def main(args):
if len(args) != 3:
oechem.OEThrow.Usage("%s <protein> <ligand>" % args[0])
pifs = oechem.oemolistream()
if not pifs.open(args[1]):
oechem.OEThrow.Fatal("Unable to open %s for reading protein." %
args[1])
prot = oechem.OEGraphMol()
if not oechem.OEReadMolecule(pifs, prot):
oechem.OEThrow.Fatal("Unable to read protein")
oechem.OEAddExplicitHydrogens(prot)
oechem.OEAssignBondiVdWRadii(prot)
lifs = oechem.oemolistream()
if not lifs.open(args[2]):
oechem.OEThrow.Fatal("Unable to open %s for reading ligand." % args[2])
lig = oechem.OEGraphMol()
if not oechem.OEReadMolecule(lifs, lig):
oechem.OEThrow.Fatal("Unable to read ligand")
oechem.OEAddExplicitHydrogens(lig)
oechem.OEAssignBondiVdWRadii(lig)
comp = oechem.OEGraphMol(prot)
oechem.OEAddMols(comp, lig)
compSurf = oespicoli.OESurface()
oespicoli.OEMakeMolecularSurface(compSurf, comp)
protSurf = oespicoli.OESurface()
oespicoli.OEMakeMolecularSurface(protSurf, prot)
ligSurf = oespicoli.OESurface()
oespicoli.OEMakeMolecularSurface(ligSurf, lig)
compVol = oespicoli.OESurfaceVolume(compSurf)
protVol = oespicoli.OESurfaceVolume(protSurf)
ligVol = oespicoli.OESurfaceVolume(ligSurf)
oespicoli.OEWriteSurface("comp.oesrf", compSurf)
oespicoli.OEWriteSurface("prot.oesrf", protSurf)
oespicoli.OEWriteSurface("lig.oesrf", ligSurf)
oechem.OEThrow.Info(
"%s-%s: dV(C-P) = %.1f V(L) = %.1f V(C) = %.1f V(P) = %.1f" %
(prot.GetTitle(), lig.GetTitle(), compVol - protVol, ligVol, compVol,
protVol))
return 0
def main(args):
if len(args) != 4:
oechem.OEThrow.Usage("%s <protein> <ligand> <surface>" % args[0])
pfs = oechem.oemolistream(args[1])
prot = oechem.OEGraphMol()
oechem.OEReadMolecule(pfs, prot)
oechem.OEAssignBondiVdWRadii(prot)
lfs = oechem.oemolistream(args[2])
lig = oechem.OEGraphMol()
oechem.OEReadMolecule(lfs, lig)
surf = oespicoli.OESurface()
oespicoli.OEMakeMolecularSurface(surf, prot)
oespicoli.OESurfaceToMoleculeDistance(surf, lig)
# Mark the vertices to keep
for i in range(surf.GetNumVertices()):
if surf.GetDistanceElement(i) < MAX_DIST:
surf.SetVertexCliqueElement(i, 1)
# Crop to the binding site and output
oespicoli.OESurfaceCropToClique(surf, 1)
oespicoli.OEWriteSurface(args[3], surf)
return 0
def main(args):
if len(args) != 4:
oechem.OEThrow.Usage("%s <protein> <ligand> <surface>" % args[0])
pfs = oechem.oemolistream(args[1])
prot = oechem.OEGraphMol()
oechem.OEReadMolecule(pfs, prot)
oechem.OEAssignBondiVdWRadii(prot)
lfs = oechem.oemolistream(args[2])
lig = oechem.OEGraphMol()
oechem.OEReadMolecule(lfs, lig)
surf = oespicoli.OESurface()
oespicoli.OEMakeMolecularSurface(surf, prot)
# Iterate through all the protein surface vertices
for i in range(surf.GetNumVertices()):
vert = surf.GetVertex(i)
# Check the distance to each atom
for atom in lig.GetAtoms():
dist2 = GetDist2(lig.GetCoords(atom), vert)
if dist2 < MAX_DIST * MAX_DIST:
surf.SetVertexCliqueElement(i, 1)
# Crop to the binding site and output
oespicoli.OESurfaceCropToClique(surf, 1)
oespicoli.OEWriteSurface(args[3], surf)
return 0
def main(argv=[__name__]):
if len(argv) != 3:
