def extract_feature(self):
print_info_nn(" >>> Adding secondary structure for database {0} ... ".format(self._database.name))
overall_time = datetime.now()
counter = 0
if not os.path.exists(self.__get_dir_name()):
os.mkdir(self.__get_dir_name())
for complex_name in self._database.complexes.keys():
protein_complex = self._database.complexes[complex_name]
proteins = [protein_complex.unbound_formation.ligand, protein_complex.unbound_formation.receptor]
for protein in proteins:
protrusion_file = self.__get_dir_name() + protein.name
if not os.path.exists(protrusion_file+".npy"):
counter += 1
if counter <= 15:
print_info_nn("{0}, ".format(protein.name))
else:
counter = 0
print_info("{0}".format(protein.name))
pdb_file = self._database.directory + pdb_directory + protein.name + ".pdb"
result_dict = run_psaia(pdb_file)
protrusion_array = np.zeros((len(protein.residues), 5 + 5 + 5 + 6 + 6 + 1))
if result_dict is not None:
for index, residue in enumerate(protein.biopython_residues):
key = self.get_residue_id(residue.get_full_id())
if key in result_dict:
values = result_dict[key]
protrusion_array[index, :] = self._normalize_features(*values)
else:
print('key not found in PSAIA processing!')
np.save(protrusion_file, protrusion_array)
protrusion_array = np.load(protrusion_file+".npy")
for index, residue in enumerate(protein.residues):
residue.add_feature(Features.PROTRUSION_INDEX, protrusion_array[index, 21:])
print_info("took {0} seconds.".format((datetime.now() - overall_time).seconds))
def __compute_profiles(self, db='nr', niter=3):
print_info_nn(" >>> Adding the profile features for dataset {0} ...".format(self._database.name))
start_time = datetime.now()
for complex_name in self._database.complexes.keys():
protein_complex = self._database.complexes[complex_name]
proteins = [protein_complex.unbound_formation.ligand, protein_complex.unbound_formation.receptor]
for protein in proteins:
fasta_file = self._database.directory + unbound_sequence_directory + protein.name + ".fasta"
output_file = self._database.directory + pssm_directory + protein.name
if not os.path.exists(output_file + ".mat"):
print_info("... processing protein {0} ... ".format(protein.name))
command = "cd {4} \n " \
"{5} " \
"-query {0} -db {1} -out {2}.psi.txt -num_iterations {3} -out_ascii_pssm {2}.mat" \
.format(fasta_file, db, output_file, niter, psiblast_db_folder, psiblast_executable)
print_info(command)
error_code = os.system(command)
if error_code == 0:
print_info('Successful!')
else:
print_error('Failed with error code {0}'.format(error_code))
pssm, psfm, info = ProfileExtractor.__parse_pssm_file(output_file + ".mat")
wpssm = ProfileExtractor.__get_wpsm(pssm)
wpsfm = ProfileExtractor.__get_wpsm(psfm)
for i, res in enumerate(protein.residues):
res.add_feature(Features.POSITION_SPECIFIC_SCORING_MATRIX, self._normalize(pssm[:, i]))
res.add_feature(Features.POSITION_SPECIFIC_FREQUENCY_MATRIX, self._normalize(psfm[:, i]))
res.add_feature(Features.WINDOWED_POSITION_SPECIFIC_SCORING_MATRIX, self._normalize(wpssm[:, i]))
res.add_feature(Features.WINDOWED_POSITION_SPECIFIC_FREQUENCY_MATRIX, self._normalize(wpsfm[:, i]))
print_info("took {0} seconds.".format((datetime.now() - start_time).seconds))
def extract_feature(self):
seed(self.seed)
counter = 0
print_info_nn(" >>> Adding D2 category based shape distribution for database {0} ... ".format(self._database.name))
overall_time = datetime.now()
if not os.path.exists(self._get_dir_name()):
os.makedirs(self._get_dir_name())
for complex_name in self._database.complexes.keys():
protein_complex = self._database.complexes[complex_name]
proteins = [protein_complex.unbound_formation.ligand, protein_complex.unbound_formation.receptor]
for protein in proteins:
shape_dist_file = self._get_dir_name() + protein.name
if not os.path.exists(shape_dist_file + ".npy"):
counter += 1
if counter <= 15:
print_info_nn("{0}, ".format(protein.name))
else:
counter = 0
print_info("{0}".format(protein.name))
atoms = protein.atoms
neighbour_search = NeighborSearch(atoms)
distributions = np.zeros((len(protein.residues), self.number_of_bins))
for i in range(len(protein.residues)):
residue = protein.residues[i]
nearby_residues = neighbour_search.search(residue.center, self.radius, "R")
distributions[i, :] = self._compute_distribution(nearby_residues)
np.save(shape_dist_file, distributions)
distributions = np.load(shape_dist_file + ".npy")
for i in range(len(protein.residues)):
protein.residues[i].add_feature(Features.D2_CATEGORY_SHAPE_DISTRIBUTION, distributions[i, :])
print_info("took {0} seconds.".format((datetime.now() - overall_time).seconds))
def extract_feature(self):
seed(self.seed)
print_info_nn(
" >>> Adding D1 surface atoms shape distribution for {0} ... ".
