def get_sequence(structure: oechem.OEGraphMol) -> str:
"""
Get the amino acid sequence with one letter characters of an OpenEye molecule holding a protein structure. All
residues not perceived as amino acid will receive the character 'X'.
Parameters
----------
structure: oechem.OEGraphMol
An OpenEye molecule holding a protein structure.
Returns
-------
sequence: str
The amino acid sequence of the protein with one letter characters.
"""
sequence = []
hv = oechem.OEHierView(structure)
for residue in hv.GetResidues():
if oechem.OEIsStandardProteinResidue(residue):
sequence.append(
oechem.OEGetAminoAcidCode(
oechem.OEGetResidueIndex(residue.GetResidueName())))
else:
sequence.append("X")
sequence = "".join(sequence)
return sequence
def ResCount(ifs):
nrmol = 0
mol = oechem.OEGraphMol()
while oechem.OEReadMolecule(ifs, mol):
nrmol += 1
nratom = 0
nrwat = 0
nrres = 0
nrfrag = 0
nrchain = 0
if not oechem.OEHasResidues(mol):
oechem.OEPerceiveResidues(mol, oechem.OEPreserveResInfo_All)
hv = oechem.OEHierView(mol)
for chain in hv.GetChains():
nrchain += 1
for frag in chain.GetFragments():
nrfrag += 1
for res in frag.GetResidues():
nrres += 1
if oechem.OEGetResidueIndex(res.GetOEResidue()) == oechem.OEResidueIndex_HOH:
nrwat += 1
else:
for atom in res.GetAtoms():
nratom += 1
print("===============================================")
print("Molecule : %d Title: %s" % (nrmol, mol.GetTitle()))
print("Chains : %d" % nrchain)
print("Fragments: %d" % nrfrag)
print("Residues : %d (%d waters)" % (nrres, nrwat))
print("Atoms : %d" % nratom)
def CisCheck(ifs):
nrmol = 0
nrcis = 0
mol = oechem.OEGraphMol()
while oechem.OEReadMolecule(ifs, mol):
nrmol += 1
print("===========================================================")
print("Molecule: %s Title: %s" % (nrmol, mol.GetTitle()))
if not oechem.OEHasResidues(mol):
oechem.OEPerceiveResidues(mol, oechem.OEPreserveResInfo_All)
hv = oechem.OEHierView(mol)
resiter = oechem.ConstOEHierResidueIter()
resiter = hv.GetResidues()
while (resiter.IsValid()):
res = resiter.Target()
resiter.Next()
if not oechem.OEIsStandardProteinResidue(res):
continue
torsion = oechem.OEGetTorsion(res, oechem.OEProtTorType_Omega)
if torsion != -100.0:
if torsion < math.pi / 2.0 and torsion > -math.pi / 2.0:
if resiter.IsValid():
nextres = resiter.Target()
oenextres = nextres.GetOEResidue()
if oechem.OEGetResidueIndex(
oenextres) == oechem.OEResidueIndex_PRO:
continue
nrcis += 1
oeres = res.GetOEResidue()
print("%s %s %2d omega torsion = %.2f degree" %
(oeres.GetName(), oeres.GetChainID(),
oeres.GetResidueNumber(),
torsion * oechem.cvar.Rad2Deg))
print(" %d cis amide bond(s) identified\n" % nrcis)
def MakeAlpha(ifs, ofs):
phival = math.pi / -3.0
psival = math.pi / -3.0
chival = math.pi
nrphis = 0
nrpsis = 0
nrchis = 0
mol = oechem.OEGraphMol()
while oechem.OEReadMolecule(ifs, mol):
if not oechem.OEHasResidues(mol):
oechem.OEPerceiveResidues(mol, oechem.OEPreserveResInfo_All)
# remove cross-links
for bond in mol.GetBonds():
if bond.GetBgn().GetAtomicNum() == oechem.OEElemNo_S and \
bond.GetEnd().GetAtomicNum() == oechem.OEElemNo_S:
mol.DeleteBond(bond)
oechem.OEFindRingAtomsAndBonds(mol)
hv = oechem.OEHierView(mol)
for res in hv.GetResidues():
if not oechem.OEIsStandardProteinResidue(res):
continue
# set psi and phi angles
if not oechem.OESetTorsion(res, oechem.OEProtTorType_Phi, phival):
oeres = res.GetOEResidue()
print("Unable to set phi for %s %d" %
(oeres.GetName(), oeres.GetResidueNumber()))
else:
nrphis += 1
if not oechem.OESetTorsion(res, oechem.OEProtTorType_Psi, psival):
oeres = res.GetOEResidue()
print("Unable to set psi for %s %d" %
