def cdfMol_pdb(pdb, output, name):
initial_time = time.time()
cdf_mol = Chem.BasicMolecule()
pdb_mol = Chem.BasicMolecule()
pdb_str = open(pdb, 'r').read().replace('WAT', 'HOH').replace('HIE', 'HIS')
pdb_reader = Biomol.PDBMoleculeReader(Base.StringIOStream(pdb_str))
Biomol.setPDBApplyDictAtomBondingToNonStdResiduesParameter(
pdb_reader, True)
if not pdb_reader.read(pdb_mol):
return None
Chem.calcImplicitHydrogenCounts(pdb_mol, False)
Chem.perceiveHybridizationStates(pdb_mol, False)
Chem.setAtomSymbolsFromTypes(pdb_mol, False)
Chem.perceiveSSSR(pdb_mol, False)
Chem.setRingFlags(pdb_mol, False)
Chem.setAromaticityFlags(pdb_mol, False)
cdf_mol.assign(pdb_mol)
for atom in cdf_mol.atoms:
Chem.set3DCoordinatesArray(atom, Math.Vector3DArray())
i = 0
while i < cdf_mol.numAtoms:
Chem.get3DCoordinatesArray(cdf_mol.getAtom(i)).addElement(
Chem.get3DCoordinates(pdb_mol.getAtom(i)))
i += 1
tmp_output = output + name + ".cdf"
try:
Chem.FileCDFMolecularGraphWriter(tmp_output).write(cdf_mol)
except:
print('> Cdf_mol writing failure.')
raise
residues = Biomol.ResidueList(cdf_mol)
tmp_output = output + name + "_residue_info.txt"
with open(tmp_output, 'w') as txt_writer:
txt_writer.write('residue name_resid_chain\n')
for res in residues:
res_id = getResidueID(res)
txt_writer.write('{}: \n'.format(res_id))
calc_time = time.time() - initial_time
print('> Cdf and amino acid residue number list files generated in {}s'.
format(int(calc_time)))
def process():
if len(sys.argv) < 3:
print >> sys.stderr, 'Usage:', sys.argv[
0], '[input CDF-file] [output CDF-file] [[residue subset]]'
sys.exit(2)
print '- Processing CDF-file:', sys.argv[1], '...'
mol = Util.loadCDFMolecule(sys.argv[1])
if not mol:
print '!! Could not read file'
sys.exit(2)
residues = Biomol.ResidueList(mol)
print '- Num. residues:', residues.getSize()
if len(sys.argv) > 3:
res_subset_ids = Util.toIntegerList(Util.readLines(sys.argv[3]))
print '- Residue subset:', res_subset_ids
Util.filterResidues(residues, res_subset_ids)
print '- num residues', len(residues)
num_confs = Chem.getNumConformations(mol)
print '- Num. frames:', num_confs
print '- Aligning frames...'
res_positions = []
for res in residues:
atoms = Util.getBackboneAtoms(res)
positions = []
i = 0
while i < num_confs:
positions.append(Util.calcAtomSetCentroid(atoms, i))
i += 1
res_positions.append(positions)
alignment = Math.DKabschAlgorithm()
al_ref_positions = Math.DMatrix(3, residues.getSize())
al_positions = Math.DMatrix(3, residues.getSize())
i = 0
while i < residues.getSize():
pos = res_positions[i][0]
al_ref_positions.setElement(0, i, pos[0])
al_ref_positions.setElement(1, i, pos[1])
al_ref_positions.setElement(2, i, pos[2])
i += 1
i = 1
xform = Math.Matrix4D()
while i < num_confs:
j = 0
while j < residues.getSize():
pos = res_positions[j][i]
al_positions.setElement(0, j, pos[0])
al_positions.setElement(1, j, pos[1])
al_positions.setElement(2, j, pos[2])
j += 1
if not alignment.align(al_positions, al_ref_positions):
print '!! Could not align frame', i
else:
xform.assign(alignment.getTransform())
Chem.transformConformation(mol, i, xform)
i += 1
if not Util.saveCDFMolecule(sys.argv[2], mol):
print '!! Could not write output file'
sys.exit(2)