def main():
if len(sys.argv) != 5: # if no input
print "ERORR: not the right number of arguments"
print "syntax: ~/zzz.scripts/be_blasti.py ( --pdbcode pdbcodename | --pdbfile pdbfilename ) ( carbohydrate| nocarbohydrate ) ( renumber | original_numbers )"
return
## input pdb
#pdbcode = '3T4G'
flag = sys.argv[1]
if flag == '--pdbcode':
## if a pdbcode is spesified then we will download it from the pdb.
pdbcode = sys.argv[2]
#file = '/raid9/tbalius/Projects/ProteomicDOCKing/plversion1/'+pdbcode+'/'+pdbcode+'/'+pdbcode+'.pdb.ori'
#file = '/raid9/tbalius/Projects/ProteomicDOCKing/plversion1/'+pdbcode+'/'+pdbcode+'/'+pdbcode+'.pdb'
#url = 'ftp://ftp.wwpdb.org/pub/pdb/data/biounit/coordinates/all/' + pdbcode + '.pdb1.gz'
url = 'http://www.rcsb.org/pdb/files/' + pdbcode + '.pdb'
#url = 'http://www.rcsb.org/pdb/files/'+pdbcode+'.pdb1' # biological subunit
print "downloading with urllib"
urllib.urlretrieve(url, pdbcode + ".pdb")
file = pdbcode + ".pdb"
elif flag == '--pdbfile':
# if a filename is spesified then we will
# process the file name
# the filename should have the following formate:
# /path/pdbcode.pdb
file = sys.argv[2]
pdbcode = process_filename_for_pdb(file)
else:
print "flag is needed."
print "options: --pdbcode (download from pdb) or --pdbfile (spesify the file locations)"
exit()
print "pdbcode = " + pdbcode
print "file = " + file
if (sys.argv[3] == 'carbohydrate'):
flag_carbohydrate = True
elif (sys.argv[3] == 'nocarbohydrate'):
flag_carbohydrate = False
else:
print "ERORR: the second parameter can be carbohydrate or nocarbohydrate"
exit()
if (sys.argv[4] == 'renumber'):
flag_renumber = True
elif (sys.argv[4] == 'original_numbers'):
flag_renumber = False
else:
print "ERORR: the third parameter can be renumber (renumber residues or original_numbers (use the curent numbering)"
print " the renumber is recomended. get ride of code for insertion of residues."
exit()
# this function will split up "Alternate location indicator"
# ALI is not stored in BIO PDB.
# At this step we may want to do other processing
# This will create 3 files: (1) the original files downloaded, (2) everything incomon + the ALI mark A, and (3) everything incomon + the ALI mark B.
# the file (2) will be used for additional steps and is copied to pdbcode.pdb
Preprocess_PDB(file)
#exit()
if (not os.path.exists(file) or os.path.getsize(file) == 0):
print file + " is empty or does not exist "
exit()
parser = BP.PDBParser()
struc = parser.get_structure(pdbcode, file)
io = BP.PDBIO()
io.set_structure(struc)
io.save("everything.pdb")
surf = BP.get_surface(file)
get_structure_stat(struc, surf)
## remove waters.
struc = get_substructure_remove_list(struc, ['HOH'])
## remove waters and other small molecules (Hetatms) that are not posible ligand.
struc = get_substructure_remove_list(struc, notligand_list)
#struc = get_substructure_remove_waters(struc)
## remove carbohydrates
if not (flag_carbohydrate):
struc = get_substructure_remove_list(struc, carbohydrate_list)
io.set_structure(struc)
io.save("nowaters.pdb")
#get_structure_stat(struc,surf)
## if multiple models choose the first model.
struc = get_structure_one_model(struc)
#get_structure_stat(struc,surf)
## idenify small peptides
print "idenifying small peptides"
peptides_list, peptides_struc_list = get_peptides(struc)
## write out peptides
pepnum = write_list('pep', 1, peptides_struc_list, surf, io)
#remove peptides
struc = get_receptor(struc, [], peptides_list, -1)
## idenify ligands
print "idenifying ligands"
lig_list, lig_struc_list = get_ligs(struc)
## write out ligands:
lignum = write_list('lig', 1, lig_struc_list, surf, io)
## check if Attached to neighbor
## check if Attached to or clash?
are_ligands_close(lig_list)
## Idenify a recptor compatable with the ligands/peptides
## we only include chains close to a ligand/peptide as
## part of protein.
## evaluate chains by seeing how close the ligand is to chain.
## get_receptor will keep chains with in a certein distance (7
## Angstroms) from the ligand or the the chain closest to the ligand.
receptor_struc = get_receptor(struc, lig_list, [], lignum)
# renumber all chains. Each chain will start at one.
if (flag_renumber):
renumber_residues(receptor_struc)
io.set_structure(receptor_struc)
io.save("rec.pdb")
pdbcode = sys.argv[1]
#file = '/raid9/tbalius/Projects/ProteomicDOCKing/plversion1/'+pdbcode+'/'+pdbcode+'/'+pdbcode+'.pdb.ori'
file = '/raid9/tbalius/Projects/ProteomicDOCKing/plversion1/' + pdbcode + '/' + pdbcode + '/' + pdbcode + '.pdb'
if (not os.path.exists(file) or os.path.getsize(file) == 0):
print file + " is empty or does not exist "
exit()
parser = BP.PDBParser()
struc = parser.get_structure(pdbcode, file)
io = BP.PDBIO()
io.set_structure(struc)
io.save("everything.pdb")
surf = BP.get_surface(file)
get_structure_stat(struc, surf)
## remove waters.
struc = get_substructure_remove_list(struc, ['HOH'])
#struc = get_substructure_remove_waters(struc)
io.save("nowaters.pdb")
get_structure_stat(struc, surf)
## if multiple models choose the first model.
struc = get_structure_one_model(struc)
get_structure_stat(struc, surf)
## idenify ligands
