def instanceMatricesFromGroup(molecule):
returnMatrices = [numpy.eye(4, 4)]
crystal = Crystal(molecule.cellLength, molecule.cellAngles)
matrices = spaceGroups[molecule.spaceGroup]
for matrix in matrices:
tmpMatix = numpy.eye(4, 4)
tmpMatix[:3, :3] = matrix[0]
tmpMatix[:3, 3] = crystal.toCartesian(matrix[1])
returnMatrices.append(tmpMatix)
molecule.crystal = crystal
return returnMatrices
def instanceMatricesFromGroup(molecule):
returnMatrices = [numpy.eye(4,4)]
crystal = Crystal(molecule.cellLength, molecule.cellAngles)
matrices = spaceGroups[molecule.spaceGroup]
for matrix in matrices:
tmpMatix = numpy.eye(4,4)
tmpMatix[:3, :3] = matrix[0]
tmpMatix[:3, 3] = crystal.toCartesian(matrix[1])
returnMatrices.append(tmpMatix)
molecule.crystal = crystal
return returnMatrices
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):
"""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
