def PrintAltGroupInfo(mol):
if not oechem.OEHasResidues(mol):
oechem.OEPerceiveResidues(mol, oechem.OEPreserveResInfo_All)
alf = oechem.OEAltLocationFactory(mol) # create factory for mol
print("%s\t(%s groups)" % (mol.GetTitle(), alf.GetGroupCount()))
for grp in alf.GetGroups():
print("\t%s locs:%s" %
(grp.GetLocationCount(), alf.GetLocationCodes(grp)))
def PrintGroups(mol):
"""summarize alternate location group info"""
if not oechem.OEHasResidues(mol):
oechem.OEPerceiveResidues(mol, oechem.OEPreserveResInfo_All)
alf = oechem.OEAltLocationFactory(mol)
print("%s\t(%s groups)" % (mol.GetTitle(), alf.GetGroupCount()))
for grp in alf.GetGroups():
print("\t%s locs:%s" %
(grp.GetLocationCount(), alf.GetLocationCodes(grp)))
def PrintResidues(mol):
"""list alternate location code and occupancy by group and residue"""
if not oechem.OEHasResidues(mol):
oechem.OEPerceiveResidues(mol, oechem.OEPreserveResInfo_All)
alf = oechem.OEAltLocationFactory(mol)
print("%s - %d alternate location groups:" %
(mol.GetTitle(), alf.GetGroupCount()))
for grp in alf.GetGroups():
print("%d) %d alternate locations" %
(grp.GetGroupID() + 1, grp.GetLocationCount()),
end=" ")
prev = oechem.OEResidue()
prevCodes = ""
sumOcc = []
atNum = []
for atom in alf.GetAltAtoms(grp):
res = oechem.OEAtomGetResidue(atom)
if not oechem.OESameResidue(res, prev):
for i, code in enumerate(prevCodes):
print("%c(%.0f%c) " %
(code, (sumOcc[i] * 100.0) / atNum[i], "%"),
end=" ")
print()
prevCodes = ""
sumOcc = []
atNum = []
print("\t%s%d%c chain '%c': " %
(res.GetName(), res.GetResidueNumber(),
res.GetInsertCode(), res.GetChainID()),
end=" ")
prev = res
code = res.GetAlternateLocation()
whichCode = prevCodes.find(code)
if whichCode < 0:
prevCodes += code
sumOcc.append(res.GetOccupancy())
atNum.append(1)
else:
sumOcc[whichCode] += res.GetOccupancy()
atNum[whichCode] += 1
for i, code in enumerate(prevCodes):
print("%c(%.0f%c) " % (code, (sumOcc[i] * 100.0) / atNum[i], "%"),
end=" ")
print()
def main(argv=[__name__]):
itf = oechem.OEInterface(InterfaceData)
if not oechem.OEParseCommandLine(itf, argv):
oechem.OEThrow.Fatal("Unable to interpret command line!")
# @ <SNIPPET-ALTLOCFACT-FLAVOR>
ims = oechem.oemolistream()
ims.SetFlavor(oechem.OEFormat_PDB, oechem.OEIFlavor_PDB_ALTLOC)
# @ </SNIPPET-ALTLOCFACT-FLAVOR>
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)
# @ <SNIPPET-ALTLOCFACT-PRIMARY>
alf = oechem.OEAltLocationFactory(mol)
if alf.GetGroupCount() != 0:
alf.MakePrimaryAltMol(mol)
# @ </SNIPPET-ALTLOCFACT-PRIMARY>
# @ <SNIPPET-PLACE-HYDROGENS-BASIC>
if oechem.OEPlaceHydrogens(mol):
# ...
# @ </SNIPPET-PLACE-HYDROGENS-BASIC>
print("success")
# @ <SNIPPET-PLACE-HYDROGENS-OPTIONS>
opt = oechem.OEPlaceHydrogensOptions()
opt.SetStandardizeBondLen(False)
# @ </SNIPPET-PLACE-HYDROGENS-OPTIONS>
# @ <SNIPPET-PLACE-HYDROGENS-DETAILS>
# given molecule mol and OEPlaceHydrogensOptions opt...
details = oechem.OEPlaceHydrogensDetails()
if oechem.OEPlaceHydrogens(mol, details, opt):
print(details.Describe())
# @ </SNIPPET-PLACE-HYDROGENS-DETAILS>
ims.close()
def addh(self, altProcess='occupancy', processName='fullsearch', \
ihopt=T, standardize=T, badclash=0.4, flipbias=1.0, maxStates=20):#7):
imol = self.mol.CreateCopy()
wp = oechem.OEPlaceHydrogensWaterProcessing_Ignore
if processName == 'fullsearch':
wp = oechem.OEPlaceHydrogensWaterProcessing_FullSearch
elif processName == 'focused':
wp = oechem.OEPlaceHydrogensWaterProcessing_Focused
keepAlts = (altProcess != "a")
highestOcc = (altProcess == "occupancy")
compareAlts = (altProcess == "compare")
print('#1')
if highestOcc or compareAlts:
alf = oechem.OEAltLocationFactory(imol)
if alf.GetGroupCount() != 0:
if highestOcc:
oechem.OEThrow.Verbose(
"Dropping alternate locations from input.")
