def copy(self, newname=None):
"""copy makes a new Protein instance with 'newname' and
other protein level parameters from self. Next,self.allAtoms is copied
atom by atom. First: '_fit_atom_into_tree', which uses the same
logic as pdbParser, builds up new instances of residues and chains
as necessary. Then: _copy_atom_attr copies the remaining
String, Int, Float, None, List and Tuple attributes into new atom
instances. The new molecule is returned by copy.
NB: subsequently the two copies can be visualized:
copy2=mv.Mols[0].copy()
mv.addMolecule(copy2)
mv.GUI.VIEWER.TransformRootOnly( yesno=0)
mv.GUI.VIEWER.currentObject=copy2.geomContainer.geoms['master']
then mouse movements would move only copy2, the new object """
if not newname: newname = self.name + "_copy"
newmol=Protein(name=newname, parent=self.parent,
elementType=self.elementType, childrenName=self.childrenName,
setClass=self.setClass, childrenSetClass=self.childrenSetClass,
top=self.top)
newmol.curChain=Chain()
newmol.curRes=Residue()
newmol.allAtoms= AtomSet()
newmol.parser = self.parser
for at in self.allAtoms:
self._fit_atom_into_tree(newmol, at)
newmol.buildBondsByDistance()
return newmol
def buildPdb(map_dict,
npts,
name='DlgBuilt',
ctr=0,
outputfile='results.pdb',
scale=1.0):
if debug: print "in buildPdb: tolerance=", tolerance
name = 'DlgBuilt'
mol = Protein(name=name)
mol.curChain = Chain()
mol.chains = ChainSet([mol.curChain])
mol.curRes = Residue()
mol.curChain.adopt(mol.curRes)
mol.allAtoms = AtomSet()
mol.curRes.atoms = mol.allAtoms
nzpts = nypts = nxpts = npts
#nxpts, nypts, nzpts = npts
ctr = 0
for ADtype, m in map_dict.items():
if debug:
print "PROCESSING ", ADtype, " array:", max(m.ravel()), ':', min(
m.ravel())
vals = []
tctr = 0 #for number of each type
for z in range(nzpts):
for y in range(nypts):
for x in range(nxpts):
val = scale * abs(m[x, y, z])
vals.append(val)
#if abs(val)>.005:
if val > tolerance * scale:
ctr += 1
name = ADtype + str(ctr)
#version3:
#info_lo = (xcen - numxcells*spacing,
# ycen - numycells*spacing,
# zcen - numzcells *spacing)
#using lower back pt of cube, i think
#xcoord = (x-info_lo[0])/spacing
#ycoord = (y-info_lo[1])/spacing
#zcoord = (z-info_lo[2])/spacing
#version2:
xcoord = (x - numxcells) * spacing + xcen
ycoord = (y - numycells) * spacing + ycen
zcoord = (z - numzcells) * spacing + zcen
coords = (xcoord, ycoord, zcoord)
tctr += 1
# #print "addAtom: name=",name,"ADtype=", ADtype," val=", val, "coords=", coords,"ctr=", ctr
addAtom(mol, name, ADtype, val, coords, ctr)
print "added ", tctr, '<-', ADtype, " atoms"
if debug:
print ADtype, ':', tctr, ' ', ctr
print "total atoms=", ctr
writer = PdbWriter()
writer.write(outputfile, mol.allAtoms, records=['ATOM'])
def buildPdb(map_dict, npts, name='DlgBuilt', ctr=0, outputfile='results.pdb',
scale=1.0):
if debug: print "in buildPdb: tolerance=", tolerance
name = 'DlgBuilt'
mol = Protein(name=name)
mol.curChain = Chain()
mol.chains = ChainSet([mol.curChain])
mol.curRes = Residue()
mol.curChain.adopt(mol.curRes)
mol.allAtoms = AtomSet()
mol.curRes.atoms = mol.allAtoms
nzpts=nypts=nxpts = npts
#nxpts, nypts, nzpts = npts
ctr = 0
for ADtype, m in map_dict.items():