format(self._database.name))
overall_time = datetime.now()
if not os.path.exists(self._get_dir_name()):
os.makedirs(self._get_dir_name())
for complex_name in self._database.complexes.keys():
protein_complex = self._database.complexes[complex_name]
proteins = [
protein_complex.unbound_formation.ligand,
protein_complex.unbound_formation.receptor
]
for protein in proteins:
shape_dist_file = self._get_dir_name() + protein.name
if not os.path.exists(shape_dist_file + ".npy"):
print_info("{0}".format(protein.name))
pdb_file_name = self._database.directory + pdb_directory + protein.name + '.pdb'
surface, normals = get_surface_atoms(pdb_file_name)
distributions = np.zeros(
(len(protein.residues), 2 * (self.number_of_bins + 1)))
for i in range(len(protein.residues)):
residue = protein.residues[i]
distributions[i, :] = self.get_distributions(
residue.center, surface, normals)
np.save(shape_dist_file, distributions)
distributions = np.load(shape_dist_file + ".npy")
for i in range(len(protein.residues)):
protein.residues[i].add_feature(
Features.D1_SURFACE_SHAPE_DISTRIBUTION,
distributions[i, :])
print_info("took {0} seconds.".format(
(datetime.now() - overall_time).seconds))
def extract_feature(self):
secondary_structure_dict = dict(
zip(ss_abbreviations, range(len(ss_abbreviations))))
print_info_nn(
" >>> Adding secondary structure for database {0} ... ".format(
self._database.name))
overall_time = datetime.now()
counter = 0
if not os.path.exists(self.__get_dir_name()):
os.mkdir(self.__get_dir_name())
for complex_name in self._database.complexes.keys():
protein_complex = self._database.complexes[complex_name]
proteins = [
protein_complex.unbound_formation.ligand,
protein_complex.unbound_formation.receptor
]
for protein in proteins:
stride_x_file = self.__get_dir_name() + protein.name + ".npy"
if not os.path.exists(stride_x_file):
counter += 1
if counter <= 15:
print_info_nn("{0}, ".format(protein.name))
else:
counter = 0
print_info("{0}".format(protein.name))
pdb_file = self._database.directory + pdb_directory + protein.name + ".pdb"
n = len(protein.residues)
stride_x = stride_dict_from_pdb_file(pdb_file)
stride_x_array = np.zeros((n, 11))
for index, residue in enumerate(
protein.biopython_residues):
key = self.get_residue_id(residue.get_full_id())
if key in stride_x:
(_, s, phi, psi, asa, rasa) = stride_x[key]
if s not in secondary_structure_dict:
raise ValueError(
"unknown secondary structure! Add to dictionary!"
)
ss = np.zeros(len(secondary_structure_dict))
ss[secondary_structure_dict[s]] = 1
stride_x_array[index, :7] = ss
stride_x_array[index, 7] = phi
stride_x_array[index, 8] = psi
stride_x_array[index, 9] = asa
stride_x_array[index, 10] = rasa
np.save(stride_x_file, stride_x_array)
stride_x = np.load(stride_x_file)
for i, res in enumerate(protein.residues):
res.add_feature(Features.SECONDARY_STRUCTURE,
stride_x[i, :7])
res.add_feature(Features.PHI, stride_x[i, 7])
res.add_feature(Features.PSI, stride_x[i, 8])
res.add_feature(Features.ACCESSIBLE_SURFACE_AREA,
stride_x[i, 9])
res.add_feature(Features.RELATIVE_ACCESSIBLE_SURFACE_AREA,
stride_x[i, 10])
print_info("took {0} seconds.".format(
(datetime.now() - overall_time).seconds))
def extract_feature(self):
counter = 0
overall_time = datetime.now()
number_of_amino_acids = len(standard_aa_names)
print_info_nn(" >>> Adding Half Surface Exposure ... ".format(self._database.name))
if not os.path.exists(self._get_dir_name()):
os.makedirs(self._get_dir_name())
for complex_name in self._database.complexes.keys():
protein_complex = self._database.complexes[complex_name]
proteins = [protein_complex.unbound_formation.ligand, protein_complex.unbound_formation.receptor]
for protein in proteins:
hse_file = self._get_dir_name() + protein.name
if not os.path.exists(hse_file + ".npy"):
counter += 1
if counter <= 15:
print_info_nn("{0}, ".format(protein.name))
else:
counter = 0
print_info("{0}".format(protein.name))
number_of_residues = len(protein.biopython_residues)
un = np.zeros(number_of_residues)
dn = np.zeros(number_of_residues)
uc = np.zeros((number_of_amino_acids, number_of_residues))
dc = np.zeros((number_of_amino_acids, number_of_residues))
for index, residue in enumerate(protein.biopython_residues):
u = self.get_side_chain_vector(residue)
if u is None:
un[index] = np.nan
