def parsepdb(self,lines):
import PDBparser
Y=PDBparser.fast_PDBparser(lines,self.parse_terms)
Y.parse()
self.atoms=Y.atoms
self.Update()
self.attribute=Y.attribute
return
def parsepdb(self,lines):
"""
Parses a PDB file, which is contained in lines (a list of lines)
"""
import PDBparser
Y=PDBparser.PDBparser(lines,self.parse_terms)
Y.parse()
self.atoms=Y.atoms
self.Update()
self.attribute=Y.attribute
return
def readpdb(self,filename=None,data=None,parse=1,readmodels=1,use_NMRnumber=True):
"""
# Reads a pdb file and lets PDBparser.parse do the parsing
"""
import os
if data != None:
import StringIO
stream = StringIO.StringIO(data)
self.lines = stream.readlines()
elif os.path.isfile(filename):
if not silent:
print 'Reading: ',filename
fd=open(filename)
self.lines=fd.readlines()
fd.close()
else:
raise FileNotFoundError(filename)
if parse:
import PDBparser
Y=PDBparser.PDBparser(self.lines,self.parse_terms)
Y.readmodels=readmodels
if not use_NMRnumber:
Y.ignore_NMRmodel=True
#
Y.parse()
self.atoms=Y.atoms
if hasattr(Y,'spacegroup'):
self.spacegroup=Y.spacegroup # Transfer spacegroup info
else:
self.spacegroup='Unknown'
self.header=''
if hasattr(Y,'header'):
self.header=Y.header
#
# Transfer crystal symmetry info
#
self.scale=Y.scale
self.orig=Y.orig
self.cryst=Y.cryst
#
# Update
#
self.Update()
self.attribute=Y.attribute
if not silent:
print 'Read file with %3d residues and %5d atoms' %(len(self.residues.keys()),len(self.atoms.keys()))
return
def readpdb(self,filename,parse=1):
#
# Reads a pdb file and lets PDBparser.parse do the parsing
#
import os
if os.path.isfile(filename):
fd=open(filename)
self.lines=fd.readlines()
fd.close()
if parse:
import PDBparser
Y=PDBparser.fast_PDBparser(self.lines,self.parse_terms)
Y.parse()
self.atoms=Y.atoms
self.Update()
self.attribute=Y.attribute
return
else:
raise FileNotFoundError,filename
def addpdblines(self,lines):
"""Add the atoms in lines to the current set of atoms"""
import PDBparser
Y=PDBparser.PDBparser(lines,self.parse_terms)
Y.parse()
error=False
for atom in Y.atoms.keys():
if not self.atoms.has_key(atom):
self.atoms[atom]=Y.atoms[atom]
else:
print 'Name clash for',atom
error=True
if not error:
self.Update()
self.attribute=Y.attribute
return
else:
print 'Protool does not allow name clashes'
import os
os._exit(0)
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
import os
import subprocess
import numpy as np
import PDBparser as pdbp
import PDBmanip as pdbm
pdbs = {}
with open("PDBsToCheck.txt", "r") as inData:
for line in inData:
line = line.strip()
pdbs[line[0:4]] = line[5]
print(pdbs)
pdbp.download_pdbs(list(pdbs.keys()), output_path="CompPDBs/")
for key in pdbs:
pdbm.one_chain_pdb("CompPDBs/%s.pdb" % key,
key,
chainID=pdbs[key],
remove_tags=False)
with open("PDBsToCheck_NoChain.txt", "w+") as outData:
outData.write("\n".join(list(pdbs.keys())))
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)
if "ATOM" == line[0:4] and check_lines == False:
#print(line[22:26])
check_lines = True
if check_lines == False:
print(filename)
for filename in glob.glob("PDBFiles/*.pdb"):
pdb_id = filename.split("/")
pdb_id = pdb_id[-1][:-4]
print(pdb_id)
if pdb_id == "3jc8_Qd" or pdb_id == "4v6m_AZ":
continue
with open(filename, "r") as pdb_file:
pdb_lines = pdb_file.readlines()
sequence = pdbp.pdb_to_seq(pdb_lines, filename[-5])
pdb_seq = pdbp.seq_from_struct(pdb_lines, filename[-5])
#print(sequence)
if "PDB chain" in pdb_lines[0]:
print("pdb has been adjusted")
else:
print("Checking file %s, chain is %s" % (pdb_id, filename[-5]))
with open("PDBFiles/%s.pdb" % pdb_id, "w+") as pdb_file:
atom_records = pdbp.one_chain_pdb(pdb_lines, filename[-5])
if pdb_seq[0:20] == sequence[0:20]:
#print("Same seq")
atom_records = pdbp.renumber_pdb_inplace(atom_records, 1)
else:
interupt = sequence.split(pdb_seq[0:20])
#print(len(interupt[0]))
atom_records = pdbp.renumber_pdb_inplace(