if debug:
print "PROCESSING ", ADtype, " array:", max(m.ravel()), ':', min(m.ravel())
vals = []
tctr = 0 #for number of each type
for z in range(nzpts):
for y in range(nypts):
for x in range(nxpts):
val = scale * abs(m[x,y,z])
vals.append(val)
#if abs(val)>.005:
if val>tolerance*scale:
ctr += 1
name = ADtype + str(ctr)
#version3:
#info_lo = (xcen - numxcells*spacing,
# ycen - numycells*spacing,
# zcen - numzcells *spacing)
#using lower back pt of cube, i think
#xcoord = (x-info_lo[0])/spacing
#ycoord = (y-info_lo[1])/spacing
#zcoord = (z-info_lo[2])/spacing
#version2:
xcoord = (x-numxcells)*spacing + xcen
ycoord = (y-numycells)*spacing + ycen
zcoord = (z-numzcells)*spacing + zcen
coords = (xcoord,ycoord,zcoord)
tctr += 1
# #print "addAtom: name=",name,"ADtype=", ADtype," val=", val, "coords=", coords,"ctr=", ctr
addAtom(mol, name, ADtype, val, coords, ctr)
print "added ",tctr, '<-', ADtype, " atoms"
if debug:
print ADtype, ':', tctr , ' ', ctr
print "total atoms=", ctr
writer = PdbWriter()
writer.write(outputfile, mol.allAtoms, records=['ATOM'])
def makeMoleculeFromAtoms(molname, atomSet):
"""
create a new molecule from a list of atoms
mol <- makeMoleculeFromAtoms(molname, atomSet)
"""
from MolKit.molecule import Atom, AtomSet
from MolKit.protein import Protein, Chain, Residue
# create the top object
mol = Protein(name=molname)
# find out all residues
residues = atomSet.parent.uniq()
# find out all chains
chains = residues.parent.uniq()
# create all chains
chainsd = {}
for c in chains:
newchain = Chain(c.id, mol, top=mol)
chainsd[c] = newchain
# create all residues
resd = {}
for res in residues:
newres = Residue(res.name[:3], res.name[3:], res.icode,
chainsd[res.parent], top=mol)
resd[res] = newres
newres.hasCA = 0
newres.hasO = 0
# create all the atoms
newats = []
for num, at in enumerate(atomSet):
name = at.name
res = resd[at.parent]
if name == 'CA':
res.hasCA = 1
if name == 'O' or name == 'OXT' or (len(name)>3 and name[:3]=='OCT'):
res.hasO = 2
newat = Atom(name, res, at.element, top=mol)
newats.append(newat)
# set constructotr attributes
newat._coords = []
for coords in at._coords:
newat._coords.append(coords[:])
newat.conformation = at.conformation
newat.chemElem = at.chemElem
newat.atomicNumber = at.atomicNumber
newat.bondOrderRadius = at.bondOrderRadius
newat.covalentRadius = at.covalentRadius
newat.vdwRadius = at.vdwRadius
newat.maxBonds = at.maxBonds
newat.organic = at.organic
newat.colors = at.colors.copy()
newat.opacities = at.opacities.copy()
newat._charges = at._charges.copy()
newat.chargeSet = at.chargeSet
# set attributes from PDB parser
newat.segID = at.segID
newat.hetatm = at.hetatm
newat.normalname = at.normalname
newat.number = num #at.number
newat.occupancy = at.occupancy
newat.temperatureFactor = at.temperatureFactor
newat.altname = at.altname
# attribute created by PQR parser
if hasattr(at, 'pqrRadius'):
newat.pqrRadius = at.pqrRadius
# attribute created by F2D parser
if hasattr(at, 'hbstatus'):
newat.hbstatus = at.hbstatus
# attribute created by PDBQ parser
if hasattr(at, 'autodock_element'):
newat.autodock_element = at.autodock_element
# attribute created by PDBQT parser
#if hasattr(at, ''):
# newat. = at.
# attribute created by PDBQS parser
if hasattr(at, 'AtVol'):
newat.AtVol = at.AtVol
newat.AtSolPar = at.AtSolPar
mol.allAtoms = AtomSet(newats)
return mol
def parse( self, objClass=Protein ):
if self.allLines is None and self.filename:
self.readFile()
if self.allLines is None or len(self.allLines)==0:
return
mol = Protein()
self.mol = mol
molList = mol.setClass()
molList.append( mol )
current_residue_number = None
current_chain = None
current_residue = None
number_of_atoms = int(self.allLines[1][:5])
self.configureProgressBar( init=1, mode='increment',
authtext='parse atoms', max=number_of_atoms )
current_chain = Chain( id='GRO',)
#FIX this: The existence of allAtoms attribute (and the fact that it is an empty set rather than all atoms in the chain) causes getNodesByMolecule() to return wrong values
if hasattr(current_chain, "allAtoms"):
del(current_chain.allAtoms)
#current_chain = Chain( id='GRO',parent = mol)
mol.adopt( current_chain, setChildrenTop=1 )
for index in range( 2,number_of_atoms+2 ):
residue_number = int(self.allLines[index][:5])
if residue_number!=current_residue_number:#
#current_chain should adopt the current residue if there is one
#create new residue
res_type = self.allLines[index][5:10]
residue_type = res_type.split(' ')[0]
current_residue = Residue( type=residue_type, number=residue_number )
current_residue_number = residue_number
if current_residue is not None: #REMEMBER TO ADOPT THE LAST ONE!!!
current_chain.adopt( current_residue, setChildrenTop=1 )
n = self.allLines[index][10:15]
name = n.split(' ')[-1]
element = name
if element in babel_elements.keys():
element = element
else:
if residue_type == "System" or residue_type == "SOL":
#if element[1] == 'W':
# element = 'H'
# group is treated as one particle
#else:
element = element[0]
elif element[:2] == 'Me':
element = 'C'
else:
element = element[0]
#if len(element)>1:
# if type(element[1]) == types.StringType:
#
# if element[1] == element[1].lower():
# element =element
# else:
# element = element[0]
#
# else:
# element = element[0]
atom = Atom( name, current_residue, element, top=mol )
c = self.allLines[index][15:20]
cx = self.allLines[index][20:28]
cy = self.allLines[index][28:36]
cz = self.allLines[index][36:44]
x = float(cx)*10
y = float(cy)*10
z = float(cz)*10
atom._coords = [[x, y, z]]
atom._charges = []
atom.segID = mol.name
atom.normalname = name
atom.number = int(self.allLines[index][15:20])
atom.elementType = name[0]
mol.atmNum[atom.number] = atom
atom.altname = None
atom.hetatm = 0
mol.name = os.path.split(os.path.splitext(self.filename)[0])[-1]
mol.allAtoms = mol.chains.residues.atoms
mol.parser = self
mol.levels = [Protein, Chain, Residue, Atom]
name = ''
for n in molList.name:
name = n + ','
name = name[:-1]
molList.setStringRepr( name )
strRpr = name + ':::'
molList.allAtoms.setStringRepr( strRpr )
for m in molList:
mname = m.name
strRpr = mname + ':::'
m.allAtoms.setStringRepr( strRpr )
strRpr = mname + ':'
m.chains.setStringRepr( strRpr )
for c in m.chains:
cname = c.id
strRpr = mname + ':' + cname + ':'
c.residues.setStringRepr( strRpr )
for r in c.residues:
rname = r.name
strRpr = mname + ':' + cname + ':' + rname + ':'
r.atoms.setStringRepr( strRpr )
return molList
def parse(self, objClass=Protein):
"""Parses mmCIF dictionary (self.mmCIF_dict) into MolKit object"""
if self.allLines is None and self.filename:
self.readFile()
if self.allLines is None or len(self.allLines)==0:
return
self.mmCIF2Dict()
type_symbol = None
B_iso_or_equiv = None
mmCIF_dict = self.mmCIF_dict
fileName, fileExtension = os.path.splitext(self.filename)
molName = os.path.basename(fileName)
if mmCIF_dict.has_key('_entry.id'):
molName = mmCIF_dict['_entry.id']
if mmCIF_dict.has_key('_atom_site.id'):