dn[index] = np.nan
uc[:, index] = np.nan
dc[:, index] = np.nan
else:
residue_index = self._residue_index_table[residue.get_resname()]
uc[residue_index, index] += 1
dc[residue_index, index] += 1
neighbours_indices = protein.residues[index].get_feature(Features.RESIDUE_NEIGHBOURHOOD)
# print neighbours_indices
for neighbour_index in neighbours_indices:
if neighbour_index == -1:
break
neighbour_residue = protein.biopython_residues[int(neighbour_index)]
if is_aa(neighbour_residue) and neighbour_residue.has_id('CA'):
neighbour_vector = neighbour_residue['CA'].get_vector()
residue_index = self._residue_index_table[neighbour_residue.get_resname()]
if u[1].angle((neighbour_vector - u[0])) < np.pi / 2.0:
un[index] += 1
uc[residue_index, index] += 1
else:
dn[index] += 1
dc[residue_index, index] += 1
uc = (uc / (1.0 + un)).T
dc = (dc / (1.0 + dn)).T
hse_array = np.hstack((uc, dc))
np.save(hse_file, hse_array)
hse = np.load(hse_file + ".npy")
for i in range(len(protein.residues)):
protein.residues[i].add_feature(Features.HALF_SPHERE_EXPOSURE, hse[i, :])
print_info("took {0} seconds.".format((datetime.now() - overall_time).seconds))
def __extract_examples(self):
"""
This function returns the set of all positive and negative examples from DBD4 dataset. In protein complex C,
wth receptor R and ligand L, two residues r on R and r' on L are considered as a positive example if in the
bound form they are nearer than the threshold distance. All other pairs (r,r') with r on R and r' on L are
considered as negative examples. Extracted examples are saved in self.examples
"""
print_info("Finding the positive and negative examples in DBD4 ... {0}".format(self.positives_size))
start_time = datetime.now()
counter = 1
start_index = 0
neg_no = 0
pos_no = 0
for complex_name in self.complexes.keys():
print_info_nn("{0}/{1}... processing complex {2}".format(counter, len(self.complexes), complex_name))
protein_complex = self.complexes[complex_name]
bound_ligand_bio_residues = protein_complex.bound_formation.ligand.biopython_residues
bound_receptor_bio_residues = protein_complex.bound_formation.receptor.biopython_residues
bound_ligand_residues = protein_complex.bound_formation.ligand.residues
bound_receptor_residues = protein_complex.bound_formation.receptor.residues
pos = []
neg = []
for i in range(len(bound_ligand_bio_residues)):
for j in range(len(bound_receptor_bio_residues)):
bound_ligand_residue = bound_ligand_bio_residues[i]
bound_receptor_residue = bound_receptor_bio_residues[j]
l_atoms = [atom.get_coord() for atom in bound_ligand_residue.get_list()]
r_atoms = [atom.get_coord() for atom in bound_receptor_residue.get_list()]
dist_mat = cdist(l_atoms, r_atoms)
ligand_b2u = protein_complex.ligand_bound_to_unbound
receptor_b2u = protein_complex.receptor_bound_to_unbound
# if the residues have an unbound counterpart
# this is due to the fact that the unbound and bound formations may have slightly different residues
if bound_ligand_residues[i] in ligand_b2u and bound_receptor_residues[j] in receptor_b2u:
unbound_ligand_res = ligand_b2u[bound_ligand_residues[i]]
unbound_receptor_res = receptor_b2u[bound_receptor_residues[j]]
unbound_ligand_res_index = self.__get_residue_index(unbound_ligand_res)
unbound_receptor_res_index = self.__get_residue_index(unbound_receptor_res)
if dist_mat.min() < self.interaction_threshold:
pos.append((unbound_ligand_res_index, unbound_receptor_res_index, +1))
else:
neg.append((unbound_ligand_res_index, unbound_receptor_res_index, -1))
self.examples.extend(copy.copy(pos))
self.examples.extend(copy.copy(neg))
pos_no += len(pos)
neg_no += len(neg)
self.complexes_example_range[complex_name] = (
start_index, start_index + len(pos), start_index + len(neg) + len(pos))
print_info(" ( {0:03d}/{1:05d} ) -{2}".format(len(pos), len(neg), self.complexes_example_range[complex_name]))
start_index += len(pos) + len(neg)
counter += 1
all_e = pos + neg
for e in all_e:
self.example_complex["{0}_{1}".format(e[0], e[1])] = complex_name
print_info("Finding examples in DBD4 took " + str((datetime.now() - start_time).seconds) + " seconds. ")
print_info("The total number of examples found: " + str(pos_no + neg_no))
def extract_feature(self):
seed(self.seed)
print_info_nn(
" >>> Adding D1 surface shape distribution for database {0} ... ".