alf.MakePrimaryAltMol(imol)
elif compareAlts:
oechem.OEThrow.Verbose("Fixing alternate location issues.")
imol = alf.GetSourceMol()
omol = imol
print('#2')
oechem.OEThrow.Verbose("Adding hydrogens to complex.")
hopt = oechem.OEPlaceHydrogensOptions()
if ihopt:
hopt.SetAltsMustBeCompatible(compareAlts)
hopt.SetStandardizeBondLen(standardize)
hopt.SetWaterProcessing(wp)
hopt.SetBadClashOverlapDistance(badclash)
hopt.SetFlipBiasScale(flipbias)
hopt.SetMaxSubstateCutoff(maxStates)
if self.verbose:
print('#3')
details = oechem.OEPlaceHydrogensDetails()
if not oechem.OEPlaceHydrogens(omol, details, hopt):
oechem.OEThrow.Fatal(
"Unable to place hydrogens and get details on %s." %
self.inmol.GetTitle())
oechem.OEThrow.Verbose(details.Describe())
else:
if not oechem.OEPlaceHydrogens(omol, hopt):
oechem.OEThrow.Fatal("Unable to place hydrogens on %s." %
self.inmol.GetTitle())
self.mol = omol
def ReadFromPDB(pdb_file, mol):
ifs = oechem.oemolistream()
ifs.SetFlavor(oechem.OEFormat_PDB, oechem.OEIFlavor_PDB_Default | oechem.OEIFlavor_PDB_DATA | oechem.OEIFlavor_PDB_ALTLOC) # noqa
if not ifs.open(pdb_file):
oechem.OEThrow.Fatal("Unable to open %s for reading." % pdb_file)
temp_mol = oechem.OEGraphMol()
if not oechem.OEReadMolecule(ifs, temp_mol):
oechem.OEThrow.Fatal("Unable to read molecule from %s." % pdb_file)
ifs.close()
fact = oechem.OEAltLocationFactory(temp_mol)
mol.Clear()
fact.MakePrimaryAltMol(mol)
return (mol)
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 PrintLocations(mol, hideAtoms):
"""list alternate location codes and atom info (unless hideAtoms is True)"""
if not oechem.OEHasResidues(mol):
oechem.OEPerceiveResidues(mol, oechem.OEPreserveResInfo_All)
alf = oechem.OEAltLocationFactory(mol)
print("%s" % mol.GetTitle())
print("grp-cnt=%d" % alf.GetGroupCount(), end=" ")
if alf.GetGroupCount() > 0:
print("{")
else:
print()
for grp in alf.GetGroups():
print(" grp=%d loc-cnt=%d grp-codes='%s'" %
(grp.GetGroupID(), grp.GetLocationCount(),
alf.GetLocationCodes(grp)))
for loc in grp.GetLocations():
print(" grp=%d loc=%d loc-codes='%s'" %
(loc.GetGroupID(), loc.GetLocationID(),
alf.GetLocationCodes(loc)),
end=" ")
if not hideAtoms:
print("[", end=" ")
num_atoms = 0
for atom in alf.GetAltAtoms(loc):
num_atoms += 1
if not hideAtoms:
res = oechem.OEAtomGetResidue(atom)
print("%s:%c:%s%d%c:c%cm%d;" %
(atom.GetName(), res.GetAlternateLocation(),
res.GetName(), res.GetResidueNumber(),
res.GetInsertCode(), res.GetChainID(),
res.GetModelNumber()),
end=" ")
if not hideAtoms:
print("]", end=" ")
print(num_atoms)
if alf.GetGroupCount() > 0:
print("}")
def PrintStates(mol):
"""list alternate location state information"""
if not oechem.OEHasResidues(mol):
oechem.OEPerceiveResidues(mol, oechem.OEPreserveResInfo_All)
alf = oechem.OEAltLocationFactory(mol)
print("%s\t%d groups" % (mol.GetTitle(), alf.GetGroupCount()), end=" ")
tot = 1
totexp = 0.0
for grp in alf.GetGroups():
tot *= grp.GetLocationCount()
totexp += math.log10(grp.GetLocationCount())
if totexp > 7.0:
print("\tover 10^%.0f states" % totexp)
print("too many states to enumerate")
else:
print("\t%d states" % tot)
locs = [grp.GetLocations() for grp in alf.GetGroups()]
EnumerateStates(alf, locs, 0, len(locs))
def do(controller):
"""
"""
# get the controller command
cmd = controller.command
# get the command line arguments and options
args = controller.pargs
# predicate to remove non-polymer atoms from structure
nonpolymers = oechem.OEOrAtom(
OEAtomHasIntData(('entity_type_bm', 0)),