#The description of the data names can be found in the following link
#http://mmcif.pdb.org/dictionaries/mmcif_pdbx.dic/Items
ids = mmCIF_dict['_atom_site.id'] #1 number
group_PDB = mmCIF_dict['_atom_site.group_PDB'] #2 atom/hetatm
atom_id = mmCIF_dict['_atom_site.label_atom_id'] #3 name
comp_id = mmCIF_dict['_atom_site.label_comp_id'] #4 residue type
label_asym_id = mmCIF_dict['_atom_site.label_asym_id'] #5 chain
#Note: chain ID from mmCIF file might be different from PDB file
seq_id = mmCIF_dict['_atom_site.label_seq_id'] #6 residue number
x_coords = mmCIF_dict['_atom_site.Cartn_x'] #7 xcoord
y_coords = mmCIF_dict['_atom_site.Cartn_y'] #8 ycoord
z_coords = mmCIF_dict['_atom_site.Cartn_z'] #9 zcoord
occupancy = mmCIF_dict['_atom_site.occupancy'] #10
B_iso_or_equiv = mmCIF_dict['_atom_site.B_iso_or_equiv']#11
type_symbol = mmCIF_dict['_atom_site.type_symbol']
elif mmCIF_dict.has_key('_atom_site_label'):
#ftp://ftp.iucr.org/pub/cif_core.dic
atom_id = mmCIF_dict['_atom_site_label']
len_atoms = len(atom_id)
ids = range(len_atoms)
group_PDB = len_atoms*['HETATM']
comp_id = len_atoms*["CIF"]
label_asym_id = len_atoms*['1']
seq_id = len_atoms*[1]
from mglutil.math.crystal import Crystal
a = mmCIF_dict['_cell.length_a'] = float(mmCIF_dict['_cell_length_a'].split('(')[0])
b = mmCIF_dict['_cell.length_b'] = float(mmCIF_dict['_cell_length_b'].split('(')[0])
c = mmCIF_dict['_cell.length_c'] = float(mmCIF_dict['_cell_length_c'].split('(')[0])
alpha = mmCIF_dict['_cell.angle_alpha'] = float(mmCIF_dict['_cell_angle_alpha'].split('(')[0])
beta = mmCIF_dict['_cell.angle_beta'] = float(mmCIF_dict['_cell_angle_beta'].split('(')[0])
gamma = mmCIF_dict['_cell.angle_gamma'] = float(mmCIF_dict['_cell_angle_gamma'].split('(')[0])
cryst = Crystal((a, b, c), (alpha, beta, gamma))
x = []
for item in mmCIF_dict['_atom_site_fract_x']:
x.append(float(item.split('(')[0]))
y = []
for item in mmCIF_dict['_atom_site_fract_y']:
y.append(float(item.split('(')[0]))
z = []
for item in mmCIF_dict['_atom_site_fract_z']:
z.append(float(item.split('(')[0]))
x_coords = []
y_coords = []
z_coords = []
B_iso_or_equiv = []
for i in ids:
trans = cryst.toCartesian([x[i], y[i], z[i]])
x_coords.append(trans[0])
y_coords.append(trans[1])
z_coords.append(trans[2])
if mmCIF_dict.has_key('_atom_site_U_iso_or_equiv'):
B_iso_or_equiv.append(mmCIF_dict['_atom_site_U_iso_or_equiv'][i].split('(')[0])
if mmCIF_dict.has_key('_atom_site_type_symbol'):
type_symbol = mmCIF_dict['_atom_site_type_symbol']
if mmCIF_dict.has_key('_atom_site_occupancy'):
occupancy = mmCIF_dict['_atom_site_occupancy']
if mmCIF_dict.has_key('_chemical_name_common'):
molName = mmCIF_dict['_chemical_name_common']
elif mmCIF_dict.has_key('_chemical_name_mineral'):
molName = mmCIF_dict['_chemical_name_mineral']
if mmCIF_dict.has_key('_symmetry_space_group_name_H-M'):
mmCIF_dict['_symmetry.space_group_name_H-M'] = mmCIF_dict['_symmetry_space_group_name_H-M']
else:
print 'No _atom_site.id or _atom_site_label record is available in %s' % self.filename
return None
mol = Protein()
self.mol = mol
self.mol.allAtoms = AtomSet([])
molList = mol.setClass()
molList.append( mol )
current_chain_id = None
current_residue_number = None
current_chain = None
current_residue = None
number_of_atoms = len(ids)
self.configureProgressBar(init=1, mode='increment',
authtext='parse atoms', max=number_of_atoms)
for index in range(number_of_atoms):
#make a new atom for the current index
chain_id = label_asym_id[index]
if chain_id != current_chain_id: #make a new chain
#molecule should adopt the current chain if there is one
current_chain = Chain(id=chain_id)
# FIXME: current_chain should not have allAtoms attribute
delattr(current_chain, "allAtoms")
current_chain_id = chain_id
if current_chain is not None: #REMEMBER TO ADOPT THE LAST ONE!!!