(oeres.GetName(), oeres.GetResidueNumber()))
else:
nrpsis += 1
# set chis
if oechem.OEGetResidueIndex(
res.GetOEResidue().GetName()) == oechem.OEResidueIndex_PRO:
continue # It does not make sense to set Proline chi angles to 180
for chi in oechem.OEGetChis(res):
if not oechem.OESetTorsion(res, chi, chival):
oeres = res.GetOEResidue()
print("Unable to set chi %s for %s %d" %
(oechem.OEGetProteinTorsionName(chi),
oeres.GetName(), oeres.GetResidueNumber()))
else:
nrchis += 1
oechem.OEWriteMolecule(ofs, mol)
print(nrphis, " phi torsion angle set to ", phival * oechem.cvar.Rad2Deg)
print(nrpsis, " psi torsion angle set to ", psival * oechem.cvar.Rad2Deg)
print(nrchis, " chis torsion angle set to ", chival * oechem.cvar.Rad2Deg)
def strip_water_ions(in_system):
"""
This function remove waters and ions molecules
from the input system
Parameters:
----------
in_system : oechem.OEMol
The bio-molecular system to clean
opt: python dictionary
The system option
Output:
-------
clean_system : oechem.OEMol
The cleaned system
"""
# Copy the input system
system = in_system.CreateCopy()
# Create a bit vector mask
bv = oechem.OEBitVector(system.GetMaxAtomIdx())
bv.NegateBits()
# Create a Hierarchical View of the protein system
hv = oechem.OEHierView(
system,
oechem.OEAssumption_BondedResidue + oechem.OEAssumption_ResPerceived)
# Looping over the system residues
for chain in hv.GetChains():
for frag in chain.GetFragments():
for hres in frag.GetResidues():
res = hres.GetOEResidue()
# Check if a residue is a mono atomic ion
natoms = 0
for at in hres.GetAtoms():
natoms += 1
# Set the atom bit mask off
if oechem.OEGetResidueIndex(
res) == oechem.OEResidueIndex_HOH or natoms == 1:
# Set Bit mask
atms = hres.GetAtoms()
for at in atms:
bv.SetBitOff(at.GetIdx())
# Extract the system without waters or ions
pred = oechem.OEAtomIdxSelected(bv)
clean_system = oechem.OEMol()
oechem.OESubsetMol(clean_system, system, pred)
return clean_system
def AtomInHydrophobicResidue(atom):
residues = set([oechem.OEResidueIndex_ALA,
oechem.OEResidueIndex_ILE,
oechem.OEResidueIndex_LEU,
oechem.OEResidueIndex_MET,
oechem.OEResidueIndex_PHE,
oechem.OEResidueIndex_PRO,
oechem.OEResidueIndex_TRP,
oechem.OEResidueIndex_VAL])
if oechem.OEGetResidueIndex(atom) in residues:
return True
else:
return False
def main(argv=[__name__]):
itf = oechem.OEInterface(InterfaceData)
if not oechem.OEParseCommandLine(itf, argv):
oechem.OEThrow.Fatal("Unable to interpret command line!")
ims = oechem.oemolistream()
ims.SetFlavor(oechem.OEFormat_PDB, oechem.OEIFlavor_PDB_ALTLOC)
inputFile = itf.GetString("-in")
if not ims.open(inputFile):
oechem.OEThrow.Fatal("Unable to open %s for reading." % inputFile)
if not oechem.OEIs3DFormat(ims.GetFormat()):
oechem.OEThrow.Fatal("%s is not in a 3D format." % inputFile)
mol = oechem.OEGraphMol()
if not oechem.OEReadMolecule(ims, mol):
oechem.OEThrow.Fatal("Unable to read %s." % inputFile)
if not oechem.OEHasResidues(mol):
oechem.OEPerceiveResidues(mol, oechem.OEPreserveResInfo_All)
alf = oechem.OEAltLocationFactory(mol)
if alf.GetGroupCount() != 0:
alf.MakePrimaryAltMol(mol)
# in our example, we will select the first histidine
selectedResidue = oechem.OEResidue()
for atom in mol.GetAtoms():
res = oechem.OEAtomGetResidue(atom)
if oechem.OEGetResidueIndex(res) == oechem.OEResidueIndex_HIS:
selectedResidue = res
break
# @ <SNIPPET-PLACE-HYDROGENS-PRED>
# given predicate IsSameResidue, residue selectedResidue and molecule mol...
opt = oechem.OEPlaceHydrogensOptions()
opt.SetNoFlipPredicate(IsSameResidue(selectedResidue))
if oechem.OEPlaceHydrogens(mol, opt):
