def __drawOrigCoords(origCoords):
"""Display the original pre-rotamerize coordinates as a generic object
ARGUMENTS:
origCoords - a chain object containing the atoms to be drawn
RETURNS:
drawNum - the generic object number
EFFECTS:
creates and displays a new Coot generic object
"""
#create a new generic display object
drawNum = new_generic_object_number("Pre-rotamerize coordinates")
set_display_generic_object(drawNum, 1)
lineList = [] #a list of all the bonds to be drawn
#draw bonds for each nucleotide
prevO3 = None
for curNuc in origCoords.nucs:
#draw each bond if both atoms are present
for (atom1, atom2) in (BOND_LIST_FULL["backbone"] +
BOND_LIST_FULL[curNuc.type]):
if curNuc.hasAtom(atom1) and curNuc.hasAtom(atom2):
atom1Coords = curNuc.atoms[atom1]
atom2Coords = curNuc.atoms[atom2]
lineList.append(atom1Coords + atom2Coords)
#draw a bond between O5' and the previous phosphate if both atoms are present
if prevO3 is not None and curNuc.hasAtom("P"):
lineList.append(prevO3 + curNuc.atoms["P"])
#update prevPhos
if curNuc.hasAtom("O3'"):
prevO3 = curNuc.atoms["O3'"]
else:
prevO3 = None
#actually draw the bonds
for curLine in lineList:
to_generic_object_add_line(drawNum, ORIG_COORDS_COLOR, 6, *curLine)
graphics_draw()
return drawNum
def __drawOrigCoords(origCoords):
"""Display the original pre-rotamerize coordinates as a generic object
ARGUMENTS:
origCoords - a chain object containing the atoms to be drawn
RETURNS:
drawNum - the generic object number
EFFECTS:
creates and displays a new Coot generic object
"""
#create a new generic display object
drawNum = new_generic_object_number("Pre-rotamerize coordinates")
set_display_generic_object(drawNum, 1)
lineList = [] #a list of all the bonds to be drawn
#draw bonds for each nucleotide
prevO3 = None
for curNuc in origCoords.nucs:
#draw each bond if both atoms are present
for (atom1, atom2) in (BOND_LIST_FULL["backbone"] + BOND_LIST_FULL[curNuc.type]):
if curNuc.hasAtom(atom1) and curNuc.hasAtom(atom2):
atom1Coords = curNuc.atoms[atom1]
atom2Coords = curNuc.atoms[atom2]
lineList.append(atom1Coords + atom2Coords)
#draw a bond between O5' and the previous phosphate if both atoms are present
if prevO3 is not None and curNuc.hasAtom("P"):
lineList.append(prevO3 + curNuc.atoms["P"])
#update prevPhos
if curNuc.hasAtom("O3'"):
prevO3 = curNuc.atoms["O3'"]
else:
prevO3 = None
#actually draw the bonds
for curLine in lineList:
to_generic_object_add_line(drawNum, ORIG_COORDS_COLOR, 6, *curLine)
graphics_draw()
return drawNum
def cluster_and_display_waters(site_number, w_positions_np):
def optimize_n(positions_np, n_data):
bic = {}
for n in [x + 1 for x in range(20)]:
if n < len(positions_np):
gmm = mixture.GMM(n_components=n, covariance_type="spherical", n_iter=20)
gmm.fit(positions_np)
score = sum(gmm.score(positions_np))
lambda_c = 15 # 3 too few
bic_l = score - lambda_c * 0.5 * math.log(n_data) * n
bic[n] = bic_l
for key in bic:
print " water bic", key, bic[key]
key, value = max(bic.iteritems(), key=lambda x: x[1])
return key
n_components = optimize_n(w_positions_np, len(w_positions_np))
print "optimize_n for water:::::::::::::", n_components
dpgmm = mixture.GMM(n_components, covariance_type="spherical", n_iter=40)
dpgmm.fit(w_positions_np)
cluster_assignments = dpgmm.predict(w_positions_np)
color_list = [
"green",
"greentint",
"sea",
"yellow",
"yellowtint",
"aquamarine",
"forestgreen",