mol.adopt(current_chain, setChildrenTop=1)
residue_number = seq_id[index]
if residue_number != current_residue_number or chain_id != label_asym_id[index-1]: #make a new chain:
#current_chain should adopt the current residue if there is one
#create new residue
residue_type = comp_id[index]
current_residue = Residue(type=residue_type, number=residue_number)
current_residue_number = residue_number
if current_residue is not None: #REMEMBER TO ADOPT THE LAST ONE!!!
current_chain.adopt(current_residue, setChildrenTop=1)
name = atom_id[index]
if type_symbol:
element = type_symbol[index]
else:
element = None
atom = Atom( name, current_residue, element, top=mol )
atom._coords = [[float(x_coords[index]), float(y_coords[index]), float(z_coords[index])]]
atom._charges = {}
atom.segID = mol.name
atom.normalname = name
atom.number = int(ids[index])
mol.atmNum[atom.number] = atom
atom.occupancy = float(occupancy[index])
if B_iso_or_equiv:
atom.temperatureFactor = float(B_iso_or_equiv[index])
atom.altname = None
atom.hetatm = 0
if group_PDB[index]=='HETATM':
atom.hetatm = 1
self.updateProgressBar()
self.parse_MMCIF_CELL()
try:
self.parse_MMCIF_HYDBND()
except:
print >>sys.stderr,"Parsing Hydrogen Bond Record Failed in",self.filename
mol.name = molName
mol.allAtoms = mol.chains.residues.atoms
mol.parser = self
mol.levels = [Protein, Chain, Residue, Atom]
name = ''
for n in molList.name:
name = n + ','
name = name[:-1]
molList.setStringRepr(name)
strRpr = name + ':::'
molList.allAtoms.setStringRepr(strRpr)
for m in molList:
mname = m.name
strRpr = mname + ':::'
m.allAtoms.setStringRepr(strRpr)
strRpr = mname + ':'
m.chains.setStringRepr(strRpr)
for c in m.chains:
cname = c.id
strRpr = mname + ':' + cname + ':'
c.residues.setStringRepr(strRpr)
for r in c.residues:
rname = r.name
strRpr = mname + ':' + cname + ':' + rname + ':'
r.atoms.setStringRepr(strRpr)
self.buildBonds()
return molList
def makeMoleculeFromAtoms(molname, atomSet):
"""
create a new molecule from a list of atoms
mol <- makeMoleculeFromAtoms(molname, atomSet)
"""
from MolKit.molecule import Atom, AtomSet
from MolKit.protein import Protein, Chain, Residue
# create the top object
mol = Protein(name=molname)
# find out all residues
residues = atomSet.parent.uniq()
# find out all chains
chains = residues.parent.uniq()
# create all chains
chainsd = {}
for c in chains:
newchain = Chain(c.id, mol, top=mol)
chainsd[c] = newchain
# create all residues
resd = {}
for res in residues:
newres = Residue(res.name[:3],
res.name[3:],
res.icode,
chainsd[res.parent],
top=mol)
resd[res] = newres
newres.hasCA = 0
newres.hasO = 0
# create all the atoms
newats = []
for num, at in enumerate(atomSet):
name = at.name
res = resd[at.parent]
name1 = name
if hasattr(at, "altname") and at.altname != None:
name = at.name.split("@")[0]
if name == 'CA':
res.hasCA = 1
if name == 'O' or name == 'OXT' or (len(name) > 3
and name[:3] == 'OCT'):
res.hasO = 2
newat = Atom(name, res, at.element, top=mol)
if name != name1:
newat.name = name1
newat.altname = at.altname
newats.append(newat)
# set constructotr attributes
newat._coords = []
for coords in at._coords:
newat._coords.append(coords[:])
newat.conformation = at.conformation
newat.chemElem = at.chemElem
newat.atomicNumber = at.atomicNumber
newat.bondOrderRadius = at.bondOrderRadius
newat.covalentRadius = at.covalentRadius
newat.vdwRadius = at.vdwRadius
newat.maxBonds = at.maxBonds
newat.organic = at.organic
newat.colors = at.colors.copy()
newat.opacities = at.opacities.copy()
newat._charges = at._charges.copy()
newat.chargeSet = at.chargeSet
# set attributes from PDB parser
try: # pdbqs do not have this
newat.segID = at.segID
except AttributeError:
pass
newat.hetatm = at.hetatm
try: # pdbqs do not have this
newat.normalname = at.normalname
except AttributeError:
pass
newat.number = num #at.number
newat.occupancy = at.occupancy
newat.temperatureFactor = at.temperatureFactor
newat.altname = at.altname
# attribute created by PQR parser
if hasattr(at, 'pqrRadius'):
newat.pqrRadius = at.pqrRadius
# attribute created by F2D parser
if hasattr(at, 'hbstatus'):
newat.hbstatus = at.hbstatus
# attribute created by PDBQ parser
if hasattr(at, 'autodock_element'):
newat.autodock_element = at.autodock_element
# attribute created by PDBQT parser
#if hasattr(at, ''):
