def main(pdb):
## speed up by not reading atom section...
d_mmCIF = parse_mmCIF.main(pdb)
a = float(d_mmCIF['_cell.length_a'][0])
b = float(d_mmCIF['_cell.length_b'][0])
c = float(d_mmCIF['_cell.length_c'][0])
alpha = float(d_mmCIF['_cell.angle_alpha'][0])
beta = float(d_mmCIF['_cell.angle_beta'][0])
gamma = float(d_mmCIF['_cell.angle_gamma'][0])
Z = int(d_mmCIF['_cell.Z_PDB'][0])
mw = 0
for i in range(len(d_mmCIF['_entity.id'])):
if d_mmCIF['_entity.type'][i] == 'polymer':
mw += float(d_mmCIF['_entity.formula_weight'][i])
VM = calc(
a,
b,
c,
alpha,
beta,
gamma,
mw,
Z,
)
print pdb, VM
return VM
def one_polypeptide(pdb,):
l_data_categories = ['_entity_poly',]
d = parse_mmCIF.main(
pdb,
l_data_categories = l_data_categories,
)
bool_append = False
## make sure polymer is present (not vacomycin 1aa5)
if '_entity_poly.type' in d.keys():
## one polypeptide?
if d['_entity_poly.type'].count('polypeptide(L)') == 1:
bool_append = True
## if not ',' in ''.join(d['_entity_poly.pdbx_strand_id']):
## bool_append = True
## list_entity.pdbx_number_of_molecules__1.txt
return bool_append
def modres_not_MSE(pdb,):
l_data_categories = ['_pdbx_struct_mod_residue']
d = parse_mmCIF.main(
pdb,
l_data_categories = l_data_categories,
)
bool_append = False
## has MODRES
if '_pdbx_struct_mod_residue.id' in d.keys():
if d['_pdbx_struct_mod_residue.label_comp_id'] != d['_pdbx_struct_mod_residue.auth_comp_id']:
print pdb
stop
## at least one MODRES is different from MSE
if d['_pdbx_struct_mod_residue.auth_comp_id'] != len(d['_pdbx_struct_mod_residue.auth_comp_id'])*['MSE']:
bool_append = True
return bool_append
def main(pdb):
## speed up by not reading atom section...
d_mmCIF = parse_mmCIF.main(pdb)
a = float(d_mmCIF['_cell.length_a'][0])
b = float(d_mmCIF['_cell.length_b'][0])
c = float(d_mmCIF['_cell.length_c'][0])
alpha = float(d_mmCIF['_cell.angle_alpha'][0])
beta = float(d_mmCIF['_cell.angle_beta'][0])
gamma = float(d_mmCIF['_cell.angle_gamma'][0])
Z = int(d_mmCIF['_cell.Z_PDB'][0])
mw = 0
for i in range(len(d_mmCIF['_entity.id'])):
if d_mmCIF['_entity.type'][i] == 'polymer':
mw += float(d_mmCIF['_entity.formula_weight'][i])
VM = calc(a,b,c,alpha,beta,gamma,mw,Z,)
print pdb, VM
return VM
def modres_not_MSE(pdb, ):
l_data_categories = ['_pdbx_struct_mod_residue']
d = parse_mmCIF.main(
pdb,
l_data_categories=l_data_categories,
)
bool_append = False
## has MODRES
if '_pdbx_struct_mod_residue.id' in d.keys():
if d['_pdbx_struct_mod_residue.label_comp_id'] != d[
'_pdbx_struct_mod_residue.auth_comp_id']:
print pdb
stop
## at least one MODRES is different from MSE
if d['_pdbx_struct_mod_residue.auth_comp_id'] != len(
d['_pdbx_struct_mod_residue.auth_comp_id']) * ['MSE']:
bool_append = True
return bool_append
def one_polypeptide(pdb, ):
l_data_categories = [
'_entity_poly',
]
d = parse_mmCIF.main(
pdb,
l_data_categories=l_data_categories,
)
bool_append = False
## make sure polymer is present (not vacomycin 1aa5)
if '_entity_poly.type' in d.keys():
## one polypeptide?
if d['_entity_poly.type'].count('polypeptide(L)') == 1:
bool_append = True
## if not ',' in ''.join(d['_entity_poly.pdbx_strand_id']):
## bool_append = True
## list_entity.pdbx_number_of_molecules__1.txt
return bool_append
def parse_coords(pdb):
d_mmCIF = parse_mmCIF.main(pdb, )
d_coords, l_coords_alpha = mmCIF2coords.main(pdb, d_mmCIF)
return d_mmCIF, l_coords_alpha
def parse_dihedrals():
import sys
path = '/data/mmCIF'
d_phipsi_res = {
'ALA':[],'CYS':[],'ASP':[],'GLU':[],'PHE':[],
'GLY':[],'HIS':[],'ILE':[],'LYS':[],'LEU':[],
'MET':[],'ASN':[],'PRO':[],'GLN':[],'ARG':[],
'SER':[],'THR':[],'VAL':[],'TRP':[],'TYR':[],
'prePRO':[],'prePRO_notGLY':[],'prePRO_GLY':[],
'cisPro':[],'transPro':[],
'all_notgly_notpro_notprepro':[],
}
d_phipsi_ss = {
'sheet':[], ## _struct_sheet_order.sense
##_struct_conf.pdbx_PDB_helix_class
'helix_alpha':[], ## i+4 # 1
'helix_pi':[], ## i+5 # 3
'helix_310':[], ## i+3 # 5
'Turn':[], ## i+?
##
'turns_notgly_notpro_notprepro':[],
}
d_counts = {
'cisProALA':0,
'cisProCYS':0,
'cisProASP':0,
'cisProGLU':0,
'cisProPHE':0,
'cisProGLY':0,
'cisProHIS':0,
'cisProILE':0,
'cisProLYS':0,
'cisProLEU':0,
'cisProMET':0,
'cisProASN':0,
'cisProPRO':0,
'cisProGLN':0,
'cisProARG':0,
'cisProSER':0,
'cisProTHR':0,
'cisProVAL':0,
'cisProTRP':0,
'cisProTYR':0,
'cisPro_helix':0,
'cisPro_sheet':0,
'cisPro_turn':0,
'cisPro_random':0,
}
l_dn = os.listdir(path)
l_dn.sort()
l_dn.remove('mmCIF.py')
for dn in l_dn:
if dn < sys.argv[-2]:
continue
if dn > sys.argv[-1]:
continue
print '*',dn
l_fn = os.listdir('%s/%s' %(path,dn,))
l_fn.sort()
for fn in l_fn:
pdb = fn[:4]
print pdb
d_mmCIF = parse_mmCIF.main(
pdb,
d_breaks = {'_exptl.method':['SOLUTION NMR']},
l_data_categories = [
'_exptl',
'_refine',
'_struct_conf', ## HELIX
'_struct_sheet_range', ## SHEET
'_entity',
'_entity_poly',
'_entity_poly_seq',
'_atom_site',
],
)
## skip NMR models
if ''.join(d_mmCIF['_exptl.method']) in [
'SOLUTION NMR',
'POWDER DIFFRACTION',
'ELECTRON MICROSCOPY',
]:
continue
if not '_refine.ls_d_res_high' in d_mmCIF.keys():
print d_mmCIF['_exptl.method']
continue
## skip if multiple resolutions
if len(d_mmCIF['_refine.ls_d_res_high']) > 1:
continue
## skip if no resolution
if ''.join(d_mmCIF['_refine.ls_d_res_high']) == '?':
continue
## skip low resolution structures
if float(''.join(d_mmCIF['_refine.ls_d_res_high'])) > 2:
continue
if not 'polymer' in d_mmCIF['_entity.type']:
continue
if not '_entity_poly.type' in d_mmCIF.keys(): ## e.g. 1hhu
continue
if d_mmCIF['_entity_poly.type'] == ['polydeoxyribonucleotide/polyribonucleotide hybrid']:
continue
if d_mmCIF['_entity_poly.type'] == ['polydeoxyribonucleotide']:
continue
d_sequence = {}
for i_entity_poly_seq in range(len(d_mmCIF['_entity_poly_seq.entity_id'])):
entity_id = int(d_mmCIF['_entity_poly_seq.entity_id'][i_entity_poly_seq])
if not entity_id in d_sequence.keys():
d_sequence[entity_id] = []
res_no = int(d_mmCIF['_entity_poly_seq.num'][i_entity_poly_seq])
res_name = d_mmCIF['_entity_poly_seq.mon_id'][i_entity_poly_seq]
d_sequence[entity_id] += [{'res_no':res_no,'res_name':res_name,}]
l_entities_poly = []
for i_entity_poly in range(len(d_mmCIF['_entity_poly.entity_id'])):
## skip if not polypeptide
entity_poly_type = d_mmCIF['_entity_poly.type'][i_entity_poly]
if entity_poly_type != 'polypeptide(L)':
continue
## skip if nonstd linkages
if d_mmCIF['_entity_poly.nstd_linkage'][i_entity_poly] == 'yes':
print pdb
stop
continue
## parse entity_id and chains
entity_id = int(d_mmCIF['_entity_poly.entity_id'][i_entity_poly])
l_entities_poly += [entity_id]
## skip if no polypeptide chains
if l_entities_poly == []:
continue
d_coords = {}
for i_atom_site in range(len(d_mmCIF['_atom_site.id'])):
entity_id = int(d_mmCIF['_atom_site.label_entity_id'][i_atom_site])
## not a polymer
if not entity_id in l_entities_poly:
continue
## polymer, append
elif not entity_id in d_coords.keys():
d_coords[entity_id] = {}
model = int(d_mmCIF['_atom_site.pdbx_PDB_model_num'][i_atom_site])
if model > 1:
continue
chain = d_mmCIF['_atom_site.label_asym_id'][i_atom_site]
if not chain in d_coords[entity_id].keys():
d_coords[entity_id][chain] = {}
res_no = int(d_mmCIF['_atom_site.label_seq_id'][i_atom_site])
if not res_no in d_coords[entity_id][chain].keys():
d_coords[entity_id][chain][res_no] = {}
atom_name = d_mmCIF['_atom_site.label_atom_id'][i_atom_site]
altloc = d_mmCIF['_atom_site.label_alt_id'][i_atom_site]
if altloc not in ['.','A','1',]:
continue
## skip if zero occupancy
occupancy = float(d_mmCIF['_atom_site.occupancy'][i_atom_site])
if altloc == '.' and occupancy == 0:
continue
if atom_name in ['CA','C','O','N',] and atom_name in d_coords[entity_id][chain][res_no].keys():
print pdb, chain, res_no, atom_name
print d_mmCIF['_atom_site.Cartn_x'][i_atom_site], d_mmCIF['_atom_site.Cartn_y'][i_atom_site]
print d_coords[entity_id][chain][res_no][atom_name]
stop
x = float(d_mmCIF['_atom_site.Cartn_x'][i_atom_site])
y = float(d_mmCIF['_atom_site.Cartn_y'][i_atom_site])
z = float(d_mmCIF['_atom_site.Cartn_z'][i_atom_site])
coord = numpy.array([x,y,z,])