oechem.OEThrow.Usage("%s <molfile.pdb> <out.srf>" % argv[0])
mol = oechem.OEGraphMol()
ifs = oechem.oemolistream(argv[1])
oechem.OEReadMolecule(ifs, mol)
if not oechem.OEHasResidues(mol):
oechem.OEPerceiveResidues(mol, oechem.OEPreserveResInfo_All)
serials = {}
for atom in mol.GetAtoms():
res = oechem.OEAtomGetResidue(atom)
serials[res.GetSerialNumber()] = atom
outsurf = oespicoli.OESurface()
center = oechem.OEFloatArray(3)
for line in open(argv[1]):
if line.startswith("ANISOU"):
serno, factors = ParseFactors(line)
if serno in serials:
mol.GetCoords(serials[serno], center)
surf = GetEllipsoidalSurface(center, factors)
oespicoli.OEAddSurfaces(outsurf, surf)
oespicoli.OEWriteSurface(argv[2], outsurf)
def AverageSurfaceArea(mcmol):
area = 0.0
parea = 0.0
for conf in mcmol.GetConfs():
surf = oespicoli.OESurface()
oespicoli.OEMakeMolecularSurface(surf, conf, 0.5)
MakeCliques(surf, conf)
area += oespicoli.OESurfaceArea(surf)
parea += oespicoli.OESurfaceCliqueArea(surf, 1)
area /= mcmol.NumConfs()
parea /= mcmol.NumConfs()
return area, parea
def main(args):
if len(args) != 3:
oechem.OEThrow.Usage("%s <ref> <fit>" % args[0])
refifs = oechem.oemolistream()
if not refifs.open(args[1]):
oechem.OEThrow.Fatal("Unable to open %s for reading" % args[1])
refmol = oechem.OEGraphMol()
oechem.OEReadMolecule(refifs, refmol)
oechem.OEAssignBondiVdWRadii(refmol)
fitifs = oechem.oemolistream()
if not fitifs.open(args[2]):
oechem.OEThrow.Fatal("Unable to open %s for reading" % args[2])
fitmol = oechem.OEGraphMol()
oechem.OEReadMolecule(fitifs, fitmol)
oechem.OEAssignBondiVdWRadii(fitmol)
# Map the reference molecule onto a grid
grd = oegrid.OEScalarGrid()
oegrid.OEMakeMolecularGaussianGrid(grd, refmol, 0.5)
# Get the total volume of the reference molecule
refsrf = oespicoli.OESurface()
oespicoli.OEMakeSurfaceFromGrid(refsrf, grd, 1.0)
totalv = oespicoli.OESurfaceVolume(refsrf)
# Mask out the fit molecule
oegrid.OEMaskGridByMolecule(grd, fitmol)
# Find how much of the reference volume is remaining
fitsrf = oespicoli.OESurface()
oespicoli.OEMakeSurfaceFromGrid(fitsrf, grd, 1.0)
remaining = oespicoli.OESurfaceVolume(fitsrf)
print("Percent overlap: %f" % ((1 - remaining / totalv) * 100))
return 0
def GetEllipsoidalSurface(center, factors):
surf = oespicoli.OESurface()
dir1 = oechem.OEFloatArray(3)
dir1[0] = factors[0]
dir1[1] = factors[3]
dir1[2] = factors[4]
dir2 = oechem.OEFloatArray(3)
dir2[0] = factors[3]
dir2[1] = factors[1]
dir2[2] = factors[5]
dir3 = oechem.OEFloatArray(3)
dir3[0] = factors[4]
dir3[1] = factors[5]
dir3[2] = factors[2]
oespicoli.OEMakeEllipsoidSurface(surf, center, 10.0, 10.0, 10.0, dir1,
dir2, dir3, 4)
return surf
def main(args):
if len(args) != 3:
oechem.OEThrow.Usage("%s <protein> <surface>" % args[0])
ifs = oechem.oemolistream()
if not ifs.open(args[1]):
oechem.OEThrow.Fatal("Unable to open %s for reading" % args[1])
mol = oechem.OEGraphMol()
oechem.OEReadMolecule(ifs, mol)
oechem.OEPerceiveResidues(mol)
oechem.OEAssignBondiVdWRadii(mol)
# Generate the molecular surface
surf = oespicoli.OESurface()
oespicoli.OEMakeMolecularSurface(surf, mol, 0.5)
