def pdbMutator(pdb,residue,mutation,chain=None,run_charmm=True):
"""
Standardize a pdb file: remove HETATM and ANISOU entries, renumber atoms,
take only a particular chain, remove alternate conformations.
"""
# grab header
header = [l for l in pdb if l[0:6] not in pdb_clean.COORD_RECORDS and
l[0:6] not in pdb_clean.DEPRECATED_RECORDS]
# Grab coordinates
coord = [l for l in pdb if l[0:6] == "ATOM "]
if pdb_clean.pdbCheck(coord):
err = "There are no ATOM entries in this pdb file!"
raise MutatorError(err)
coord, original_aa = mutateResidue(coord,residue,mutation,chain)
mutation_string = "%s%i%s" % (AA3_TO_AA1[original_aa],residue,
AA3_TO_AA1[mutation])
# Set up log
log = ["REMARK %s introduced by pdb_mutator ([email protected])\n" % \
mutation_string]
log_fmt = "REMARK - %s\n"
log.append(log_fmt % ("Process time: %s" % time.asctime()))
if chain == None:
log.append(log_fmt % ("Mutation introduced on all chains"))
else:
log.append(log_fmt % ("Mutation introduced on chain %s" % chain))
# Add missing atoms using CHARMM
if run_charmm:
print log_fmt % "Adding mutated side chain using CHARMM",
seqres = [l for l in header if l[0:6] == "SEQRES"]
coord = pdb_clean.addMissingAtoms(coord,seqres)
log.append(log_fmt % "Mutated sidechain built with CHARMM")
# Renumber atoms from 1
coord = pdb_atom_renumber.pdbAtomRenumber(coord)
log.append(log_fmt % "Renumbered atoms from 1")
print log[-1],
# Standardize atom-type on far right pdb column
coord = ["%s %s \n" % (c[:66],c[13]) for c in coord]
log.append(log_fmt % "Atom types were standardized.")
print log[-1],
# Final check
if pdb_clean.pdbCheck(coord):
err = "Unknown error occured and pdb has been mangled!"
raise MutatorError(err)
# Return processed pdb file.
out_pdb = []
out_pdb.extend(log)
out_pdb.extend(header)
out_pdb.extend(coord)
return out_pdb, mutation_string
def pdbClean(pdb,pdb_id="temp",chains="all",renumber_residues=False,
keep_temp=False,fix_atoms=True,num_steps=500):
"""
Standardize a pdb file:
- Remove waters, ligands, and other HETATMS
- Convert modified residues (i.e. Se-Met) to the normal residue
- Remove alternate conformations (taking first in pdb file)
- Find and remove residues with missing backbone atoms
-
- Take only the specified chain
- Renumber residues from 1
"""
# Set up log
log = ["REMARK PDB processed using pdb_clean.py ([email protected])\n"]
log_fmt = "REMARK - %s\n"
log.append(log_fmt % ("Process time: %s" % time.asctime()))
# Check pdb files for Brookhaven-added error warnings (CAVEAT and OBSLTE)
error = [l for l in pdb if l[0:6] in ERROR_RECORDS]
if len(error) != 0:
err = "PDB might have problem!\n" + "".join(error)
raise PdbCleanError(err)
# Grab pdb header, excluding coordinates and deprecated records.
header = [l for l in pdb if l[0:6] not in COORD_RECORDS]
# Convert non-standard amino acids to standard ones
coord = [l for l in pdb if l[0:6] in COORD_RECORDS]
coord, header, converted = convertModifiedAA(coord,header)
if len(converted) != 0:
log.append(log_fmt % "Modified amino acids converted.")
print log[-1],
log.extend(converted)
if pdbCheck(coord):
err = "Modified amino acid converter removed all atoms! Mangled pdb!"
raise PdbCleanError(err)
# Strip all entries in COORD_RECORDS except ATOM
coord = [l for l in coord if l[0:6] == "ATOM "]
if pdbCheck(coord):
err = "There are no ATOM entries in this pdb file!"
raise PdbCleanError(err)
else:
log.append(log_fmt % "HETATM entries removed.")
print log[-1],
# Grab only the chain we want, if specified
if chains != "all":
coord = [l for l in coord if l[21] in chains]
log.append(log_fmt % ("Took only chain %r." % chains))
print log[-1],
if pdbCheck(coord):
err = "Chain filter (%r) removed all atoms in pdb file!" % chains
raise PdbCleanError(err)
# Strip alternate conformations
coord, skipped = stripACS(coord)
if len(skipped) != 0:
log.append(log_fmt % "Alternate conformations were removed.")