d_coords[entity_id][chain][res_no][atom_name] = coord
d_helices = {}
## helices or turns present?
if '_struct_conf.id' in d_mmCIF.keys():
for i_struct_conf in range(len(d_mmCIF['_struct_conf.id'])):
chain1 = d_mmCIF['_struct_conf.beg_label_asym_id'][i_struct_conf]
chain2 = d_mmCIF['_struct_conf.end_label_asym_id'][i_struct_conf]
res_no1 = int(d_mmCIF['_struct_conf.beg_label_seq_id'][i_struct_conf])
res_no2 = int(d_mmCIF['_struct_conf.end_label_seq_id'][i_struct_conf])
conf_type_id = d_mmCIF['_struct_conf.conf_type_id'][i_struct_conf]
if chain1 != chain2:
print chain1, chain2, pdb
stop
if conf_type_id == 'HELX_P':
helix_class = int(d_mmCIF['_struct_conf.pdbx_PDB_helix_class'][i_struct_conf])
elif conf_type_id == 'TURN_P':
helix_class = 99
else:
print conf_type_id
print pdb
stop
l_res_nos = range(res_no1,res_no2+1,)
if not chain1 in d_helices.keys():
d_helices[chain1] = {}
for res_no in l_res_nos:
d_helices[chain1][res_no] = helix_class
d_sheets = {}
## sheet present?
if '_struct_sheet_range.sheet_id' in d_mmCIF.keys():
for i_struct_sheet_range in range(len(d_mmCIF['_struct_sheet_range.sheet_id'])):
chain1 = d_mmCIF['_struct_sheet_range.beg_label_asym_id'][i_struct_sheet_range]
chain2 = d_mmCIF['_struct_sheet_range.end_label_asym_id'][i_struct_sheet_range]
res_no1 = int(d_mmCIF['_struct_sheet_range.beg_label_seq_id'][i_struct_sheet_range])
res_no2 = int(d_mmCIF['_struct_sheet_range.end_label_seq_id'][i_struct_sheet_range])
l_res_nos = range(res_no1,res_no2+1,)
if chain1 != chain2:
print chain1, chain2, pdb
stop
if not chain1 in d_sheets.keys():
d_sheets[chain1] = []
for res_no in l_res_nos:
d_sheets[chain1] += l_res_nos
for entity_id in l_entities_poly:
for chain in d_coords[entity_id].keys():
## skip if short peptide (e.g. 13gs)
if len(d_sequence[entity_id]) <= 3:
continue
for i_res_no in range(1,len(d_sequence[entity_id])-1):
res_no_prev = int(d_sequence[entity_id][i_res_no-1]['res_no'])
res_no = int(d_sequence[entity_id][i_res_no]['res_no'])
res_no_next = int(d_sequence[entity_id][i_res_no+1]['res_no'])
res_name = d_sequence[entity_id][i_res_no]['res_name']
if res_name == 'MSE':
res_name = 'MET'
res_name_next = d_sequence[entity_id][i_res_no+1]['res_name']
## not a standard residue
if not res_name in d_phipsi_res.keys():
continue
## residue not observed
if not res_no_prev in d_coords[entity_id][chain].keys():
continue
if not res_no in d_coords[entity_id][chain].keys():
continue
if not res_no_next in d_coords[entity_id][chain].keys():
continue
## atom not observed
if not 'C' in d_coords[entity_id][chain][res_no_prev]:
continue
if not 'N' in d_coords[entity_id][chain][res_no]:
continue
if not 'CA' in d_coords[entity_id][chain][res_no]:
continue
if not 'C' in d_coords[entity_id][chain][res_no]:
continue
if not 'N' in d_coords[entity_id][chain][res_no_next]:
continue
C_prev = d_coords[entity_id][chain][res_no_prev]['C']
N = d_coords[entity_id][chain][res_no]['N']
CA = d_coords[entity_id][chain][res_no]['CA']
C = d_coords[entity_id][chain][res_no]['C']
N_next = d_coords[entity_id][chain][res_no_next]['N']
phi = calc_dihedral(C_prev,N,CA,C,)
psi = calc_dihedral(N,CA,C,N_next,)
if 'CA' in d_coords[entity_id][chain][res_no_prev].keys():
CA_prev = d_coords[entity_id][chain][res_no_prev]['CA']
omega = calc_dihedral(CA_prev,C_prev,N,CA,)
else:
omega = None
if omega:
if (
omega
and
omega < 150
and
omega > -150
): ## 12e8, PRO44D
if abs(omega) > 30: ## 12e8 PRO196D, 1a44 GLU82A
omega = None
## cis
else:
omega = 'cis'
pass
## trans
else:
omega = 'trans'
pass
else:
omega = None
bool_helix = False
if chain in d_helices.keys():
if res_no in d_helices[chain].keys():
bool_helix = True
helix_class = d_helices[chain][res_no]
bool_sheet = False
if chain in d_sheets.keys():
if res_no in d_sheets[chain]:
bool_sheet = True
## if bool_helix == True and bool_sheet == True and helix_class != 99:
## print pdb, chain, res_no, 'sheet and helix'
#### stop
if res_name_next == 'PRO':
d_phipsi_res['prePRO'] += [[phi,psi,]]
if res_name != 'GLY':
d_phipsi_res['prePRO_notGLY'] += [[phi,psi,]]
else:
d_phipsi_res['prePRO_GLY'] += [[phi,psi,]]
else:
d_phipsi_res[res_name] += [[phi,psi,]]
if res_name not in ['GLY','PRO',]:
d_phipsi_res['all_notgly_notpro_notprepro'] += [[phi,psi,]]
elif res_name == 'PRO' and omega:
d_phipsi_res['%sPro' %(omega)] += [[phi,psi,]]
if omega == 'cis':
d_counts['cisPro%s' %(res_name)] += 1
if bool_helix == True:
if helix_class == 1:
d_counts['cisPro_helix'] += 1
elif helix_class == 99:
d_counts['cisPro_turn'] += 99
elif bool_sheet == True:
d_counts['cisPro_sheet'] += 1
else:
d_counts['cisPro_random'] += 1
if bool_helix == True:
## if helix_class not in [1,3,5,99,]:
## print pdb, chain, res_no, helix_class
## print 'unexpected helix class'
#### stop_helix_class
if helix_class == 1:
d_phipsi_ss['helix_alpha'] += [[phi,psi,]]
elif helix_class == 3:
d_phipsi_ss['helix_pi'] += [[phi,psi,]]
elif helix_class == 5:
d_phipsi_ss['helix_310'] += [[phi,psi,]]
elif helix_class == 99:
d_phipsi_ss['Turn'] += [[phi,psi,]]
if (
res_name_next != 'PRO'
and
res_name not in ['GLY','PRO',]
):
d_phipsi_ss['turns_notgly_notpro_notprepro'] += [[phi,psi,]]
if bool_sheet == True:
d_phipsi_ss['sheet'] += [[phi,psi,]]
l = []
for k in d_counts.keys():
count = d_counts[k]
l += ['%s %s\n' %(k,count,)]
fd = open('count.txt','w')
fd.writelines(l)
fd.close()
return d_phipsi_res, d_phipsi_ss
def unobs_nonterminal_residues():
##
## unobs or zero occup not at terminals!!! (combination...)
## eg dont exlude 200l w 163,164 missing
## dont exclude 201l w 163,164 missing, but internally in _pdbx_poly_seq_scheme because 2 chains
##
category = fn = '_pdbx_unobs_or_zero_occ_residues'
fd = open('%s/list%s.txt' %(path,fn))
s = fd.read()
fd.close()
l_pdbs_in = s.split()
l_data_categories = [
'_pdbx_poly_seq_scheme',
'_pdbx_unobs_or_zero_occ_residues',
'_entity_poly',
]
fn_out = 'list_pdbx_unobs_residues__NONTERMINAL'
loop_residues(category,fn_out,)
l_pdbs_out = []
for pdb in l_pdbs_in:
## if pdb[1:3] < 'oa':
## continue
## if pdb != '2hub':
## continue
## no residues are present! (e.g. 1oax, 1oay)
if pdb in ['1oax','1oay',]:
continue
d = parse_mmCIF.main(pdb,l_data_categories=l_data_categories,)
## print pdb
if not category in d.keys():
continue
bool_append = False
s = ''.join(d['_pdbx_poly_seq_scheme.pdb_strand_id'])
for chains in d['_entity_poly.pdbx_strand_id']:
for chain in chains.split(','):
index1 = s.index(chain)
index2 = s.rindex(chain)
## print chain
l_auth_seq_num = d['_pdbx_poly_seq_scheme.auth_seq_num'][index1:index2+1]
while l_auth_seq_num[0] == '?':
l_auth_seq_num = l_auth_seq_num[1:]
while l_auth_seq_num[-1] == '?':
l_auth_seq_num = l_auth_seq_num[:-1]
## non-terminal residues missing?
if '?' in l_auth_seq_num:
print '****', pdb
bool_append = True
break
if bool_append == True:
break
if bool_append == True:
print pdb
l_pdbs_out += [pdb]
## continue
fd = open('%s/%s' %(path,fn_out,),'w')
fd.write('\n'.join(l_pdbs_out))
fd.close()
return
def main():
d = {}
if os.path.isfile('db_resolution.txt'):
fd = open('db_resolution.txt', 'r')
lines = fd.readlines()
fd.close()
for line in lines:
l = line.strip().split()
pdb = l[0]
v = l[1]
d[pdb] = v
path = '/media/WDMyBook1TB/2TB/mmCIF'
l_dns = os.listdir(path)
l_dns.sort()
lines_out = []
for i in range(len(l_dns)):
dn = l_dns[i]
if dn < sys.argv[-1]:
continue
if not os.path.isdir('%s/%s' % (path, dn)):
continue
print '%s/%s %s' % (i + 1, len(l_dns), dn)
l_fns = os.listdir('%s/%s' % (path, dn))
l_fns.sort()
for fn in l_fns:
if fn[-3:] == '.gz':
continue
pdb = fn[0:4]
if pdb in d.keys():
continue
print pdb
fd = open('%s/%s/%s' % (path, dn, fn), 'r')
lines = fd.readlines()
fd.close()
d_mmCIF = parse_mmCIF.main(
pdb,
lines,
l_data_categories=[
'_refine',
'_refine_hist',
], ## parse selected data categories
l_data_categories_break=[
'_refine',
## '_refine_hist',
],
d_breaks_negation={
## break if not x-ray diffraction
'_exptl.method': 'X-RAY DIFFRACTION',
})
if d_mmCIF['_exptl.method'] != ['X-RAY DIFFRACTION']:
continue
resolution = d_mmCIF['_refine.ls_d_res_high']
line = '%s %s\n' % (
pdb,
resolution,
)
lines_out += [line]
fd = open('db_resolution.txt', 'a')
fd.write(line)
fd.close()
d[pdb] = resolution
##
## write to file
##
lines_out = []
for pdb, resolution in d.items():
line = '%s %s\n' % (
pdb,
resolution,
)
lines_out += [line]
fd = open('db_resolution.txt', 'w')
fd.writelines(lines_out)
fd.close()
d = {}
fd = open('db_resolution.txt', 'r')
lines = fd.readlines()
fd.close()
lines_out = []
for line in lines:
resolution = line.strip().split()[1][2:-2]
if resolution == '.':
continue
resolution = float(resolution)
resolution = round(resolution, 2)
if not resolution in d.keys():
d[resolution] = 0
d[resolution] += 1
lines_out += ['%s\n' % (resolution, )]
fd = open('histogram_resolution.txt', 'w')
fd.writelines(lines_out)
fd.close()
stop
lines_out = []
l_resolutions = d.keys()
l_resolutions.sort()
## for resolution,count in d.items():
for resolution in l_resolutions:
count = d[resolution]
lines_out += ['%s %s\n' % (
resolution,
count,
)]
fd = open('histogram_resolution.txt', 'w')
fd.writelines(lines_out)
fd.close()
return
def main():
fd = open('radius_of_gyration.txt','r')
lines = fd.readlines()
fd.close()
d_radii = {}
for line in lines:
l = line.strip().split()
pdb = l[0]
r = l[1]
d_radii[pdb] = r
lines_out = []
path = '/media/WDMyBook1TB/2TB/mmCIF'
l_dns = os.listdir(path)
l_dns.sort()
for i in range(len(l_dns)):
dn = l_dns[i]
if dn < sys.argv[-1]:
continue
if not os.path.isdir('%s/%s' %(path,dn)):
continue
print '%s/%s %s' %(i+1,len(l_dns), dn)
l_fns = os.listdir('%s/%s' %(path,dn))
l_fns.sort()
for fn in l_fns:
if fn[-3:] == '.gz':
continue
pdb = fn[0:4]
if pdb in d_radii.keys():
continue
print pdb
fd = open('%s/%s/%s' %(path, dn, fn), 'r')
lines = fd.readlines()
fd.close()
d_mmCIF = parse_mmCIF.main(
pdb,lines,
d_breaks = {
## break if multiple polymer types (not monomeric)
'_entity_poly.entity_id':'2',
## '_exptl.method':'SOLUTION NMR', ## break if e.g. _exptl.method = SOLUTION NMR
## break if multiple chains
'_entity_poly.pdbx_strand_id':',',
},
d_breaks_negation = {
## break if not x-ray diffraction
'_exptl.method':'X-RAY DIFFRACTION',
## break if not monomeric
'_pdbx_struct_assembly.oligomeric_details':'monomeric',
},
l_data_categories = [
'_atom_site',
'_entity_poly',
'_pdbx_struct_assembly',
], ## parse selected data categories
)
