def run(self):
sqlite = (
'select'
' CrystalName,'
' PANDDA_site_event_map,'
' PANDDA_site_ligand_resname,'
' PANDDA_site_ligand_chain,'
' PANDDA_site_ligand_sequence_number,'
' PANDDA_site_ligand_altLoc '
'from panddaTable '
'where PANDDA_site_event_map not like "event%"'
)
query=self.db.execute_statement(sqlite)
progress_step=1
if len(query) != 0:
progress_step=100/float(len(query))
else:
progress_step=1
progress=0
self.emit(QtCore.SIGNAL('update_progress_bar'), progress)
for item in query:
xtalID=str(item[0])
event_map=str(item[1])
resname=str(item[2])
chainID=str(item[3])
resseq=str(item[4])
altLoc=str(item[5])
if os.path.isfile(os.path.join(self.initial_model_directory,xtalID,'refine.pdb')):
os.chdir(os.path.join(self.initial_model_directory,xtalID))
self.Logfile.insert('extracting ligand (%s,%s,%s,%s) from refine.pdb' %(str(resname),str(chainID),str(resseq),str(altLoc)))
XChemUtils.pdbtools('refine.pdb').save_specific_ligands_to_pdb(resname,chainID,resseq,altLoc)
if os.path.isfile('ligand_%s_%s_%s_%s.pdb' %(str(resname),str(chainID),str(resseq),str(altLoc))):
ligand_pdb='ligand_%s_%s_%s_%s.pdb' %(str(resname),str(chainID),str(resseq),str(altLoc))
print os.path.join(self.initial_model_directory,xtalID,ligand_pdb)
else:
self.Logfile.insert('could not extract ligand; trying next...')
continue
else:
self.Logfile.insert('directory: '+os.path.join(self.initial_model_directory,xtalID)+' -> cannot find refine.pdb; trying next')
continue
if os.path.isfile(os.path.join(self.initial_model_directory,xtalID,'refine.mtz')):
resolution=XChemUtils.mtztools(os.path.join(self.initial_model_directory,xtalID,'refine.mtz')).get_high_resolution_from_mtz()
else:
self.Logfile.insert('directory: '+os.path.join(self.initial_model_directory,xtalID)+' -> cannot find refine.mtz; trying next')
continue
convert_event_map_to_SF(self.initial_model_directory,xtalID,event_map,ligand_pdb,self.xce_logfile,self.datasource,resolution).run()
progress += progress_step
self.emit(QtCore.SIGNAL('update_progress_bar'), progress)
def get_datasets_which_fit_to_reference_file(self,ref,reference_directory,cluster_dict,allowed_unitcell_difference_percent):
refStructure=XChemUtils.pdbtools(os.path.join(reference_directory,ref+'.pdb'))
symmRef=refStructure.get_spg_number_from_pdb()
ucVolRef=refStructure.calc_unitcell_volume_from_pdb()
cluster_dict[ref]=[]
cluster_dict[ref].append(os.path.join(reference_directory,ref+'.pdb'))
for dataset in glob.glob(os.path.join(self.data_directory,self.pdb_style)):
datasetStructure=XChemUtils.pdbtools(dataset)
symmDataset=datasetStructure.get_spg_number_from_pdb()
ucVolDataset=datasetStructure.calc_unitcell_volume_from_pdb()
if symmDataset == symmRef:
try:
difference=math.fabs(1-(float(ucVolRef)/float(ucVolDataset)))*100
if difference < allowed_unitcell_difference_percent:
sampleID=dataset.replace('/'+self.pdb_style,'')[dataset.replace('/'+self.pdb_style,'').rfind('/')+1:]
cluster_dict[ref].append(sampleID)
except ZeroDivisionError:
continue
return cluster_dict
def compare_number_of_atoms_in_reference_vs_all_datasets(self,refData,dataset_list):
mismatched_datasets=[]
pdbtools=XChemUtils.pdbtools(refData)
refPDB=refData[refData.rfind('/')+1:]
refPDBlist=pdbtools.get_init_pdb_as_list()
n_atom_ref=len(refPDBlist)
for n_datasets,dataset in enumerate(dataset_list):
if os.path.isfile(os.path.join(self.data_directory.replace('*',''),dataset,self.pdb_style)):
n_atom=len(pdbtools.get_pdb_as_list(os.path.join(self.data_directory.replace('*',''),dataset,self.pdb_style)))
if n_atom_ref == n_atom:
self.Logfile.insert('%s: atoms in PDB file (%s): %s; atoms in Reference file: %s ===> OK' %(dataset,self.pdb_style,str(n_atom),str(n_atom_ref)))
if n_atom_ref != n_atom:
self.Logfile.insert('%s: atoms in PDB file (%s): %s; atoms in Reference file: %s ===> ERROR' %(dataset,self.pdb_style,str(n_atom),str(n_atom_ref)))
mismatched_datasets.append(dataset)
return n_datasets,mismatched_datasets
