def calc_distance():
u = mda.Universe(STRUCTFNAME, TRAJFILE)
head_atms = u.atoms.select_atoms("name {}".format(HEADATM))
tail_atms = u.atoms.select_atoms("name {}".format(' '.join(TAILATMS)))
tail_atms = mda.AtomGroup(list(chunks(tail_atms, len(TAILATMS))))
LOGGER.debug("head_atms: %s tail atms %s", head_atms, tail_atms)
if not isinstance(mda.AtomGroup, list):
head_atms = mda.AtomGroup(head_atms)
with open(OUTPUTFILENAME, "w") as outf:
outf.write("{: <15}{: <10}{: <10}{: <20}\n".format(
"time", "resid", "chain", "dist"))
for ts in u.trajectory:
LOGGER.info("at time %s", ts.time)
outp_inf = []
#distances = distance_array(np.array([head.position for head in head_atms]), np.array([tail.position for tail in tail_atms]))
for head, tail in zip(head_atms, tail_atms):
#print("HEAD", head)
distances = distance_array(head.position, tail.position)[0]
#LOGGER.debug("distances:\n%s", distances)
residue = head.residue
#LOGGER.info("at residue %s", residue)
for chainid, dist in enumerate(distances):
outpline = "{: <15}{: <10}{: <10}{: <20}\n"\
.format(ts.time, residue.resid, chainid, dist )
outp_inf.append(outpline)
for line in outp_inf:
outf.write(line)
def __init__(self, atomgroups, orders, **kwargs):
"""Parameters
----------
atomgroups : list
a list of atomgroups for which the dihedral angles are calculated
Raises
------
ValueError
If any atomgroups do not contain 4 atoms
"""
super(DihedralFromAtoms,
self).__init__(atomgroups[0].universe.trajectory, **kwargs)
self.atomgroups = atomgroups
if any([len(ag) != 4 for ag in atomgroups]):
raise ValueError("All AtomGroups must contain 4 atoms")
if len(atomgroups) != len(orders):
raise ValueError(
"Order data should be provided for every atom group")
self.ag1 = mda.AtomGroup(
[atomgroups[i][orders[i][0]] for i in range(len(atomgroups))])
self.ag2 = mda.AtomGroup(
[atomgroups[i][orders[i][1]] for i in range(len(atomgroups))])
self.ag3 = mda.AtomGroup(
[atomgroups[i][orders[i][2]] for i in range(len(atomgroups))])
self.ag4 = mda.AtomGroup(
[atomgroups[i][orders[i][3]] for i in range(len(atomgroups))])
def __init__(self, atomgroups, **kwargs):
super(Angles, self).__init__(atomgroups[0].universe.trajectory,
**kwargs)
self.atomgroups = atomgroups
if any([len(ag) != 3 for ag in atomgroups]):
raise ValueError("All AtomGroups must contain 3 atoms")
self.ag1 = md.AtomGroup([ag[0] for ag in atomgroups])
self.ag2 = md.AtomGroup([ag[1] for ag in atomgroups])
self.ag3 = md.AtomGroup([ag[2] for ag in atomgroups])
def convert_traj(args):
u = mda.Universe(args.coords, args.traj)
if args.output is None:
args.output = args.traj.rsplit(".")[0] + ".pdb"
sel = mda.AtomGroup(u.atoms) # so we can use sel.n_atoms later
if args.nodrudes:
sel = sel.select_atoms("not name D*")
if args.novirtuals:
sel = sel.select_atoms("not name V*")
if args.sel:
sel = sel.select_atoms(args.sel)
if args.start and args.end:
frames = u.trajectory[args.start:args.end]
elif args.start:
frames = u.trajectory[args.start:]
elif args.end:
frames = u.trajectory[:args.end]
else:
frames = u.trajectory
with mda.Writer(args.output, sel.n_atoms) as f:
for _ in completion(frames):
f.write(sel)
def __init__(self, atomgroup, **kwargs):
"""Parameters
----------
atomgroup : AtomGroup or ResidueGroup
atoms for residues for which :math:`\phi` and :math:`\psi` are
calculated
Raises
------
ValueError
If the selection of residues is not contained within the protein
"""
super(Ramachandran, self).__init__(atomgroup.universe.trajectory, **kwargs)
self.atomgroup = atomgroup
residues = self.atomgroup.residues
protein = self.atomgroup.universe.select_atoms("protein").residues
if not residues.issubset(protein):
raise ValueError("Found atoms outside of protein. Only atoms "
"inside of a 'protein' selection can be used to "
"calculate dihedrals.")
