print("No grid file", pdb_id, site_id) continue elif os.path.isfile("%s/%s_ElectFeatures.txt"%(root_dir, pdb_id)) == False: #is there bluues electrostatics data? print("No electro file", pdb_id, site_id) continue elif os.path.isfile("%s/%s.findgeo"%(root_dir, pdb_id)) == False: #is there findgeo/CMM data? print("No geom file", pdb_id, site_id) continue else: print(pdb_id, site_id) chain = entry.chainID if relax == True: pdb_file = "%s_Relaxed.pdb"%pdb_id else: pdb_file = "%s.pdb"%pdb_id residues, res_nums, header = pdbp.create_res("%s/%s"%(root_dir, pdb_file)) #print(res_nums) this_protein = pdbp.Protein(residues, res_nums, header) center_of_mass = np.mean(this_protein.Coords, axis = 0) #print(center_of_mass) metals = set([str(entry.seqNum1), str(entry.seqNum2), str(entry.seqNum3), str(entry.seqNum4)]) metal_res = [] for x in metals: if x != "0": metal_res.append(str(round(float(x))) + chain ) metals = [entry.resName1, entry.resName2, entry.resName3, entry.resName4] site_atom_count = 0 for x in metals: if x != "0": site_atom_count += metal_size[x] #general SITE info
if relaxed == "Relaxed": pdb_id = pdb_id + "_Relaxed" if os.path.isfile( "/panfs/pfs.local/work/slusky/MSEAL/data/PDB_chains/%s/%s/%s/%s/%s.pdb" % (pdb_id[0], pdb_id[1], pdb_id[0:6], relaxed, pdb_id)) == False: #pdb_id[0], pdb_id[1], #if os.path.isfile("SampleData/%s/UnRelaxed/%s.pdb"%(pdb_id, pdb_id) ) == False: #pdb_id[0], pdb_id[1], continue else: print(pdb_id, metals) chain = pdb_id[5] metal_res = [str(x) + chain for x in metals] #residues, res_nums, header = pdbp.create_res("SampleData/%s/UnRelaxed/%s.pdb"%(pdb_id, pdb_id)) #test on local residues, res_nums, header = pdbp.create_res( "/panfs/pfs.local/work/slusky/MSEAL/data/PDB_chains/%s/%s/%s/%s/%s.pdb" % (pdb_id[0], pdb_id[1], pdb_id[0:6], relaxed, pdb_id)) #for production run on CRC #print(res_nums) this_protein = pdbp.Protein(residues, res_nums, header) SITE_center_pt = SITE_center(metal_res, this_protein) index = entry.Index site_list.loc[index, "X"] = SITE_center_pt[0] site_list.loc[index, "Y"] = SITE_center_pt[1] site_list.loc[index, "Z"] = SITE_center_pt[2] site_list.loc[index, "NearNeigh"] = nearest_neigh(SITE_center_pt, metal_res, this_protein) #print(site_list.loc[index,:]) site_list.to_csv("SITECenters_%s.txt" % relaxed, sep="\t", index=False)