp(path):
sec_struct_codes = {
0: "I",
1: "S",
2: "H",
3: "E",
4: "G",
5: "B",
6: "T",
7: "C"
}
mmtf_file = mmtf.MMTFFile.read(path)
array = mmtf.get_structure(mmtf_file, model=1)
array = array[array.hetero == False]
first_chain_id = array.chain_id[0]
chain = array[array.chain_id == first_chain_id]
n_residues = struc.get_residue_count(chain)
# Secondary structure annotation in PDB use also DSSP
# -> compare PDB and local DSSP
sse = mmtf_file["secStructList"]
sse = sse[:n_residues]
if (sse == -1).all():
# First chain is not a polypeptide chain (presumably DNA/RNA)
# DSSP not applicable -> return
return
sse = np.array([sec_struct_codes[code] for code in sse], dtype="U1")
chain = array[array.chain_id == first_chain_id]
sse_from_app = DsspApp.annotate_sse(chain)
np.set_printoptions(threshold=10000)
# PDB uses different DSSP version -> slight differences possible
# -> only 90% must be identical
assert np.count_nonzero(sse_from_app == sse) / len(sse) > 0.9
def test_get_residues(array):
ids, names = struc.get_residues(array)
assert ids.tolist() == list(range(1, 21))
assert names.tolist() == [
"ASN", "LEU", "TYR", "ILE", "GLN", "TRP", "LEU", "LYS", "ASP", "GLY",
"GLY", "PRO", "SER", "SER", "GLY", "ARG", "PRO", "PRO", "PRO", "SER"
]
assert len(ids) == struc.get_residue_count(array)
def plot_rna(pdb_id, axes):
# Download the PDB file and read the structure
pdb_file_path = rcsb.fetch(pdb_id, "pdb", gettempdir())
pdb_file = pdb.PDBFile.read(pdb_file_path)
atom_array = pdb.get_structure(pdb_file)[0]
nucleotides = atom_array[struc.filter_nucleotides(atom_array)]
# Compute the base pairs and their pseudoknot order
base_pairs = struc.base_pairs(nucleotides)
base_pairs = struc.get_residue_positions(
nucleotides, base_pairs.flatten()
).reshape(base_pairs.shape)
pseudoknot_order = struc.pseudoknots(base_pairs)[0]
# Set the linestyle according to the pseudoknot order
linestyles = np.full(base_pairs.shape[0], '-', dtype=object)
linestyles[pseudoknot_order == 1] = '--'
linestyles[pseudoknot_order == 2] = ':'
# Indicate canonical nucleotides with an upper case one-letter-code
# and non-canonical nucleotides with a lower case one-letter-code
base_labels = []
for base in struc.residue_iter(nucleotides):
one_letter_code, exact = struc.map_nucleotide(base)
if exact:
base_labels.append(one_letter_code)
else:
base_labels.append(one_letter_code.lower())
# Color canonical Watson-Crick base pairs with a darker orange and
# non-canonical base pairs with a lighter orange
colors = np.full(base_pairs.shape[0], biotite.colors['brightorange'])
for i, (base1, base2) in enumerate(base_pairs):
name1 = base_labels[base1]
name2 = base_labels[base2]
if sorted([name1, name2]) in [["A", "U"], ["C", "G"]]:
colors[i] = biotite.colors["dimorange"]
# Plot the secondary structure
graphics.plot_nucleotide_secondary_structure(
axes, base_labels, base_pairs, struc.get_residue_count(nucleotides),
pseudoknot_order=pseudoknot_order, bond_linestyle=linestyles,
bond_color=colors,
# Margin to compensate for reduced axis limits in shared axis
border=0.13
)
# Use the PDB ID to label each plot
axes.set_title(pdb_id, loc="left")
atom_name == "CA"]
ca_trajectory_kinase_right = trajectory_kinase_right[:,
trajectory_kinase_right.