elif not residues.isdisjoint(protein[[0, -1]]):
warnings.warn("Cannot determine phi and psi angles for the first "
"or last residues")
residues = residues.difference(protein[[0, -1]])
phi_sel = [res.phi_selection() for res in residues]
psi_sel = [res.psi_selection() for res in residues]
# phi_selection() and psi_selection() currently can't handle topologies
# with an altloc attribute so this removes any residues that have either
# angle return none instead of a value
if any(sel is None for sel in phi_sel):
warnings.warn("Some residues in selection do not have phi selections")
remove = [i for i, sel in enumerate(phi_sel) if sel is None]
phi_sel = [sel for i, sel in enumerate(phi_sel) if i not in remove]
psi_sel = [sel for i, sel in enumerate(psi_sel) if i not in remove]
if any(sel is None for sel in psi_sel):
warnings.warn("Some residues in selection do not have psi selections")
remove = [i for i, sel in enumerate(psi_sel) if sel is None]
phi_sel = [sel for i, sel in enumerate(phi_sel) if i not in remove]
psi_sel = [sel for i, sel in enumerate(psi_sel) if i not in remove]
self.ag1 = mda.AtomGroup([atoms[0] for atoms in phi_sel])
self.ag2 = mda.AtomGroup([atoms[1] for atoms in phi_sel])
self.ag3 = mda.AtomGroup([atoms[2] for atoms in phi_sel])
self.ag4 = mda.AtomGroup([atoms[3] for atoms in phi_sel])
self.ag5 = mda.AtomGroup([atoms[3] for atoms in psi_sel])
def _reorg_groups(groups: List[EnsembleAtomGroup]):
ag1 = []
ag2 = []
ag3 = []
ag4 = []
ag_keys = []
names = []
for group in groups:
ag1 += [
mda.AtomGroup([ag[0]])
for ag in [group[k] for k in group.keys()]
]
ag2 += [
mda.AtomGroup([ag[1]])
for ag in [group[k] for k in group.keys()]
]
ag3 += [
mda.AtomGroup([ag[2]])
for ag in [group[k] for k in group.keys()]
]
ag4 += [
mda.AtomGroup([ag[3]])
for ag in [group[k] for k in group.keys()]
]
names.append('-'.join([
ag1[-1].atoms[0].name, ag2[-1].atoms[0].name,
ag3[-1].atoms[0].name, ag4[-1].atoms[0].name
]))
for k in group.keys():
ag_keys.append((names[-1], k[0], k[1], k[2]))
eag1 = EnsembleAtomGroup(
{ag_keys[i]: ag1[i]
for i in range(len(ag_keys))}, groups[0].ensemble)
eag2 = EnsembleAtomGroup(
{ag_keys[i]: ag2[i]
for i in range(len(ag_keys))}, groups[0].ensemble)
eag3 = EnsembleAtomGroup(
{ag_keys[i]: ag3[i]
for i in range(len(ag_keys))}, groups[0].ensemble)
eag4 = EnsembleAtomGroup(
{ag_keys[i]: ag4[i]
for i in range(len(ag_keys))}, groups[0].ensemble)
return eag1, eag2, eag3, eag4, names
def get_atom_groups(bin_int): for cluster in cluster_atoms_under(bin_int): atom_group_inds = [] bin_positions_ind = np.where(inds < bin_int)[0] bin_positions = [positions[i] for i in bin_positions_ind] for ind in cluster: point = [bin_positions[ind][0], bin_positions[ind][1], bin_positions[ind][2]] index = positions.index(point) atom_group_inds.append(index) atom_group = mda.AtomGroup(atom_group_inds, u) atom_groups_clusters_under.append(atom_group) for cluster in cluster_atoms_over(bin_int): atom_group_inds = [] bin_positions_ind = np.where(inds > bin_int)[0] bin_positions = [positions[i] for i in bin_positions_ind] for ind in cluster: point = [bin_positions[ind][0], bin_positions[ind][1], bin_positions[ind][2]] index = positions.index(point) atom_group_inds.append(index) atom_group = mda.AtomGroup(atom_group_inds, u) atom_groups_clusters_over.append(atom_group)
def __init__(self, atomgroups, **kwargs):
"""Parameters
----------
atomgroups : list
a list of atomgroups for which the dihedral angles are calculated
Raises
------
ValueError
If any atomgroups do not contain 4 atoms
"""
super(Dihedral, self).__init__(atomgroups[0].universe.trajectory, **kwargs)