format(self._database.name))
overall_time = datetime.now()
counter = 0
if not os.path.exists(self._get_dir_name()):
os.makedirs(self._get_dir_name())
for complex_name in self._database.complexes.keys():
protein_complex = self._database.complexes[complex_name]
proteins = [
protein_complex.unbound_formation.ligand,
protein_complex.unbound_formation.receptor
]
for protein in proteins:
shape_dist_file = self._get_dir_name() + protein.name
if not os.path.exists(shape_dist_file + ".npy"):
counter += 1
if counter <= 15:
print_info_nn("{0}, ".format(protein.name))
else:
counter = 0
print_info("{0}".format(protein.name))
atoms = protein.atoms
neighbour_search = NeighborSearch(atoms)
distributions = np.zeros(
(len(protein.residues), self.number_of_bins + 1))
for i in range(len(protein.residues)):
residue = protein.residues[i]
nearby_residues = [protein.biopython_residues[i]]
temp_nearby_residues = neighbour_search.search(
residue.center, self.radius, "R")
for nearby_residue in temp_nearby_residues:
if nearby_residue not in protein.biopython_residues:
continue
residues_index = protein.biopython_residues.index(
nearby_residue)
residue = protein.residues[residues_index]
if residue.get_feature(
Features.RELATIVE_ACCESSIBLE_SURFACE_AREA
) >= self.rASA_threshold:
nearby_residues.append(nearby_residue)
distributions[i, :] = self._compute_distribution(
nearby_residues, residue.center)
np.save(shape_dist_file, distributions)
distributions = np.load(shape_dist_file + ".npy")
for i in range(len(protein.residues)):
protein.residues[i].add_feature(
Features.D1_SURFACE_SHAPE_DISTRIBUTION,
distributions[i, :])
print_info("took {0} seconds.".format(
(datetime.now() - overall_time).seconds))
def extract_feature(self):
print_info_nn(
" >>> Adding secondary structure for database {0} ... ".format(
self._database.name))
overall_time = datetime.now()
if not os.path.exists(self.__get_dir_name()):
os.mkdir(self.__get_dir_name())
for complex_name in self._database.complexes.keys():
protein_complex = self._database.complexes[complex_name]
proteins = [
protein_complex.unbound_formation.ligand,
protein_complex.unbound_formation.receptor
]
for protein in proteins:
dssp_file = self.__get_dir_name() + protein.name + ".npy"
if not os.path.exists(dssp_file):
print_info_nn("... running DSSP for protein " +
protein.name)
start_time = datetime.now()
dssp = DSSP(
protein.structure[0], self._database.directory +
pdb_directory + protein.name + ".pdb")
dssp_array = np.ndarray((len(protein.residues), 6))
for (i, res) in enumerate(protein.biopython_residues):
(_, _, cid, rid) = res.get_full_id()
key = (cid, rid)
if key in dssp:
dssp_array[i, 2:] = (dssp[key])[2:]
else:
dssp_array[i, 2:] = [0, 0, 0, 0]
# print_error("WTH")
# sys.exit(0)
# print('here')
# pdb.set_trace()
# self.SS[:, index] = np.nan
# self.ASA[index] = np.nan
# self.rASA[index] = np.nan
# self.Phi[index] = np.nan
# self.Psi[index] = np.nan
np.save(dssp_file, dssp_array)
print_info("took {0} seconds.".format(
(datetime.now() - start_time).seconds))
dssp = np.load(dssp_file)
for i, res in enumerate(protein.residues):
# (_, s, ASA, rASA, phi, psi)
res.add_feature(Features.ACCESSIBLE_SURFACE_AREA, dssp[i,
2])
res.add_feature(Features.RELATIVE_ACCESSIBLE_SURFACE_AREA,
dssp[i, 3])
res.add_feature(Features.PHI, dssp[i, 4])
res.add_feature(Features.PSI, dssp[i, 5])
print_info("took {0} seconds.".format(
(datetime.now() - overall_time).seconds))
def extract_feature(self):
secondary_structure_dict = dict(zip(ss_abbreviations, range(len(ss_abbreviations))))
print_info_nn(" >>> Adding secondary structure for database {0} ... ".format(self._database.name))
overall_time = datetime.now()
counter = 0
if not os.path.exists(self.__get_dir_name()):
os.mkdir(self.__get_dir_name())
for complex_name in self._database.complexes.keys():
protein_complex = self._database.complexes[complex_name]
proteins = [protein_complex.unbound_formation.ligand, protein_complex.unbound_formation.receptor]
for protein in proteins:
stride_x_file = self.__get_dir_name() + protein.name + ".npy"
if not os.path.exists(stride_x_file):
counter += 1
if counter <= 15:
print_info_nn("{0}, ".format(protein.name))
else:
counter = 0
print_info("{0}".format(protein.name))
pdb_file = self._database.directory + pdb_directory + protein.name + ".pdb"
n = len(protein.residues)
stride_x = stride_dict_from_pdb_file(pdb_file)
stride_x_array = np.zeros((n, 11))
for index, residue in enumerate(protein.biopython_residues):
key = self.get_residue_id(residue.get_full_id())
if key in stride_x:
(_, s, phi, psi, asa, rasa) = stride_x[key]
if s not in secondary_structure_dict:
raise ValueError("unknown secondary structure! Add to dictionary!")