# Mark all the vertices associated with hydrophobic atoms
for i in range(surf.GetNumVertices()):
atom = mol.GetAtom(oechem.OEHasAtomIdx(surf.GetAtomsElement(i)))
if (AtomInHydrophobicResidue(atom)):
surf.SetVertexCliqueElement(i, 1)
# Crop to only those triangles
oespicoli.OESurfaceCropToClique(surf, 1)
# nlqs is the number of different connected components
nclqs = oespicoli.OEMakeConnectedSurfaceCliques(surf)
# Find the largest component
maxclq = 0
maxarea = 0.0
for i in range(nclqs):
area = oespicoli.OESurfaceCliqueArea(surf, i+1)
print("clique: %d area: %f" % (i+1, area))
if (area > maxarea):
maxclq = i+1
maxarea = area
# Crop to it
oespicoli.OESurfaceCropToClique(surf, maxclq)
oespicoli.OEWriteSurface(args[2], surf)
return 0
def main(args):
if len(args) != 3:
oechem.OEThrow.Usage("%s <protein> <surface>" % args[0])
prtfs = oechem.oemolistream()
if not prtfs.open(args[1]):
oechem.OEThrow.Fatal("Unable to open %s for reading" % args[1])
prt = oechem.OEGraphMol()
oechem.OEReadMolecule(prtfs, prt)
oechem.OEAssignBondiVdWRadii(prt)
surf = oespicoli.OESurface()
oespicoli.OEMakeCavitySurfaces(prt, surf)
oespicoli.OEInvertSurface(surf)
oespicoli.OEWriteSurface(args[2], surf)
return 0
def main(args):
if len(args) != 3:
oechem.OEThrow.Usage("%s <molecules> <oebfile>" % args[0])
ifs = oechem.oemolistream()
if not ifs.open(args[1]):
oechem.OEThrow.Fatal("Unable to open %s for reading" % args[1])
ofs = oechem.oemolostream()
if not ofs.open(args[2]):
oechem.OEThrow.Fatal("Unable to open %s for writing" % args[2])
for mol in ifs.GetOEGraphMols():
oechem.OEAssignBondiVdWRadii(mol)
surf = oespicoli.OESurface()
oespicoli.OEMakeMolecularSurface(surf, mol, 0.5)
ColorSurface(surf, mol)
mol.SetData("psasurf", surf)
oechem.OEWriteMolecule(ofs, mol)
return 0
def main(args):
if len(args) != 4:
oechem.OEThrow.Usage("%s <protein> <ligand> <surface>" % args[0])
prtfs = oechem.oemolistream(args[1])
prt = oechem.OEGraphMol()
oechem.OEReadMolecule(prtfs, prt)
oechem.OESuppressHydrogens(prt)
oechem.OEAssignBondiVdWRadii(prt)
ligfs = oechem.oemolistream(args[2])
lig = oechem.OEGraphMol()
oechem.OEReadMolecule(ligfs, lig)
oechem.OESuppressHydrogens(lig)
oechem.OEAssignBondiVdWRadii(lig)
grid = oegrid.OEScalarGrid()
oespicoli.OEMakeVoidVolume(prt, lig, grid, 0.5)
surf = oespicoli.OESurface()
oespicoli.OEMakeSurfaceFromGrid(surf, grid, 0.5)
oespicoli.OEWriteSurface(args[3], surf)
return 0
from openeye import oespicoli
if len(sys.argv) != 2:
oechem.OEThrow.Usage("%s <input>" % sys.argv[0])
ims = oechem.oemolistream()
if not ims.open(sys.argv[1]):
oechem.OEThrow.Fatal("Unable to open %s" % sys.argv[1])
mol = oechem.OEGraphMol()
if not oechem.OEReadMolecule(ims, mol):
oechem.OEThrow.Fatal("Unable to read a molecule")
oechem.OEAssignBondiVdWRadii(mol)
# @ <SNIPPET-SetData>
surf = oespicoli.OESurface()
oespicoli.OEMakeMolecularSurface(surf, mol)
mol.SetData("surface", surf)
ofs = oechem.oemolostream("foo.oeb")
oechem.OEWriteMolecule(ofs, mol)
# @ </SNIPPET-SetData>
ofs.close()
# @ <SNIPPET-GetData>
ifs = oechem.oemolistream("foo.oeb")
oechem.OEReadMolecule(ifs, mol)