OEAtomBinaryAndIntData(('entity_type_bm', 3)))
assemblysets = get_assembly_sets(args)
# directory containing all the biological assemblies in OEB format
OEB_ASSEMBLIES_DIR = app.config.get('directories', 'quat_oeb')
# directory where surface areas will be written
CREDO_DATA_DIR = app.config.get('directories', 'credo_data')
ifs = oechem.oemolistream()
ifs.SetFormat(oechem.OEFormat_OEB)
# initialize progressbar
if args.progressbar:
bar = ProgressBar(widgets=[
'PDB entries: ',
SimpleProgress(), ' ',
Percentage(),
Bar()
],
maxval=len(assemblysets)).start()
# iterate through assembly sets
for counter, (pdb, assemblyset) in enumerate(assemblysets, 1):
if args.progressbar: bar.update(counter)
# create a data directory for this structure to which all data will be written
struct_data_dir = os.path.join(CREDO_DATA_DIR, pdb[1:3].lower(),
pdb.lower())
# make necessary directories recursively if they do not exist yet
if not exists(struct_data_dir):
os.makedirs(struct_data_dir)
# path to the file where the atom surface areas of all atoms will be written
surface_areas_path = os.path.join(
struct_data_dir, 'binding_site_atom_surface_areas.credo')
# do not recalculate atom surface area contributions if incremental
if args.incremental and exists(
surface_areas_path) and getsize(surface_areas_path) > 0:
continue
elif (args.update and exists(surface_areas_path)
and getmtime(surface_areas_path) >= time() -
(args.update * 60 * 60 * 24) and getsize(surface_areas_path)):
app.log.info("Output for PDB entry {0} exists and is more recent than {1} days. Skipped."\
.format(pdb, args.update))
continue
# output file stream and CSV writer
atomfs = open(surface_areas_path, 'w')
atomwriter = csv.writer(atomfs, dialect='tabs')
# deal with each found assembly separately
# some pdb entries consist of more than one
for assembly in assemblyset:
if args.quat:
path = os.path.join(OEB_ASSEMBLIES_DIR, pdb[1:3].lower(),
pdb.lower(), assembly)
else:
app.log.error("the calculation of buried ligand surface areas "
"is only supported for quaternary structures.")
sys.exit(1)
if not os.path.isfile(path):
app.log.warn("cannot calculate buried surface areas: "
"file {} does not exist!".format(path))
# get the quaternary structure
ifs.open(str(path))
try:
assembly = ifs.GetOEGraphMols().next()
except StopIteration:
assembly = None
if not assembly:
app.log.warn(
"cannot calculate buried surface areas: "
"file {} does not contain a valid molecule!".format(path))
continue
if not assembly.GetListData('ligands'):
continue
# identifier of the assembly
assembly_serial = assembly.GetIntData('assembly_serial')
# remove all non-polymers from assembly
for atom in assembly.GetAtoms(nonpolymers):
assembly.DeleteAtom(atom)
# ignore bizarre assemblies
if not assembly.NumAtoms():
app.log.warn(
"cannot calculate buried surface areas: "
"file {} contains assembly with no atoms!".format(path))
continue
# keep only the location state with the largest average occupancy
assembly_hi_occ = oechem.OEGraphMol()
altlocfactory = oechem.OEAltLocationFactory(assembly)
altlocfactory.MakeCurrentAltMol(assembly_hi_occ)
# get the ligands
ligands = assembly_hi_occ.GetListData('ligands')
# iterate through all ligands of the biomolecule and calculate the buried
# surface area atom contributions for all involved atoms
for ligand in ligands:
# ignore small ligands
if oechem.OECount(ligand, oechem.OEIsHeavy()) < 7: continue
entity_serial = ligand.GetIntData('entity_serial')
# keep only the location state with the largest average occupancy
altlig = oechem.OEGraphMol()