## some unknown temporary error... or break before reaching this part when parsing...
if not '_pdbx_struct_assembly.oligomeric_details' in d_mmCIF.keys():
continue
## NMR structure?
if d_mmCIF['_exptl.method'] != ['X-RAY DIFFRACTION']:
stop2
continue
## no polymers in structure?
if not '_entity_poly.entity_id' in d_mmCIF.keys():
continue
## polymer(s) is/are not polypeptide(s)
if d_mmCIF['_entity_poly.type'] != len(d_mmCIF['_entity_poly.type'])*['polypeptide(L)']:
continue
## biounit not monomeric
if d_mmCIF['_pdbx_struct_assembly.oligomeric_details'] != len(d_mmCIF['_pdbx_struct_assembly.oligomeric_details'])*['monomeric']:
continue
## one polymer in assymetric unit
if len(d_mmCIF['_entity_poly.entity_id']) > 1:
continue
print pdb
##
## calculate center of mass
##
center_of_mass = numpy.array([0.,0.,0.,])
l_coords = []
l_masses = []
for i_atom_site in range(len(d_mmCIF['_atom_site.id'])):
if d_mmCIF['_atom_site.label_entity_id'][i_atom_site] not in d_mmCIF['_entity_poly.entity_id']:
continue
element = d_mmCIF['_atom_site.type_symbol'][i_atom_site]
## only do heavy atoms
if element == 'H':
continue
if element not in d_mass.keys():
print pdb, d_mmCIF['_atom_site.type_symbol'][i_atom_site]
continue
mass = d_mass[element]
l_masses += [mass]
x = float(d_mmCIF['_atom_site.Cartn_x'][i_atom_site])
y = float(d_mmCIF['_atom_site.Cartn_y'][i_atom_site])
z = float(d_mmCIF['_atom_site.Cartn_z'][i_atom_site])
coord = numpy.array([x,y,z,])
l_coords += [coord]
center_of_mass += mass*coord
center_of_mass /= sum(l_masses)
##
## calculate radius of gyration
##
sum_r = 0
for i_coord in range(len(l_coords)):
coord = l_coords[i_coord]
mass = l_masses[i_coord]
sq_dist_from_center_of_mass = sum((coord-center_of_mass)**2)
sum_r += mass*sq_dist_from_center_of_mass
radius_of_gyration = math.sqrt(sum_r/sum(l_masses))
print pdb, center_of_mass, radius_of_gyration
line = '%s %s\n' %(pdb,radius_of_gyration,)
lines_out += [line]
fd = open('radius_of_gyration.txt','a')
fd.write(line)
fd.close()
d_radii[pdb] = radius_of_gyration
##
## write calculated radii of gyration to file
##
lines_out = []
for pdb,radius_of_gyration in d_radii.items():
line = '%s %s\n' %(pdb,radius_of_gyration,)
lines_out += [line]
fd = open('radius_of_gyration.txt','w')
fd.writelines(lines_out)
fd.close()
return
def one_polysaccharide(pdb,):
l_data_categories = [
'_entity',
'_chem_comp',
'_entity_poly',
]
d = parse_mmCIF.main(
pdb,
l_data_categories = l_data_categories,
)
bool_append = False
bool_polysaccharide = False
if '_chem_comp.type' in d.keys():
for chem_comp_type in d['_chem_comp.type']:
if chem_comp_type.lower() in [
'd-saccharide 1,4 and 1,4 linking', # 3amm
'l-saccharide','d-saccharide','saccharide'
]:
bool_polysaccharide = True
break
## elif 'acchar' in chem_comp_type.lower():
## print d
## print chem_comp_type
## print pdb
## print set(['D-saccharide','saccharide'])&set(d['_chem_comp.type'])
## stop
## else:
## print pdb
## stop
count_polymer_sugar = 0
bool_monosaccharide = False ## included to exclude 1a14 which contains polymers and monomers
for i in range(len(d['_entity.type'])):
entity_type = d['_entity.type'][i]
if entity_type in [
'polymer',
]:
if d['_entity.pdbx_description'][i][:7] == 'SUGAR (':
count_polymer_sugar += int(d['_entity.pdbx_number_of_molecules'][i])
continue
## ## polypeptide or polynucleotide (just a check)
## elif d['_entity.pdbx_description'][i][:5] == 'SUGAR': ## eg 2c49
## if d['_entity.id'][i] not in d['_entity_poly.entity_id']:
## print pdb
## stop
elif entity_type == 'non-polymer' and d['_entity.pdbx_description'][i][:5] == 'SUGAR':
bool_monosaccharide = True
## ## just a check
## if d['_entity.pdbx_description'][i][:7] != 'SUGAR (' and pdb not in ['1iuc',]:
## print pdb
## print d['_entity.pdbx_description'][i]
## stop
## ## anything else named SUGAR? just a check
## elif entity_type != 'non-polymer' and d['_entity.pdbx_description'][i][:5] == 'SUGAR':
## print d
## print pdb
## print entity_type
## print d['_entity.pdbx_description'][i]
## stop
if bool_monosaccharide == False and bool_polysaccharide == True and count_polymer_sugar == 1:
bool_append = True
## elif pdb in ['3gvj','3gvk','3gvl','3hmy','3msg','1v0f',]:
## bool_append = False
## ## error check
## elif bool_polysaccharide == False and count_polymer_sugar > 0:
## print d
## print bool_polysaccharide
## print d['_entity.pdbx_description']
## print count_polymer_sugar
## print pdb
## stop_no_poly_but_poly
if pdb == '1dl2':
print count_polymer_sugar
print bool_append
stop
return bool_append
def main():
fd = open('remediation_negativeBiso.txt', 'r')
lines = fd.readlines()
fd.close()
l_pdbs = []
for line in lines:
if line.strip() == '':
continue
if line[0] == '#':
continue
l = line.strip().split()
pdb = l[0]
l_pdbs += [pdb]
path = '/media/WDMyBook1TB/2TB/mmCIF'
l_dns = os.listdir(path)
l_dns.sort()
for i in range(len(l_dns)):
dn = l_dns[i]
if dn < sys.argv[-1]:
continue
if not os.path.isdir('%s/%s' % (path, dn)):
continue
print '%s/%s %s' % (i + 1, len(l_dns), dn)
l_fns = os.listdir('%s/%s' % (path, dn))
l_fns.sort()
for fn in l_fns:
if fn[-3:] == '.gz':
continue
pdb = fn[0:4]
if not pdb in l_pdbs:
continue
print pdb
fd = open('%s/%s/%s' % (path, dn, fn), 'r')
lines = fd.readlines()
fd.close()
d_mmCIF = parse_mmCIF.main(
pdb,
lines,
d_breaks_negation={
## break if not x-ray diffraction
'_exptl.method': 'X-RAY DIFFRACTION',
},
l_data_categories=[
## parse selected data categories
'_database_PDB_rev',
'_computing',
'_atom_site',
'_refine'
],
)