"goldenrod",
"orangered",
"orange",
"cyan",
"red",
"blue",
]
color_list.extend(color_list)
color_list.extend(color_list)
color_list.extend(color_list)
color_list.extend(color_list)
color_list.extend(color_list)
color_list.extend(color_list)
color_list.extend(color_list)
color_list.extend(color_list)
color_list.extend(color_list)
color_list.extend(color_list)
color_list.extend(color_list)
means = dpgmm.means_
cvs = dpgmm._get_covars()
weights = dpgmm.weights_
obj = coot.new_generic_object_number("CFC Site " + str(site_number) + " selected waters")
for i, pos in enumerate(w_positions_np):
mean = means[cluster_assignments[i]]
# reject spheres at the origin - (from DPGMM strangeness)
d = mean[0] * mean[0] + mean[1] * mean[1] + mean[2] * mean[2]
if d > 1.0:
col = color_list[cluster_assignments[i]]
coot.to_generic_object_add_point(obj, col, 10, pos[0], pos[1], pos[2])
else:
print "reject prediction", i, "for cluster", cluster_assignments[i]
# set_display_generic_object(obj, 1)
obj = coot.new_generic_object_number("CFC Site " + str(site_number) + " water cluster means")
for i, cv in enumerate(cvs):
mean = means[i]
d = mean[0] * mean[0] + mean[1] * mean[1] + mean[2] * mean[2]
v, w = linalg.eigh(cv)
# print "mean ", mean
# print "weight", weights[i], "prec", precs[i]
# print "weight", weights[i]
# print "v", v
if d > 1.0:
pos = mean
thick = 2
cluster_star_obj(obj, pos, thick, v[0])
else:
print "reject", mean, v
coot.set_display_generic_object(obj, 1)
cluster_assignments_as_list = [int(x) for x in cluster_assignments]
return (dpgmm, cluster_assignments_as_list)
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 cluster_and_display_chemical_features(site_number, type, chemical_features_list):
def optimize_n(type, positions_np, n_data):
print "cluster_and_display_chemical_features.optimize_n called " "with n_data = ", n_data
bic = {}
for n in [x + 1 for x in range(10)]:
if n < n_data:
gmm = mixture.GMM(n_components=n, covariance_type="spherical", n_iter=20)
gmm.fit(positions_np)
score = sum(gmm.score(positions_np))
lambda_c = 15
if type == "Aromatic":
lambda_c = 20
bic_l = score - lambda_c * 0.5 * math.log(n_data) * n
bic[n] = bic_l
if len(bic) > 1:
key, value = max(bic.iteritems(), key=lambda x: x[1])
return key
else:
return 1
def analyse_bic(type, positions_np, n_data):
for n in [x + 1 for x in range(14)]:
gmm = mixture.GMM(n_components=n, covariance_type="spherical", n_iter=20)
gmm.fit(positions_np)
score = sum(gmm.score(positions_np))
lambda_c = 3
if type == "Aromatic":
lambda_c = 3000
bic = score - lambda_c * 0.5 * n_data * n
print type, len(positions_np), n, "converged?", gmm.converged_, "score:", score, "bic", bic
def get_cfc_col(type):
if type == "Donor":
return "blue"
if type == "Acceptor":
return "red"
if type == "Hydrophobe":
return "yellow"
if type == "Aromatic":
return "orange"
return "grey"
# --- main line ----
# no fake points
# positions_np = np.array([item[0] for item in chemical_features_list])
ext_chemical_features_list = [item[0] for item in chemical_features_list]
for item_b in chemical_features_list:
delta = 0.25
item = item_b[0]
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]]
ext_chemical_features_list.append(p1)
ext_chemical_features_list.append(p2)
ext_chemical_features_list.append(p3)
ext_chemical_features_list.append(p4)
ext_chemical_features_list.append(p5)
ext_chemical_features_list.append(p6)