# newat. = at.
# attribute created by PDBQS parser
if hasattr(at, 'AtVol'):
newat.AtVol = at.AtVol
newat.AtSolPar = at.AtSolPar
mol.allAtoms = AtomSet(newats)
return mol
def parse(self, objClass=Protein):
"""Parses mmCIF dictionary (self.mmCIF_dict) into MolKit object"""
if self.allLines is None and self.filename:
self.readFile()
if self.allLines is None or len(self.allLines) == 0:
return
self.mmCIF2Dict()
type_symbol = None
B_iso_or_equiv = None
mmCIF_dict = self.mmCIF_dict
fileName, fileExtension = os.path.splitext(self.filename)
molName = os.path.basename(fileName)
if mmCIF_dict.has_key('_entry.id'):
molName = mmCIF_dict['_entry.id']
if mmCIF_dict.has_key('_atom_site.id'):
#The description of the data names can be found in the following link
#http://mmcif.pdb.org/dictionaries/mmcif_pdbx.dic/Items
ids = mmCIF_dict['_atom_site.id'] #1 number
group_PDB = mmCIF_dict['_atom_site.group_PDB'] #2 atom/hetatm
atom_id = mmCIF_dict['_atom_site.label_atom_id'] #3 name
comp_id = mmCIF_dict['_atom_site.label_comp_id'] #4 residue type
label_asym_id = mmCIF_dict['_atom_site.label_asym_id'] #5 chain
#Note: chain ID from mmCIF file might be different from PDB file
seq_id = mmCIF_dict['_atom_site.label_seq_id'] #6 residue number
x_coords = mmCIF_dict['_atom_site.Cartn_x'] #7 xcoord
y_coords = mmCIF_dict['_atom_site.Cartn_y'] #8 ycoord
z_coords = mmCIF_dict['_atom_site.Cartn_z'] #9 zcoord
occupancy = mmCIF_dict['_atom_site.occupancy'] #10
B_iso_or_equiv = mmCIF_dict['_atom_site.B_iso_or_equiv'] #11
type_symbol = mmCIF_dict['_atom_site.type_symbol']
elif mmCIF_dict.has_key('_atom_site_label'):
#ftp://ftp.iucr.org/pub/cif_core.dic
atom_id = mmCIF_dict['_atom_site_label']
len_atoms = len(atom_id)
ids = range(len_atoms)
group_PDB = len_atoms * ['HETATM']
comp_id = len_atoms * ["CIF"]
label_asym_id = len_atoms * ['1']
seq_id = len_atoms * [1]
from mglutil.math.crystal import Crystal
a = mmCIF_dict['_cell.length_a'] = float(
mmCIF_dict['_cell_length_a'].split('(')[0])
b = mmCIF_dict['_cell.length_b'] = float(
mmCIF_dict['_cell_length_b'].split('(')[0])
c = mmCIF_dict['_cell.length_c'] = float(
mmCIF_dict['_cell_length_c'].split('(')[0])
alpha = mmCIF_dict['_cell.angle_alpha'] = float(
mmCIF_dict['_cell_angle_alpha'].split('(')[0])
beta = mmCIF_dict['_cell.angle_beta'] = float(
mmCIF_dict['_cell_angle_beta'].split('(')[0])
gamma = mmCIF_dict['_cell.angle_gamma'] = float(
mmCIF_dict['_cell_angle_gamma'].split('(')[0])
cryst = Crystal((a, b, c), (alpha, beta, gamma))
x = []
for item in mmCIF_dict['_atom_site_fract_x']:
x.append(float(item.split('(')[0]))
y = []
for item in mmCIF_dict['_atom_site_fract_y']:
y.append(float(item.split('(')[0]))
z = []
for item in mmCIF_dict['_atom_site_fract_z']:
z.append(float(item.split('(')[0]))
x_coords = []
y_coords = []
z_coords = []
B_iso_or_equiv = []
for i in ids:
trans = cryst.toCartesian([x[i], y[i], z[i]])
x_coords.append(trans[0])
y_coords.append(trans[1])
z_coords.append(trans[2])
if mmCIF_dict.has_key('_atom_site_U_iso_or_equiv'):
B_iso_or_equiv.append(
mmCIF_dict['_atom_site_U_iso_or_equiv'][i].split(
'(')[0])
if mmCIF_dict.has_key('_atom_site_type_symbol'):
type_symbol = mmCIF_dict['_atom_site_type_symbol']
if mmCIF_dict.has_key('_atom_site_occupancy'):
occupancy = mmCIF_dict['_atom_site_occupancy']
if mmCIF_dict.has_key('_chemical_name_common'):
molName = mmCIF_dict['_chemical_name_common']
elif mmCIF_dict.has_key('_chemical_name_mineral'):
molName = mmCIF_dict['_chemical_name_mineral']
if mmCIF_dict.has_key('_symmetry_space_group_name_H-M'):
mmCIF_dict['_symmetry.space_group_name_H-M'] = mmCIF_dict[
'_symmetry_space_group_name_H-M']
else:
print 'No _atom_site.id or _atom_site_label record is available in %s' % self.filename
return None
mol = Protein()
self.mol = mol
self.mol.allAtoms = AtomSet([])
molList = mol.setClass()
molList.append(mol)
current_chain_id = None
current_residue_number = None
current_chain = None
current_residue = None
number_of_atoms = len(ids)
self.configureProgressBar(init=1,
mode='increment',
authtext='parse atoms',
max=number_of_atoms)
for index in range(number_of_atoms):
#make a new atom for the current index
chain_id = label_asym_id[index]
if chain_id != current_chain_id: #make a new chain
#molecule should adopt the current chain if there is one
current_chain = Chain(id=chain_id)
# FIXME: current_chain should not have allAtoms attribute
delattr(current_chain, "allAtoms")
current_chain_id = chain_id
if current_chain is not None: #REMEMBER TO ADOPT THE LAST ONE!!!
mol.adopt(current_chain, setChildrenTop=1)
residue_number = seq_id[index]
if residue_number != current_residue_number or chain_id != label_asym_id[
index - 1]: #make a new chain:
#current_chain should adopt the current residue if there is one
#create new residue
residue_type = comp_id[index]
current_residue = Residue(type=residue_type,
number=residue_number)
current_residue_number = residue_number
if current_residue is not None: #REMEMBER TO ADOPT THE LAST ONE!!!
current_chain.adopt(current_residue, setChildrenTop=1)
name = atom_id[index]
if type_symbol:
element = type_symbol[index]
else:
element = None
atom = Atom(name, current_residue, element, top=mol)
atom._coords = [[
float(x_coords[index]),
float(y_coords[index]),
float(z_coords[index])
]]
atom._charges = {}
atom.segID = mol.name
atom.normalname = name
atom.number = int(ids[index])
mol.atmNum[atom.number] = atom
atom.occupancy = float(occupancy[index])
if B_iso_or_equiv:
atom.temperatureFactor = float(B_iso_or_equiv[index])
atom.altname = None
atom.hetatm = 0
if group_PDB[index] == 'HETATM':
atom.hetatm = 1
self.updateProgressBar()
self.parse_MMCIF_CELL()
try:
self.parse_MMCIF_HYDBND()
except:
print >> sys.stderr, "Parsing Hydrogen Bond Record Failed in", self.filename
mol.name = molName
mol.allAtoms = mol.chains.residues.atoms
mol.parser = self
mol.levels = [Protein, Chain, Residue, Atom]
name = ''
for n in molList.name:
name = n + ','
name = name[:-1]
molList.setStringRepr(name)
strRpr = name + ':::'
molList.allAtoms.setStringRepr(strRpr)
for m in molList:
mname = m.name
strRpr = mname + ':::'
m.allAtoms.setStringRepr(strRpr)
strRpr = mname + ':'
m.chains.setStringRepr(strRpr)
for c in m.chains:
cname = c.id
strRpr = mname + ':' + cname + ':'
c.residues.setStringRepr(strRpr)
for r in c.residues:
rname = r.name
strRpr = mname + ':' + cname + ':' + rname + ':'
r.atoms.setStringRepr(strRpr)
self.buildBonds()
return molList
def parse(self, objClass=Protein):
if self.allLines is None and self.filename:
self.readFile()
if self.allLines is None or len(self.allLines) == 0:
return
mol = Protein()
self.mol = mol
molList = mol.setClass()
molList.append(mol)
current_residue_number = None
current_chain = None
current_residue = None
number_of_atoms = int(self.allLines[1][:5])
self.configureProgressBar(init=1,
mode='increment',
authtext='parse atoms',
max=number_of_atoms)
current_chain = Chain(id='GRO', )
# FIX this: The existence of allAtoms attribute (and the fact that it is an empty set rather than all atoms in
# the chain) causes getNodesByMolecule() to return wrong values
if hasattr(current_chain, "allAtoms"):
del current_chain.allAtoms
# current_chain = Chain( id='GRO',parent = mol)
mol.adopt(current_chain, setChildrenTop=1)
for index in range(2, number_of_atoms + 2):
residue_number = int(self.allLines[index][:5])
if residue_number != current_residue_number: #
# current_chain should adopt the current residue if there is one
# create new residue
res_type = self.allLines[index][5:10]
residue_type = res_type.split(' ')[0]
current_residue = Residue(type=residue_type,
number=residue_number)
current_residue_number = residue_number
if current_residue is not None: # REMEMBER TO ADOPT THE LAST ONE!!!
current_chain.adopt(current_residue, setChildrenTop=1)
n = self.allLines[index][10:15]
name = n.split(' ')[-1]
element = name
if element in list(babel_elements.keys()):
element = element
else:
if residue_type == "System" or residue_type == "SOL":
# if element[1] == 'W':
# element = 'H'
# group is treated as one particle
# else:
element = element[0]
elif element[:2] == 'Me':
element = 'C'
else:
element = element[0]
# if len(element)>1:
# if type(element[1]) == types.StringType:
#
# if element[1] == element[1].lower():
# element =element
# else:
# element = element[0]
#
# else:
# element = element[0]
atom = Atom(name, current_residue, element, top=mol)
c = self.allLines[index][15:20]
cx = self.allLines[index][20:28]
cy = self.allLines[index][28:36]
cz = self.allLines[index][36:44]
x = float(cx) * 10
y = float(cy) * 10
z = float(cz) * 10
atom._coords = [[x, y, z]]
atom._charges = []
atom.segID = mol.name
atom.normalname = name
atom.number = int(self.allLines[index][15:20])
atom.elementType = name[0]
mol.atmNum[atom.number] = atom
atom.altname = None
atom.hetatm = 0
mol.name = os.path.split(os.path.splitext(self.filename)[0])[-1]
mol.allAtoms = mol.chains.residues.atoms
mol.parser = self
mol.levels = [Protein, Chain, Residue, Atom]
name = ''
for n in molList.name:
name = n + ','
name = name[:-1]
molList.setStringRepr(name)
strRpr = name + ':::'
molList.allAtoms.setStringRepr(strRpr)
for m in molList:
mname = m.name
strRpr = mname + ':::'
m.allAtoms.setStringRepr(strRpr)
strRpr = mname + ':'
m.chains.setStringRepr(strRpr)
for c in m.chains:
cname = c.id
strRpr = mname + ':' + cname + ':'
c.residues.setStringRepr(strRpr)
for r in c.residues:
rname = r.name
strRpr = mname + ':' + cname + ':' + rname + ':'
r.atoms.setStringRepr(strRpr)
return molList