## ## no polymers in structure?
## if not '_entity_poly.entity_id' in d_mmCIF.keys():
## continue
if d_mmCIF['_exptl.method'] != ['X-RAY DIFFRACTION']:
continue
print pdb
##
## parse bfactors
##
for i_atom_site in range(len(d_mmCIF['_atom_site.id'])):
bfactor = float(
d_mmCIF['_atom_site.B_iso_or_equiv'][i_atom_site])
## if bfactor == '?':
## continue
element = d_mmCIF['_atom_site.type_symbol'][i_atom_site]
comp_id = d_mmCIF['_atom_site.label_comp_id'][i_atom_site]
if float(bfactor) < -0.01:
if (element != 'H' and comp_id in [
'ALA',
'CYS',
'ASP',
'GLU',
'PHE',
'GLY',
'HIS',
'ILE',
'LYS',
'MET',
'ASN',
'PRO',
'GLN',
'ARG',
'SER',
'THR',
'VAL',
'TRP',
'TYR',
]):
print
print 'negative'
print
year = int(d_mmCIF['_database_PDB_rev.date'][0][:4])
atom_id = int(d_mmCIF['_atom_site.id'][i_atom_site])
refinement = ''.join(
d_mmCIF['_computing.structure_refinement'])
solution = ''.join(
d_mmCIF['_computing.structure_solution'])
resolution = float(''.join(
d_mmCIF['_refine.ls_d_res_high']))
fd = open('remediation_negativeBiso.txt', 'a')
fd.write(
## '%4s %4i %4i %3s %2s %6.2f %30s %20s\n' %(
'%4s\t%4i\t%4i\t%3s\t%2s\t%6.2f\t%6.2f\t%30s\t%20s\n'
% (
pdb,
year,
atom_id,
comp_id,
element,
bfactor,
resolution,
solution.ljust(30),
refinement.ljust(20),
))
fd.close()
break
return
def main():
d_MV = {}
path = '/data/mmCIF'
l_dn = os.listdir(path)
l_dn.sort()
for dn in l_dn:
if dn == 'mmCIF.py':
continue
if dn < sys.argv[-2]:
continue
if dn > sys.argv[-1]:
continue
l_fn = os.listdir('%s/%s' % (path, dn))
for fn in l_fn:
pdb = fn[:4]
## if pdb.upper() not in s_pdbs:
## continue
d_mmCIF = parse_mmCIF.main(
pdb,
d_breaks={'_exptl.method': 'SOLUTION NMR'},
l_data_categories=[
'_cell',
'_entity',
'_exptl',
'_exptl_crystal',
'_entity_poly',
'_symmetry',
## virus
'_pdbx_struct_assembly',
## split structure
'_pdbx_database_related',
],
)
## x-ray structure
if d_mmCIF['_exptl.method'] != ['X-RAY DIFFRACTION']:
continue
## polymer present
if not '_entity_poly.type' in d_mmCIF.keys():
continue
## only polymer present is protein
if d_mmCIF['_entity_poly.type'] != len(
d_mmCIF['_entity_poly.type']) * ['polypeptide(L)']:
continue
if not '_pdbx_struct_assembly.oligomeric_count' in d_mmCIF.keys():
continue
if d_mmCIF['_pdbx_struct_assembly.oligomeric_count'] == len(
d_mmCIF['_pdbx_struct_assembly.oligomeric_count']) * ['?']:
continue
## virus
if int(d_mmCIF['_pdbx_struct_assembly.oligomeric_count']
[0]) % 60 == 0:
continue
## not monomer
if d_mmCIF['_pdbx_struct_assembly.oligomeric_count'] != len(
d_mmCIF['_pdbx_struct_assembly.oligomeric_count']) * ['1']:
continue
## split structure
if '_pdbx_database_related' in d_mmCIF.keys():
if 'split' in d_mmCIF['_pdbx_database_related']:
continue
if 'SPLIT' in d_mmCIF['_pdbx_database_related']:
print pdb
stop
if not '_cell.Z_PDB' in d_mmCIF.keys():
continue
if pdb in [
## treshold
'1e54',
'1e9i',
## difference between calculated MV and MV in mmCIF
'3eiq',
## The crystals diffracted to 1.7Angstrom and appeared to be I centered tetragonal with
## unit cell dimension a=198.42Angstrom and c=396.6Angstrom, however the data only merged successfully in P1
## unit cell a=196.61 b=196.48 c=240.63 alpha=65.91 beta=65.91 gamma=90.01.
## Toscana has published with Hellinga...
'2cjf',
'2bt4',
]:
continue
## if not ''.join(d_mmCIF['_symmetry.space_group_name_H-M']) in [
## 'P 1','P 43 21 2','P 21 3','P 42 3 2','C 1 2 1','F 2 3','P 64 2 2','H 3',
## ]:
## continue ## tmp!!!
a = float(d_mmCIF['_cell.length_a'][0])
b = float(d_mmCIF['_cell.length_b'][0])
c = float(d_mmCIF['_cell.length_c'][0])
alpha = float(d_mmCIF['_cell.angle_alpha'][0])
beta = float(d_mmCIF['_cell.angle_beta'][0])
gamma = float(d_mmCIF['_cell.angle_gamma'][0])
Z = int(d_mmCIF['_cell.Z_PDB'][0])
mw = 0
for i in range(len(d_mmCIF['_entity.id'])):
## if d_mmCIF['_entity.type'][i] == 'polymer':
s = d_mmCIF['_entity.formula_weight'][i]
## unknown ligand
if s == '?':
continue
mw += float(s)
MV = matthews_coefficient.main(a, b, c, alpha, beta, gamma, mw, Z)
spacegroup = ''.join(d_mmCIF['_symmetry.space_group_name_H-M'])
if spacegroup not in [
'F 4 3 2',
'F 41 3 2',
'I 41 3 2',
]:
continue ## tmp!!!
if MV > 10:
print pdb
print 'mw', mw
print 'MV', MV, d_mmCIF['_exptl_crystal.density_Matthews']
print 'Z', Z
import math
alpha *= math.pi / 180.
beta *= math.pi / 180.
gamma *= math.pi / 180.
V = a * b * c * math.sqrt(
1 - math.cos(alpha)**2 - math.cos(beta)**2 -
math.cos(gamma)**2 + 2 *
(math.cos(alpha) * math.cos(beta) * math.cos(gamma)))
print 'V', V
continue
stop_treshold
stop
if '_exptl_crystal.density_Matthews' in d_mmCIF.keys():
if d_mmCIF['_exptl_crystal.density_Matthews'] not in [
['?'],
len(d_mmCIF['_exptl_crystal.density_Matthews']) *
['?'],
]:
if abs(MV -
float(d_mmCIF['_exptl_crystal.density_Matthews'][0])
) > 1:
print 'MV', MV
print 'MV', d_mmCIF['_exptl_crystal.density_Matthews']
print 'mw', mw
print 'Z', Z
continue
stop_difference
if not spacegroup in d_MV.keys():
d_MV[spacegroup] = []
d_MV[spacegroup] += [MV]
print pdb, round(MV, 2), spacegroup
## fd = open('MV_v_spacegroup.txt','w')
## fd.write(str(d_MV))
## fd.close()
l = ['# MV_average MV_stddev n spacegroup\n']
for spacegroup in d_MV.keys():
l_MV = d_MV[spacegroup]
if len(l_MV) <= 1:
continue
average, stddev = statistics.do_stddev(l_MV)
average, stderr = statistics.do_stderr(l_MV)
## l += ['%s %s %s %s\n' %(average,stddev,len(l_MV),spacegroup,)]
l += ['%s %s %s %s\n' % (
average,
stderr,
len(l_MV),
spacegroup,
)]
fd = open('MV_v_spacegroup.txt', 'w')
fd.writelines(l)
fd.close()
return
def get_position_ligand(pdb,pdb_apo,d_apo2holo,):
pdb_holo = d_apo2holo[pdb_apo]['holo']
d_mmCIF_holo = parse_mmCIF.main(pdb_holo,)
d_coords, l_coords_alpha_holo = mmCIF2coords.main(pdb_holo,d_mmCIF_holo)
##
##
##
ligand = d_apo2holo[pdb_apo]['ligand']
l_residues = []
for i in range(len(d_mmCIF_holo['_struct_site.id'])):
if not 'BINDING SITE FOR RESIDUE %s' %(ligand) in d_mmCIF_holo['_struct_site.details'][i]:
continue
if len(l_residues) > 0:
print pdb, pdb_apo, pdb_holo
print l_residues
print d_mmCIF_holo['_struct_site.details'][i]
stop
struct_site_ID = d_mmCIF_holo['_struct_site.id'][i]
for j in range(len(d_mmCIF_holo['_struct_site_gen.site_id'])):
struct_site_gen_ID = d_mmCIF_holo['_struct_site_gen.site_id'][j]
if struct_site_ID == struct_site_gen_ID:
residue = int(d_mmCIF_holo['_struct_site_gen.auth_seq_id'][j])
## l_residues += [residue]
## include neighboring residues
l_residues += [residue-1,residue,residue+1]
l_residues = list(set(l_residues))
if len(l_residues) == 0:
print pdb
stop
##
l_coords_ligand = []
for i in range(len(d_mmCIF_holo['_atom_site.id'])):
if (
d_mmCIF_holo['_atom_site.group_PDB'][i] == 'HETATM'
and
d_mmCIF_holo['_atom_site.label_comp_id'][i] == ligand
):
x = float(d_mmCIF_holo['_atom_site.Cartn_x'][i])
y = float(d_mmCIF_holo['_atom_site.Cartn_y'][i])
z = float(d_mmCIF_holo['_atom_site.Cartn_z'][i])
coord = numpy.array([x,y,z,])
l_coords_ligand += [coord]
d_mmCIF_apo = parse_mmCIF.main(pdb_apo,)
d_coords, l_coords_alpha_apo = mmCIF2coords.main(pdb_apo,d_mmCIF_apo)
## structural alignment
## solution that works in all cases
## also for 2d59 and 2d5a, which have residues missing at the Nterm and Cterm, respectively
## first non-?
index1_seq_apo = next((i for i,v in enumerate(d_mmCIF_apo['_pdbx_poly_seq_scheme.pdb_mon_id']) if v != '?'))
index1_seq_holo = next((i for i,v in enumerate(d_mmCIF_holo['_pdbx_poly_seq_scheme.pdb_mon_id']) if v != '?'))
## last non-?
index2_seq_apo = len(d_mmCIF_apo['_pdbx_poly_seq_scheme.pdb_mon_id'])-next((i for i,v in enumerate(reversed(d_mmCIF_apo['_pdbx_poly_seq_scheme.pdb_mon_id'])) if v != '?'))
index2_seq_holo = len(d_mmCIF_holo['_pdbx_poly_seq_scheme.pdb_mon_id'])-next((i for i,v in enumerate(reversed(d_mmCIF_holo['_pdbx_poly_seq_scheme.pdb_mon_id'])) if v != '?'))
## first common non-?
index1_coord_apo = max(0,index1_seq_holo-index1_seq_apo)
index1_coord_holo = max(0,index1_seq_apo-index1_seq_holo)
## last common non-?
index2_coord_apo = len(l_coords_alpha_apo)+min(0,index2_seq_holo-index2_seq_apo)
index2_coord_holo = len(l_coords_alpha_holo)+min(0,index2_seq_apo-index2_seq_holo)
l_coords_alpha_apo = l_coords_alpha_apo[index1_coord_apo:index2_coord_apo]
l_coords_alpha_holo = l_coords_alpha_holo[index1_coord_holo:index2_coord_holo]
if pdb == pdb_apo:
l_seq_num = d_mmCIF_apo['_pdbx_poly_seq_scheme.pdb_seq_num'][index1_coord_apo:index2_coord_apo]
chain = ''.join(d_mmCIF_apo['_entity_poly.pdbx_strand_id'])
n_residues = len(l_coords_alpha_apo)
l_coords_alpha = l_coords_alpha_apo
else:
l_seq_num = d_mmCIF_holo['_pdbx_poly_seq_scheme.pdb_seq_num'][index1_coord_holo:index2_coord_holo]
chain = ''.join(d_mmCIF_holo['_entity_poly.pdbx_strand_id'])
n_residues = len(l_coords_alpha_holo)
l_coords_alpha = l_coords_alpha_holo
overlap_site = 1.