ss = np.zeros(len(secondary_structure_dict))
ss[secondary_structure_dict[s]] = 1
stride_x_array[index, :7] = ss
stride_x_array[index, 7] = phi
stride_x_array[index, 8] = psi
stride_x_array[index, 9] = asa
stride_x_array[index, 10] = rasa
np.save(stride_x_file, stride_x_array)
stride_x = np.load(stride_x_file)
for i, res in enumerate(protein.residues):
res.add_feature(Features.SECONDARY_STRUCTURE, stride_x[i, :7])
res.add_feature(Features.PHI, stride_x[i, 7])
res.add_feature(Features.PSI, stride_x[i, 8])
res.add_feature(Features.ACCESSIBLE_SURFACE_AREA, stride_x[i, 9])
res.add_feature(Features.RELATIVE_ACCESSIBLE_SURFACE_AREA, stride_x[i, 10])
print_info("took {0} seconds.".format((datetime.now() - overall_time).seconds))
def extract_feature(self):
print_info_nn(" >>> Adding residue depth for database {0} ... ".format(self._database.name))
overall_time = datetime.now()
counter = 0
if not os.path.exists(self._get_dir_name()):
os.makedirs(self._get_dir_name())
for complex_name in self._database.complexes.keys():
protein_complex = self._database.complexes[complex_name]
proteins = [protein_complex.unbound_formation.ligand, protein_complex.unbound_formation.receptor]
for protein in proteins:
residue_depth_file = self._get_dir_name() + protein.name + ".npy"
if not os.path.exists(residue_depth_file):
counter += 1
if counter <= 15:
print_info_nn("{0}, ".format(protein.name))
else:
counter = 0
print_info("{0}".format(protein.name))
pdb_file = self._database.directory + pdb_directory + protein.name + ".pdb"
rd = ResidueDepth(protein.structure[0], pdb_file)
rd_array = np.ndarray((len(protein.residues), 2)) # self.number_of_bins +
# surface = get_surface(pdb_file)
for (i, res) in enumerate(protein.biopython_residues):
(_, _, c, (h, rn, ic)) = res.get_full_id()
key = (c, (h, rn, ic))
if key in rd:
rdv = rd[key]
if rdv[0] is None:
rdv = (0, rdv[1])
print "WTH?"
if rdv[1] is None:
rdv = (rdv[0], 0)
print "WTH?"
rd_array[i, :2] = rdv
else:
print_error('WTH')
rd_array[i, :2] = [0, 0]
# rd_array[i, 2:] = self._compute_distribution_(surface, protein.residues[i].center)
np.save(residue_depth_file, rd_array)
surface_features = np.load(residue_depth_file)
for i, res in enumerate(protein.residues):
res.add_feature(Features.RESIDUE_DEPTH, self._normalize(surface_features[i, :2]))
print_info("took {0} seconds.".format((datetime.now() - overall_time).seconds))
def extract_feature(self):
seed(self.seed)
counter = 0
overall_time = datetime.now()
print_info_nn(
" >>> Adding D2 shape distribution for database {0} ... ".format(
self._database.name))
if not os.path.exists(self._get_dir_name()):
os.makedirs(self._get_dir_name())
for complex_name in self._database.complexes.keys():
protein_complex = self._database.complexes[complex_name]
proteins = [
protein_complex.unbound_formation.ligand,
protein_complex.unbound_formation.receptor
]
for protein in proteins:
shape_dist_file = self._get_dir_name() + protein.name
if not os.path.exists(shape_dist_file + ".npy"):
counter += 1
if counter <= 15:
print_info_nn("{0}, ".format(protein.name))
else:
counter = 0
print_info("{0}".format(protein.name))
atoms = protein.atoms
neighbour_search = NeighborSearch(atoms)
distributions = np.zeros(
(len(protein.residues), self.number_of_bins))
# distributions = np.zeros((len(protein.residues), self.number_of_bins+2))
for i in range(len(protein.residues)):
residue = protein.residues[i]
nearby_residues = neighbour_search.search(
residue.center, self.radius, "R")
distributions[i, :] = self._compute_distribution(
nearby_residues)
# distributions[i:, -1] = len(nearby_residues)
np.save(shape_dist_file, distributions)
distributions = np.load(shape_dist_file + ".npy")
for i in range(len(protein.residues)):
protein.residues[i].add_feature(
Features.D2_PLAIN_SHAPE_DISTRIBUTION,
distributions[i, :])
# protein.residues[i].add_feature(Features.NUMBER_OF_NEIGHBOURS, distributions[i, -1])
print_info("took {0} seconds.".format(
(datetime.now() - overall_time).seconds))
def extract_feature(self):
counter = 0
print_info_nn(" >>> Adding Residue Neighbourhood ... ")
overall_time = datetime.now()
if not os.path.exists(self._get_dir_name()):
os.makedirs(self._get_dir_name())
for complex_name in self._database.complexes.keys():
protein_complex = self._database.complexes[complex_name]
proteins = [protein_complex.unbound_formation.ligand, protein_complex.unbound_formation.receptor]
for protein in proteins:
residue_neighbourhood_file = self._get_dir_name() + protein.name
if not os.path.exists(residue_neighbourhood_file + ".npy"):
counter += 1
if counter <= 15:
print_info_nn("{0}, ".format(protein.name))
else:
counter = 0
print_info("{0}".format(protein.name))
neighbourhood = []
max_length = 0
for i, query_residue in enumerate(protein.residues):
neighbourhood.append([])
for j, neighbour_residue in enumerate(protein.residues):
# if i == j:
# continue
distance = cdist(query_residue.get_coordinates(), neighbour_residue.get_coordinates()).min()
similarity = np.exp(-(distance ** 2) / self._sigma)
if distance <= 7.5:
neighbourhood[-1].append(j)
if len(neighbourhood[-1]) > max_length:
max_length = len(neighbourhood[-1])
neighbourhood_array = -np.ones((len(protein.residues), max_length))
# print len(neighbourhood)
for i, residue_neighbourhood in enumerate(neighbourhood):
for j, neighbour_index in enumerate(neighbourhood[i]):
neighbourhood_array[i, j] = neighbourhood[i][j]
# print neighbourhood_array[i, :]
np.save(residue_neighbourhood_file, neighbourhood_array)
neighbourhood_array = np.load(residue_neighbourhood_file+".npy")
for index, residue in enumerate(protein.residues):
residue.add_feature(Features.RESIDUE_NEIGHBOURHOOD, neighbourhood_array[index, :])
print_info("took {0} seconds.".format((datetime.now() - overall_time).seconds))
def extract_feature(self):
print_info_nn(" >>> Adding secondary structure for database {0} ... ".format(self._database.name))
overall_time = datetime.now()
if not os.path.exists(self.__get_dir_name()):
os.mkdir(self.__get_dir_name())
for complex_name in self._database.complexes.keys():
protein_complex = self._database.complexes[complex_name]
proteins = [protein_complex.unbound_formation.ligand, protein_complex.unbound_formation.receptor]
for protein in proteins:
dssp_file = self.__get_dir_name() + protein.name + ".npy"
if not os.path.exists(dssp_file):
print_info_nn("... running DSSP for protein " + protein.name)
start_time = datetime.now()
dssp = DSSP(protein.structure[0], self._database.directory + pdb_directory + protein.name + ".pdb")
dssp_array = np.ndarray((len(protein.residues), 6))
for (i, res) in enumerate(protein.biopython_residues):
(_, _, cid, rid) = res.get_full_id()
key = (cid, rid)
if key in dssp:
dssp_array[i, 2:] = (dssp[key])[2:]
else:
dssp_array[i, 2:] = [0, 0, 0, 0]
# print_error("WTH")
# sys.exit(0)
# print('here')
# pdb.set_trace()
# self.SS[:, index] = np.nan
# self.ASA[index] = np.nan
# self.rASA[index] = np.nan
# self.Phi[index] = np.nan
# self.Psi[index] = np.nan
np.save(dssp_file, dssp_array)
print_info("took {0} seconds.".format((datetime.now() - start_time).seconds))
dssp = np.load(dssp_file)
for i, res in enumerate(protein.residues):
# (_, s, ASA, rASA, phi, psi)
res.add_feature(Features.ACCESSIBLE_SURFACE_AREA, dssp[i, 2])
res.add_feature(Features.RELATIVE_ACCESSIBLE_SURFACE_AREA, dssp[i, 3])
res.add_feature(Features.PHI, dssp[i, 4])
res.add_feature(Features.PSI, dssp[i, 5])
print_info("took {0} seconds.".format((datetime.now() - overall_time).seconds))
def extract_feature(self):
seed(self.seed)
print_info_nn(" >>> Adding D1 surface shape distribution for database {0} ... ".format(self._database.name))
overall_time = datetime.now()
counter = 0
if not os.path.exists(self._get_dir_name()):
os.makedirs(self._get_dir_name())
for complex_name in self._database.complexes.keys():
protein_complex = self._database.complexes[complex_name]
proteins = [protein_complex.unbound_formation.ligand, protein_complex.unbound_formation.receptor]
for protein in proteins:
shape_dist_file = self._get_dir_name() + protein.name
if not os.path.exists(shape_dist_file + ".npy"):
counter += 1
if counter <= 15:
print_info_nn("{0}, ".format(protein.name))
else:
counter = 0
print_info("{0}".format(protein.name))
atoms = protein.atoms
neighbour_search = NeighborSearch(atoms)
distributions = np.zeros((len(protein.residues), self.number_of_bins + 1))
for i in range(len(protein.residues)):
residue = protein.residues[i]
nearby_residues = [protein.biopython_residues[i]]
temp_nearby_residues = neighbour_search.search(residue.center, self.radius, "R")
for nearby_residue in temp_nearby_residues:
if nearby_residue not in protein.biopython_residues:
continue
residues_index = protein.biopython_residues.index(nearby_residue)
residue = protein.residues[residues_index]
if residue.get_feature(Features.RELATIVE_ACCESSIBLE_SURFACE_AREA) >= self.rASA_threshold:
nearby_residues.append(nearby_residue)
distributions[i, :] = self._compute_distribution(nearby_residues, residue.center)
np.save(shape_dist_file, distributions)
distributions = np.load(shape_dist_file + ".npy")
for i in range(len(protein.residues)):
protein.residues[i].add_feature(Features.D1_SURFACE_SHAPE_DISTRIBUTION, distributions[i, :])
print_info("took {0} seconds.".format((datetime.now() - overall_time).seconds))
def _load(self, file_name=None):
"""
This function load all the attributes of the class: positive and negative examples, ligands and receptors and
complex names are saved in pickle format.