msrf = mol.GetData("surface")
# @ </SNIPPET-GetData>
def nmax_waters(protein, ligand, cutoff):
# Grid Spacing in A
spacing = 0.5
complex = oechem.OEMol(protein)
oechem.OEAddMols(complex, ligand)
surf = oespicoli.OESurface()
oespicoli.OEMakeMolecularSurface(surf, complex, spacing)
# oespicoli.OEWriteSurface("test_surf.oesrf", surf)
center = oechem.OEFloatArray(3)
extents = oechem.OEFloatArray(3)
oechem.OEGetCenterAndExtents(ligand, center, extents)
extents = oechem.OEFloatArray(
[max(extents) * 2,
max(extents) * 2,
max(extents) * 2])
grid_reference = oegrid.OEScalarGrid()
oegrid.OEMakeGridFromCenterAndExtents(grid_reference, center, extents,
spacing)
grid_spicoli = oegrid.OEScalarGrid()
oespicoli.OEMakeBitGridFromSurface(grid_spicoli, surf)
for iz in range(grid_reference.GetZDim()):
for iy in range(grid_reference.GetYDim()):
for ix in range(grid_reference.GetXDim()):
x = grid_reference.GetX(ix)
y = grid_reference.GetY(iy)
z = grid_reference.GetZ(iz)
ix_spicoli = grid_spicoli.GetXIdx(x)
iy_spicoli = grid_spicoli.GetYIdx(y)
iz_spicoli = grid_spicoli.GetZIdx(z)
value = grid_spicoli.GetValue(ix_spicoli, iy_spicoli,
iz_spicoli)
grid_reference.SetValue(ix, iy, iz, value)
# Invert Grid
for iz in range(grid_reference.GetZDim()):
for iy in range(grid_reference.GetYDim()):
for ix in range(grid_reference.GetXDim()):
# print("ix = {} iy = {} iz = {} value = {}".format(ix, iy, iz , grid.GetValue(ix, iy, iz)))
if grid_reference.GetValue(ix, iy, iz) == 0.0:
grid_reference.SetValue(ix, iy, iz, 1.0)
else:
grid_reference.SetValue(ix, iy, iz, 0.0)
ligand_coords = ligand.GetCoords()
for iz in range(grid_reference.GetZDim()):
for iy in range(grid_reference.GetYDim()):
for ix in range(grid_reference.GetXDim()):
if grid_reference.GetValue(ix, iy, iz) == 1.0:
x = grid_reference.GetX(ix)
y = grid_reference.GetY(iy)
z = grid_reference.GetZ(iz)
min_sq = cutoff * cutoff
for coord in ligand_coords.values():
distsq = dist2(coord, (x, y, z))
if distsq < min_sq:
min_sq = distsq
break
if min_sq == cutoff * cutoff:
grid_reference.SetValue(ix, iy, iz, 0.0)
protein_coords = protein.GetCoords()
for iz in range(grid_reference.GetZDim()):
for iy in range(grid_reference.GetYDim()):
for ix in range(grid_reference.GetXDim()):
if grid_reference.GetValue(ix, iy, iz) == 1.0:
x = grid_reference.GetX(ix)
y = grid_reference.GetY(iy)
z = grid_reference.GetZ(iz)
min_sq = cutoff * cutoff
for coord in protein_coords.values():
distsq = dist2(coord, (x, y, z))
if distsq < min_sq:
min_sq = distsq
break
if min_sq == cutoff * cutoff:
grid_reference.SetValue(ix, iy, iz, 0.0)
# oegrid.OEWriteGrid("protein_ligand.grd", grid_reference)
count = 0
for iz in range(grid_reference.GetZDim()):
for iy in range(grid_reference.GetYDim()):
for ix in range(grid_reference.GetXDim()):
if grid_reference.GetValue(ix, iy, iz) == 1.0:
count += 1
# Calculate Volume from count in Angstrom
vcount = (spacing**3) * count
# Number of water molecule in vcount volume
nwaters = int(0.034 * vcount)
return nwaters
# def select_nmax_waters()
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()
