def SplitMolComplexAllSites(oms, inmol, splitCovalent):
lig = oechem.OEGraphMol()
prot = oechem.OEGraphMol()
wat = oechem.OEGraphMol()
other = oechem.OEGraphMol()
if splitCovalent:
# @ <SNIPPET-SPLIT-MOL-COMPLEX-ALL-SITES-SPLIT>
opt = oechem.OESplitMolComplexOptions()
allSites = 0
opt.ResetFilters(allSites)
opt.SetSplitCovalent()
# @ </SNIPPET-SPLIT-MOL-COMPLEX-ALL-SITES-SPLIT>
if oechem.OESplitMolComplex(lig, prot, wat, other, inmol, opt):
WriteResultMols(oms, lig, prot, wat, other)
else:
# @ <SNIPPET-SPLIT-MOL-COMPLEX-ALL-SITES>
opt = oechem.OESplitMolComplexOptions()
allSites = 0
opt.ResetFilters(allSites)
# @ </SNIPPET-SPLIT-MOL-COMPLEX-ALL-SITES>
if oechem.OESplitMolComplex(lig, prot, wat, other, inmol, opt):
WriteResultMols(oms, lig, prot, wat, other)
def SplitMolComplex(oms, inmol, splitCovalent, separateResidues):
# limiting lig, prot and wat to just near the first binding site
# (a very common pattern)
lig = oechem.OEGraphMol()
prot = oechem.OEGraphMol()
wat = oechem.OEGraphMol()
other = oechem.OEGraphMol()
if not splitCovalent and not separateResidues:
# @ <SNIPPET-SPLIT-MOL-COMPLEX-SIMPLE>
# for input molecule inmol ...
lig = oechem.OEGraphMol()
prot = oechem.OEGraphMol()
wat = oechem.OEGraphMol()
other = oechem.OEGraphMol()
if oechem.OESplitMolComplex(lig, prot, wat, other, inmol):
# work with the output molecules lig, prot, ...
# @ </SNIPPET-SPLIT-MOL-COMPLEX-SIMPLE>
WriteResultMols(oms, lig, prot, wat, other)
elif splitCovalent and not separateResidues:
# @ <SNIPPET-SPLIT-MOL-COMPLEX-SPLIT-COVALENT>
# given input and output molecules ...
opt = oechem.OESplitMolComplexOptions()
opt.SetSplitCovalent()
if oechem.OESplitMolComplex(lig, prot, wat, other, inmol, opt):
# ...
# @ </SNIPPET-SPLIT-MOL-COMPLEX-SPLIT-COVALENT>
WriteResultMols(oms, lig, prot, wat, other)
elif not splitCovalent and separateResidues:
# @ <SNIPPET-SPLIT-MOL-COMPLEX-SEPARATE-RES>
opt = oechem.OESplitMolComplexOptions()
opt.SetSeparateResidues()
if not oechem.OESplitMolComplex(lig, prot, wat, other, inmol, opt):
oechem.OEThrow.Fatal("Unable to split mol complex from %s" %
inmol.GetTitle())
# @ </SNIPPET-SPLIT-MOL-COMPLEX-SEPARATE-RES>
else:
WriteResultMols(oms, lig, prot, wat, other)
else:
# @ <SNIPPET-SPLIT-MOL-COMPLEX-OPTIONS>
opt = oechem.OESplitMolComplexOptions()
opt.SetSplitCovalent(splitCovalent)
opt.SetSeparateResidues(separateResidues)
if not oechem.OESplitMolComplex(lig, prot, wat, other, inmol, opt):
oechem.OEThrow.Fatal("Unable to split mol complex from %s" %
inmol.GetTitle())
# @ </SNIPPET-SPLIT-MOL-COMPLEX-OPTIONS>
else:
WriteResultMols(oms, lig, prot, wat, other)
def _prepare_ligand_template(
self, ligand_template: pd.Series, kinase_domain: oechem.OEGraphMol
) -> oechem.OEGraphMol:
"""
Prepare a PDB structure containing the ligand template of interest.
Parameters
----------
ligand_template: pd.Series
A data series containing entries 'pdb', 'chain', 'ligand' and 'alt'.
kinase_domain: oechem.OEGraphMol
An OpenEye molecule holding the kinase domain the ligand template structure should be superposed to.
Returns
-------
: oechem.OEGraphMol
An OpenEye molecule holding the prepared ligand structure.
"""
from openeye import oechem
from ..modeling.OEModeling import (
read_molecules,
select_chain,
select_altloc,
remove_non_protein,
superpose_proteins,
)
from ..utils import FileDownloader
logging.debug("Interpreting structure ...")
ligand_template_structure = PDBProtein(ligand_template.pdb)
if not ligand_template_structure.path.is_file():
logging.debug(f"Downloading PDB entry {ligand_template.pdb} ...")
FileDownloader.rcsb_structure_pdb(ligand_template.pdb)
logging.debug("Reading structure ...")
ligand_template_structure = read_molecules(ligand_template_structure.path)[0]
logging.debug("Selecting chain ...")
ligand_template_structure = select_chain(ligand_template_structure, ligand_template.chain)
logging.debug("Selecting alternate location ...")
ligand_template_structure = select_altloc(ligand_template_structure, ligand_template.alt)
logging.debug("Removing everything but protein, water and ligand of interest ...")
ligand_template_structure = remove_non_protein(
ligand_template_structure, exceptions=[ligand_template.ligand], remove_water=False
)
logging.debug("Superposing structure on kinase domain ...")
ligand_template_structure = superpose_proteins(kinase_domain, ligand_template_structure)
logging.debug("Adding hydrogens ...")
oechem.OEPlaceHydrogens(ligand_template_structure)
split_options = oechem.OESplitMolComplexOptions()
logging.debug("Extracting ligand ...")