self.atomgroups = atomgroups
if any([len(ag) != 4 for ag in atomgroups]):
raise ValueError("All AtomGroups must contain 4 atoms")
self.ag1 = mda.AtomGroup([ag[0] for ag in atomgroups])
self.ag2 = mda.AtomGroup([ag[1] for ag in atomgroups])
self.ag3 = mda.AtomGroup([ag[2] for ag in atomgroups])
self.ag4 = mda.AtomGroup([ag[3] for ag in atomgroups])
def select_by_helixandbase(self, helix_range: List[int],
base_range: List[int]):
"""select all atoms of the cadnano subset of helices and baseposition-range"""
def DhpsFid(h, p, s) -> int:
return self.link.DidFid[self.link.DhpsDid[(h, p, s)]]
u = self.link.u
stsc_bases = self._parse_selection(base_range, helix_range)
atoms = mda.AtomGroup([], u)
for idx, bases in enumerate(stsc_bases):
for base in bases:
Fid = DhpsFid(base.h, base.p, bool(idx))
atoms += u.residues[Fid].atoms
return atoms, self.link.Dcolor
def test_unwrap_empty_group(self, level, compound, reference,
is_triclinic):
# get a pristine test universe:
u = UnWrapUniverse(is_triclinic=is_triclinic)
if level == 'atoms':
group = mda.AtomGroup([], u)
elif level == 'residues':
group = mda.ResidueGroup([], u)
elif level == 'segments':
group = mda.SegmentGroup([], u)
group.unwrap(compound=compound, reference=reference, inplace=True)
# check for correct (empty) result:
assert_array_equal(group.atoms.positions,
np.empty((0, 3), dtype=np.float32))
def __init__(self, atom1, atom2, universe):
"""Initialise the Bond object.
Input
-----
atom1 : index of the first atom involved in bond
atom2 : index of the second atom involve in bond
universe: MDAnalysis universe instance defining the bond
"""
# Store the atoms in 1-based indices
self.atom1 = atom1
self.atom2 = atom2
# We generate the atom group from the zero-based indices
self.atomgroup = mda.AtomGroup([atom1 - 1, atom2 - 1], universe)
print(self.atomgroup.atoms[0])
print(self.atomgroup.atoms[1])
self.data = VectorData(universe.trajectory.n_frames)
def __init__(self, atom1, atom2, atom3, universe):
"""Initialise the Angle object.
Input
-----
atom1 : index of the first atom involved in angle
atom2 : index of the second atom involved in angle
atom3 : index of third atom involved in angle
universe: MDAnalysis universe instance defining the bond
"""
# Store the atoms in 1-based indices
self.atom1 = atom1
self.atom2 = atom2
self.atom3 = atom3
# We generate the atom group from the zero-based indices
self.atomgroup = mda.AtomGroup([atom1 - 1, atom2 - 1, atom3 - 1],
universe)
self.data = VectorData(universe.trajectory.n_frames)
post_filter_area = auc(FPR_post_ordered, TPR_post_ordered)
roc_area[i] = post_filter_area
# for every beta phi value calculate area under the curve - cluster filtering
# also create atom group that will visualize the atoms that are being filtered out
ag_filtered = []
for i in range(0, 264, 4):
print(i)
FP_dict_filter = {}
TP_dict_filter = {}
num_clusters, cluster_dict, singleton_ind, doubles_ind, triples_ind = clustering_info_pred_interface_atoms(
i)
total_ind = singleton_ind
filtered_ag = mda.AtomGroup(total_ind, u_dewet)
ag_filtered.append(filtered_ag)
for j in range(0, 264, 4):
if len(total_ind) == 0:
break
else:
new_ind_FP = list(set(FP_dict[j]) - set(total_ind))
new_ind_TP = list(set(TP_dict[j]) - set(total_ind))
FP_dict_filter[j] = new_ind_FP
TP_dict_filter[j] = new_ind_TP
if len(total_ind) == 0:
roc_area[i] = pre_filter_area
else:
FPR_post = [len(x) / float(P) for x in FP_dict_filter.values()]
def test_empty_atomgroup_access(self):
ag = mda.AtomGroup([], case1())
assert ag.fragments == tuple()
assert_equal(ag.fragindices, np.array([], dtype=np.int64))