# selectedResidue will not be flipped...
# @ </SNIPPET-PLACE-HYDROGENS-PRED>
print("success")
ims.close()
def _OEFixConnectionNH(protein):
"""
Temporary fix, thanks to Jesper!
"""
for atom in protein.GetAtoms(
oechem.OEAndAtom(oespruce.OEIsModeledAtom(),
oechem.OEIsNitrogen())):
if oechem.OEGetPDBAtomIndex(atom) == oechem.OEPDBAtomName_N:
expected_h_count = 1
if oechem.OEGetResidueIndex(atom) == oechem.OEResidueIndex_PRO:
expected_h_count = 0
if atom.GetTotalHCount() != expected_h_count:
oechem.OESuppressHydrogens(atom)
atom.SetImplicitHCount(1)
oechem.OEAddExplicitHydrogens(protein, atom)
for nbr in atom.GetAtoms(oechem.OEIsHydrogen()):
oechem.OESet3DHydrogenGeom(protein, nbr)
def CalcResCounts(mol):
hv = oechem.OEHierView(mol)
chainCt = 0
fragCt = 0
resCt = 0
watCt = 0
for chain in hv.GetChains():
chainCt += 1
for frag in chain.GetFragments():
fragCt += 1
for hres in frag.GetResidues():
resCt += 1
if (oechem.OEGetResidueIndex(
hres.GetOEResidue()) == oechem.OEResidueIndex_HOH):
watCt += 1
print("Molecule : %s" % mol.GetTitle())
print("Chains : %d" % chainCt)
print("Fragments: %d" % fragCt)
print("Residues : %d (%d waters)" % (resCt, watCt))
def Rename(ims, oms):
for mol in ims.GetOEGraphMols():
# @ <SNIPPET-PERCEIVE-RES>
if not oechem.OEHasResidues(mol):
oechem.OEPerceiveResidues(mol, oechem.OEPreserveResInfo_All)
# @ </SNIPPET-PERCEIVE-RES>
# @ <SNIPPET-MSE-TO-MET-CORE>
for atom in mol.GetAtoms():
thisRes = oechem.OEAtomGetResidue(atom)
if oechem.OEGetResidueIndex(thisRes) == oechem.OEResidueIndex_MSE:
thisRes.SetName("MET") # modify res properties
thisRes.SetHetAtom(False)
oechem.OEAtomSetResidue(atom, thisRes) # store updated residue
if atom.GetAtomicNum() == oechem.OEElemNo_Se:
atom.SetAtomicNum(
oechem.OEElemNo_S) # fix atom type & name
atom.SetName(" SD ")
# @ </SNIPPET-MSE-TO-MET-CORE>
oechem.OEWriteMolecule(oms, mol)
def DropLigandFromProtein(prot, lig):
"""delete atoms from the protein w/same coords as the ligand
as well as any waters"""
approximatelyTheSame = 0.05
nn = oechem.OENearestNbrs(prot, approximatelyTheSame)
# mark ligand atoms for deletion
bv = oechem.OEBitVector(prot.GetMaxAtomIdx())
for nbrs in nn.GetNbrs(lig):
r1 = oechem.OEAtomGetResidue(nbrs.GetBgn())
r2 = oechem.OEAtomGetResidue(nbrs.GetEnd())
if r1.GetModelNumber() == r2.GetModelNumber():
bv.SetBitOn(nbrs.GetBgn().GetIdx())
# mark waters for deletion too
for atom in prot.GetAtoms():
res = oechem.OEAtomGetResidue(atom)
if oechem.OEGetResidueIndex(res) == oechem.OEResidueIndex_HOH:
bv.SetBitOn(atom.GetIdx())
pred = oechem.OEAtomIdxSelected(bv)
for atom in prot.GetAtoms(pred):
prot.DeleteAtom(atom)
