def compute_mdtraj_order_parmeters(trajectory_file, rmsd_reference_structure=None):
# documentation: http://mdtraj.org/1.8.0/analysis.html#
trajectory = md.load(trajectory_file)
return_values = []
return_value_names = []
if not rmsd_reference_structure == None:
reference = md.load(rmsd_reference_structure)
rmsd = md.rmsd(trajectory, reference)
return_values.append(rmsd)
return_value_names.append("RMSD")
hydrogen_bonds = np.array([np.sum(x) for x in md.kabsch_sander(trajectory)])
return_values.append(hydrogen_bonds)
return_value_names.append("HBondEnergy")
ss = md.compute_dssp(trajectory)
shape = ss.shape
transdict = dict(zip(list(set(list(ss.flatten()))),range(len(list(set(list(ss.flatten())))))))
ss = np.array([transdict[x] for x in ss.flatten()]).reshape(shape).T
return_values.append(ss)
return_value_names.append("SecondaryStructure")
rg = md.compute_rg(trajectory)
return_values.append(rg)
return_value_names.append("Rg")
distances, residue_pairs = md.compute_contacts(trajectory, scheme='ca')
contacts = md.geometry.squareform(distances, residue_pairs)
return_values.append(contacts)
return_value_names.append("Contacts")
return dict(zip(return_value_names, return_values))
def hydrogenbond(pdbfile):
"""
Calculate number of hydrogen bonds [1,2] and hydrogen bond energy [3]
using three methods as implemented in MDtraj [4] for a single PDB file.
[1] E. N. Baker and R. E. Hubbard, "Hydrogen bonding in globular proteins",
Progress in Biophysics and Molecular Biology, vol. 44, no. 2,
pp. 97-179, 1984.
[2] P. Wernet et al., "The Structure of the First Coordination Shell in
Liquid Water", Science, vol. 304, no. 5673, pp. 995-999, 2004.
[3] W. Kabsch and C. Sander, "Dictionary of protein secondary structure:
Pattern recognition of hydrogen-bonded and geometrical features",
Biopolymers, vol. 22, no. 12, pp. 2577"2637, 1983.
[4] R. T. McGibbon et al., "MDTraj: A Modern Open Library for the
Analysis of Molecular Dynamics Trajectories", Biophysical Journal,
vol. 109, no. 8, pp. 1528-1532, 2015.
"""
pdb = mdtraj.load(pdbfile)
desc = dict()
desc['HB_BH'] = float(mdtraj.baker_hubbard(pdb).shape[0])
desc['HB_WN'] = float(mdtraj.wernet_nilsson(pdb)[0].shape[0])
desc['HB_KS'] = float(mdtraj.kabsch_sander(pdb)[0].sum())
return desc
formatter_class=argparse.RawDescriptionHelpFormatter)
#parser.add_argument('-', "--", help="", default="")
parser.add_argument("-v",
"--verbose",
action="store_true",
help="be verbose")
parser.add_argument("file", help="", default="", nargs='+')
return parser
if __name__ == '__main__':
parser = get_parser()
args = parser.parse_args()
if list != type(args.file):
args.file = [args.file]
for f in args.file:
import mdtraj as md
print(f, '---------------------')
t = md.load(f)
print(md.kabsch_sander(t))
hb = md.wernet_nilsson(t)
print(hb)
print(len(hb[0]))
hb = md.baker_hubbard(t)
print(hb)
print(len(hb))
#Step 7 Analysis (change the input file name)
import pickle
import mdtraj as md
with open('fs-khybrid-clusters0020-centers.pickle', 'rb') as f:
ctr_structs = md.join(pickle.load(f))
#Step 8
hbonds = md.kabsch_sander(ctr_structs)
#Step 9
import matplotlib.pylab as plt
weighted_hbond_mtx = sum(p * h for p, h in zip(m.eq_probs_, hbonds)).todense()
plt.imshow(weighted_hbond_mtx, cmap='viridis_r')
plt.colorbar()
all_hbonds = set()
#Step11
# accumulate all the possible pairs of residues involved in hbonds
for i in range(len(ctr_structs)):
donors, acceptors = np.where(hbonds[i].todense() != 0)
all_hbonds.update([(d, a) for d, a in zip(donors, acceptors)])
# make a list so that it's ordered
all_hbonds = list(all_hbonds)
# this matrix of length n_states will have each binary feature vector
hbond_presence = np.zeros((m.n_states_, len(all_hbonds)), dtype='uint8')
# set each value i, j to one if state i has hbond j.