assert ag.n_fragments == 0
elif args.indMM:
atoms_num = read_ndx(args.indMM)
# Build selection kwd
selection = 'bynum '
for num in atoms_num:
selection += str(num) + ' '
# Apply selection (static)
try:
# Ensure no overlap with QM layer
#layerMM = exclusive_selection(u,selection,layerQM)
layerMM = u.select_atoms(selection, updating=False)
except:
raise BaseException("Error setting MM layer. Check index file")
else:
# return an empty AtomGroup (acts as None type within if clauses)
layerMM = MDAnalysis.AtomGroup([], u)
# -- Point charges layer --
if args.selPC:
try:
# Ensure no overlap with QM/MM layers
#layerPC = exclusive_selection(u,args.selPC,layerQM+layerMM)
layerPC = u.select_atoms(args.selPC, updating=True)
except:
raise BaseException(
"Error setting PC layer. Maybe due to missplells in selection keyword"
)
elif args.indPC:
atoms_num = read_ndx(args.indPC)
# Build selection kwd
selection = 'bynum '
indices_post = np.argsort(FPR_post)
FPR_post_ordered = (np.asarray(FPR_post))[indices_post]
TPR_post_ordered = (np.asarray(TPR_post))[indices_post]
plt.plot(FP_dict.keys(), FPR_post_ordered, label='FPR')
plt.plot(FP_dict.keys(), TPR_post_ordered, label='TPR')
plt.title('FPR and TPR, Post-Filter')
plt.legend()
plt.show()
#visualize_post_FPR_TPR()
# create atom groups for visualizations
contact_ind = np.where(contact == 1)[0].tolist()
ag_contact = mda.AtomGroup(contact_ind, u_dewet)
ag_filtered_FP = []
ag_filtered_TP = []
ag_FP = []
ag_TP = []
for i in range(0, 404, 4):
ag = mda.AtomGroup(FP_dict[i], u_dewet)
ag_FP.append(ag)
# ag = mda.AtomGroup(FP_removed[i], u_dewet)
# ag_filtered_FP.append(ag)
ag = mda.AtomGroup(TP_dict[i], u_dewet)
ag_TP.append(ag)
def createForce(self, common_core_names):
"""Actually creates the force, after dismissing all idxs not in the common core from the molecule.
Args:
common_core_names (array[str]): - Array with strings of the common core names. Usually provided by the restraint.yaml file.
Returns:
openMM.CustomCentroidBondForce: An openMM force object representing the restraint bond.
"""
# Only done for g1, as it is the ligand group - theres no common core for the protein
logger.debug(f"Before CC check: {self.g1.names}")
self.g1_in_cc = MDAnalysis.AtomGroup([], self.topology)
for atom in self.g1:
if atom.name in common_core_names:
self.g1_in_cc += atom
logger.debug(f"After CC check: {self.g1_in_cc.names}")
self.common_core_idxs = [atom.id for atom in self.g1_in_cc]
# convert MDAnalysis syntax into openMM usable idxs
self.g1_openmm = [int(id) for id in self.g1_in_cc.ix]
self.g2_openmm = [int(id) for id in self.g2.ix]
logger.debug(f"G1 openMM ix: {self.g1_openmm}\nG2 openMM ix: {self.g2_openmm}")
self.g1pos = self.g1_in_cc.center_of_mass()
self.g2pos = self.g2.center_of_mass()
self.initial_distance = np.linalg.norm(self.g1pos - self.g2pos)
if not "r0" in self.kwargs.keys(): # default value - equilibrium distance is the initial distance. Otherwise, overriden with the r0 specified
self.r0 = self.initial_distance * angstrom
else:
self.r0 = self.kwargs["r0"] * angstrom
if self.shape == "harmonic":
# create force with harmonic potential
self.force = CustomCentroidBondForce(2, "0.5*k*(distance(g1,g2)-r0)^2")
self.force.addPerBondParameter("k")
self.force.addPerBondParameter("r0")
self.force.addGroup(self.g1_openmm)
self.force.addGroup(self.g2_openmm)
self.force.addBond(
[0, 1], [self.force_constant, self.r0]
)
logger.info(
f"""Restraint force (centroid/bonded, shape is {self.shape}, initial distance: {self.initial_distance}, k={self.force_constant}"""
)