## ##
## ## eigenvector
## ##
## cutoff = 10
## matrix_hessian = NMA.hessian_calculation(l_coords_alpha,cutoff,)
## eigenvectors, eigenvalues = NMA.diagonalize_hessian(matrix_hessian)
##
## ## apply transformation matrix
## if pdb == pdb_apo:
## instance_geometry = geometry.geometry()
## rmsd = instance_geometry.superpose(l_coords_alpha_apo,l_coords_alpha_holo,)
## tv1 = instance_geometry.fitcenter
## rm = instance_geometry.rotation
## tv2 = instance_geometry.refcenter
## for i_coord in range(len(l_coords_ligand)):
## l_coords_ligand[i_coord] = numpy.dot(l_coords_ligand[i_coord]-tv1,rm)+tv2
##
## ##
## ## apo/holo eigenvector
## ##
## vector_apo2holo = []
## for i in range(len(l_coords_alpha_holo)):
## vector_apo2holo += [
## l_coords_alpha_holo[i][0]-l_coords_alpha_apo[i][0],
## l_coords_alpha_holo[i][1]-l_coords_alpha_apo[i][1],
## l_coords_alpha_holo[i][2]-l_coords_alpha_apo[i][2],
## ]
## vector_apo2holo = numpy.array(vector_apo2holo)
##
## ##
## ## calculate overlap between normal modes and difference vector
## ## in the ligand binding site!!!
## ##
## vector_apo2holo_site = []
## eigenvector_site = []
## ## exclude coordinate not at the ligand binding site
## for i_seq_num in range(len(l_seq_num)):
## seq_num = int(l_seq_num[i_seq_num])
## if seq_num in l_residues:
## eigenvector_site += list(eigenvectors[6][3*i_seq_num:3*i_seq_num+3])
## vector_apo2holo_site += list(vector_apo2holo[3*i_seq_num:3*i_seq_num+3])
## ## calculate overlap
## vector_apo2holo_site = numpy.array(vector_apo2holo_site)
## eigenvector_site = numpy.array(eigenvector_site)
## overlap_site = abs(
## numpy.dot(eigenvector_site,vector_apo2holo_site)
## /
## math.sqrt(
## numpy.dot(eigenvector_site,eigenvector_site)
## *
## numpy.dot(vector_apo2holo_site,vector_apo2holo_site)
## )
## )
## if overlap_site > 0.8:
## print vector_apo2holo_site
## print eigenvector_site
## print pdb
## print l_residues
position_ligand = sum(l_coords_ligand)/len(l_coords_ligand)
n_atoms = len(l_coords_ligand)
return position_ligand, chain, n_residues, n_atoms, ligand, overlap_site
def main():
set_pdbs = exclude_include()
l_pdbs_remove = [
'4a3h','2wf5','1arl','1ee3', ## incorrect _struct_ref_seq.pdbx_db_accession
'1uyd','1uye','1uyf','2byh','2byi', ## remediation _struct_ref_seq_dif
'2xdu','3dn8','3dna','1ps3','1ouf','1l35','2eun','1rtc','1zon', ## _struct_ref_seq_dif missing
'1pwl','1pwm','2fz8','2fz9', ## remediation incorrect _struct_ref.pdbx_seq_one_letter_code
]
set_pdbs.remove('1f92') ## remediation _struct_ref_seq_dif incorrect residue number
set_pdbs.remove('2f6f') ## remediation _pdbx_poly_seq_scheme.auth_mon_id wrong
set_pdbs.remove('3a5j') ## remediation _struct_ref_seq_dif.db_mon_id is ? but should be MET
set_pdbs.remove('2rhx') ## remediation _struct_ref_seq_dif.db_mon_id is ? but should be SER
set_pdbs.remove('2fzb') ## remediation incorrect _struct_ref.pdbx_seq_one_letter_code
set_pdbs.remove('2fzd') ## remediation incorrect _struct_ref.pdbx_seq_one_letter_code
set_pdbs.remove('3dn5') ## remediation incorrect _struct_ref.pdbx_seq_one_letter_code
set_pdbs.remove('1x96') ## remediation incorrect _struct_ref.pdbx_seq_one_letter_code
set_pdbs.remove('1x97') ## remediation incorrect _struct_ref.pdbx_seq_one_letter_code
set_pdbs.remove('1x98') ## remediation incorrect _struct_ref.pdbx_seq_one_letter_code
set_pdbs.remove('1z3n') ## GenBank DBref - not an error...
set_pdbs.remove('1z8a') ## GenBank DBref - not an error...
set_pdbs.remove('1z89') ## GenBank DBref - not an error...
set_pdbs.remove('2pf8') ## stupid use of alt_ids (C for highest occupancy and only altloc)
set_pdbs.remove('2pyr') ## stupid use of alt_ids (G and R)
set_pdbs.remove('3pdn') ## stupid use of alt_ids (B and C)
set_pdbs.remove('2v4c') ## alt_id B used for 100% occupancy atoms
set_pdbs.remove('1jxt') ## weird alt_id microheterogeneity...
set_pdbs.remove('1jxu') ## weird alt_id microheterogeneity...
set_pdbs.remove('1jxw') ## weird alt_id microheterogeneity...
set_pdbs.remove('1jxx') ## weird alt_id microheterogeneity...
set_pdbs.remove('1jxy') ## weird alt_id microheterogeneity...
## set_pdbs.remove('1ac4') ## multiple strains and taxonomy ids but all same organism (S. cerevisiae)...
## set_pdbs.remove('1ac8') ## multiple strains and taxonomy ids but all same organism (S. cerevisiae)...
## set_pdbs.remove('1aeb') ## multiple strains and taxonomy ids but all same organism (S. cerevisiae)...
## set_pdbs.remove('2rbt') ## multiple strains and taxonomy ids but all same organism (S. cerevisiae)... UNP A7A026, TAX 307796, STRAIN YJM789
## set_pdbs.remove('2rbu') ## multiple strains and taxonomy ids but all same organism (S. cerevisiae)... UNP A7A026, TAX 307796, STRAIN YJM789
## set_pdbs.remove('2rbv') ## multiple strains and taxonomy ids but all same organism (S. cerevisiae)... UNP A7A026, TAX 307796, STRAIN YJM789
for pdb in l_pdbs_remove:
set_pdbs.remove(pdb)
fd = open('%s/bc-100.out' %(path_mmCIF),'r')
lines = fd.readlines()
fd.close()
for i_line in range(len(lines)):
cluster = i_line
if cluster < 4816:
continue
## if cluster not in [5,]:
## continue
line = lines[i_line]
l_pdbs = line.lower().split()
l_pdbs.sort()
for i_pdb in range(len(l_pdbs)):
l_pdbs[i_pdb] = l_pdbs[i_pdb][:4]
for i_pdb1 in range(0,len(l_pdbs)-1):
pdb1 = l_pdbs[i_pdb1]
## if pdb1 != '1t49': ## tmp!!!
## continue
if not pdb1 in set_pdbs:
continue
print pdb1
stop
d_mmCIF1 = parse_mmCIF.main(pdb1,)
bool_monomeric = check_monomeric(d_mmCIF1)
if bool_monomeric == False:
if i_pdb1 == 0:
break
else:
continue
bool_remediation_modres = check_modres(d_mmCIF1,pdb1,)
if bool_remediation_modres == True:
continue
if '_struct_ref_seq_dif.details' in d_mmCIF1.keys():
if 'DELETION' in d_mmCIF1['_struct_ref_seq_dif.details']:
continue
for i_entity in range(len(d_mmCIF1['_entity.id'])):
if d_mmCIF1['_entity.type'][i_entity] == 'polymer':
if int(d_mmCIF1['_entity.pdbx_number_of_molecules'][i_entity]) != 1:
print d_mmCIF1['_entity.pdbx_number_of_molecules']
print pdb1, cluster
stop
SG1 = d_mmCIF1['_symmetry.space_group_name_H-M']
for i_pdb2 in range(i_pdb1+1,len(l_pdbs)):
pdb2 = l_pdbs[i_pdb2]
## if pdb2 != '2pf8': ## tmp!!!
## continue
## if pdb1 != '3fui' or pdb2 != '3fuj':
## continue
if not pdb2 in set_pdbs:
continue
d_mmCIF2 = parse_mmCIF.main(pdb2,)
bool_monomeric = check_monomeric(d_mmCIF2)
if bool_monomeric == False:
continue
bool_remediation_modres = check_modres(d_mmCIF2,pdb2,)
if bool_remediation_modres == True:
continue
if '_struct_ref_seq_dif.seq_num' in d_mmCIF2.keys():
if 'DELETION' in d_mmCIF2['_struct_ref_seq_dif.details']:
continue
## biounit monomeric?
for i_entity in range(len(d_mmCIF2['_entity.id'])):
if d_mmCIF2['_entity.type'][i_entity] == 'polymer':
if int(d_mmCIF2['_entity.pdbx_number_of_molecules'][i_entity]) != 1:
continue
SG2 = d_mmCIF2['_symmetry.space_group_name_H-M']
if SG1 != SG2:
continue
## parse coordinates again after being shortened in previous loop
try:
d_coords1, l_coords_alpha1 = mmCIF2coords.main(pdb1, d_mmCIF1)
except:
fd = open('remediation_atom_site.label_alt_id.txt','a')
fd.write('%s\n' %(pdb1,))
fd.close()
try:
d_coords2, l_coords_alpha2 = mmCIF2coords.main(pdb2, d_mmCIF2)
except:
fd = open('remediation_atom_site.label_alt_id.txt','a')
fd.write('%s\n' %(pdb2,))
fd.close()
## align sequences/coordinates
try:
l_coords_alpha1, l_coords_alpha2 = create_apo_holo_dataset.sequential_alignment_of_coordinates(
l_coords_alpha1, l_coords_alpha2,
d_mmCIF1, d_mmCIF2,
pdb1, pdb2,
)
except:
fd = open('remediation_struct_ref_seq_dif.txt','a')
fd.write(
'%s %s %s %s\n' %(
pdb1,pdb2,
d_mmCIF1['_struct_ref_seq.pdbx_db_accession'],
d_mmCIF2['_struct_ref_seq.pdbx_db_accession'],
)
)
fd.close()
continue
if len(l_coords_alpha1) != len(l_coords_alpha2):
print d_mmCIF1['_pdbx_poly_seq_scheme.pdb_mon_id']
print d_mmCIF2['_pdbx_poly_seq_scheme.pdb_mon_id']
print 'coords', len(l_coords_alpha1), len(l_coords_alpha2)
print 'seq', len(d_mmCIF1['_pdbx_poly_seq_scheme.pdb_mon_id'])
print 'seq', len(d_mmCIF2['_pdbx_poly_seq_scheme.pdb_mon_id'])
print pdb1, pdb2
d_coords1, l_coords_alpha1 = mmCIF2coords.main(pdb1, d_mmCIF1)
d_coords1, l_coords_alpha2 = mmCIF2coords.main(pdb1, d_mmCIF2)
print len(l_coords_alpha1), len(l_coords_alpha2)
stop
continue
##
## align structure 1 and 2
##
instance_geometry = geometry.geometry()
rmsd = instance_geometry.superpose(l_coords_alpha1,l_coords_alpha2)
tv1 = instance_geometry.fitcenter
rm = instance_geometry.rotation
tv2 = instance_geometry.refcenter
## structural alignment
for i_coord in range(len(l_coords_alpha2)):
l_coords_alpha2[i_coord] = numpy.dot(l_coords_alpha2[i_coord]-tv1,rm)+tv2
##
## vector from structure 1 to 2
##
vector = []
for i in range(len(l_coords_alpha1)):
vector += [
l_coords_alpha1[i][0]-l_coords_alpha2[i][0],
l_coords_alpha1[i][1]-l_coords_alpha2[i][1],
l_coords_alpha1[i][2]-l_coords_alpha2[i][2],
]
vector = numpy.array(vector)
##
## calculate normal modes of structure 1
##
cutoff = 10
try:
matrix_hessian1 = NMA.hessian_calculation(l_coords_alpha1, cutoff, verbose = False)
eigenvectors1, eigenvalues1 = NMA.diagonalize_hessian(matrix_hessian1, verbose = False)
matrix_hessian2 = NMA.hessian_calculation(l_coords_alpha2, cutoff, verbose = False)
eigenvectors2, eigenvalues2 = NMA.diagonalize_hessian(matrix_hessian2, verbose = False)
except:
continue
##
## calculate overlap between normal modes and difference vector
##
eigenvector1 = eigenvectors1[6]
eigenvector2 = eigenvectors2[6]
overlap1 = calc_overlap(eigenvector1,vector)
overlap2 = calc_overlap(eigenvector2,vector)
overlap3a = calc_overlap(eigenvector1,eigenvector2)
overlap3b = calc_overlap(eigenvectors1[6],eigenvectors2[7])
overlap3c = calc_overlap(eigenvectors1[7],eigenvectors2[6])
overlap3 = max(overlap3a,overlap3b,overlap3c)
fd = open('rmsd_v_overlap2/cluster%i.txt' %(i_line),'a')
fd.write('%s %s\n' %(rmsd,overlap1))
fd.close()
fd = open('rmsd_v_overlap2/cluster%i.txt' %(i_line),'a')
fd.write('%s %s\n' %(rmsd,overlap2))
fd.close()
fd = open('rmsd_v_overlap2/cluster%i_ev_v_ev.txt' %(i_line),'a')
fd.write('%s %s\n' %(rmsd,overlap3a))
fd.close()
fd = open('rmsd_v_overlap2/cluster%i_ev_v_ev_max.txt' %(i_line),'a')
fd.write('%s %s\n' %(rmsd,overlap3))
fd.close()
print pdb1, pdb2, 'cluster', i_line, 'size', len(l_pdbs),
print 'overlap', '%4.2f' %(round(overlap1,2)), '%4.2f' %(round(overlap2,2)), '%4.2f' %(round(overlap3,2)), 'rmsd', '%4.2f' %(round(rmsd,2))
return
def main():
fn_out = 'db_MatthewsCoefficient.txt'
fd = open(fn_out,'r')
lines = fd.readlines()
fd.close()
d = {}
for line in lines:
l = line.strip().split()
pdb = l[0]
v = l[1]
if pdb == '2p51':
v = '1.72610466393'
d[pdb] = v
lines_out = []
path = '/media/WDMyBook1TB/2TB/mmCIF'
l_dns = os.listdir(path)
l_dns.sort()
for i in range(len(l_dns)):
dn = l_dns[i]
if dn < sys.argv[-1]:
continue
if not os.path.isdir('%s/%s' %(path,dn)):
continue
print '%s/%s %s' %(i+1,len(l_dns), dn)
l_fns = os.listdir('%s/%s' %(path,dn))
l_fns.sort()
for fn in l_fns:
if fn[-3:] == '.gz':
continue
pdb = fn[0:4]
if pdb in d.keys():
