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 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
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 __init__(self, command, file): master = command.vf.GUI.ROOT self.autoLigandCommand = command.vf.AutoLigandCommand self.autoLigandCommand.spheres.Set(visible=1) self.autoLigandCommand.halo.Set(visible=1) pkl_file = open(file, 'rb') self.floods = [] try: data = pickle.load(pkl_file) except Exception as inst: print("Error loading ", __file__, "\n", inst) self.xcent = data[0] self.ycent = data[1] self.zcent = data[2] self.centerx = data[3] self.centery = data[4] self.centerz = data[5] self.spacing = data[6] self.centers = [] data = pickle.load(pkl_file) self.floods.append(data[1]) try: while data: data = pickle.load(pkl_file) flood = copy.copy(self.floods[-1]) for item in data[0]: flood.remove(item) for item in data[1]: flood.append(item) self.floods.append(flood) except EOFError: pass pkl_file.close() fileName = os.path.splitext(os.path.split(file)[-1])[0] self.mol = Protein(fileName) self.mol.allAtoms = AtomSet([]) chain = Chain() self.residue = Residue(type="UNK") chain.adopt(self.residue, setChildrenTop=1) self.mol.adopt(chain, setChildrenTop=1) self.mol.parser = None self.filename = file fl = self.floods[0][0] x = (fl[1] - self.xcent) * self.spacing + self.centerx y = (fl[2] - self.ycent) * self.spacing + self.centery z = (fl[3] - self.zcent) * self.spacing + self.centerz if fl[4] == 7: atomchr = 'P' # note, this will color the NA atom pink (the PDB color for Phosphorus) radius = AAradii[13][0] if fl[4] == 6: atomchr = 'S' radius = AAradii[13][0] if fl[4] == 5: atomchr = 'A' radius = AAradii[10][0] if fl[4] == 4: atomchr = 'O' radius = AAradii[1][0] if fl[4] == 3: atomchr = 'N' radius = AAradii[4][0] if fl[4] == 2: atomchr = 'C' radius = AAradii[10][0] if fl[4] == 1: atomchr = 'H' radius = AAradii[15][0] a = Atom(atomchr, self.residue, atomchr, top=self.mol) a._coords = [[x, y, z]] a._charges = {} a.hetatm = 1 a.number = 0 a.radius = radius self.mol.allAtoms = self.residue.atoms self.mol = self.autoLigandCommand.vf.addMolecule(self.mol, False) self.mol.levels = [Protein, Chain, Residue, Atom] self.autoLigandCommand.vf.displayCPK(self.mol, scaleFactor=0.4) self.autoLigandCommand.vf.colorByAtomType(self.mol, ['cpk'], log=0) self.autoLigandCommand.vf.displayLines(self.mol, negate=True, displayBO=False, lineWidth=2, log=0, only=False) self.colorKeys = list(a.colors.keys()) maxLen = len(self.floods) - 1 Player.__init__(self, master=master, endFrame=maxLen, maxFrame=maxLen, titleStr="AutoLigand Flood Player", hasSlider=True) try: # withdrew SetAnim button self.form.ifd.entryByName['setanimB']['widget'].grid_forget() self.form.autoSize() except: pass self.nextFrame(0) self.form.root.protocol('WM_DELETE_WINDOW', self.hide_cb)