elif self.shape in ["flatbottom","flatbottom-oneside"]:
# create force with flat-bottom potential identical to the one used in openmmtools
logger.debug("creating flatbottom-1side-soft")
self.force = CustomCentroidBondForce(
2, "step(distance(g1,g2)-r0) * (k/2)*(distance(g1,g2)-r0)^2"
)
self._add_flatbottom_parameters()
elif self.shape == "flatbottom-oneside-sharp":
# create force with flat-bottom potential
logger.debug("creating flatbottom-1side-sharp")
self.force = CustomCentroidBondForce(
2, "step(distance(g1,g2)-r0) * (k/2)*(distance(g1,g2))^2"
)
self._add_flatbottom_parameters()
elif self.shape == "flatbottom-twoside":
# create force with flat-bottom potential
logger.debug("creating flatbottom-2side-sharp")
self.force = CustomCentroidBondForce(
2, "step(abs(distance(g1,g2)-r0)-w)*k*(distance(g1,g2)-r0)^2"
)
self._add_flatbottom_parameters()
else:
raise NotImplementedError(f"Cannot create potential of shape {self.shape}")
logger.debug(
f"""
Group 1 (COM: {self.g1pos}): {[self.g1_in_cc.names]}
Group 2 (COM: {self.g2pos}): {[self.g2.names]}"""
)
del self.topology # delete the enormous no longer needed universe asap
return self.force
def coarse_grain(universe,
residue_list,
simulation_name='simulation_name',
export=False):
# ============== Misc Initiation ============== #
with open('src/mapping_dict.json', "r") as f:
mapping_dict = load(f)
with open('src/abrev_dict.json', "r") as f:
abrev_dict = load(f)
u = universe
# ================= Execution ================= #
print('Calculating Bond connections...')
resnames = ' '.join(residue_list)
original_bond_count = len(u.bonds)
u.select_atoms(f'resname {resnames}').guess_bonds(vdwradii=config.vdw_radi)
print(
f'Original file contained {original_bond_count} bonds. {len(u.bonds) - original_bond_count} additional bonds infered.'
)
print(f'Begining Coarse-Graining process...')
bead_data = []
cg_beads = []
dummy_parents = {}
non_water_atoms = u.select_atoms('not resname WAT')
for residue in non_water_atoms.residues: # loops thu each matching residue id
resid = residue.resid # store int id
resname = residue.resname
if resname in residue_list: # if resname == "PHOSPHATE" or resname == "RIBOSE":
# resname_atoms = u.atoms.select_atoms('resname DA DT DG DC DU')
# else:
# resname_atoms = u.atoms.select_atoms(f'resname {resname}') # selects all resname-specific atoms
if len(resname) == 4 and resname[0] == 'D': # for D-varants
resname_key = resname[1:]
else:
resname_key = resname
try:
segments = mapping_dict[resname_key].keys()
for segment in segments: # loops thru each segment of each residue
params = 'name ' + ' '.join(
mapping_dict[resname_key][segment]
['atoms']) # generates param
# selects all atoms in a given residue segment
atms = residue.atoms.select_atoms(params)
dummy = atms[0]
# names dummy atom in propper format
dummy.name = str(abrev_dict[resname_key]) + str(
segment[0]) + str(resid)
dummy.type = mapping_dict[resname_key][segment]['name']
dummy.charge = mapping_dict[resname_key][segment]['charge']
bead_data.append((dummy, atms))
cg_beads.append(dummy)
for atm in atms:
dummy_parents[atm.ix] = dummy
except KeyError:
print(
f'{resname_key} was not found in mapping/abrev_dict, skipping coarse grain. Please add its parameters to the dictionary. (See README section A3. for help)'
)
new_bonds = []