continue
## Matthews Coefficient not calculated...
if pdb in [
'1vh7','1vho','1vhu','1vi3','1vi4','1vis',
]:
continue
## Matthews Coefficient *wrong*
if pdb in [
'2p51',
## too high
'1c5v','1q9i','1ut6','1x6x','1x6y','1xdn','1y63','1zix',
## too low
'1t95','1jih','1t95','1d5t','1c7k',
'1dbo','1d9x','1qt9','1ia5','1dcq',
]:
continue
fd = open('%s/%s/%s' %(path, dn, fn), 'r')
lines = fd.readlines()
fd.close()
d_mmCIF = parse_mmCIF.main(
pdb,lines,
d_breaks = {
## break if multiple polymer types (not monomeric)
'_entity_poly.entity_id':'2',
## '_exptl.method':'SOLUTION NMR', ## break if e.g. _exptl.method = SOLUTION NMR
## break if multiple chains
'_entity_poly.pdbx_strand_id':',',
},
d_breaks_negation = {
## break if not x-ray diffraction
'_exptl.method':'X-RAY DIFFRACTION',
## break if not monomeric
'_pdbx_struct_assembly.oligomeric_details':'monomeric',
},
l_data_categories = [
'_exptl_crystal',
], ## parse selected data categories
l_data_categories_break = ['_exptl_crystal']
)
## some unknown temporary error... or break before reaching this part when parsing...
if not '_pdbx_struct_assembly.oligomeric_details' in d_mmCIF.keys():
continue
## NMR structure?
if d_mmCIF['_exptl.method'] != ['X-RAY DIFFRACTION']:
stop2
continue
## no polymers in structure?
if not '_entity_poly.entity_id' in d_mmCIF.keys():
continue
## polymer(s) is/are not polypeptide(s)
if d_mmCIF['_entity_poly.type'] != len(d_mmCIF['_entity_poly.type'])*['polypeptide(L)']:
continue
## biounit not monomeric
if d_mmCIF['_pdbx_struct_assembly.oligomeric_details'] != len(d_mmCIF['_pdbx_struct_assembly.oligomeric_details'])*['monomeric']:
continue
## one polymer in assymetric unit
if len(d_mmCIF['_entity_poly.entity_id']) > 1:
continue
if d_mmCIF['_exptl_crystal.density_Matthews'] == ['?']:
v = VM = calc_matthews_coefficient.main(pdb)
## continue
else:
v = float(''.join(d_mmCIF['_exptl_crystal.density_Matthews']))
line = '%s %s\n' %(pdb,v,)
fd = open(fn_out,'a')
fd.write(line)
fd.close()
d[pdb] = v
##
## write calculated radii of gyration to file
##
lines_out = []
for pdb,v in d.items():
line = '%s %s\n' %(pdb,v,)
lines_out += [line]
fd = open(fn_out,'w')
fd.writelines(lines_out)
fd.close()
return
def main():
d_MV = {}
path = '/data/mmCIF'
l_dn = os.listdir(path)
l_dn.sort()
for dn in l_dn:
if dn == 'mmCIF.py':
continue
if dn < sys.argv[-2]:
continue
if dn > sys.argv[-1]:
continue
l_fn = os.listdir('%s/%s' %(path,dn))
for fn in l_fn:
pdb = fn[:4]
## if pdb.upper() not in s_pdbs:
## continue
d_mmCIF = parse_mmCIF.main(
pdb,
d_breaks = {'_exptl.method':'SOLUTION NMR'},
l_data_categories = [
'_cell','_entity','_exptl','_exptl_crystal',
'_entity_poly',
'_symmetry',
## virus
'_pdbx_struct_assembly',
## split structure
'_pdbx_database_related',
],
)
## x-ray structure
if d_mmCIF['_exptl.method'] != ['X-RAY DIFFRACTION']:
continue
## polymer present
if not '_entity_poly.type' in d_mmCIF.keys():
continue
## only polymer present is protein
if d_mmCIF['_entity_poly.type'] != len(d_mmCIF['_entity_poly.type'])*['polypeptide(L)']:
continue
if not '_pdbx_struct_assembly.oligomeric_count' in d_mmCIF.keys():
continue
if d_mmCIF['_pdbx_struct_assembly.oligomeric_count'] == len(d_mmCIF['_pdbx_struct_assembly.oligomeric_count'])*['?']:
continue
## virus
if int(d_mmCIF['_pdbx_struct_assembly.oligomeric_count'][0]) % 60 == 0:
continue
## not monomer
if d_mmCIF['_pdbx_struct_assembly.oligomeric_count'] != len(d_mmCIF['_pdbx_struct_assembly.oligomeric_count'])*['1']:
continue
## split structure
if '_pdbx_database_related' in d_mmCIF.keys():
if 'split' in d_mmCIF['_pdbx_database_related']:
continue
if 'SPLIT' in d_mmCIF['_pdbx_database_related']:
print pdb
stop
if not '_cell.Z_PDB' in d_mmCIF.keys():
continue
if pdb in [
## treshold
'1e54','1e9i',
## difference between calculated MV and MV in mmCIF
'3eiq',
## The crystals diffracted to 1.7Angstrom and appeared to be I centered tetragonal with
## unit cell dimension a=198.42Angstrom and c=396.6Angstrom, however the data only merged successfully in P1
## unit cell a=196.61 b=196.48 c=240.63 alpha=65.91 beta=65.91 gamma=90.01.
## Toscana has published with Hellinga...
'2cjf','2bt4',
]:
continue
## if not ''.join(d_mmCIF['_symmetry.space_group_name_H-M']) in [
## 'P 1','P 43 21 2','P 21 3','P 42 3 2','C 1 2 1','F 2 3','P 64 2 2','H 3',
## ]:
## continue ## tmp!!!
a = float(d_mmCIF['_cell.length_a'][0])
b = float(d_mmCIF['_cell.length_b'][0])
c = float(d_mmCIF['_cell.length_c'][0])
alpha = float(d_mmCIF['_cell.angle_alpha'][0])
beta = float(d_mmCIF['_cell.angle_beta'][0])
gamma = float(d_mmCIF['_cell.angle_gamma'][0])
Z = int(d_mmCIF['_cell.Z_PDB'][0])
mw = 0
for i in range(len(d_mmCIF['_entity.id'])):
## if d_mmCIF['_entity.type'][i] == 'polymer':
s = d_mmCIF['_entity.formula_weight'][i]
## unknown ligand
if s == '?':
continue
mw += float(s)
MV = matthews_coefficient.main(a,b,c,alpha,beta,gamma,mw,Z)
spacegroup = ''.join(d_mmCIF['_symmetry.space_group_name_H-M'])
if spacegroup not in [
'F 4 3 2',
'F 41 3 2',
'I 41 3 2',
]:
continue ## tmp!!!
if MV > 10:
print pdb
print 'mw', mw
print 'MV', MV, d_mmCIF['_exptl_crystal.density_Matthews']
print 'Z', Z
import math
alpha *= math.pi/180.
beta *= math.pi/180.
gamma *= math.pi/180.