"""
if file_name is None:
object_model_file_name = self.directory + pickle_directory + dbd4_object_model_file
else:
object_model_file_name = file_name
f = open(object_model_file_name)
print_info_nn("Loading the object model from {0} ... ".format(
object_model_file_name))
start_time = datetime.now()
(self.directory, self.complexes, self.residues,
self.complexes_example_range, self.examples,
self.example_complex) = cPickle.load(f)
f.close()
gc.collect()
print_info("took {0} seconds.".format(
(datetime.now() - start_time).seconds))
def _save(self, file_name=None):
"""
This function saves all the attributes of the class: positive and negative examples, ligands and receptors and
complex names are saved in pickle format.
"""
if not os.path.exists(self.directory + pickle_directory):
os.mkdir(self.directory + pickle_directory)
if file_name is None:
object_model_file_name = self.directory + pickle_directory + dbd4_object_model_file
else:
object_model_file_name = file_name
f = open(object_model_file_name, "wb")
print_info_nn("Saving the object model into {0} ... ".format(
object_model_file_name))
start_time = datetime.now()
cPickle.dump((self.directory, self.complexes, self.residues,
self.complexes_example_range, self.examples,
self.example_complex), f)
f.close()
print_info("took {0} seconds.".format(
(datetime.now() - start_time).seconds))
def _load(self, file_name=None):
"""
This function load all the attributes of the class: positive and negative examples, ligands and receptors and
complex names are saved in pickle format.
"""
if file_name is None:
object_model_file_name = self.directory + pickle_directory + dbd4_object_model_file
else:
object_model_file_name = file_name
f = open(object_model_file_name)
print_info_nn("Loading the object model from {0} ... ".format(object_model_file_name))
start_time = datetime.now()
(self.directory,
self.complexes,
self.residues,
self.complexes_example_range,
self.examples,
self.example_complex) = cPickle.load(f)
f.close()
gc.collect()
print_info("took {0} seconds.".format((datetime.now() - start_time).seconds))
def _save(self, file_name=None):
"""
This function saves all the attributes of the class: positive and negative examples, ligands and receptors and
complex names are saved in pickle format.
"""
if not os.path.exists(self.directory + pickle_directory):
os.mkdir(self.directory + pickle_directory)
if file_name is None:
object_model_file_name = self.directory + pickle_directory + dbd4_object_model_file
else:
object_model_file_name = file_name
f = open(object_model_file_name, "wb")
print_info_nn("Saving the object model into {0} ... ".format(object_model_file_name))
start_time = datetime.now()
cPickle.dump((self.directory,
self.complexes,
self.residues,
self.complexes_example_range,
self.examples,
self.example_complex), f)
f.close()
print_info("took {0} seconds.".format((datetime.now() - start_time).seconds))
def extract_feature(self):
counter = 0
overall_time = datetime.now()
print_info_nn(" >>> Adding B Factor ... ".format(self._database.name))
if not os.path.exists(self._get_dir_name()):
os.makedirs(self._get_dir_name())
for complex_name in self._database.complexes.keys():
protein_complex = self._database.complexes[complex_name]
proteins = [
protein_complex.unbound_formation.ligand,
protein_complex.unbound_formation.receptor
]
for protein in proteins:
b_factor_filename = self._get_dir_name() + protein.name
if not os.path.exists(b_factor_filename + ".npy"):
counter += 1
if counter <= 15:
print_info_nn("{0}, ".format(protein.name))
else:
counter = 0
print_info("{0}".format(protein.name))
b_factor_array = np.zeros(len(protein.residues))
for (index,
residue) in enumerate(protein.biopython_residues):
b_factor_array[index] = max(
[atom.get_bfactor() for atom in residue])
np.save(b_factor_filename, b_factor_array)
b_factor_array = np.load(b_factor_filename + ".npy")
# print b_factor_array
for i in range(len(protein.residues)):
protein.residues[i].add_feature(Features.B_VALUE,
b_factor_array[i])
print_info("took {0} seconds.".format(
(datetime.now() - overall_time).seconds))
def __extract_examples(self):
"""
This function returns the set of all positive and negative examples from DBD4 dataset. In protein complex C,
wth receptor R and ligand L, two residues r on R and r' on L are considered as a positive example if in the
bound form they are nearer than the threshold distance. All other pairs (r,r') with r on R and r' on L are
considered as negative examples. Extracted examples are saved in self.examples
"""
print_info(
"Finding the positive and negative examples in DBD4 ... {0}".