altlocfactory = oechem.OEAltLocationFactory(ligand)
altlocfactory.MakeCurrentAltMol(altlig)
cmplx_srf = oespicoli.OESurface()
ligand_srf = oespicoli.OESurface()
# make solvent-accessible surface of ligand
oespicoli.OEMakeAccessibleSurface(ligand_srf, altlig, 0.5, 1.4)
# get the atom contributions of the assembly surface
ligand_atom_areas = get_atom_surface_areas(altlig, ligand_srf)
# extract the binding site of the assembly to speed up surface
# area calculation
binding_site = get_binding_site(assembly_hi_occ, altlig)
# make solvent-accessible surface of binding site
binding_site_srf = oespicoli.OESurface()
oespicoli.OEMakeAccessibleSurface(binding_site_srf,
binding_site, 0.5, 1.4)
# get the atom contributions of the assembly surface
binding_site_atom_areas = get_atom_surface_areas(
binding_site, binding_site_srf)
# create complex
cmplx = oechem.OEGraphMol()
oechem.OEAddMols(cmplx, binding_site)
oechem.OEAddMols(cmplx, altlig)
# make solvent-accessible surface of the complex
oespicoli.OEMakeAccessibleSurface(cmplx_srf, cmplx, 0.5, 1.4)
# surface area atom contributions of the whole complex
cmplx_atom_areas = get_atom_surface_areas(cmplx, cmplx_srf)
## extract the atom surface areas in the bound state through slices
binding_site_atom_areas_bound = cmplx_atom_areas[:binding_site.
NumAtoms()]
ligand_atom_areas_bound = cmplx_atom_areas[binding_site.
NumAtoms():]
# difference between apo and bound state per polymer atom
binding_site_delta = binding_site_atom_areas - binding_site_atom_areas_bound
ligand_delta = ligand_atom_areas - ligand_atom_areas_bound
# boolean map indicating for which atom the surface area has changed
binding_site_atom_map = binding_site_delta != 0
ligand_atom_map = ligand_delta != 0
if args.dry_run: continue
# only record the atoms where the solvent-accessible surface
# area has actually changed
write_atoms(atomwriter, binding_site, binding_site_atom_map,
pdb, assembly_serial, entity_serial,
binding_site_atom_areas,
binding_site_atom_areas_bound)
# only record the atoms where the solvent-accessible surface area
# has actually changed
write_atoms(atomwriter, altlig, ligand_atom_map, pdb,
assembly_serial, entity_serial, ligand_atom_areas,
ligand_atom_areas_bound)
app.log.debug("wrote buried surface areas for all ligands in "
"biomolecule {} to {}.".format(
pdb, surface_areas_path))
atomfs.flush()
atomfs.close()
if args.progressbar:
bar.finish()
oechem.OEThrow.Usage("%s <mol-infile>" % sys.argv[0])
ims = oechem.oemolistream()
if not ims.open(sys.argv[1]):
oechem.OEThrow.Fatal("Unable to open %s for reading" % sys.argv[1])
# @ <SNIPPET-ALTLOCFACT-MAKEALTMOL-FLAVOR>
ims.SetFlavor(oechem.OEFormat_PDB, oechem.OEIFlavor_PDB_ALTLOC)
# @ </SNIPPET-ALTLOCFACT-MAKEALTMOL-FLAVOR>
for mol in ims.GetOEGraphMols():
if not oechem.OEHasResidues(mol):
oechem.OEPerceiveResidues(mol, oechem.OEPreserveResInfo_All)
# @ <SNIPPET-ALTLOCFACT-MAKEALTMOL-ALF>
alf = oechem.OEAltLocationFactory(mol)
# @ </SNIPPET-ALTLOCFACT-MAKEALTMOL-ALF>
print("# atoms original.. %d" % alf.GetSourceMol().GetMaxAtomIdx())
atom = alf.GetAltAtoms()
if atom.IsValid():
# @ <SNIPPET-ALTLOCFACT-MAKEALTMOL-SSMOL>
# given OEAltLocationFactory alf and OEAtomBaseIter atom ...
loc = alf.GetLocation(atom.next(), 'B')
ssmol = oechem.OEGraphMol()
if alf.MakeAltMol(ssmol, loc):
# use the subset mol...
# @ </SNIPPET-ALTLOCFACT-MAKEALTMOL-SSMOL>
print("# atoms subset.... %d" % ssmol.GetMaxAtomIdx())
else:
print("no alternate location atoms")