V = a*b*c*math.sqrt(1-math.cos(alpha)**2-math.cos(beta)**2-math.cos(gamma)**2+2*(math.cos(alpha)*math.cos(beta)*math.cos(gamma)))
print 'V', V
continue
stop_treshold
stop
if '_exptl_crystal.density_Matthews' in d_mmCIF.keys():
if d_mmCIF['_exptl_crystal.density_Matthews'] not in [['?'],len(d_mmCIF['_exptl_crystal.density_Matthews'])*['?'],]:
if abs(MV-float(d_mmCIF['_exptl_crystal.density_Matthews'][0])) > 1:
print 'MV', MV
print 'MV', d_mmCIF['_exptl_crystal.density_Matthews']
print 'mw', mw
print 'Z', Z
continue
stop_difference
if not spacegroup in d_MV.keys():
d_MV[spacegroup] = []
d_MV[spacegroup] += [MV]
print pdb, round(MV,2), spacegroup
## fd = open('MV_v_spacegroup.txt','w')
## fd.write(str(d_MV))
## fd.close()
l = ['# MV_average MV_stddev n spacegroup\n']
for spacegroup in d_MV.keys():
l_MV = d_MV[spacegroup]
if len(l_MV) <= 1:
continue
average, stddev = statistics.do_stddev(l_MV)
average, stderr = statistics.do_stderr(l_MV)
## l += ['%s %s %s %s\n' %(average,stddev,len(l_MV),spacegroup,)]
l += ['%s %s %s %s\n' %(average,stderr,len(l_MV),spacegroup,)]
fd = open('MV_v_spacegroup.txt','w')
fd.writelines(l)
fd.close()
return
def main():
fd = open('db_authors.txt','r')
lines = fd.readlines()
fd.close()
d_authors = {}
for line in lines:
l = line.strip().split()
pdb = l[0]
s_authors = l[1:]
d_authors[pdb] = s_authors
lines_out = []
path = '/media/WDMyBook1TB/2TB/mmCIF'
l_dns = os.listdir(path)
l_dns.sort()
for i in range(len(l_dns)):
dn = l_dns[i]
if dn < sys.argv[-1]:
continue
if not os.path.isdir('%s/%s' %(path,dn)):
continue
print '%s/%s %s' %(i+1,len(l_dns), dn)
l_fns = os.listdir('%s/%s' %(path,dn))
l_fns.sort()
for fn in l_fns:
if fn[-3:] == '.gz':
continue
pdb = fn[0:4]
if pdb in d_authors.keys():
continue
print pdb
fd = open('%s/%s/%s' %(path, dn, fn), 'r')
lines = fd.readlines()
fd.close()
d_mmCIF = parse_mmCIF.main(
pdb,lines,
l_data_categories = [
'_audit_author',
'_citation_author',
], ## parse selected data categories
l_data_categories_break = [
'_citation_author',
],
)
l_authors = d_mmCIF['_audit_author.name']
s_authors = ';'.join(l_authors)
if d_mmCIF['_audit_author.name'] == []:
print d_mmCIF['_citation_author.name']
print d_mmCIF['_audit_author.name']
stop
line = '%s %s\n' %(pdb,s_authors,)
lines_out += [line]
fd = open('db_authors.txt','a')
fd.write(line)
fd.close()
d_authors[pdb] = s_authors
##
## write to file
##
lines_out = []
for pdb,s_authors in d_authors.items():
line = '%s %s\n' %(pdb,s_authors,)
lines_out += [line]
fd = open('db_authors.txt','w')
fd.writelines(lines_out)
fd.close()
return
def main():
fd = open('remediation_negativeBiso.txt','r')
lines = fd.readlines()
fd.close()
l_pdbs = []
for line in lines:
if line.strip() == '':
continue
if line[0] == '#':
continue
l = line.strip().split()
pdb = l[0]
l_pdbs += [pdb]
path = '/media/WDMyBook1TB/2TB/mmCIF'
l_dns = os.listdir(path)
l_dns.sort()
for i in range(len(l_dns)):
dn = l_dns[i]
if dn < sys.argv[-1]:
continue
if not os.path.isdir('%s/%s' %(path,dn)):
continue
print '%s/%s %s' %(i+1,len(l_dns), dn)
l_fns = os.listdir('%s/%s' %(path,dn))
l_fns.sort()
for fn in l_fns:
if fn[-3:] == '.gz':
continue
pdb = fn[0:4]
if not pdb in l_pdbs:
continue
print pdb
fd = open('%s/%s/%s' %(path, dn, fn), 'r')
lines = fd.readlines()
fd.close()
d_mmCIF = parse_mmCIF.main(
pdb,lines,
d_breaks_negation = {
## break if not x-ray diffraction
'_exptl.method':'X-RAY DIFFRACTION',
},
l_data_categories = [
## parse selected data categories
'_database_PDB_rev',
'_computing',
'_atom_site',
'_refine'
],
)
## ## no polymers in structure?
## if not '_entity_poly.entity_id' in d_mmCIF.keys():
## continue
if d_mmCIF['_exptl.method'] != ['X-RAY DIFFRACTION']:
continue
print pdb
##
## parse bfactors
##
for i_atom_site in range(len(d_mmCIF['_atom_site.id'])):
bfactor = float(d_mmCIF['_atom_site.B_iso_or_equiv'][i_atom_site])
## if bfactor == '?':
## continue
element = d_mmCIF['_atom_site.type_symbol'][i_atom_site]
comp_id = d_mmCIF['_atom_site.label_comp_id'][i_atom_site]
if float(bfactor) < -0.01:
if (
element != 'H'
and
comp_id in ['ALA','CYS','ASP','GLU','PHE','GLY','HIS','ILE','LYS','MET','ASN','PRO','GLN','ARG','SER','THR','VAL','TRP','TYR',]
):
print
print 'negative'
print
year = int(d_mmCIF['_database_PDB_rev.date'][0][:4])
atom_id = int(d_mmCIF['_atom_site.id'][i_atom_site])
refinement = ''.join(d_mmCIF['_computing.structure_refinement'])
solution = ''.join(d_mmCIF['_computing.structure_solution'])
resolution = float(''.join(d_mmCIF['_refine.ls_d_res_high']))
fd = open('remediation_negativeBiso.txt','a')
fd.write(
## '%4s %4i %4i %3s %2s %6.2f %30s %20s\n' %(
'%4s\t%4i\t%4i\t%3s\t%2s\t%6.2f\t%6.2f\t%30s\t%20s\n' %(
pdb,year,atom_id,
comp_id,element,bfactor,resolution,
solution.ljust(30),refinement.ljust(20),
)
)
fd.close()
break
return
def parse_dihedrals():
import sys
path = '/data/mmCIF'
d_phipsi_res = {
'ALA': [],
'CYS': [],
'ASP': [],
'GLU': [],
'PHE': [],
'GLY': [],
'HIS': [],
'ILE': [],
'LYS': [],
'LEU': [],
'MET': [],
'ASN': [],
'PRO': [],
'GLN': [],
'ARG': [],
'SER': [],
'THR': [],
'VAL': [],
'TRP': [],
'TYR': [],
'prePRO': [],
'prePRO_notGLY': [],
'prePRO_GLY': [],
'cisPro': [],
'transPro': [],
'all_notgly_notpro_notprepro': [],
}
d_phipsi_ss = {
'sheet': [], ## _struct_sheet_order.sense
##_struct_conf.pdbx_PDB_helix_class
'helix_alpha': [], ## i+4 # 1
'helix_pi': [], ## i+5 # 3
'helix_310': [], ## i+3 # 5
'Turn': [], ## i+?
##
'turns_notgly_notpro_notprepro': [],
}
d_counts = {
'cisProALA': 0,
'cisProCYS': 0,
'cisProASP': 0,
'cisProGLU': 0,
'cisProPHE': 0,
'cisProGLY': 0,
'cisProHIS': 0,
'cisProILE': 0,
'cisProLYS': 0,
'cisProLEU': 0,
'cisProMET': 0,
'cisProASN': 0,
'cisProPRO': 0,
'cisProGLN': 0,
'cisProARG': 0,
'cisProSER': 0,
'cisProTHR': 0,
'cisProVAL': 0,
'cisProTRP': 0,
'cisProTYR': 0,
'cisPro_helix': 0,
'cisPro_sheet': 0,
'cisPro_turn': 0,
'cisPro_random': 0,
}
l_dn = os.listdir(path)
l_dn.sort()
l_dn.remove('mmCIF.py')
for dn in l_dn:
if dn < sys.argv[-2]:
continue
if dn > sys.argv[-1]:
continue
print '*', dn
l_fn = os.listdir('%s/%s' % (
path,
dn,
))
l_fn.sort()
for fn in l_fn:
pdb = fn[:4]
print pdb
d_mmCIF = parse_mmCIF.main(
pdb,
d_breaks={'_exptl.method': ['SOLUTION NMR']},
l_data_categories=[
'_exptl',
'_refine',
'_struct_conf', ## HELIX
'_struct_sheet_range', ## SHEET
'_entity',
'_entity_poly',
'_entity_poly_seq',
'_atom_site',
],
)
## skip NMR models
if ''.join(d_mmCIF['_exptl.method']) in [
'SOLUTION NMR',
'POWDER DIFFRACTION',
'ELECTRON MICROSCOPY',
]:
continue
if not '_refine.ls_d_res_high' in d_mmCIF.keys():
print d_mmCIF['_exptl.method']
continue
## skip if multiple resolutions
if len(d_mmCIF['_refine.ls_d_res_high']) > 1:
continue
## skip if no resolution
if ''.join(d_mmCIF['_refine.ls_d_res_high']) == '?':
continue
## skip low resolution structures
if float(''.join(d_mmCIF['_refine.ls_d_res_high'])) > 2:
continue
if not 'polymer' in d_mmCIF['_entity.type']:
continue
if not '_entity_poly.type' in d_mmCIF.keys(): ## e.g. 1hhu
continue
if d_mmCIF['_entity_poly.type'] == [
'polydeoxyribonucleotide/polyribonucleotide hybrid'
]:
continue
if d_mmCIF['_entity_poly.type'] == ['polydeoxyribonucleotide']:
continue
d_sequence = {}
for i_entity_poly_seq in range(
len(d_mmCIF['_entity_poly_seq.entity_id'])):
entity_id = int(
d_mmCIF['_entity_poly_seq.entity_id'][i_entity_poly_seq])
if not entity_id in d_sequence.keys():
d_sequence[entity_id] = []
res_no = int(
d_mmCIF['_entity_poly_seq.num'][i_entity_poly_seq])
res_name = d_mmCIF['_entity_poly_seq.mon_id'][
i_entity_poly_seq]
d_sequence[entity_id] += [{
'res_no': res_no,
'res_name': res_name,
}]
l_entities_poly = []
for i_entity_poly in range(len(d_mmCIF['_entity_poly.entity_id'])):
## skip if not polypeptide
entity_poly_type = d_mmCIF['_entity_poly.type'][i_entity_poly]
if entity_poly_type != 'polypeptide(L)':
continue
## skip if nonstd linkages
if d_mmCIF['_entity_poly.nstd_linkage'][
i_entity_poly] == 'yes':
print pdb
stop
continue
## parse entity_id and chains
entity_id = int(
d_mmCIF['_entity_poly.entity_id'][i_entity_poly])
l_entities_poly += [entity_id]
## skip if no polypeptide chains
if l_entities_poly == []:
continue
d_coords = {}
for i_atom_site in range(len(d_mmCIF['_atom_site.id'])):
entity_id = int(
d_mmCIF['_atom_site.label_entity_id'][i_atom_site])
## not a polymer
if not entity_id in l_entities_poly:
continue
## polymer, append
elif not entity_id in d_coords.keys():
d_coords[entity_id] = {}
model = int(
d_mmCIF['_atom_site.pdbx_PDB_model_num'][i_atom_site])
if model > 1:
continue
chain = d_mmCIF['_atom_site.label_asym_id'][i_atom_site]
if not chain in d_coords[entity_id].keys():
d_coords[entity_id][chain] = {}
res_no = int(d_mmCIF['_atom_site.label_seq_id'][i_atom_site])
if not res_no in d_coords[entity_id][chain].keys():
d_coords[entity_id][chain][res_no] = {}
atom_name = d_mmCIF['_atom_site.label_atom_id'][i_atom_site]
altloc = d_mmCIF['_atom_site.label_alt_id'][i_atom_site]
if altloc not in [
'.',
'A',
'1',
]:
continue
## skip if zero occupancy
occupancy = float(d_mmCIF['_atom_site.occupancy'][i_atom_site])
if altloc == '.' and occupancy == 0:
continue
if atom_name in [
'CA',
'C',
'O',
'N',
] and atom_name in d_coords[entity_id][chain][res_no].keys():
print pdb, chain, res_no, atom_name
print d_mmCIF['_atom_site.Cartn_x'][i_atom_site], d_mmCIF[
'_atom_site.Cartn_y'][i_atom_site]
print d_coords[entity_id][chain][res_no][atom_name]
stop
x = float(d_mmCIF['_atom_site.Cartn_x'][i_atom_site])
y = float(d_mmCIF['_atom_site.Cartn_y'][i_atom_site])
z = float(d_mmCIF['_atom_site.Cartn_z'][i_atom_site])
coord = numpy.array([
x,
y,
z,
])