# for residue in residue_list:
# for mapping in mapping_dict[residue]["Bonds"]:
# first_code = mapping[0] # segment, resid offset, resname
# seccond_code = mapping[1] if isinstance(mapping[1], list) else [mapping[1], 0, residue]
# type_params = list(mapping_dict[residue]["Mapping"].keys())[first_code]
# first_atoms = cg_beads.select_atoms(f'resname {residue} and type {type_params}')
# for first_atom in first_atoms:
# type_params = list(mapping_dict[residue]["Mapping"].keys())[seccond_code[0]] # segment
# seccond_atom_resid = int(first_atom.resid) + int(seccond_code[1])
# try:
# seccond_atom = cg_beads.atoms.select_atoms(f'resname {seccond_code[2]} and type {type_params} and resid {seccond_atom_resid}')
# except IndexError:
# pass
# if isinstance(seccond_atom, mda.core.groups.AtomGroup):
# closest = seccond_atom[0]
# closest_dist = mda.AtomGroup([first_atom, seccond_atom[0]]).bond.length()
# for atom in seccond_atom:
# dist = mda.AtomGroup([first_atom, atom]).bond.length()
# if dist < closest_dist:
# closest = atom
# closest_dist = dist
# seccond_atom = closest
# new_bonds.append([first_atom.index, seccond_atom.index])
# new_bonds = []
for dummy, atms in bead_data:
# connect all parents with connected children
for atom in atms:
for bond in atom.bonds:
for bonded_atom in bond.atoms:
if bonded_atom not in atms: # make more efficent if atms were a set
# by the end of all these loops and ifs, every bonded_atom that gets to this point is an atom connected to the edge of the cluster of atoms assigned to the coarse grain dummy bead in question
try:
new_bonds.append([
cg_beads.index(dummy),
cg_beads.index(dummy_parents[bonded_atom.ix])
]) # type is used to store the cluster dummy
except KeyError: # raises if atom does not belong to a coarse grain bead
pass
# try:
# new_bonds.append([cg_beads.index(dummy), cg_beads.index(bonded_atom)]) # adds the bond between the dummies
# except ValueError: # if the other atom is just an atom withouot a coarse grain bead parent, ignore it
# pass
cg_beads = mda.AtomGroup(cg_beads)
# TODO: EXPORT NEW_U INSTEAD OF OLD U
# TODO: EXPORT NEW_U TO HAVE APPROPRIATE FRAMES
# TODO: SHIFT THE DEFINITION OF CENTERS IN THE UNIVERSE EVEN IF NOT EXPORTING
# TODO: AUTOTUNE THE CURVE TO FIND THE RIGHT STEP
progress(0)
number_of_frames = len(u.trajectory)
for frame in u.trajectory: # loops tru each frame
f = frame.frame
# positions a dummy atoms at cluster center of mass
for dummy, atms in bead_data:
dummy.position = AtomGroup(atms).center_of_mass()
progress(f / number_of_frames)
progress(1)
print()
for dummy, atms in bead_data:
dummy.mass = AtomGroup(atms).masses.sum()
# purge existing reminant bonds
u.delete_bonds(u.bonds)
u.delete_angles(u.angles)
u.delete_dihedrals(u.dihedrals)
print(f'Building new coarse-grained universe...')
coordinates = AnalysisFromFunction(lambda ag: ag.positions.copy(),
cg_beads).run().results
new_u = mda.Merge(cg_beads)
new_u.load_new(coordinates, format=MemoryReader)
new_u.add_TopologyAttr('bonds', new_bonds)
new_u.add_TopologyAttr('angles', guess_angles(new_u.bonds))
new_u.add_TopologyAttr('dihedrals', guess_dihedrals(new_u.angles))
print(
f'Built universe with {len(new_u.atoms)} coarse-grained beads, {len(new_u.bonds)} bonds, {len(new_u.angles)} angles, and {len(new_u.dihedrals)} dihedrals'
)
if export:
print('Writing Output Files...')
out_file = f'outputs/CoarseGrain/{simulation_name}_CG.pdb'
with open(out_file, 'w+') as _:
new_u.atoms.write(out_file, bonds='all')
print(f'Topology written to {simulation_name}_CG.pdb!')
is_multiframe = number_of_frames > 1
with mda.Writer(f'outputs/CoarseGrain/{simulation_name}_CG.dcd',
new_u.atoms.n_atoms,
multiframe=is_multiframe,
bonds='all') as w:
for frame in new_u.trajectory[1:]: # loops tru each frame
w.write(new_u.atoms)
print('Generated All Coarse Grained Molecules!')
print(f'Trajectory written to {simulation_name}_CG.dcd!')