format(self.positives_size))
start_time = datetime.now()
counter = 1
start_index = 0
neg_no = 0
pos_no = 0
for complex_name in self.complexes.keys():
print_info_nn("{0}/{1}... processing complex {2}".format(
counter, len(self.complexes), complex_name))
protein_complex = self.complexes[complex_name]
bound_ligand_bio_residues = protein_complex.bound_formation.ligand.biopython_residues
bound_receptor_bio_residues = protein_complex.bound_formation.receptor.biopython_residues
bound_ligand_residues = protein_complex.bound_formation.ligand.residues
bound_receptor_residues = protein_complex.bound_formation.receptor.residues
pos = []
neg = []
for i in range(len(bound_ligand_bio_residues)):
for j in range(len(bound_receptor_bio_residues)):
bound_ligand_residue = bound_ligand_bio_residues[i]
bound_receptor_residue = bound_receptor_bio_residues[j]
l_atoms = [
atom.get_coord()
for atom in bound_ligand_residue.get_list()
]
r_atoms = [
atom.get_coord()
for atom in bound_receptor_residue.get_list()
]
dist_mat = cdist(l_atoms, r_atoms)
ligand_b2u = protein_complex.ligand_bound_to_unbound
receptor_b2u = protein_complex.receptor_bound_to_unbound
# if the residues have an unbound counterpart
# this is due to the fact that the unbound and bound formations may have slightly different residues
if bound_ligand_residues[
i] in ligand_b2u and bound_receptor_residues[
j] in receptor_b2u:
unbound_ligand_res = ligand_b2u[
bound_ligand_residues[i]]
unbound_receptor_res = receptor_b2u[
bound_receptor_residues[j]]
unbound_ligand_res_index = self.__get_residue_index(
unbound_ligand_res)
unbound_receptor_res_index = self.__get_residue_index(
unbound_receptor_res)
if dist_mat.min() < self.interaction_threshold:
pos.append((unbound_ligand_res_index,
unbound_receptor_res_index, +1))
else:
neg.append((unbound_ligand_res_index,
unbound_receptor_res_index, -1))
self.examples.extend(copy.copy(pos))
self.examples.extend(copy.copy(neg))
pos_no += len(pos)
neg_no += len(neg)
self.complexes_example_range[complex_name] = (start_index,
start_index +
len(pos),
start_index +
len(neg) + len(pos))
print_info(" ( {0:03d}/{1:05d} ) -{2}".format(
len(pos), len(neg),
self.complexes_example_range[complex_name]))
start_index += len(pos) + len(neg)
counter += 1
all_e = pos + neg
for e in all_e:
self.example_complex["{0}_{1}".format(e[0],
e[1])] = complex_name
print_info("Finding examples in DBD4 took " +
str((datetime.now() - start_time).seconds) + " seconds. ")
print_info("The total number of examples found: " +
str(pos_no + neg_no))
def extract_feature(self):
counter = 0
overall_time = datetime.now()
number_of_amino_acids = len(standard_aa_names)
print_info_nn(" >>> Adding Half Surface Exposure ... ".format(
self._database.name))
if not os.path.exists(self._get_dir_name()):
os.makedirs(self._get_dir_name())
for complex_name in self._database.complexes.keys():
protein_complex = self._database.complexes[complex_name]
proteins = [
protein_complex.unbound_formation.ligand,
protein_complex.unbound_formation.receptor
]
for protein in proteins:
hse_file = self._get_dir_name() + protein.name
if not os.path.exists(hse_file + ".npy"):
counter += 1
if counter <= 15:
print_info_nn("{0}, ".format(protein.name))
else:
counter = 0
print_info("{0}".format(protein.name))
number_of_residues = len(protein.biopython_residues)
un = np.zeros(number_of_residues)
dn = np.zeros(number_of_residues)
uc = np.zeros((number_of_amino_acids, number_of_residues))
dc = np.zeros((number_of_amino_acids, number_of_residues))
for index, residue in enumerate(
protein.biopython_residues):
u = self.get_side_chain_vector(residue)
if u is None:
un[index] = np.nan
dn[index] = np.nan
uc[:, index] = np.nan
dc[:, index] = np.nan
else:
residue_index = self._residue_index_table[
residue.get_resname()]
uc[residue_index, index] += 1
dc[residue_index, index] += 1
neighbours_indices = protein.residues[
index].get_feature(
Features.RESIDUE_NEIGHBOURHOOD)
# print neighbours_indices
for neighbour_index in neighbours_indices:
if neighbour_index == -1:
break
neighbour_residue = protein.biopython_residues[
int(neighbour_index)]
if is_aa(neighbour_residue
) and neighbour_residue.has_id('CA'):
neighbour_vector = neighbour_residue[
'CA'].get_vector()
residue_index = self._residue_index_table[
neighbour_residue.get_resname()]
if u[1].angle((neighbour_vector -
u[0])) < np.pi / 2.0:
un[index] += 1
uc[residue_index, index] += 1
else:
dn[index] += 1
dc[residue_index, index] += 1
uc = (uc / (1.0 + un)).T
dc = (dc / (1.0 + dn)).T
hse_array = np.hstack((uc, dc))
np.save(hse_file, hse_array)
hse = np.load(hse_file + ".npy")
for i in range(len(protein.residues)):
protein.residues[i].add_feature(
Features.HALF_SPHERE_EXPOSURE, hse[i, :])
print_info("took {0} seconds.".format(
(datetime.now() - overall_time).seconds))