# The radius does merely fluctuate in a range of approx. 0.5 Angstrom
# 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)
ax.plot(np.arange(1, 21), rmsf, color=biotite.colors["dimorange"])
ax.set_xlim(1, 20)
ax.set_xlabel("Residue")
ax.set_ylabel("RMSF (Angstrom)")
ax.set_xticks(np.arange(1, 21))
ax.set_xticklabels(np.arange(1, 21))
figure.tight_layout()
plt.show()
legend_x = 1
legend_y = 0.5
plt.legend(loc='center left', bbox_to_anchor=(legend_x, legend_y))
#plt.legend(loc="best")
plt.tight_layout()
plt.savefig("radius_two.png", dpi=600)
plt.clf()
ca_trajectory_kinase_left = trajectory_kinase_left[:, trajectory_kinase_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")
def test_rmsf(stack, as_coord):
if as_coord:
stack = stack.coord
assert struc.rmsf(struc.average(stack), stack).tolist() \
== pytest.approx([21.21320344] * 5)
def test_rmsf(stack):
assert struc.rmsf(struc.average(stack), stack).tolist() \
== pytest.approx([21.21320344] * 5)
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()
########################################################################
# Fetch and load human CD2 NMR structure and remove glycan
mmtf_file = mmtf.MMTFFile.read(rcsb.fetch("1gya", "mmtf"))
cd2 = mmtf.get_structure(mmtf_file, include_bonds=True)
cd2 = cd2[..., struc.filter_amino_acids(cd2)]
# Push first model to PyMOL
pymol_cd2 = ammolite.PyMOLObject.from_structure(cd2[0])
ammolite.show(PNG_SIZE)
########################################################################
# Use RMSF between NMR models as measure of flexibility
rmsf = struc.rmsf(struc.average(cd2), cd2)
# Use logarithmic scale
log_rmsf = np.log(rmsf)
# Set maximum value for a CA to 1.0
flexibility = log_rmsf / np.max(log_rmsf[cd2.atom_name == "CA"])
# Use a Matplotlib color map for flexibility coloring
# Use discrete color 'steps'
N_COLORS = 20
cmap = plt.get_cmap("Reds")
for threshold_flex in np.linspace(1.0, 0.0, N_COLORS):
# Discard alpha channel
color = cmap(threshold_flex)[:3]
pymol_cd2.color(color, flexibility <= threshold_flex)
ammolite.show(PNG_SIZE)
# sphinx_gallery_thumbnail_number = 2
# to a reference model, which is usually the averaged structure.
# Since we are only interested in the backbone flexibility, we consider
# only CA atoms.
# Before we can calculate a reasonable RMSF, we have to superimpose each
# model on a reference model (we choose the first model),
# which minimizes the *root mean square deviation* (RMSD).
stack = strucio.load_structure(file_path)
# We consider only CA atoms
stack = stack[:, stack.atom_name == "CA"]
# Superimposing all models of the structure onto the first model
stack, transformation_tuple = struc.superimpose(stack[0], stack)
print("RMSD for each model to first model:")
print(struc.rmsd(stack[0], stack))
# Calculate the RMSF relative to average of all models
rmsf = struc.rmsf(struc.average(stack), stack)
# Plotting stuff
plt.plot(np.arange(1, 21), rmsf)
plt.xlim(0, 20)
plt.xticks(np.arange(1, 21))
plt.xlabel("Residue")
plt.ylabel("RMSF")
plt.show()
########################################################################
# As you can see, both terminal residues are most flexible.
#
# Calculating accessible surface area
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
#
# Another interesting value for a protein structure is the