# for dummy, atms in bead_data:
# dummy.type = ''
print(f'Reduced {len(u.atoms)} atoms to {len(new_u.atoms)} beads!')
print('Coarse Graining Task complete!')
return new_u
def create_cc_orderfiles():
'''
'''
u = mda.Universe(GRO, TRJ)
## Gather all input data for _calc_scd_output function
len_traj = len(u.trajectory)
with open(OUTPUTFILENAME, "w") as scdfile, open("ztilt_randaxis.csv",
"w") as axf:
#### Print header files ####
print("{: <12}{: <10}{: <15}{: <15}{: <15}{: <20}{: <20}{: <20}"\
.format("time", "axndx", "S", "proj_ch1", "proj_ch2", "ax_x", "ax_y", "ax_z"),
file=scdfile)
print("time,tilt", file=axf)
tailatms = SCD_TAIL_ATOMS_OF[LIPID[:2]]
s_atoms = []
for sn in tailatms:
atms = u.atoms.select_atoms( "name {}"\
.format(' '.join(sn) ) )
idmap = {id: pos for pos, id in enumerate(sn)}
atms = sorted(atms, key=lambda atom: idmap[atom.name])
s_atoms.append(atms)
### from get randaxis from PC vector ###
#glycatms_ref = mda.AtomGroup([u.atoms.select_atoms("name P"), u.atoms.select_atoms("name C1")])
#glycatms_plane = mda.AtomGroup([u.atoms.select_atoms("name C1"), u.atoms.select_atoms("name C3")])
########################################
chainvec_atms1 = mda.AtomGroup([
u.atoms.select_atoms("name P"),
u.atoms.select_atoms("name C216")
])
chainvec_atms2 = mda.AtomGroup([
u.atoms.select_atoms("name P"),
u.atoms.select_atoms("name C316")
])
for t in range(len_traj):
time = u.trajectory[t].time
LOGGER.info("At time %s", time)
tailatms = SCD_TAIL_ATOMS_OF[LIPID[:2]]
positions = []
for atms in s_atoms:
positions.append([atm.position for atm in atms])
### from get randaxis from PC vector ###
#glycvecref = (glycatms_ref.positions[0] - glycatms_ref.positions[1])[0]
#glycvecref = glycvecref / np.linalg.norm(glycvecref)
#glycvecplane = (glycatms_plane.positions[0] - glycatms_plane.positions[1])[0]
#glycvecplane = glycvecplane / np.linalg.norm(glycvecplane)
########################################
chainatmvec1 = (chainvec_atms1.positions[0] -
chainvec_atms1.positions[1])[0]
#chainatmvec1 = chainatmvec1 / np.linalg.norm(chainatmvec1)
chainatmvec2 = (chainvec_atms2.positions[0] -
chainvec_atms2.positions[1])[0]
#chainatmvec2 = chainatmvec2 / np.linalg.norm(chainatmvec2)
for i in range(1000):
#### from get randaxis from PC vector ###
#refaxis = get_rand_axis(glycvecref, glycvecplane)
#tiltref = np.arccos(np.dot(refaxis, glycvecref)) * 180/np.pi
#print("{},{}".format(time, tiltref), file=axf)
#########################################
refaxis = np.random.random_sample((3, ))
refaxis = refaxis / np.linalg.norm(refaxis)
# projection of chainvec to new axis
projection_mag1 = np.dot(chainatmvec1, refaxis)
projection_mag2 = np.dot(chainatmvec2, refaxis)
order_val, s_prof = get_cc_order(positions, ref_axis=refaxis)
LOGGER.debug("printing to files ...")
