def check_msms(self, prot_file, first_100_residues):
p = PDBParser()
with warnings.catch_warnings():
warnings.simplefilter("ignore", PDBConstructionWarning)
s = p.get_structure("X", prot_file)
model = s[0]
rd = ResidueDepth(model)
res_chain = ""
for item in rd.property_list[:100]:
res_chain = res_chain + item[0].get_resname()
self.assertEqual(res_chain, first_100_residues)
def check_msms(self, prot_file, first_100_residues):
"""Wrap calls to MSMS and the respective tests."""
with warnings.catch_warnings():
warnings.simplefilter("ignore", PDBConstructionWarning)
s = self.pdbparser.get_structure("X", prot_file)
model = s[0]
rd = ResidueDepth(model)
residues = []
for item in rd.property_list[:100]:
residues.append(item[0].get_resname())
self.assertEqual("".join(residues), first_100_residues)
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))
print("ERROR: Cannot open output file!")
parser = PDBParser(PERMISSIVE=1)
try:
pdb_path = sys.argv[1]
st = parser.get_structure('st', pdb_path)
except OSError:
print("ERROR: We cannot load the PDB! Did you provide a proper path?")
sys.exit(2)
if len(st) > 1: # Checking for models
print("WARNING: Several Models found, using only first")
# Using Model 0 any way and the first chain
st = st[0]
st = tuple(st.get_chains())[0] # In case there is more than one line
residueID__depth = {}
resdepth = ResidueDepth(st)
for resInfo, depth in resdepth:
residueID__depth[(resInfo.get_resname(),
resInfo.get_full_id()[-1][1])] = depth[0]
print("aa", "pos", "surface", file=outFile, sep="\t")
for k in residueID__depth:
if residueID__depth[k] < distanceSurface:
print(k[0], k[1], 1, file=outFile, sep="\t")
else:
print(k[0], k[1], 0, file=outFile, sep="\t")
outFile.close()
elif args.exp == "CN":
hse = ExposureCN(m, RADIUS)
k = "EXP_CN"
elif args.exp == "ANGLE":
hse = HSExposureCA(m, RADIUS)
k = "EXP_CB_PCB_ANGLE"
format = "%4.1f"
elif args.exp == "DSSPR":
d = DSSP(m, args.pdbfile, dssp=args.dssp)
k = "EXP_DSSP_RASA"
format = "%.4f"
elif args.exp == "DSSPA":
d = DSSP(m, args.pdbfile, dssp=args.dssp)
k = "EXP_DSSP_ASA"
elif args.exp == "RD":
d = ResidueDepth(m, args.pdbfile, msms_exec=args.msms)
k = "EXP_RD"
format = "%4.1f"
elif args.exp == "RDA":
d = ResidueDepth(m, args.pdbfile, msms_exec=args.msms)
k = "EXP_RD_CA"
format = "%4.1f"
else:
print("ERROR: Unknown option.")
sys.exit()
residue_list = Selection.unfold_entities(m, "R")
for r in residue_list:
if k in r.xtra: