def searchReplacement (smile, PDB_query, PDB_ref, name_ligand, in_cycle = 0) :
metal_find = searchMetal (smile)
if metal_find != 0 :
p_dir_dataset = pathManage.dataset(name_ligand + "/" + PDB_ref)
l_PDB_query = pathManage.findPDBQueryDataset(p_dir_dataset)
for p_query in l_PDB_query :
if search (PDB_query, p_query):
p_PDB_query = p_query
break
if "p_PDB_query" in locals() :
l_atom_parsed = parsePDB.loadCoordSectionPDB(p_query)
l_ions_PDB = parsePDB.retrieveListIon(l_atom_parsed)
if metal_find in l_ions_PDB :
l_atom_ion = parsePDB.retrieveLigand(l_atom_parsed, metal_find)
filout = open (p_dir_dataset + str(metal_find) + "_" + p_query.split("/")[-1], "w")
for atom_ion in l_atom_ion :
writePDBfile.coordinateSection(filout, atom_ion, recorder = "HETATM", header = str(metal_find), connect_matrix = 0)
filout.close ()
return "metal", metal_find
if in_cycle == 0:
if searchRing(smile) == 1 :
return "cycle",""
if searchP(smile) == 1 :
return "P", ""
elif searchB(smile) == 1 :
return "B",""
elif searchF (smile) == 1 :
return "F", ""
elif searchCl (smile) == 1 :
return "Cl", ""
elif searchBr (smile) == 1 :
return "Br", ""
elif searchBe (smile) == 1 :
return "Be", ""
elif searchNO2 (smile) == 1 :
return "NO2", ""
elif searchSulfonyl(smile) == 1:
return "SO2",""
elif searchS (smile) == 1 :
return "S", ""
elif searchCON (smile) == 1 :
return "CON",""
elif searchCarboxy (smile) == 1 :
return "COO",""
elif searchConly(smile) == 1 :
return "onlyC", ""
elif searchCandO (smile) == 1 :
return "C+O", ""
elif searchCandN (smile) == 1 :
return "C+N", ""
elif searchCandOandN (smile) == 1 :
return "C+O+N", ""
return "other" ,""
def datasetPreparation (ligand_ID, clean = 1):
p_dir_dataset = pathManage.dataset(ligand_ID)
l_folder = listdir(p_dir_dataset)
indent = 0
for ref_folder in l_folder :
# file include in dataset folder
if len (ref_folder) != 4:
continue
l_pdbfile = listdir(p_dir_dataset + ref_folder + "/")
indent = indent + 1
print ref_folder, indent
# clean repertory -> only PDB ref and PDB
l_pdbfile = listdir(p_dir_dataset + ref_folder + "/")
if clean == 1 :
for pdbfile in l_pdbfile :
p_file_pdb = p_dir_dataset + ref_folder + "/" + pdbfile
if not search (".pdb", pdbfile ) or search ("subref", pdbfile) or len (pdbfile.split("_")[0]) == 3:
remove (p_file_pdb)
l_pdbfile = listdir(p_dir_dataset + ref_folder + "/")
for pdbfile in l_pdbfile :
p_file_pdb = p_dir_dataset + ref_folder + "/" + pdbfile
# extract ligand in PDB
l_ligand = parsePDB.retrieveListLigand(p_file_pdb)
# print l_ligand
if l_ligand == []:
continue
else:
l_atom_pdb_parsed = parsePDB.loadCoordSectionPDB(p_file_pdb)
for name_ligand in l_ligand :
l_lig_parsed = parsePDB.retrieveLigand(l_atom_pdb_parsed, name_ligand)
if l_lig_parsed == [] :
continue
p_filout_ligand = p_dir_dataset + ref_folder + "/" + name_ligand + "_" + path.split(p_file_pdb)[1]
writePDBfile.coordinateSection(p_filout_ligand , l_lig_parsed[0], "HETATM", header=0 , connect_matrix = 1)
# ligand_ID write for shaep
# print p_dir_dataset + ref_folder + "/"
p_lig_ref = pathManage.findligandRef(p_dir_dataset + ref_folder + "/", ligand_ID)
if p_lig_ref == 0:
continue
# print p_lig_ref
lig_ref_parsed = parsePDB.loadCoordSectionPDB(p_lig_ref)
d_l_atom_substruct = substructTools.retrieveSubstruct(lig_ref_parsed, ligand_ID)
# case with AMP without phosphate
if d_l_atom_substruct == {}:
continue
# write ligand_ID
for subs in d_l_atom_substruct.keys ():
p_filout_substruct = p_dir_dataset + ref_folder + "/subref_" + subs + "_" + ref_folder + ".pdb"
writePDBfile.coordinateSection(p_filout_substruct , d_l_atom_substruct [subs], "HETATM", header=0 , connect_matrix = 1)
return 1
def datasetPreparation(ligand_ID, clean=1):
p_dir_dataset = pathManage.dataset(ligand_ID)
l_folder = listdir(p_dir_dataset)
indent = 0
for ref_folder in l_folder:
# file include in dataset folder
if len(ref_folder) != 4:
continue
l_pdbfile = listdir(p_dir_dataset + ref_folder + "/")
indent = indent + 1
print ref_folder, indent
# clean repertory -> only PDB ref and PDB
l_pdbfile = listdir(p_dir_dataset + ref_folder + "/")
if clean == 1:
for pdbfile in l_pdbfile:
p_file_pdb = p_dir_dataset + ref_folder + "/" + pdbfile
if not search(".pdb", pdbfile) or search(
"subref", pdbfile) or len(pdbfile.split("_")[0]) == 3:
remove(p_file_pdb)
l_pdbfile = listdir(p_dir_dataset + ref_folder + "/")
for pdbfile in l_pdbfile:
p_file_pdb = p_dir_dataset + ref_folder + "/" + pdbfile
# extract ligand in PDB
l_ligand = parsePDB.retrieveListLigand(p_file_pdb)
# print l_ligand
if l_ligand == []:
continue
else:
l_atom_pdb_parsed = parsePDB.loadCoordSectionPDB(p_file_pdb)
for name_ligand in l_ligand:
l_lig_parsed = parsePDB.retrieveLigand(
l_atom_pdb_parsed, name_ligand)
if l_lig_parsed == []:
continue
p_filout_ligand = p_dir_dataset + ref_folder + "/" + name_ligand + "_" + path.split(
p_file_pdb)[1]
writePDBfile.coordinateSection(p_filout_ligand,
l_lig_parsed[0],
"HETATM",
header=0,
connect_matrix=1)
# ligand_ID write for shaep
# print p_dir_dataset + ref_folder + "/"
p_lig_ref = pathManage.findligandRef(p_dir_dataset + ref_folder + "/",
ligand_ID)
if p_lig_ref == 0:
continue
# print p_lig_ref
lig_ref_parsed = parsePDB.loadCoordSectionPDB(p_lig_ref)
d_l_atom_substruct = substructTools.retrieveSubstruct(
lig_ref_parsed, ligand_ID)
# case with AMP without phosphate
if d_l_atom_substruct == {}:
continue
# write ligand_ID
for subs in d_l_atom_substruct.keys():
p_filout_substruct = p_dir_dataset + ref_folder + "/subref_" + subs + "_" + ref_folder + ".pdb"
writePDBfile.coordinateSection(p_filout_substruct,
d_l_atom_substruct[subs],
"HETATM",
header=0,
connect_matrix=1)
return 1