### Print everything to files ###
line_scd = "{: <12.2f}{: <10}{: <15.8}{: <15.5}{: <15.5}{: <20}{: <20}{: <20}".format(
time, i, order_val, projection_mag1, projection_mag2,
*refaxis)
print(line_scd, file=scdfile)
def get_data():
first = True
for protein in protein_files:
filename = '%s/prot_atoms_dewetting_order.pdb' % (protein)
ppdb = PandasPdb()
ppdb.read_pdb(filename)
if protein == 'thymidylate_synthase':
u = mda.Universe('%s/actual_contact.pdb' % (protein))
contact = u.atoms.tempfactors
contact_ind = np.where(contact == 1)[0].tolist()
ag_contact = mda.AtomGroup(contact_ind, u)
interface_col = np.where(contact == 1, 1, 0)
else:
u = mda.Universe(protein + '/beta_phi_400/pred_contact_tp_fp.pdb')
contact = u.atoms.tempfactors.astype(int)
interface_col = np.where(contact == 1, 1, 0)
# create Pandas dataframe
df = ppdb.df['ATOM']
df = df.drop(columns=['record_name', 'atom_number', 'residue_number', 'x_coord', 'y_coord', 'z_coord', 'chain_id', 'blank_1', 'alt_loc', 'blank_2', 'insertion', 'blank_3', 'occupancy', 'blank_4',
'segment_id', 'element_symbol', 'charge', 'line_idx'])
# encode nominal variables
df = pd.get_dummies(df, columns=['atom_name'], prefix=['atom_name'])
df = pd.get_dummies(df, columns=['residue_name'], prefix=['residue_name'])
# add column that indicates whether atom is part of interface
df['Interface'] = interface_col
# for each beta phi value, access atoms that are predicted to be a part of the interface and compare to
# the actual contact atoms
if protein == 'thymidylate_synthase':
start = 0
end = 204
else:
start = 0
end = 204
for i in range(start, end, 4):
print(i)
df_concat = df
df_concat['Beta Phi Prediction Value'] = float(i) / 100
filename = protein + '/beta_phi_%03d/pred_contact_mask.dat' % (i)
contact_pred = np.loadtxt(filename)
df_concat['Prediction'] = contact_pred
# df_concat = df_concat.drop(df_concat[df_concat.Prediction == 0].index)
# df_concat['True Positive'] = (df_concat['Interface'] == 1) & (df_concat['Prediction'] == 1)
# df_concat = df_concat.drop(columns=['Prediction', 'Interface'])
if i == 0:
df_final = df_concat
else:
df_final = pd.concat([df_final, df_concat], ignore_index=True)
nn_col = get_num_nn(protein)
dewet_nn_col = get_num_dewet_nn(protein)
df_final['Number Nearest Neighbors'] = nn_col
df_final['Number Dewetted Nearest Neighbors'] = dewet_nn_col
df_final = df_final.drop(df_final[df_final.Prediction == 0].index)
df_final['True Positive'] = (df_final['Interface'] == 1) & (df_final['Prediction'] == 1)
df_final = df_final.drop(columns=['Prediction', 'Interface'])
if first:
df_final_final = df_final
first = False
else:
df_final_final = pd.concat([df_final_final, df_final], ignore_index=True)
df_final_final[['True Positive']] *= 1
df_final_final = df_final_final.loc[df_final_final['b_factor'] > -2]
# randomize rows in dataframe
df_final_final = df_final_final.sample(frac=1)
df_final_final = df_final_final.fillna(0)
x = df_final_final.iloc[:, df_final_final.columns != 'True Positive'].values
y = df_final_final['True Positive'].values
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.15)
# scale values
sc = StandardScaler()
x_train = sc.fit_transform(x_train)
x_test = sc.transform(x_test)
return x_train, x_test, y_train, y_test, df_final_final
atom_groups_clusters = []
positions = positions.tolist()
for n in range(len(hist) - 1):
if hist[n] == 0 or hist[n] == 1:
n += 1
else:
for cluster in cluster_atoms(n + 1):
atom_group_inds = []
bin_positions_ind = np.where(inds == (n + 1))[0]
bin_positions = [positions[i] for i in bin_positions_ind]
for ind in cluster:
point = [bin_positions[ind][0], bin_positions[ind][1], bin_positions[ind][2]]
index = positions.index(point)
atom_group_inds.append(index)
atom_group = mda.AtomGroup(atom_group_inds, u)
atom_groups_clusters.append(atom_group)
# create atom groups with atoms in same bin
atom_groups_bins = []
for i in range(1, max(inds)):
atom_group_inds = [m for m, n in enumerate(inds) if n == i]
atom_group = mda.AtomGroup(atom_group_inds, u)
atom_groups_bins.append(atom_group)
# write selections to vmd file
with mda.selections.vmd.SelectionWriter('selection.vmd', mode='w') as vmd:
cluster_num = 0
for ag in atom_groups_clusters: