def get_residue_name(imol, res_spec):
return coot.residue_name(imol, rsu.residue_spec_to_chain_id(res_spec), rsu.residue_spec_to_res_no(res_spec), "")
def find_the_sites(self, file_name_comp_id_list):
# main line
#
coords_with_spec = []
for fn_comp_id in file_name_comp_id_list:
fn = fn_comp_id[0]
comp_id = fn_comp_id[1]
imol = coot.handle_read_draw_molecule_with_recentre(fn_comp_id[0], 0)
# what are the residue specs for the given comp_ids?
residue_specs = coot.get_residue_specs_in_mol_py(imol, comp_id)
print fn, residue_specs
for spec in residue_specs:
# centre = residue_centre_from_spec_py(imol, spec)
chain_id = rsu.residue_spec_to_chain_id(spec)
res_no = rsu.residue_spec_to_res_no(spec)
ins_code = ""
res_info = coot.residue_info_py(imol, chain_id, res_no, ins_code)
for atom in res_info:
coords_with_spec.append([rsu.residue_atom_to_position(atom), imol, spec])
# print coords_with_spec
# now cluster coords. There will be 1 (usually), maybe 2 possibly 3 sites
if len(coords_with_spec) < 3:
return False
else:
coords = [x[0] for x in coords_with_spec]
positions_np = np.array(coords)
n_components = self.optimize_n(positions_np, len(positions_np))
print "optimize_n for sites::::::::::::", n_components
dpgmm = mixture.GMM(n_components, covariance_type="full", n_iter=40)
dpgmm.fit(positions_np)
cluster_assignments = dpgmm.predict(positions_np)
means = dpgmm.means_
weights = dpgmm.weights_
print cluster_assignments
print means
print weights
print "cluster_assignments", cluster_assignments
merge_map = self.find_mergeable_clusters(means, weights)
# which key (i.e. cluster index) has the most number of other clusters
# that can be merged in?
#
# convert to a list of ints (not <type 'numpy.int64'>) (because, on decoding Python->C++ object
# we do a PyInt_Check for the site_idx (and a <type 'numpy.int64'> fails that test)
#
new_cluster_assignments = [int(x) for x in self.merge_clusters(cluster_assignments, merge_map)]
print "new cluster_assignments", new_cluster_assignments
specs = [x[1:] for x in coords_with_spec]
cluster_assignments_with_specs = zip(new_cluster_assignments, specs)
sites = coot.chemical_feature_clusters_accept_site_clusters_info_py(cluster_assignments_with_specs)
# show me them
if True: # debug
o = coot.new_generic_object_number("site clusters")
for mean in means:
cluster_star_obj(o, mean, 2, 2)
# coot.set_display_generic_object(o, 1) this is for debugging
self.sites = sites
def cfc_process_site(site_number, imol_ligand_specs, first_ligand_spec):
imol_first = imol_ligand_specs[0][0] # others are lsq fitted to this
env_residue_specs = coot.residues_near_residue_py(imol_first, first_ligand_spec, 6)
protein_res_specs = [r for r in env_residue_specs if get_residue_name(imol_first, r) != "HOH"]
# only lsq the first (0th) one - that one has the most ligands in the site
#
if site_number == 0:
print "DEBUG:: protein_res_specs (for lsqing):"
for spec in protein_res_specs:
print " ", spec, get_residue_name(imol_first, spec)
for res_spec in protein_res_specs:
chain_id = rsu.residue_spec_to_chain_id(res_spec)
res_no = rsu.residue_spec_to_res_no(res_spec)
coot.add_lsq_match(res_no, res_no, chain_id, res_no, res_no, chain_id, 1)
for imol in imol_ligand_specs[1:]: # lsq fit others to the first in the list
coot.apply_lsq_matches_py(imol_first, imol[0])
ligand_centre = coot.residue_centre_py(
imol_first,
rsu.residue_spec_to_chain_id(first_ligand_spec),
rsu.residue_spec_to_res_no(first_ligand_spec),
"",
)
coot.set_go_to_atom_molecule(imol_first)
coot.set_rotation_centre(*ligand_centre)
combo_list = []
try:
# we have a large radius for the water selection
radius = 10 # water must be within radius of it's own ligand
radius_2 = 5 # water must be with radius_2 of any ligand atom (not just its own)
combo_list = coot.chemical_feature_clusters_py(env_residue_specs, imol_ligand_specs, radius, radius_2)
except TypeError as e:
print e
# the rest is unlikely to work if we get here
if True:
water_position_list = combo_list[0]
chemical_feature_list = combo_list[1]
# residues_sidechains_list = combo_list[1]
# ----------- handle waters -----------
w_positions_list = []
for item in [wat[2] for wat in water_position_list]:
w_positions_list.append(item)
for item in [wat[2] for wat in water_position_list]:
delta = 0.1
p1 = [item[0], item[1], item[2] + delta]
p2 = [item[0], item[1], item[2] - delta]
p3 = [item[0], item[1] + delta, item[2]]
p4 = [item[0], item[1] - delta, item[2]]
p5 = [item[0] + delta, item[1], item[2]]
p6 = [item[0] - delta, item[1], item[2]]
w_positions_list.append(p1)
w_positions_list.append(p2)
w_positions_list.append(p3)
w_positions_list.append(p4)
w_positions_list.append(p5)
w_positions_list.append(p6)
w_positions_np = np.array(w_positions_list)
# move these to the origin
# w_positions_np = w_positions_np_at_ligand
# for pos in w_positions_np:
# pos -= np.array(ligand_centre)
# dpgmm = mixture.DPGMM(n_components=25, covariance_type='spherical', alpha=1.101,
# n_iter=40000, params='wmc', init_params='wmc', tol=1e-4,
# verbose=0)
#
# the number of clusters is highly related to the dist_cutoff (the
# distance of an accepted water atom to any any atom in any of the
# ligands = currently 4.2)
#
gmm, cluster_assignments = cluster_and_display_waters(site_number, w_positions_np)
means = gmm.means_
cvs = gmm._get_covars()
weights = gmm.weights_
print "water means:"
for mean in means:
print " ", mean
# each water has been assigned a cluster, that is the cluster_assignments
#
# need to convert the array cluster_assignments to a list of items:
# [imol water_residue_spec cluster_number]
#
water_cluster_info_for_input = []
for i, water_pos in enumerate(water_position_list):
# print water_pos, cluster_assignments[i]
item = [water_pos[0], water_pos[1], cluster_assignments[i]]
water_cluster_info_for_input.append(item)
# cluster_info is a list of
# list of water cluster info
# list of [mean, weight, length] where length is the eigenvalue v[0],
# (same as v[1], v[2] - all the same for spherical model)
# list of cluster predictions for then input positions
#
ci = zip([[l[0], l[1], l[2]] for l in means], weights, [cv[0][0] for cv in cvs])
water_cluster_info = [ci, water_cluster_info_for_input]
# give those results back to c++ so that we can use them for display
#
coot.set_display_generic_objects_as_solid(1)
# ----------- handle chemical features -----------
# make a dictionary from the list of chemical features
chemical_features_dict = {}
for item in chemical_feature_list:
for type in ["Donor", "Acceptor", "Aromatic", "Hydrophobe", "LumpedHydrophobe"]:
if item[0] == type:
try:
chemical_features_dict[type].append(item[1:])
except KeyError:
chemical_features_dict[type] = [item[1:]]
chemical_feature_clusters_info = []
for key in chemical_features_dict:
# list of [type, features-annotated-by-cluster-number, cluster_means]
clusters = cluster_and_display_chemical_features(site_number, key, chemical_features_dict[key])
chemical_feature_clusters_info.append(clusters)
# print 'water_cluster_info'
# for wc in water_cluster_info:
# print wc
cluster_info = [water_cluster_info, chemical_feature_clusters_info]
coot.chemical_feature_clusters_accept_info_py(site_number, protein_res_specs, imol_ligand_specs, cluster_info)
def get_residue_name(imol, res_spec):
return coot.residue_name(imol, rsu.residue_spec_to_chain_id(res_spec),
rsu.residue_spec_to_res_no(res_spec), "")
def find_the_sites(self, file_name_comp_id_list):
# main line
#
coords_with_spec = []
for fn_comp_id in file_name_comp_id_list:
fn = fn_comp_id[0]
comp_id = fn_comp_id[1]
imol = coot.handle_read_draw_molecule_with_recentre(
fn_comp_id[0], 0)