atom_name == "CA"]
rmsf_kinase_left = struc.rmsf(struc.average(ca_trajectory_kinase_left),
ca_trajectory_kinase_left)
rmsf_upper_kinase_left = rmsf_kinase_left.max() * 1.1
rmsf_kinase_right = struc.rmsf(struc.average(ca_trajectory_kinase_right),
ca_trajectory_kinase_right)
rmsf_upper_kinase_right = rmsf_kinase_right.max() * 1.1
fig, (ax1, ax2) = plt.subplots(2, 1)
res_count = struc.get_residue_count(trajectory_kinase_left)
ax1.plot(np.arange(1, res_count + 1) + 2801,
rmsf_kinase_left,
color=biotite.colors["dimorange"])
ax1.set_title("Kinase Left")
#ax1.axvline(3828, ls="--", color="k")
#ax1.axvline(3838, ls="--", color="k")
ax1.set_xlim(2801 + 1, 2801 + res_count)
ax1.set_ylim(0, rmsf_upper_kinase_left)
ax1.set_xlabel("Residue")
ax1.set_ylabel("RMSF (Å)")
res_count = struc.get_residue_count(trajectory_kinase_right)
ax2.plot(np.arange(1, res_count + 1) + 2801,
rmsf_kinase_right,
color=biotite.colors["dimorange"])
annotation += "W"
elif edge == 2:
annotation += "H"
else:
annotation += "S"
base_labels[base] = annotation
# Create a matplotlib pyplot
fig, ax = plt.subplots(figsize=(8.0, 8.0))
# Plot the secondary structure
graphics.plot_nucleotide_secondary_structure(
ax,
base_labels,
base_pairs,
struc.get_residue_count(nucleotides),
bond_color=colors)
# Display the plot
plt.show()
########################################################################
# The sarcin-ricin loop is part of the 23s rRNA and is considered
# crucial to the ribosome‘s activity. The incorporation of the
# Leontis-Westhof nomenclature into the 2D-plot shows how the individual
# base pairs are oriented and how their glycosidic bonds are oriented
# relative to each other.
#
# This visualization enables one to see a pattern that cannot be
# communicated through the 2D structure alone. The upper part of the
# sarcin-ricin loop consists of only cis (c) oriented glycosidic bonds.
import biotite.structure as struc
import biotite.structure.io as strucio
import biotite.structure.io.xtc as xtc
from biotite.application.dssp import DsspApp
# Put here the path of the downloaded files
templ_file_path = "../../download/lysozyme_md.pdb"
traj_file_path = "../../download/lysozyme_md.xtc"
xtc_file = xtc.XTCFile.read(traj_file_path)
traj = xtc_file.get_structure(template=strucio.load_structure(templ_file_path))
time = xtc_file.get_time()
traj = traj[:, struc.filter_amino_acids(traj)]
# DSSP does not assign an SSE to the last residue -> -1
sse = np.empty((traj.shape[0], struc.get_residue_count(traj) - 1), dtype='U1')
for idx, frame in enumerate(traj):
app = DsspApp(traj[idx])
app.start()
app.join()
sse[idx] = app.get_sse()
# Matplotlib needs numbers to assign colors correctly
def sse_to_num(sse):
num = np.empty(sse.shape, dtype=int)
num[sse == 'C'] = 0
num[sse == 'E'] = 1
num[sse == 'B'] = 2
num[sse == 'S'] = 3
num[sse == 'T'] = 4
else:
annotation = "t"
if edge == 1:
annotation += "W"
elif edge == 2:
annotation += "H"
else:
annotation += "S"
base_labels[base] = annotation
# Create a matplotlib pyplot
fig, ax = plt.subplots(figsize=(8.0, 8.0))
# Plot the secondary structure
graphics.plot_nucleotide_secondary_structure(
ax, base_labels, base_pairs, struc.get_residue_count(nucleotides),
bond_color=colors
)
# Display the plot
plt.show()