ligand_template_structure = list(
oechem.OEGetMolComplexComponents(
ligand_template_structure, split_options, split_options.GetLigandFilter()
)
)[0]
return ligand_template_structure
def SplitMolComplexIterAllSitesLigName(oms, mol, ligName):
# @ <SNIPPET-SPLIT-MOL-COMPLEX-ITER-LIGNAME-AND-ALL-SITES>
opt = oechem.OESplitMolComplexOptions(ligName)
allSites = 0
opt.ResetFilters(allSites)
for frag in oechem.OEGetMolComplexComponents(mol, opt):
# ...
# @ </SNIPPET-SPLIT-MOL-COMPLEX-ITER-LIGNAME-AND-ALL-SITES>
oechem.OEWriteMolecule(oms, frag)
def SplitMolComplexIterLigName(oms, mol, ligName):
# the ligand has been identified by name
# @ <SNIPPET-SPLIT-MOL-COMPLEX-ITER-LIGNAME>
# for input molecule mol and string ligName ...
opt = oechem.OESplitMolComplexOptions(ligName)
for frag in oechem.OEGetMolComplexComponents(mol, opt):
# ...
# @ </SNIPPET-SPLIT-MOL-COMPLEX-ITER-LIGNAME>
oechem.OEWriteMolecule(oms, frag)
def split(mol):
"""
This function splits the passed system in protein, ligand,
water and excipients
Parameters:
----------
mol : oechem.OEMol
The bio-molecular system to split
Output:
-------
protein : oechem.OEMol
The split protein
ligand : oechem.OEMol
The split ligand
wat : oechem.OEMol
The spit water
other : oechem.OEMol
The excipients
"""
# Set empty molecule containers
prot = oechem.OEMol()
lig = oechem.OEMol()
wat = oechem.OEMol()
other = oechem.OEMol()
# Define the Filter options before the splitting
opt = oechem.OESplitMolComplexOptions()
# The protein filter is set to avoid that multiple
# chains are separated during the splitting
pf = oechem.OEMolComplexFilterFactory(oechem.OEMolComplexFilterCategory_Protein)
# The ligand filter is set to recognize just the ligand
lf = oechem.OEMolComplexFilterFactory(oechem.OEMolComplexFilterCategory_Ligand)
# The water filter is set to recognize just water molecules
wf = oechem.OEMolComplexFilterFactory(oechem.OEMolComplexFilterCategory_Water)
opt.SetProteinFilter(pf)
opt.SetLigandFilter(lf)
opt.SetWaterFilter(wf)
# Splitting the system
if not oechem.OESplitMolComplex(lig, prot, wat, other, mol, opt):
oechem.OEThrow.Fatal('Unable to split the complex')
# At this point prot contains the protein, lig contains the ligand,
# wat contains the water and excipients contains the excipients
return prot, lig, wat, other
def get_protein_and_ligands(protein, ligand, itf):
if (itf.HasString("-complex")):
# separate ligand and protein in complex
iname = itf.GetString("-complex")
ifs = oechem.oemolistream()
if not ifs.open(iname):
oechem.OEThrow.Fatal("Cannot open input complex file!")
complexmol = oechem.OEGraphMol()
if not oechem.OEReadMolecule(ifs, complexmol):
oechem.OEThrow.Fatal("Unable to read complex from %s" % iname)
if not oechem.OEHasResidues(complexmol):
oechem.OEPerceiveResidues(complexmol, oechem.OEPreserveResInfo_All)
sopts = oechem.OESplitMolComplexOptions()
oechem.OESetupSplitMolComplexOptions(sopts, itf)
if not split_complex(protein, ligand, sopts, complexmol):
oechem.OEThrow.Fatal("Cannot separate complex!")
else:
# read ligand and protein from separate files
pname = itf.GetString("-protein")
ifs = oechem.oemolistream()
if not ifs.open(pname):
oechem.OEThrow.Fatal("Cannot open input protein file!")
if not oechem.OEReadMolecule(ifs, protein):
oechem.OEThrow.Fatal("Unable to read protein from %s" % pname)
lname = itf.GetString("-ligand")
ifs = oechem.oemolistream()
if not ifs.open(lname):
oechem.OEThrow.Fatal("Cannot open input ligand file!")
if not oechem.OEReadMolecule(ifs, ligand):
oechem.OEThrow.Fatal("Unable to read ligand from %s" % lname)
return ligand.NumAtoms() != 0 and protein.NumAtoms() != 0
def SplitMolComplexCombineFilters(oms, inmol):
lig = oechem.OEGraphMol()
prot = oechem.OEGraphMol()
wat = oechem.OEGraphMol()
other = oechem.OEGraphMol()
# @ <SNIPPET-SPLIT-MOL-COMPLEX-COMBINE-FILTERS>
opt = oechem.OESplitMolComplexOptions()
p = opt.GetProteinFilter()
w = opt.GetWaterFilter()
opt.SetProteinFilter(oechem.OEOrRoleSet(p, w))
opt.SetWaterFilter(
oechem.OEMolComplexFilterFactory(
oechem.OEMolComplexFilterCategory_Nothing))
# @ </SNIPPET-SPLIT-MOL-COMPLEX-COMBINE-FILTERS>
if oechem.OESplitMolComplex(lig, prot, wat, other, inmol, opt):
WriteResultMols(oms, lig, prot, wat, other)
def main(argv=[__name__]):
itf = oechem.OEInterface(InterfaceData)
oechem.OEConfigureSplitMolComplexOptions(itf)
if not oechem.OEParseCommandLine(itf, argv):
oechem.OEThrow.Fatal("Unable to interpret command line!")