# what are the residue specs for the given comp_ids?
residue_specs = coot.get_residue_specs_in_mol_py(imol, comp_id)
print(fn, residue_specs)
for spec in residue_specs:
# centre = residue_centre_from_spec_py(imol, spec)
chain_id = rsu.residue_spec_to_chain_id(spec)
res_no = rsu.residue_spec_to_res_no(spec)
ins_code = ''
res_info = coot.residue_info_py(imol, chain_id, res_no,
ins_code)
for atom in res_info:
coords_with_spec.append(
[rsu.residue_atom_to_position(atom), imol, spec])
# print coords_with_spec
# now cluster coords. There will be 1 (usually), maybe 2 possibly 3 sites
if len(coords_with_spec) < 3:
return False
else:
coords = [x[0] for x in coords_with_spec]
positions_np = np.array(coords)
n_components = self.optimize_n(positions_np, len(positions_np))
print("optimize_n for sites::::::::::::", n_components)
dpgmm = mixture.GMM(n_components,
covariance_type='full',
n_iter=40)
dpgmm.fit(positions_np)
cluster_assignments = dpgmm.predict(positions_np)
means = dpgmm.means_
weights = dpgmm.weights_
print(cluster_assignments)
print(means)
print(weights)
print("cluster_assignments", cluster_assignments)
merge_map = self.find_mergeable_clusters(means, weights)
# which key (i.e. cluster index) has the most number of other clusters
# that can be merged in?
#
# convert to a list of ints (not <type 'numpy.int64'>) (because, on decoding Python->C++ object
# we do a PyInt_Check for the site_idx (and a <type 'numpy.int64'> fails that test)
#
new_cluster_assignments = [
int(x)
for x in self.merge_clusters(cluster_assignments, merge_map)
]
print("new cluster_assignments", new_cluster_assignments)
specs = [x[1:] for x in coords_with_spec]
cluster_assignments_with_specs = zip(new_cluster_assignments,
specs)
sites = coot.chemical_feature_clusters_accept_site_clusters_info_py(
cluster_assignments_with_specs)
# show me them
if True: # debug
o = coot.new_generic_object_number("site clusters")
for mean in means:
cluster_star_obj(o, mean, 2, 2)
# coot.set_display_generic_object(o, 1) this is for debugging
self.sites = sites
def cfc_process_site(site_number, imol_ligand_specs, imol_first,
first_ligand_spec):
print("debug:: in cfc_process_site with imol_ligand_specs",
imol_ligand_specs)
print("debug:: in cfc_process_site with non-first imol_ligand_specs",
imol_ligand_specs[1:])
# print("calling residues_near_residue_py", imol_first, first_ligand_spec)
env_residue_specs = coot.residues_near_residue_py(imol_first,
first_ligand_spec, 6)
# print("env_residue_specs", env_residue_specs)
protein_res_specs = [
r for r in env_residue_specs
if get_residue_name(imol_first, r) != "HOH"
]
# only lsq the first (0th) one - that one has the most ligands in the site
#
if site_number == 0:
# print("protein_res_specs (for lsqing):")
# for spec in protein_res_specs:
# print(" ", spec, get_residue_name(imol_first, spec))
for res_spec in protein_res_specs:
chain_id = rsu.residue_spec_to_chain_id(res_spec)
res_no = rsu.residue_spec_to_res_no(res_spec)
coot.add_lsq_match(res_no, res_no, chain_id, res_no, res_no,
chain_id, 1)
for imol_and_spec in imol_ligand_specs[
1:]: # lsq fit others to the first in the list
print('============================ lsq-match ', imol_first,
imol_and_spec, imol_and_spec[0])
imol, spec = imol_and_spec
# coot.apply_lsq_matches_py(imol_first, imol_and_spec[0])
coot.apply_lsq_matches_py(imol_first, imol)
make_ball_and_stick_by_spec(imol, spec)
# pass
print("Here with first_ligand_spec:", first_ligand_spec)
ligand_centre = coot.residue_centre_py(
imol_first, rsu.residue_spec_to_chain_id(first_ligand_spec),
rsu.residue_spec_to_res_no(first_ligand_spec), '')
coot.set_go_to_atom_molecule(imol_first)
coot.set_rotation_centre(*ligand_centre)
combo_list = []
try:
# we have a large radius for the water selection
radius = 10 # water must be within radius of it's own ligand
radius_2 = 5 # water must be with radius_2 of any ligand atom (not just its own)
combo_list = coot.chemical_feature_clusters_py(env_residue_specs,
imol_ligand_specs,
radius, radius_2)
except TypeError as e:
print(e)
# the rest is unlikely to work if we get here
if True:
water_position_list = combo_list[0]
chemical_feature_list = combo_list[1]
# residues_sidechains_list = combo_list[1]
# ----------- handle waters -----------
w_positions_list = []
for item in [wat[2] for wat in water_position_list]:
w_positions_list.append(item)
for item in [wat[2] for wat in water_position_list]:
delta = 0.1
p1 = [item[0], item[1], item[2] + delta]
p2 = [item[0], item[1], item[2] - delta]
p3 = [item[0], item[1] + delta, item[2]]
p4 = [item[0], item[1] - delta, item[2]]
p5 = [item[0] + delta, item[1], item[2]]
p6 = [item[0] - delta, item[1], item[2]]
w_positions_list.append(p1)
w_positions_list.append(p2)
w_positions_list.append(p3)
w_positions_list.append(p4)
w_positions_list.append(p5)
w_positions_list.append(p6)
w_positions_np = np.array(w_positions_list)
# move these to the origin
# w_positions_np = w_positions_np_at_ligand
# for pos in w_positions_np:
# pos -= np.array(ligand_centre)
# dpgmm = mixture.DPGMM(n_components=25, covariance_type='spherical', alpha=1.101,
# n_iter=40000, params='wmc', init_params='wmc', tol=1e-4,
# verbose=0)
#
# the number of clusters is highly related to the dist_cutoff (the
# distance of an accepted water atom to any any atom in any of the
# ligands = currently 4.2)
#
gmm, cluster_assignments = cluster_and_display_waters(
site_number, w_positions_np)
means = gmm.means_
cvs = gmm._get_covars()
weights = gmm.weights_
print("water means:")
for mean in means:
print(" ", mean)
# each water has been assigned a cluster, that is the cluster_assignments
#
# need to convert the array cluster_assignments to a list of items:
# [imol water_residue_spec cluster_number]
#
water_cluster_info_for_input = []
for i, water_pos in enumerate(water_position_list):
# print water_pos, cluster_assignments[i]
item = [water_pos[0], water_pos[1], cluster_assignments[i]]
water_cluster_info_for_input.append(item)
# cluster_info is a list of
# list of water cluster info
# list of [mean, weight, length] where length is the eigenvalue v[0],
# (same as v[1], v[2] - all the same for spherical model)
# list of cluster predictions for then input positions
#
ci = list(
zip([[l[0], l[1], l[2]] for l in means], weights,
[cv[0][0] for cv in cvs]))
water_cluster_info = [ci, water_cluster_info_for_input]
# give those results back to c++ so that we can use them for display
#
coot.set_display_generic_objects_as_solid(1)
# ----------- handle chemical features -----------
# make a dictionary from the list of chemical features
chemical_features_dict = {}
for item in chemical_feature_list:
for type in [
'Donor', 'Acceptor', 'Aromatic', 'Hydrophobe',
'LumpedHydrophobe'
]:
if item[0] == type:
try:
chemical_features_dict[type].append(item[1:])
except KeyError:
chemical_features_dict[type] = [item[1:]]
chemical_feature_clusters_info = []
for key in chemical_features_dict:
# list of [type, features-annotated-by-cluster-number, cluster_means]
clusters = cluster_and_display_chemical_features(
site_number, key, chemical_features_dict[key])
chemical_feature_clusters_info.append(clusters)
# print 'water_cluster_info'
# for wc in water_cluster_info:
# print wc
cluster_info = [water_cluster_info, chemical_feature_clusters_info]
coot.chemical_feature_clusters_accept_info_py(site_number,
protein_res_specs,
imol_ligand_specs,
cluster_info)