########################################################################
# The sarcin-ricin loop is part of the 23s rRNA and is considered
# crucial to the ribosome‘s activity. The incorporation of the
# Leontis-Westhof nomenclature into the 2D-plot shows how the individual
# base pairs are oriented and how their glycosidic bonds are oriented
# relative to each other.
#
# This visualization enables one to see a pattern that cannot be
# communicated through the 2D structure alone. The upper part of the
def rmsf_plot(topology,
xtc_traj,
start_frame=None,
stop_frame=None,
write_dat_files=None):
# Gromacs does not set the element symbol in its PDB files,
# but Biotite guesses the element names from the atom names,
# emitting a warning
template = strucio.load_structure(topology)
# The structure still has water and ions, that are not needed for our
# calculations, we are only interested in the protein itself
# These are removed for the sake of computational speed using a boolean
# mask
protein_mask = struc.filter_amino_acids(template)
template = template[protein_mask]
residue_names = struc.get_residues(template)[1]
xtc_file = XTCFile()
xtc_file.read(xtc_traj,
atom_i=np.where(protein_mask)[0],
start=start_frame,
stop=stop_frame + 1)
trajectory = xtc_file.get_structure(template)
time = xtc_file.get_time() # Get simulation time for plotting purposes
trajectory = struc.remove_pbc(trajectory)
trajectory, transform = struc.superimpose(trajectory[0], trajectory)
rmsd = struc.rmsd(trajectory[0], trajectory)
figure = plt.figure(figsize=(6, 3))
ax = figure.add_subplot(111)
ax.plot(time, rmsd, color=biotite.colors["dimorange"])
ax.set_xlim(time[0], time[-1])
ax.set_ylim(0, 2)
ax.set_xlabel("Time (ps)")
ax.set_ylabel("RMSD (Å)")
figure.tight_layout()
radius = struc.gyration_radius(trajectory)
figure = plt.figure(figsize=(6, 3))
ax = figure.add_subplot(111)
ax.plot(time, radius, color=biotite.colors["dimorange"])
ax.set_xlim(time[0], time[-1])
ax.set_ylim(14.0, 14.5)
ax.set_xlabel("Time (ps)")
ax.set_ylabel("Radius of gyration (Å)")
figure.tight_layout()
# In all models, mask the CA atoms
ca_trajectory = trajectory[:, trajectory.atom_name == "CA"]
rmsf = struc.rmsf(struc.average(ca_trajectory), ca_trajectory)
figure = plt.figure(figsize=(6, 3))
ax = figure.add_subplot(111)
res_count = struc.get_residue_count(trajectory)
ax.plot(np.arange(1, res_count + 1),
rmsf,
color=biotite.colors["dimorange"])
ax.set_xlim(1, res_count)
ax.set_ylim(0, 1.5)
ax.set_xlabel("Residue")
ax.set_ylabel("RMSF (Å)")
figure.tight_layout()
if write_dat_files == True:
# Write RMSD *.dat file
frames = np.array(range(start_frame - 1, stop_frame), dtype=int)
frames[0] = 0
df = pd.DataFrame(data=rmsd, index=frames, columns=["RMSD Values"])
df.index.name = 'Frames'
df.to_csv('rmsd.dat', header=True, index=True, sep='\t', mode='w')
# Write RMSF *.dat file
df1 = pd.DataFrame(data=rmsf,
index=residue_names,
columns=["RMSF Values"])
df1.index.name = 'Residues'
df1.to_csv('rmsf.dat', header=True, index=True, sep='\t', mode='w')
plt.show()
# during the entire simulation.
#
# Let's have a look at single amino acids:
# Which residues fluctuate most?
# For answering this question we calculate the RMSF
# (Root mean square fluctuation).
# It is similar to the RMSD, but instead of averaging over the atoms
# and looking at each time step, we average over the time and look at
# each residue.
# Usually the average model is taken as reference
# (compared to the starting model for RMSD).
#
# Since side chain atoms fluctuate quite a lot, they are not suitable
# for evaluation of the residue flexibility. Therefore, we consider only
# CA atoms.
# In all models, mask the CA atoms
ca_trajectory = trajectory[:, trajectory.atom_name == "CA"]
rmsf = struc.rmsf(struc.average(ca_trajectory), ca_trajectory)
figure = plt.figure(figsize=(6, 3))
ax = figure.add_subplot(111)
res_count = struc.get_residue_count(trajectory)
ax.plot(np.arange(1, res_count + 1), rmsf, color=biotite.colors["dimorange"])
ax.set_xlim(1, res_count)
ax.set_ylim(0, 1.5)
ax.set_xlabel("Residue")
ax.set_ylabel("RMSF (Å)")
figure.tight_layout()
plt.show()