iname = itf.GetString("-in")
oname = itf.GetString("-out")
ims = oechem.oemolistream()
if not itf.GetUnsignedInt("-modelnum") == 1:
ims.SetFlavor(
oechem.OEFormat_PDB,
oechem.OEGetDefaultIFlavor(oechem.OEFormat_PDB)
& ~oechem.OEIFlavor_PDB_ENDM)
if not ims.open(iname):
oechem.OEThrow.Fatal("Cannot open input file!")
oms = oechem.oemolostream()
if not oms.open(oname):
oechem.OEThrow.Fatal("Cannot open output file!")
inmol = oechem.OEGraphMol()
if not oechem.OEReadMolecule(ims, inmol):
oechem.OEThrow.Fatal("Cannot read input file!")
opts = oechem.OESplitMolComplexOptions()
oechem.OESetupSplitMolComplexOptions(opts, itf)
if itf.GetBool("-verbose"):
# don't bother counting sites unless we're going to print them
numSites = oechem.OECountMolComplexSites(inmol, opts)
oechem.OEThrow.SetLevel(oechem.OEErrorLevel_Verbose)
oechem.OEThrow.Verbose("sites %d" % numSites)
for frag in oechem.OEGetMolComplexComponents(inmol, opts):
oechem.OEThrow.Verbose("frag %s" % frag.GetTitle())
oechem.OEWriteMolecule(oms, frag)
oms.close()
def SplitMolComplexIter(oms, mol):
# limiting lig, prot and wat to just near the first binding site
# (a very common pattern)
# @ <SNIPPET-SPLIT-MOL-COMPLEX-ITER-SIMPLE>
# for input molecule mol ...
for frag in oechem.OEGetMolComplexComponents(mol):
# ...
# @ </SNIPPET-SPLIT-MOL-COMPLEX-ITER-SIMPLE>
oechem.OEWriteMolecule(oms, frag)
# other api points illustrated below
# @ <SNIPPET-SPLIT-MOL-COMPLEX-SPLIT-COVALENT>
opt = oechem.OESplitMolComplexOptions()
opt.SetSplitCovalent()
# @ </SNIPPET-SPLIT-MOL-COMPLEX-SPLIT-COVALENT>
# @ <SNIPPET-SPLIT-MOL-FILTER-SURFACE-WATERS>
site = 1
surfaceWaters = True
opt.ResetFilters(site, surfaceWaters)
opt.SetMaxSurfaceWaterDist(8.0)
def SplitMolComplexIterFilter(oms, mol):
# @ <SNIPPET-SPLIT-MOL-COMPLEX-ADD-COFACTOR>
db = oechem.OEResidueCategoryData()
db.AddToDB(oechem.OEResidueDatabaseCategory_Cofactor, "MTQ")
cat = oechem.OEMolComplexCategorizer()
cat.SetResidueCategoryData(db)
opt = oechem.OESplitMolComplexOptions()
opt.SetCategorizer(cat)
# @ </SNIPPET-SPLIT-MOL-COMPLEX-ADD-COFACTOR>
# @ <SNIPPET-SPLIT-MOL-COMPLEX-ITER-FILTER>
# for input molecule mol and options opt ...
for l in oechem.OEGetMolComplexComponents(mol, opt, opt.GetLigandFilter()):
# ...
# @ </SNIPPET-SPLIT-MOL-COMPLEX-ITER-FILTER>
oechem.OEWriteMolecule(oms, l)
# @ <SNIPPET-SPLIT-MOL-COMPLEX-EXAMPLE-FILTER>
ofilter = opt.GetOtherFilter()
# @ </SNIPPET-SPLIT-MOL-COMPLEX-EXAMPLE-FILTER>
rs = oechem.OERoles()
ofilter(rs)
def main(argv=[__name__]):
itf = oechem.OEInterface()
oechem.OEConfigure(itf, InterfaceData)
oedepict.OEConfigureImageWidth(itf, 900.0)
oedepict.OEConfigureImageHeight(itf, 600.0)
oedepict.OEConfigure2DMolDisplayOptions(
itf, oedepict.OE2DMolDisplaySetup_AromaticStyle)
oechem.OEConfigureSplitMolComplexOptions(
itf, oechem.OESplitMolComplexSetup_LigName)
if not oechem.OEParseCommandLine(itf, argv):
return 1
iname = itf.GetString("-complex")
oname = itf.GetString("-out")
ifs = oechem.oemolistream()
if not ifs.open(iname):
oechem.OEThrow.Fatal("Cannot open input file!")
ext = oechem.OEGetFileExtension(oname)
if not oedepict.OEIsRegisteredImageFile(ext):
oechem.OEThrow.Fatal("Unknown image type!")
ofs = oechem.oeofstream()
if not ofs.open(oname):
oechem.OEThrow.Fatal("Cannot open output file!")
complexmol = oechem.OEGraphMol()
if not oechem.OEReadMolecule(ifs, complexmol):
oechem.OEThrow.Fatal("Unable to read molecule from %s" % iname)
if not oechem.OEHasResidues(complexmol):
oechem.OEPerceiveResidues(complexmol, oechem.OEPreserveResInfo_All)
# Separate ligand and protein
sopts = oechem.OESplitMolComplexOptions()
oechem.OESetupSplitMolComplexOptions(sopts, itf)
ligand = oechem.OEGraphMol()
protein = oechem.OEGraphMol()
water = oechem.OEGraphMol()
other = oechem.OEGraphMol()
pfilter = sopts.GetProteinFilter()
wfilter = sopts.GetWaterFilter()
sopts.SetProteinFilter(oechem.OEOrRoleSet(pfilter, wfilter))
sopts.SetWaterFilter(
oechem.OEMolComplexFilterFactory(
oechem.OEMolComplexFilterCategory_Nothing))
oechem.OESplitMolComplex(ligand, protein, water, other, complexmol, sopts)
if ligand.NumAtoms() == 0:
oechem.OEThrow.Fatal("Cannot separate complex!")
# Perceive interactions
asite = oechem.OEInteractionHintContainer(protein, ligand)
if not asite.IsValid():
oechem.OEThrow.Fatal("Cannot initialize active site!")
asite.SetTitle(ligand.GetTitle())
oechem.OEPerceiveInteractionHints(asite)
oegrapheme.OEPrepareActiveSiteDepiction(asite)
# Depict active site with interactions
width, height = oedepict.OEGetImageWidth(itf), oedepict.OEGetImageHeight(
itf)
image = oedepict.OEImage(width, height)
cframe = oedepict.OEImageFrame(image, width * 0.80, height,
oedepict.OE2DPoint(0.0, 0.0))
lframe = oedepict.OEImageFrame(image, width * 0.20, height,
oedepict.OE2DPoint(width * 0.80, 0.0))
opts = oegrapheme.OE2DActiveSiteDisplayOptions(cframe.GetWidth(),
cframe.GetHeight())
oedepict.OESetup2DMolDisplayOptions(opts, itf)
adisp = oegrapheme.OE2DActiveSiteDisplay(asite, opts)
oegrapheme.OERenderActiveSite(cframe, adisp)
lopts = oegrapheme.OE2DActiveSiteLegendDisplayOptions(10, 1)
oegrapheme.OEDrawActiveSiteLegend(lframe, adisp, lopts)
oedepict.OEWriteImage(oname, image)
return 0
def main(argv=[__name__]):
itf = oechem.OEInterface()
oechem.OEConfigure(itf, InterfaceData)
oechem.OEConfigureSplitMolComplexOptions(
itf, oechem.OESplitMolComplexSetup_LigName)
if not oechem.OEParseCommandLine(itf, argv):
return 1
iname = itf.GetString("-complex")
ifs = oechem.oemolistream()
if not ifs.open(iname):
oechem.OEThrow.Fatal("Unable to open %s for reading" % iname)
complexmol = oechem.OEGraphMol()
if not oechem.OEReadMolecule(ifs, complexmol):
oechem.OEThrow.Fatal("Unable to read molecule from %s" % iname)
if not oechem.OEHasResidues(complexmol):
oechem.OEPerceiveResidues(complexmol, oechem.OEPreserveResInfo_All)
# Separate ligand and protein
sopts = oechem.OESplitMolComplexOptions()
oechem.OESetupSplitMolComplexOptions(sopts, itf)
ligand = oechem.OEGraphMol()
protein = oechem.OEGraphMol()
water = oechem.OEGraphMol()
other = oechem.OEGraphMol()
pfilter = sopts.GetProteinFilter()
wfilter = sopts.GetWaterFilter()
sopts.SetProteinFilter(oechem.OEOrRoleSet(pfilter, wfilter))
sopts.SetWaterFilter(
oechem.OEMolComplexFilterFactory(
oechem.OEMolComplexFilterCategory_Nothing))
oechem.OESplitMolComplex(ligand, protein, water, other, complexmol, sopts)
if ligand.NumAtoms() == 0:
oechem.OEThrow.Fatal("Cannot separate complex!")
# Perceive interactions
asite = oechem.OEInteractionHintContainer(protein, ligand)
if not oechem.OEIsValidActiveSite(asite):
oechem.OEThrow.Fatal("Cannot initialize active site!")
oechem.OEPerceiveInteractionHints(asite)
print("Number of interactions:", asite.NumInteractions())
for itype in oechem.OEGetActiveSiteInteractionHintTypes():
numinters = asite.NumInteractions(
oechem.OEHasInteractionHintType(itype))
if numinters == 0:
continue
print("%d %s :" % (numinters, itype.GetName()))
inters = [
s for s in asite.GetInteractions(
oechem.OEHasInteractionHintType(itype))
]
print("\n".join(sorted(GetInteractionString(s) for s in inters)))
print("\nResidue interactions:")
for res in oechem.OEGetResidues(
asite.GetMolecule(oechem.OEProteinInteractionHintComponent())):
PrintResidueInteractions(asite, res)
print("\nLigand atom interactions:")
for atom in asite.GetMolecule(
oechem.OELigandInteractionHintComponent()).GetAtoms():
PrintLigandAtomInteractions(asite, atom)
def split(complex, ligand_res_name='LIG'):
"""
This function splits the passed system in protein, ligand,
water and excipients
Parameters:
----------
complex : oechem.OEMol
The bio-molecular complex to split
ligand_res_name : Python string
The ligand residue name used to recognize the ligand
Output:
-------
protein : oechem.OEMol
The split protein
ligand : oechem.OEMol
The split ligand
wat : oechem.OEMol
The spit water
other : oechem.OEMol
The excipients
"""
# Set empty molecule containers
prot = oechem.OEMol()
lig = oechem.OEMol()
wat = oechem.OEMol()
other = oechem.OEMol()
# Define the Filter options before the splitting
opt = oechem.OESplitMolComplexOptions()
# The protein filter is set to avoid that multiple
# chains are separated during the splitting and peptide
# molecules are recognized as ligands
pf = oechem.OEMolComplexFilterFactory(
oechem.OEMolComplexFilterCategory_Protein)
peptide = oechem.OEMolComplexFilterFactory(
oechem.OEMolComplexFilterCategory_Peptide)
protein_filter = oechem.OEOrRoleSet(pf, peptide)
opt.SetProteinFilter(protein_filter)
# The ligand filter is set to recognize just the ligand
lf = oechem.OEMolComplexFilterFactory(
oechem.OEMolComplexFilterCategory_Ligand)
not_protein_filter = oechem.OENotRoleSet(protein_filter)
ligand_filter = oechem.OEAndRoleSet(lf, not_protein_filter)
opt.SetLigandFilter(ligand_filter)
# The water filter is set to recognize just water molecules
wf = oechem.OEMolComplexFilterFactory(
oechem.OEMolComplexFilterCategory_Water)
opt.SetWaterFilter(wf)
# Set Category
cat = oechem.OEMolComplexCategorizer()
cat.AddLigandName(ligand_res_name)
opt.SetCategorizer(cat)
# Splitting the system
if not oechem.OESplitMolComplex(lig, prot, wat, other, complex, opt):
raise ValueError('Unable to split the complex')
# At this point prot contains the protein, lig contains the ligand,
# wat contains the water and excipients contains the excipients
return prot, lig, wat, other
def split(system, ligand_res_name='LIG'):
"""
This function splits the passed molecule in components and tracks the
mapping between the original molecule and the split components. The
mapping is created as separated atom component index sets.
Parameters:
-----------
system: OEMol
The system to split in components. The components are:
the protein atoms,
the protein carbon alpha atoms
the water atoms,
the ion atoms,
the cofactor atoms
Returns:
--------
dic_set: python dictionary
The sysetm is splitted in a dictionary with token words as keys
and for value the related atom set. The token keywords are:
protein,
ca_protein,
ligand,
water,
ions,
cofactors,
system
"""
# Define Empty sets
lig_set = set()
prot_set = set()
ca_prot_set = set()
wat_set = set()
excp_set = set()
ion_set = set()
# cofactor_set = set()
# system_set = set()
# Atom Bond Set vector used to contains the whole system
frags = oechem.OEAtomBondSetVector()
# Define Options for the Filter
opt = oechem.OESplitMolComplexOptions()
# The protein filter is set to avoid that multiple
# chains are separated during the splitting and peptide
# molecules are recognized as ligands
pf = oechem.OEMolComplexFilterFactory(
oechem.OEMolComplexFilterCategory_Protein)
peptide = oechem.OEMolComplexFilterFactory(
oechem.OEMolComplexFilterCategory_Peptide)
protein_filter = oechem.OEOrRoleSet(pf, peptide)
opt.SetProteinFilter(protein_filter)
# The ligand filter is set to recognize just the ligand
lf = oechem.OEMolComplexFilterFactory(
oechem.OEMolComplexFilterCategory_Ligand)
not_protein_filter = oechem.OENotRoleSet(protein_filter)
ligand_filter = oechem.OEAndRoleSet(lf, not_protein_filter)
opt.SetLigandFilter(ligand_filter)
# The water filter is set to recognize just water molecules
wf = oechem.OEMolComplexFilterFactory(
oechem.OEMolComplexFilterCategory_Water)
opt.SetWaterFilter(wf)
# Set Category
cat = oechem.OEMolComplexCategorizer()
cat.AddLigandName(ligand_res_name)
opt.SetCategorizer(cat)
# Define the system fragments
if not oechem.OEGetMolComplexFragments(frags, system, opt):
raise ValueError('Unable to generate the system fragments')
# Set empty OEMol containers
prot = oechem.OEMol()
lig = oechem.OEMol()
wat = oechem.OEMol()
excp = oechem.OEMol()
# Split the protein from the system
atommap = oechem.OEAtomArray(system.GetMaxAtomIdx())
if not oechem.OECombineMolComplexFragments(
prot, frags, opt, opt.GetProteinFilter(), atommap):
raise ValueError('Unable to split the Protein')
# Populate the protein set and the protein carbon alpha set
pred = oechem.OEIsAlphaCarbon()
for sys_at in system.GetAtoms():
sys_idx = sys_at.GetIdx()
at_idx = atommap[sys_idx]
if at_idx:
prot_set.add(sys_idx)
at = system.GetAtom(oechem.OEHasAtomIdx(sys_idx))
if pred(at):
ca_prot_set.add(sys_idx)
# print(sys_idx, '->', at_idx)
# Split the ligand from the system
atommap = oechem.OEAtomArray(system.GetMaxAtomIdx())
if not oechem.OECombineMolComplexFragments(
lig, frags, opt, opt.GetLigandFilter(), atommap):
raise ValueError('Unable to split the Ligand')
# Populate the ligand set
for sys_at in system.GetAtoms():
sys_idx = sys_at.GetIdx()
at_idx = atommap[sys_idx]
if at_idx:
lig_set.add(sys_idx)
# print(sys_idx, '->', at_idx)
# Split the water from the system
atommap = oechem.OEAtomArray(system.GetMaxAtomIdx())
if not oechem.OECombineMolComplexFragments(
wat, frags, opt, opt.GetWaterFilter(), atommap):
raise ValueError('Unable to split the Water')
# Populate the water set
for sys_at in system.GetAtoms():
sys_idx = sys_at.GetIdx()
at_idx = atommap[sys_idx]
if at_idx:
wat_set.add(sys_idx)
# print(sys_idx, '->', at_idx)
# Split the excipients from the system
atommap = oechem.OEAtomArray(system.GetMaxAtomIdx())
if not oechem.OECombineMolComplexFragments(
excp, frags, opt, opt.GetOtherFilter(), atommap):
raise ValueError('Unable to split the Excipients')
# Populate the excipient set
for sys_at in system.GetAtoms():
sys_idx = sys_at.GetIdx()
at_idx = atommap[sys_idx]
if at_idx:
excp_set.add(sys_idx)
# print(sys_idx, '->', at_idx)
# Create the ions set
for exc_idx in excp_set:
atom = system.GetAtom(oechem.OEHasAtomIdx(exc_idx))
if atom.GetDegree() == 0:
ion_set.add(exc_idx)
# Create the cofactor set
cofactor_set = excp_set - ion_set
# Create the system set
system_set = prot_set | lig_set | excp_set | wat_set
if len(system_set) != system.NumAtoms():
raise ValueError("The total system atom number {} is different "
"from its set representation {}".format(
system.NumAtoms(), system_set))
# The dictionary is used to link the token keywords to the created molecule sets
dic_set = {
'ligand': lig_set,
'protein': prot_set,
'ca_protein': ca_prot_set,
'water': wat_set,
'ions': ion_set,
'cofactors': cofactor_set,
'system': system_set
}
return dic_set
def main(argv=[__name__]):
itf = oechem.OEInterface()
oechem.OEConfigure(itf, InterfaceData)
oedepict.OEConfigureImageWidth(itf, 600.0)
oedepict.OEConfigureImageHeight(itf, 600.0)
oedepict.OEConfigure2DMolDisplayOptions(itf, oedepict.OE2DMolDisplaySetup_AromaticStyle)
oechem.OEConfigureSplitMolComplexOptions(itf, oechem.OESplitMolComplexSetup_LigName)
if not oechem.OEParseCommandLine(itf, argv):
return 1
iname = itf.GetString("-complex")
oname = itf.GetString("-out")
ifs = oechem.oemolistream()
if not ifs.open(iname):
oechem.OEThrow.Fatal("Cannot open input file!")
ext = oechem.OEGetFileExtension(oname)
if not oedepict.OEIsRegisteredImageFile(ext):
oechem.OEThrow.Fatal("Unknown image type!")
ofs = oechem.oeofstream()
if not ofs.open(oname):
oechem.OEThrow.Fatal("Cannot open output file!")
complexmol = oechem.OEGraphMol()
if not oechem.OEReadMolecule(ifs, complexmol):
oechem.OEThrow.Fatal("Unable to read molecule from %s" % iname)
if not oechem.OEHasResidues(complexmol):
oechem.OEPerceiveResidues(complexmol, oechem.OEPreserveResInfo_All)
# Separate ligand and protein
sopts = oechem.OESplitMolComplexOptions()
oechem.OESetupSplitMolComplexOptions(sopts, itf)
ligand = oechem.OEGraphMol()
protein = oechem.OEGraphMol()
water = oechem.OEGraphMol()
other = oechem.OEGraphMol()
oechem.OESplitMolComplex(ligand, protein, water, other, complexmol, sopts)
if ligand.NumAtoms() == 0:
oechem.OEThrow.Fatal("Cannot separate complex!")
# Calculate average BFactor of the whole complex
avgbfactor = GetAverageBFactor(complexmol)
# Calculate minimum and maximum BFactor of the ligand and its environment
minbfactor, maxbfactor = GetMinAndMaxBFactor(ligand, protein)
# Attach to each ligand atom the average BFactor of the nearby protein atoms
stag = "avg residue BFfactor"
itag = oechem.OEGetTag(stag)
SetAverageBFactorOfNearbyProteinAtoms(ligand, protein, itag)
oechem.OEThrow.Info("Average BFactor of the complex = %+.3f" % avgbfactor)
oechem.OEThrow.Info("Minimum BFactor of the ligand and its environment = %+.3f" % minbfactor)
oechem.OEThrow.Info("Maximum BFactor of the ligand and its environment = %+.3f" % maxbfactor)
# Create image
imagewidth, imageheight = oedepict.OEGetImageWidth(itf), oedepict.OEGetImageHeight(itf)
image = oedepict.OEImage(imagewidth, imageheight)
mframe = oedepict.OEImageFrame(image, imagewidth,
imageheight * 0.90, oedepict.OE2DPoint(0.0, 0.0))
lframe = oedepict.OEImageFrame(image, imagewidth, imageheight * 0.10,
oedepict.OE2DPoint(0.0, imageheight * 0.90))
opts = oedepict.OE2DMolDisplayOptions(mframe.GetWidth(), mframe.GetHeight(),
oedepict.OEScale_AutoScale)
oedepict.OESetup2DMolDisplayOptions(opts, itf)
opts.SetAtomColorStyle(oedepict.OEAtomColorStyle_WhiteMonochrome)
# Create BFactor color gradient
colorg = oechem.OELinearColorGradient()
colorg.AddStop(oechem.OEColorStop(0.0, oechem.OEDarkBlue))
colorg.AddStop(oechem.OEColorStop(10.0, oechem.OELightBlue))
colorg.AddStop(oechem.OEColorStop(25.0, oechem.OEYellowTint))
colorg.AddStop(oechem.OEColorStop(50.0, oechem.OERed))
colorg.AddStop(oechem.OEColorStop(100.0, oechem.OEDarkRose))
# Prepare ligand for depiction
oegrapheme.OEPrepareDepictionFrom3D(ligand)
arcfxn = BFactorArcFxn(colorg, itag)
for atom in ligand.GetAtoms():
oegrapheme.OESetSurfaceArcFxn(ligand, atom, arcfxn)
opts.SetScale(oegrapheme.OEGetMoleculeSurfaceScale(ligand, opts))
# Render ligand and visualize BFactor
disp = oedepict.OE2DMolDisplay(ligand, opts)
colorbfactor = ColorLigandAtomByBFactor(colorg)
oegrapheme.OEAddGlyph(disp, colorbfactor, oechem.OEIsTrueAtom())
oegrapheme.OEDraw2DSurface(disp)
oedepict.OERenderMolecule(mframe, disp)
# Draw color gradient
opts = oegrapheme.OEColorGradientDisplayOptions()
opts.SetColorStopPrecision(1)
opts.AddMarkedValue(avgbfactor)
opts.SetBoxRange(minbfactor, maxbfactor)
oegrapheme.OEDrawColorGradient(lframe, colorg, opts)
oedepict.OEWriteImage(oname, image)
return 0
def split(complex, ligand_res_name='LIG'):
"""
This function splits the passed system in protein, ligand,
water and excipients.