positions_np = np.array(ext_chemical_features_list)
# analyse_bic(type, positions_np, len(chemical_features_list))
n_data = len(chemical_features_list)
n = 1
if n_data > 1:
n = optimize_n(type, positions_np, n_data)
if n <= len(chemical_features_list):
gmm = mixture.GMM(n_components=n, covariance_type="spherical", n_iter=20)
gmm.fit(positions_np)
print type, len(positions_np), n, "converged? ", gmm.converged_, "score:", sum(gmm.score(positions_np))
cluster_assignments = gmm.predict(positions_np)
features = []
for i, cf in enumerate(chemical_features_list):
# print " ", cf, cluster_assignments[i]
features.append([cf, int(cluster_assignments[i])])
means = gmm.means_
means_as_list = [[x[0], x[1], x[2]] for x in means]
obj_name = "CFC Site " + str(site_number) + " " + type + " pharmacophore-clusters"
cfc_obj = coot.new_generic_object_number(obj_name)
cfc_col = get_cfc_col(type)
for mean in means_as_list:
# coot.to_generic_object_add_dodecahedron(cfc_obj, cfc_col, 0.2, mean[0], mean[1], mean[2])
coot.to_generic_object_add_pentakis_dodecahedron(cfc_obj, cfc_col, 2.3, 0.1, mean[0], mean[1], mean[2])
coot.set_display_generic_object(cfc_obj, 1)
return [type, features, means_as_list]
# oops too many parameters for the model
return False
def cluster_and_display_waters(site_number, w_positions_np):
def optimize_n(positions_np, n_data):
bic = {}
for n in [x + 1 for x in range(20)]:
if n < len(positions_np):
gmm = mixture.GMM(n_components=n,
covariance_type='spherical',
n_iter=20)
gmm.fit(positions_np)
score = sum(gmm.score(positions_np))
lambda_c = 15 # 3 too few
bic_l = score - lambda_c * 0.5 * math.log(n_data) * n
bic[n] = bic_l
for key in bic:
print(" water bic", key, bic[key])
key, value = max(iter(bic.items()), key=lambda x: x[1])
return key
n_components = optimize_n(w_positions_np, len(w_positions_np))
print("optimize_n for water:::::::::::::", n_components)
dpgmm = mixture.GMM(n_components, covariance_type='spherical', n_iter=40)
dpgmm.fit(w_positions_np)
cluster_assignments = dpgmm.predict(w_positions_np)
color_list = [
'green', 'greentint', "sea", 'yellow', "yellowtint", "aquamarine",
"forestgreen", "goldenrod", "orangered", "orange", "cyan", 'red',
"blue"
]
color_list.extend(color_list)
color_list.extend(color_list)
color_list.extend(color_list)
color_list.extend(color_list)
color_list.extend(color_list)
color_list.extend(color_list)
color_list.extend(color_list)
color_list.extend(color_list)
color_list.extend(color_list)
color_list.extend(color_list)
color_list.extend(color_list)
means = dpgmm.means_
cvs = dpgmm._get_covars()
weights = dpgmm.weights_
obj = coot.new_generic_object_number("CFC Site " + str(site_number) +
" selected waters")
for i, pos in enumerate(w_positions_np):
mean = means[cluster_assignments[i]]
# reject spheres at the origin - (from DPGMM strangeness)
d = mean[0] * mean[0] + mean[1] * mean[1] + mean[2] * mean[2]
if d > 1.0:
col = color_list[cluster_assignments[i]]
coot.to_generic_object_add_point(obj, col, 10, pos[0], pos[1],
pos[2])
else:
print("reject prediction", i, "for cluster",
cluster_assignments[i])
# set_display_generic_object(obj, 1)
obj = coot.new_generic_object_number("CFC Site " + str(site_number) +
" water cluster means")
for i, cv in enumerate(cvs):
mean = means[i]
d = mean[0] * mean[0] + mean[1] * mean[1] + mean[2] * mean[2]
v, w = linalg.eigh(cv)