print log[-1],
log.extend(skipped)
if pdbCheck(coord):
err = "ACS stripper removed all atoms! Mangled pdb file."
raise PdbCleanError(err)
# Check for missing backbone atoms; these residues are deleted
coord, removed = backboneCheck(coord)
if len(removed) != 0:
log.append(log_fmt % "Residues with missing backbone atoms removed.")
print log[-1],
log.extend(removed)
if pdbCheck(coord):
err = "Backbone checker removed all atoms! Mangled pdb file."
raise PdbCleanError(err)
# Add missing atoms using CHARMM
print log_fmt % "Adding heavy atoms using CHARMM.",
seqres = [l for l in header if l[0:6] == "SEQRES"]
coord = addMissingAtoms(coord,seqres,keep_temp,renumber_residues,pdb_id,
fix_atoms,num_steps)
log.append(log_fmt % "Missing heavy atoms were added with CHARMM.")
# Renumber residues if requested
if renumber_residues:
log.append(log_fmt % "Residues renumbered from one.")
print log[-1],
# Renumber atoms from 1
coord = pdb_atom_renumber.pdbAtomRenumber(coord)
log.append(log_fmt % "Renumbered atoms from 1")
print log[-1],
# Standardize atom-type on far right pdb column
coord = ["%s %s \n" % (c[:66],c[13]) for c in coord]
log.append(log_fmt % "Atom types were standardized.")
print log[-1],
# Final check
if pdbCheck(coord):
err = "Unknown error occured and pdb has been mangled!"
raise PdbCleanError(err)
log = ["%-79s\n" % (l.strip()) for l in log]
try:
remark_pos = [l[0:6] for l in header].index("REMARK")
except ValueError:
remark_pos = 0
# Return processed pdb file, placing log after preliminary remarks.
out_pdb = []
out_pdb.extend(header)
out_pdb.extend(log)
out_pdb.extend(coord)
return out_pdb
def pdbMutator(pdb, residue, mutation, chain=None, run_charmm=True):
"""
Standardize a pdb file: remove HETATM and ANISOU entries, renumber atoms,
take only a particular chain, remove alternate conformations.
"""
# grab header
header = [
l for l in pdb if l[0:6] not in pdb_clean.COORD_RECORDS
and l[0:6] not in pdb_clean.DEPRECATED_RECORDS
]
# Grab coordinates
coord = [l for l in pdb if l[0:6] == "ATOM "]
if pdb_clean.pdbCheck(coord):
err = "There are no ATOM entries in this pdb file!"
raise MutatorError(err)
coord, original_aa = mutateResidue(coord, residue, mutation, chain)
mutation_string = "%s%i%s" % (AA3_TO_AA1[original_aa], residue,
AA3_TO_AA1[mutation])
# Set up log
log = ["REMARK %s introduced by pdb_mutator ([email protected])\n" % \
mutation_string]
log_fmt = "REMARK - %s\n"
log.append(log_fmt % ("Process time: %s" % time.asctime()))
if chain == None:
log.append(log_fmt % ("Mutation introduced on all chains"))
else:
log.append(log_fmt % ("Mutation introduced on chain %s" % chain))
# Add missing atoms using CHARMM
if run_charmm:
print log_fmt % "Adding mutated side chain using CHARMM",
seqres = [l for l in header if l[0:6] == "SEQRES"]
coord = pdb_clean.addMissingAtoms(coord, seqres)
log.append(log_fmt % "Mutated sidechain built with CHARMM")
# Renumber atoms from 1
coord = pdb_atom_renumber.pdbAtomRenumber(coord)
log.append(log_fmt % "Renumbered atoms from 1")
print log[-1],
# Standardize atom-type on far right pdb column
coord = ["%s %s \n" % (c[:66], c[13]) for c in coord]
log.append(log_fmt % "Atom types were standardized.")
print log[-1],
# Final check
if pdb_clean.pdbCheck(coord):
err = "Unknown error occured and pdb has been mangled!"
raise MutatorError(err)
# Return processed pdb file.
out_pdb = []
out_pdb.extend(log)
out_pdb.extend(header)
out_pdb.extend(coord)
return out_pdb, mutation_string
def pdbClean(pdb,
pdb_id="temp",
chains="all",
renumber_residues=False,
keep_temp=False,
fix_atoms=True,
num_steps=500):
"""
Standardize a pdb file:
- Remove waters, ligands, and other HETATMS
- Convert modified residues (i.e. Se-Met) to the normal residue
- Remove alternate conformations (taking first in pdb file)
- Find and remove residues with missing backbone atoms
-
- Take only the specified chain
- Renumber residues from 1
"""
# Set up log
log = ["REMARK PDB processed using pdb_clean.py ([email protected])\n"]
log_fmt = "REMARK - %s\n"
log.append(log_fmt % ("Process time: %s" % time.asctime()))
# Check pdb files for Brookhaven-added error warnings (CAVEAT and OBSLTE)
error = [l for l in pdb if l[0:6] in ERROR_RECORDS]
if len(error) != 0:
err = "PDB might have problem!\n" + "".join(error)
raise PdbCleanError(err)
# Grab pdb header, excluding coordinates and deprecated records.
header = [l for l in pdb if l[0:6] not in COORD_RECORDS]
# Convert non-standard amino acids to standard ones
coord = [l for l in pdb if l[0:6] in COORD_RECORDS]
coord, header, converted = convertModifiedAA(coord, header)
if len(converted) != 0:
log.append(log_fmt % "Modified amino acids converted.")
print log[-1],
log.extend(converted)
if pdbCheck(coord):
err = "Modified amino acid converter removed all atoms! Mangled pdb!"
raise PdbCleanError(err)
# Strip all entries in COORD_RECORDS except ATOM
coord = [l for l in coord if l[0:6] == "ATOM "]
if pdbCheck(coord):
err = "There are no ATOM entries in this pdb file!"
raise PdbCleanError(err)
else:
log.append(log_fmt % "HETATM entries removed.")
print log[-1],
# Grab only the chain we want, if specified
if chains != "all":
coord = [l for l in coord if l[21] in chains]
log.append(log_fmt % ("Took only chain %r." % chains))
print log[-1],
if pdbCheck(coord):
err = "Chain filter (%r) removed all atoms in pdb file!" % chains
raise PdbCleanError(err)
# Strip alternate conformations
coord, skipped = stripACS(coord)
if len(skipped) != 0:
log.append(log_fmt % "Alternate conformations were removed.")
print log[-1],
log.extend(skipped)
if pdbCheck(coord):
err = "ACS stripper removed all atoms! Mangled pdb file."
raise PdbCleanError(err)
# Check for missing backbone atoms; these residues are deleted
coord, removed = backboneCheck(coord)
if len(removed) != 0:
log.append(log_fmt % "Residues with missing backbone atoms removed.")
print log[-1],
log.extend(removed)
if pdbCheck(coord):
err = "Backbone checker removed all atoms! Mangled pdb file."
raise PdbCleanError(err)
# Add missing atoms using CHARMM
print log_fmt % "Adding heavy atoms using CHARMM.",
seqres = [l for l in header if l[0:6] == "SEQRES"]
coord = addMissingAtoms(coord, seqres, keep_temp, renumber_residues,
pdb_id, fix_atoms, num_steps)
log.append(log_fmt % "Missing heavy atoms were added with CHARMM.")
# Renumber residues if requested
if renumber_residues:
log.append(log_fmt % "Residues renumbered from one.")
print log[-1],
# Renumber atoms from 1
coord = pdb_atom_renumber.pdbAtomRenumber(coord)
log.append(log_fmt % "Renumbered atoms from 1")
print log[-1],
# Standardize atom-type on far right pdb column
coord = ["%s %s \n" % (c[:66], c[13]) for c in coord]
log.append(log_fmt % "Atom types were standardized.")
print log[-1],
# Final check
if pdbCheck(coord):
err = "Unknown error occured and pdb has been mangled!"
raise PdbCleanError(err)
log = ["%-79s\n" % (l.strip()) for l in log]
try:
remark_pos = [l[0:6] for l in header].index("REMARK")
except ValueError:
remark_pos = 0
# Return processed pdb file, placing log after preliminary remarks.
out_pdb = []
out_pdb.extend(header)
out_pdb.extend(log)
out_pdb.extend(coord)
return out_pdb