Parameters:
----------
complex : oechem.OEMol
The bio-molecular complex to split
ligand_res_name : Python string
The ligand residue name used to recognize the ligand
Output:
-------
protein : oechem.OEMol
The split protein
ligand : oechem.OEMol
The split ligand
wat : oechem.OEMol
The spit water
cofactors : oechem.OEMol
The cofactors
lipids : oechem.OEMol
The lipids
metals : oechem.OEMol
The metals
excipients : oechem.OEMol
The excipients
"""
# Set empty molecule containers
protein = oechem.OEMol()
ligand = oechem.OEMol()
water = oechem.OEMol()
other = oechem.OEMol()
# Define the Filter options before the splitting
opt = oechem.OESplitMolComplexOptions()
# The protein filter is set to avoid that multiple
# chains are separated during the splitting and peptide
# molecules are recognized as ligands
pf = oechem.OEMolComplexFilterFactory(
oechem.OEMolComplexFilterCategory_Protein)
peptide = oechem.OEMolComplexFilterFactory(
oechem.OEMolComplexFilterCategory_Peptide)
protein_filter = oechem.OEOrRoleSet(pf, peptide)
opt.SetProteinFilter(protein_filter)
# The ligand filter is set to recognize just the ligand
lf = oechem.OEMolComplexFilterFactory(
oechem.OEMolComplexFilterCategory_Ligand)
not_protein_filter = oechem.OENotRoleSet(protein_filter)
ligand_filter = oechem.OEAndRoleSet(lf, not_protein_filter)
opt.SetLigandFilter(ligand_filter)
# The water filter is set to recognize just water molecules
wf = oechem.OEMolComplexFilterFactory(
oechem.OEMolComplexFilterCategory_Water)
opt.SetWaterFilter(wf)
# Set Category
cat = oechem.OEMolComplexCategorizer()
cat.AddLigandName(ligand_res_name)
opt.SetCategorizer(cat)
# Splitting the system
if not oechem.OESplitMolComplex(ligand, protein, water, other, complex,
opt):
raise ValueError('Unable to split the complex')
cofactors = oechem.OEMol()
lipids = oechem.OEMol()
metals = oechem.OEMol()
excipients = oechem.OEMol()
# Splitting the subsystem
if other.NumAtoms():
opt_other = oechem.OESplitMolComplexOptions()
lipid_filter = oechem.OEMolComplexFilterFactory(
oechem.OEMolComplexFilterCategory_Lipid)
opt_other.SetProteinFilter(lipid_filter)
cofactor_filter = oechem.OEMolComplexFilterFactory(
oechem.OEMolComplexFilterCategory_Cofactor)
opt_other.SetLigandFilter(cofactor_filter)
metal_filter = oechem.OEMolComplexFilterFactory(
oechem.OEMolComplexFilterCategory_Metal)
opt_other.SetWaterFilter(metal_filter)
# Set Category
cat_other = oechem.OEMolComplexCategorizer()
opt_other.SetCategorizer(cat_other)
if not oechem.OESplitMolComplex(cofactors, lipids, metals, excipients,
other, opt_other):
raise ValueError('Unable to split the Subcategories')
return protein, ligand, water, cofactors, lipids, metals, excipients
def main(argv=[__name__]):
itf = oechem.OEInterface(InterfaceData)
oechem.OEConfigureSplitMolComplexOptions(itf)
if not oechem.OEParseCommandLine(itf, argv):
oechem.OEThrow.Fatal("Unable to interpret command line!")
if itf.GetBool("-verbose"):
oechem.OEThrow.SetLevel(oechem.OEErrorLevel_Verbose)
iname = itf.GetString("-in")
oname = itf.GetString("-out")
ims = oechem.oemolistream()
if not itf.GetUnsignedInt("-modelnum") == 1:
ims.SetFlavor(
oechem.OEFormat_PDB,
oechem.OEGetDefaultIFlavor(oechem.OEFormat_PDB)
& ~oechem.OEIFlavor_PDB_ENDM)
if not ims.open(iname):
oechem.OEThrow.Fatal("Cannot open input file!")
oms = oechem.oemolostream()
if not oms.open(oname):
oechem.OEThrow.Fatal("Cannot open output file!")
mol = oechem.OEGraphMol()
if not oechem.OEReadMolecule(ims, mol):
oechem.OEThrow.Fatal("Cannot read input file!")
if itf.GetBool("-verbose"):
oechem.OEThrow.SetLevel(oechem.OEErrorLevel_Verbose)
opt = oechem.OESplitMolComplexOptions()
oechem.OESetupSplitMolComplexOptions(opt, itf)
# @ <SNIPPET-SPLIT-MOL-COMPLEX-LOWLEVEL-FRAGMENT>
# for input molecule mol and options opt ...
frags = oechem.OEAtomBondSetVector()
if oechem.OEGetMolComplexFragments(frags, mol, opt):
# ...
# @ </SNIPPET-SPLIT-MOL-COMPLEX-LOWLEVEL-FRAGMENT>
oechem.OEThrow.Verbose("Able to fragment mol complex from %s" % iname)
else:
oechem.OEThrow.Fatal("Unable to fragment mol complex from %s" % iname)
