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 make_psaia_dict(filename):
psaia = {}
line_number = 0
try:
for line in open(filename, "r"):
line_number += 1
line_parts = line.split()
# the line containing 'chain' is the last line before real data starts
if len(line_parts) < 5 or line_parts[0] == 'chain':
continue
protein_id = line_parts[0]
if protein_id == '*':
protein_id = ' '
residue_id = (protein_id, line_parts[6])
casa = np.array(map(float, line_parts[1:6]))
rasa = np.array(map(float, line_parts[8:13]))
rrasa = np.array(map(float, line_parts[13:18]))
rdpx = np.array(map(float, line_parts[18:24]))
rcx = np.array(map(float, line_parts[24:30]))
rhph = np.array(float(line_parts[-1]))
psaia[residue_id] = (casa, rasa, rrasa, rdpx, rcx, rhph)
except Exception as e:
print_error('Error Processing psaia file {0}: {1}'.format(filename, e))
print_error('Error occurred while processing line: {0}'.format(line_number))
raise e
return psaia
def make_psaia_dict(filename):
psaia = {}
line_number = 0
try:
for line in open(filename, "r"):
line_number += 1
line_parts = line.split()
# the line containing 'chain' is the last line before real data starts
if len(line_parts) < 5 or line_parts[0] == 'chain':
continue
protein_id = line_parts[0]
if protein_id == '*':
protein_id = ' '
residue_id = (protein_id, line_parts[6])
casa = np.array(map(float, line_parts[1:6]))
rasa = np.array(map(float, line_parts[8:13]))
rrasa = np.array(map(float, line_parts[13:18]))
rdpx = np.array(map(float, line_parts[18:24]))
rcx = np.array(map(float, line_parts[24:30]))
rhph = np.array(float(line_parts[-1]))
psaia[residue_id] = (casa, rasa, rrasa, rdpx, rcx, rhph)
except Exception as e:
print_error('Error Processing psaia file {0}: {1}'.format(filename, e))
print_error(
'Error occurred while processing line: {0}'.format(line_number))
raise e
return psaia
def get_vector_form(self, features):
uncomputed_features = set(features) - set(self.get_computed_features())
if uncomputed_features != set([]):
print_error(
"Following features {0} is still not computed for this residue {1}".format(uncomputed_features, self))
return None
temp = None
for feature in features:
vector = self.computed_features[feature]
if temp is None:
temp = vector
else:
temp = np.hstack((vector, temp))
return temp
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 get_feature(self, feature):
if feature not in self.computed_features:
print_error("Feature {0} is not computed!".format(feature))
else:
return self.computed_features[feature]