# print "mean ", mean
# print "weight", weights[i], "prec", precs[i]
# print "weight", weights[i]
# print "v", v
if d > 1.0:
pos = mean
thick = 2
cluster_star_obj(obj, pos, thick, v[0])
else:
print("reject", mean, v)
coot.set_display_generic_object(obj, 1)
cluster_assignments_as_list = [int(x) for x in cluster_assignments]
return (dpgmm, cluster_assignments_as_list)
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 cluster_and_display_chemical_features(site_number, type,
chemical_features_list):
def optimize_n(type, positions_np, n_data):
print("cluster_and_display_chemical_features.optimize_n called " \
"with n_data = ", n_data)
bic = {}
for n in [x + 1 for x in range(10)]:
if n < n_data:
gmm = mixture.GMM(n_components=n,
covariance_type='spherical',
n_iter=20)
gmm.fit(positions_np)
score = sum(gmm.score(positions_np))
lambda_c = 15
if type == 'Aromatic':
lambda_c = 20
bic_l = score - lambda_c * 0.5 * math.log(n_data) * n
bic[n] = bic_l
if len(bic) > 1:
key, value = max(iter(bic.items()), key=lambda x: x[1])
return key
else:
return 1
def analyse_bic(type, positions_np, n_data):
for n in [x + 1 for x in range(14)]:
gmm = mixture.GMM(n_components=n,
covariance_type='spherical',
n_iter=20)
gmm.fit(positions_np)
score = sum(gmm.score(positions_np))
lambda_c = 3
if type == 'Aromatic':
lambda_c = 3000
bic = score - lambda_c * 0.5 * n_data * n
print(type, len(positions_np), n, "converged?", gmm.converged_,
"score:", score, "bic", bic)
def get_cfc_col(type):
if type == "Donor":
return "blue"
if type == "Acceptor":
return "red"
if type == "Hydrophobe":
return "yellow"
if type == "Aromatic":
return "orange"
return "grey"
# --- main line ----
# no fake points
# positions_np = np.array([item[0] for item in chemical_features_list])
ext_chemical_features_list = [item[0] for item in chemical_features_list]
for item_b in chemical_features_list:
delta = 0.25
item = item_b[0]
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]]
ext_chemical_features_list.append(p1)
ext_chemical_features_list.append(p2)
ext_chemical_features_list.append(p3)
ext_chemical_features_list.append(p4)
ext_chemical_features_list.append(p5)
ext_chemical_features_list.append(p6)
positions_np = np.array(ext_chemical_features_list)
# analyse_bic(type, positions_np, len(chemical_features_list))
n_data = len(chemical_features_list)
n = 1
if n_data > 1:
n = optimize_n(type, positions_np, n_data)
if n <= len(chemical_features_list):
gmm = mixture.GMM(n_components=n,
covariance_type='spherical',
n_iter=20)
gmm.fit(positions_np)
print(type, len(positions_np), n, "converged? ", gmm.converged_,
"score:", sum(gmm.score(positions_np)))
cluster_assignments = gmm.predict(positions_np)
features = []
for i, cf in enumerate(chemical_features_list):
# print " ", cf, cluster_assignments[i]
features.append([cf, int(cluster_assignments[i])])
means = gmm.means_
means_as_list = [[x[0], x[1], x[2]] for x in means]
obj_name = "CFC Site " + str(
site_number) + " " + type + " pharmacophore-clusters"
cfc_obj = coot.new_generic_object_number(obj_name)
cfc_col = get_cfc_col(type)
for mean in means_as_list:
# coot.to_generic_object_add_dodecahedron(cfc_obj, cfc_col, 0.2, mean[0], mean[1], mean[2])
coot.to_generic_object_add_pentakis_dodecahedron(
cfc_obj, cfc_col, 2.3, 0.1, mean[0], mean[1], mean[2])
coot.set_display_generic_object(cfc_obj, 1)
return [type, features, means_as_list]
# oops too many parameters for the model
return False