# @ <SNIPPET-SPLIT-MOL-COMPLEX-LOWLEVEL-COMBINE>
# for options opt and OEAtomBondSetVector frags produced earlier ...
numSites = oechem.OECountMolComplexSites(frags)
oechem.OEThrow.Verbose("sites %d" % numSites)
lig = oechem.OEGraphMol()
ligfilter = opt.GetLigandFilter()
if not oechem.OECombineMolComplexFragments(lig, frags, opt, ligfilter):
oechem.OEThrow.Warning("Unable to combine ligand frags from %s" %
mol.GetTitle())
protComplex = oechem.OEGraphMol()
p = opt.GetProteinFilter()
w = opt.GetWaterFilter()
if not oechem.OECombineMolComplexFragments(protComplex, frags, opt,
oechem.OEOrRoleSet(p, w)):
oechem.OEThrow.Warning("Unable to combine complex frags from %s" %
mol.GetTitle())
# @ </SNIPPET-SPLIT-MOL-COMPLEX-LOWLEVEL-COMBINE>
if not lig.NumAtoms() == 0:
oechem.OEThrow.Verbose(" lig %s" % lig.GetTitle())
oechem.OEWriteMolecule(oms, lig)
if not protComplex.NumAtoms() == 0:
oechem.OEThrow.Verbose(" prot %s" % protComplex.GetTitle())
oechem.OEWriteMolecule(oms, protComplex)
oms.close()
def main(argv=[__name__]):
itf = oechem.OEInterface(InterfaceData)
oechem.OEConfigureSplitMolComplexOptions(itf)
if not oechem.OEParseCommandLine(itf, argv):
oechem.OEThrow.Fatal("Unable to interpret command line!")
if itf.GetBool("-verbose"):
oechem.OEThrow.SetLevel(oechem.OEErrorLevel_Verbose)
iname = itf.GetString("-in")
oname = itf.GetString("-out")
ims = oechem.oemolistream()
if not itf.GetUnsignedInt("-modelnum") == 1:
ims.SetFlavor(oechem.OEFormat_PDB,
oechem.OEGetDefaultIFlavor(oechem.OEFormat_PDB) & ~oechem.OEIFlavor_PDB_ENDM)
if not ims.open(iname):
oechem.OEThrow.Fatal("Cannot open input file!")
oms = oechem.oemolostream()
if not oms.open(oname):
oechem.OEThrow.Fatal("Cannot open output file!")
inmol = oechem.OEGraphMol()
if not oechem.OEReadMolecule(ims, inmol):
oechem.OEThrow.Fatal("Cannot read input file!")
opts = oechem.OESplitMolComplexOptions()
oechem.OESetupSplitMolComplexOptions(opts, itf)
if itf.GetBool("-verbose"):
# don't bother counting sites unless we're going to print them
numSites = oechem.OECountMolComplexSites(inmol, opts)
oechem.OEThrow.SetLevel(oechem.OEErrorLevel_Verbose)
oechem.OEThrow.Verbose("sites %d" % numSites)
lig = oechem.OEGraphMol()
prot = oechem.OEGraphMol()
wat = oechem.OEGraphMol()
other = oechem.OEGraphMol()
if not oechem.OESplitMolComplex(lig, prot, wat, other, inmol, opts):
oechem.OEThrow.Fatal("Unable to split mol complex from %s" % iname)
if not lig.NumAtoms() == 0:
oechem.OEThrow.Verbose(" lig %s" % lig.GetTitle())
oechem.OEWriteMolecule(oms, lig)
if not prot.NumAtoms() == 0:
oechem.OEThrow.Verbose(" prot %s" % prot.GetTitle())
oechem.OEWriteMolecule(oms, prot)
if not wat.NumAtoms() == 0:
oechem.OEThrow.Verbose(" wat %s" % wat.GetTitle())
oechem.OEWriteMolecule(oms, wat)
if not other.NumAtoms() == 0:
oechem.OEThrow.Verbose("other %s" % other.GetTitle())
oechem.OEWriteMolecule(oms, other)
oms.close()
def main(argv=[__name__]):
itf = oechem.OEInterface(InterfaceData)
oechem.OEConfigureSplitMolComplexOptions(itf)
if not oechem.OEParseCommandLine(itf, argv):
oechem.OEThrow.Fatal("Unable to interpret command line!")
opts = oechem.OESplitMolComplexOptions()
oechem.OESetupSplitMolComplexOptions(opts, itf)
# @ </SNIPPET-SPLIT-MOL-COMPLEX-ITF>
iname = itf.GetString("-in")
oname = itf.GetString("-out")
ims = oechem.oemolistream()
if not itf.GetUnsignedInt("-modelnum") == 1:
ims.SetFlavor(
oechem.OEFormat_PDB,
oechem.OEGetDefaultIFlavor(oechem.OEFormat_PDB)
& ~oechem.OEIFlavor_PDB_ENDM)
if not ims.open(iname):
oechem.OEThrow.Fatal("Cannot open input file!")
oms = oechem.oemolostream()
if not oms.open(oname):
oechem.OEThrow.Fatal("Cannot open output file!")
bfixTitles = (oms.GetFormat() == oechem.OEFormat_SDF)
sTitleSDTag = "TITLE"
inmol = oechem.OEGraphMol()
if not oechem.OEReadMolecule(ims, inmol):
oechem.OEThrow.Fatal("Cannot read input file!")
lig = oechem.OEGraphMol()
prot = oechem.OEGraphMol()
wat = oechem.OEGraphMol()
other = oechem.OEGraphMol()
if not oechem.OESplitMolComplex(lig, prot, wat, other, inmol, opts):
oechem.OEThrow.Fatal("Unable to split mol complex from %s" % iname)
if not lig.NumAtoms() == 0:
if bfixTitles:
FixSDFTitle(sTitleSDTag, lig)
oechem.OEWriteMolecule(oms, lig)
if not prot.NumAtoms() == 0:
if bfixTitles:
FixSDFTitle(sTitleSDTag, prot)
oechem.OEWriteMolecule(oms, prot)
if not wat.NumAtoms() == 0:
if bfixTitles:
FixSDFTitle(sTitleSDTag, wat)
oechem.OEWriteMolecule(oms, wat)
if not other.NumAtoms() == 0:
if bfixTitles:
FixSDFTitle(sTitleSDTag, other)
oechem.OEWriteMolecule(oms, other)
oms.close()