d_coords[entity_id][chain][res_no][atom_name] = coord
d_helices = {}
## helices or turns present?
if '_struct_conf.id' in d_mmCIF.keys():
for i_struct_conf in range(len(d_mmCIF['_struct_conf.id'])):
chain1 = d_mmCIF['_struct_conf.beg_label_asym_id'][
i_struct_conf]
chain2 = d_mmCIF['_struct_conf.end_label_asym_id'][
i_struct_conf]
res_no1 = int(d_mmCIF['_struct_conf.beg_label_seq_id']
[i_struct_conf])
res_no2 = int(d_mmCIF['_struct_conf.end_label_seq_id']
[i_struct_conf])
conf_type_id = d_mmCIF['_struct_conf.conf_type_id'][
i_struct_conf]
if chain1 != chain2:
print chain1, chain2, pdb
stop
if conf_type_id == 'HELX_P':
helix_class = int(
d_mmCIF['_struct_conf.pdbx_PDB_helix_class']
[i_struct_conf])
elif conf_type_id == 'TURN_P':
helix_class = 99
else:
print conf_type_id
print pdb
stop
l_res_nos = range(
res_no1,
res_no2 + 1,
)
if not chain1 in d_helices.keys():
d_helices[chain1] = {}
for res_no in l_res_nos:
d_helices[chain1][res_no] = helix_class
d_sheets = {}
## sheet present?
if '_struct_sheet_range.sheet_id' in d_mmCIF.keys():
for i_struct_sheet_range in range(
len(d_mmCIF['_struct_sheet_range.sheet_id'])):
chain1 = d_mmCIF['_struct_sheet_range.beg_label_asym_id'][
i_struct_sheet_range]
chain2 = d_mmCIF['_struct_sheet_range.end_label_asym_id'][
i_struct_sheet_range]
res_no1 = int(
d_mmCIF['_struct_sheet_range.beg_label_seq_id']
[i_struct_sheet_range])
res_no2 = int(
d_mmCIF['_struct_sheet_range.end_label_seq_id']
[i_struct_sheet_range])
l_res_nos = range(
res_no1,
res_no2 + 1,
)
if chain1 != chain2:
print chain1, chain2, pdb
stop
if not chain1 in d_sheets.keys():
d_sheets[chain1] = []
for res_no in l_res_nos:
d_sheets[chain1] += l_res_nos
for entity_id in l_entities_poly:
for chain in d_coords[entity_id].keys():
## skip if short peptide (e.g. 13gs)
if len(d_sequence[entity_id]) <= 3:
continue
for i_res_no in range(1, len(d_sequence[entity_id]) - 1):
res_no_prev = int(d_sequence[entity_id][i_res_no -
1]['res_no'])
res_no = int(d_sequence[entity_id][i_res_no]['res_no'])
res_no_next = int(d_sequence[entity_id][i_res_no +
1]['res_no'])
res_name = d_sequence[entity_id][i_res_no]['res_name']
if res_name == 'MSE':
res_name = 'MET'
res_name_next = d_sequence[entity_id][i_res_no +
1]['res_name']
## not a standard residue
if not res_name in d_phipsi_res.keys():
continue
## residue not observed
if not res_no_prev in d_coords[entity_id][chain].keys(
):
continue
if not res_no in d_coords[entity_id][chain].keys():
continue
if not res_no_next in d_coords[entity_id][chain].keys(
):
continue
## atom not observed
if not 'C' in d_coords[entity_id][chain][res_no_prev]:
continue
if not 'N' in d_coords[entity_id][chain][res_no]:
continue
if not 'CA' in d_coords[entity_id][chain][res_no]:
continue
if not 'C' in d_coords[entity_id][chain][res_no]:
continue
if not 'N' in d_coords[entity_id][chain][res_no_next]:
continue
C_prev = d_coords[entity_id][chain][res_no_prev]['C']
N = d_coords[entity_id][chain][res_no]['N']
CA = d_coords[entity_id][chain][res_no]['CA']
C = d_coords[entity_id][chain][res_no]['C']
N_next = d_coords[entity_id][chain][res_no_next]['N']
phi = calc_dihedral(
C_prev,
N,
CA,
C,
)
psi = calc_dihedral(
N,
CA,
C,
N_next,
)
if 'CA' in d_coords[entity_id][chain][
res_no_prev].keys():
CA_prev = d_coords[entity_id][chain][res_no_prev][
'CA']
omega = calc_dihedral(
CA_prev,
C_prev,
N,
CA,
)
else:
omega = None
if omega:
if (omega and omega < 150
and omega > -150): ## 12e8, PRO44D
if abs(omega
) > 30: ## 12e8 PRO196D, 1a44 GLU82A
omega = None
## cis
else:
omega = 'cis'
pass
## trans
else:
omega = 'trans'
pass
else:
omega = None
bool_helix = False
if chain in d_helices.keys():
if res_no in d_helices[chain].keys():
bool_helix = True
helix_class = d_helices[chain][res_no]
bool_sheet = False
if chain in d_sheets.keys():
if res_no in d_sheets[chain]:
bool_sheet = True
## if bool_helix == True and bool_sheet == True and helix_class != 99:
## print pdb, chain, res_no, 'sheet and helix'
#### stop
if res_name_next == 'PRO':
d_phipsi_res['prePRO'] += [[
phi,
psi,
]]
if res_name != 'GLY':
d_phipsi_res['prePRO_notGLY'] += [[
phi,
psi,
]]
else:
d_phipsi_res['prePRO_GLY'] += [[
phi,
psi,
]]
else:
d_phipsi_res[res_name] += [[
phi,
psi,
]]
if res_name not in [
'GLY',
'PRO',
]:
d_phipsi_res[
'all_notgly_notpro_notprepro'] += [[
phi,
psi,
]]
elif res_name == 'PRO' and omega:
d_phipsi_res['%sPro' % (omega)] += [[
phi,
psi,
]]
if omega == 'cis':
d_counts['cisPro%s' % (res_name)] += 1
if bool_helix == True:
if helix_class == 1:
d_counts['cisPro_helix'] += 1
elif helix_class == 99:
d_counts['cisPro_turn'] += 99
elif bool_sheet == True:
d_counts['cisPro_sheet'] += 1
else:
d_counts['cisPro_random'] += 1
if bool_helix == True:
## if helix_class not in [1,3,5,99,]:
## print pdb, chain, res_no, helix_class
## print 'unexpected helix class'
#### stop_helix_class
if helix_class == 1:
d_phipsi_ss['helix_alpha'] += [[
phi,
psi,
]]
elif helix_class == 3:
d_phipsi_ss['helix_pi'] += [[
phi,
psi,
]]
elif helix_class == 5:
d_phipsi_ss['helix_310'] += [[
phi,
psi,
]]
elif helix_class == 99:
d_phipsi_ss['Turn'] += [[
phi,
psi,
]]
if (res_name_next != 'PRO'
and res_name not in [
'GLY',
'PRO',
]):
d_phipsi_ss[
'turns_notgly_notpro_notprepro'] += [[
phi,
psi,
]]
if bool_sheet == True:
d_phipsi_ss['sheet'] += [[
phi,
psi,
]]
l = []
for k in d_counts.keys():
count = d_counts[k]
l += ['%s %s\n' % (
k,
count,
)]
fd = open('count.txt', 'w')
fd.writelines(l)
fd.close()
return d_phipsi_res, d_phipsi_ss
def main():
l_pdbs = []
fd = open('Biso_v_resolution.gnuplotdata','r')
lines = fd.readlines()
fd.close()
for line in lines:
l = line.split()
resolution = float(l[1])
Biso = float(l[0])
if resolution > 3.5 and Biso < 10:
print line
if resolution > 2.5 and Biso < 10:
print line
if resolution > 2.0 and Biso < 5:
print line
## if resolution > 1.5 and Biso < 5:
## print line
pdb = l[2]
l_pdbs += [pdb]
Biso_average_prev = 0
l_dn = os.listdir(path)
l_dn.sort()
for dn in l_dn:
if dn < sys.argv[-2]:
continue
if dn > sys.argv[-1]:
continue
if not os.path.isdir('%s/%s' %(path,dn)):
continue
l_fns = os.listdir('%s/%s' %(path,dn))
l_fns.sort()
for fn in l_fns:
if fn[-3:] == '.gz':
continue
pdb = fn[0:4]
if pdb in l_pdbs:
continue
if pdb in [
'3bfn', ## PISA left out chains from biological unit
'2jjg','1qjb', ## _pdbx_struct_assembly missing
]:
continue
##
## parse header
##
d_mmCIF = parse_mmCIF.main(
pdb,
l_data_categories = [
'_pdbx_struct_assembly',
'_entity_poly',
'_citation',
'_pdbx_database_related',
], ## parse selected data categories
d_breaks_negation = {
## break if not x-ray diffraction
'_exptl.method':'X-RAY DIFFRACTION',
}
)
if d_mmCIF['_exptl.method'] != ['X-RAY DIFFRACTION']:
continue
if not 'polypeptide(L)' in d_mmCIF['_entity_poly.type']:
continue
if '_pdbx_database_related.content_type' in d_mmCIF.keys():
if 'split' in d_mmCIF['_pdbx_database_related.content_type']:
continue
try:
if d_mmCIF['_pdbx_struct_assembly.oligomeric_details'] != ['monomeric']:
continue
except:
print pdb
stop
if not '_citation.id' in d_mmCIF.keys():
continue
##
## parse coordinate section
##
d_mmCIF = parse_mmCIF.main(
pdb,
l_data_categories = [
'_database_PDB_rev',
'_refine',
'_refine_hist',
'_atom_site',
'_software',
'_entity','_entity_poly',
'_pdbx_struct_assembly',
'_pdbx_database_status',
], ## parse selected data categories
d_breaks_negation = {
## break if not x-ray diffraction
'_exptl.method':'X-RAY DIFFRACTION',
}
)
if d_mmCIF['_exptl.method'] != ['X-RAY DIFFRACTION']:
continue
if not 'polypeptide(L)' in d_mmCIF['_entity_poly.type']:
continue
if d_mmCIF['_pdbx_struct_assembly.oligomeric_details'] != ['monomeric']:
continue
resolution = float(''.join(d_mmCIF['_refine.ls_d_res_high']))
if (
int(d_mmCIF['_entity.pdbx_number_of_molecules'][0]) != 1
or
len(d_mmCIF['_entity_poly.pdbx_strand_id']) > 1
or
len(''.join(d_mmCIF['_entity_poly.pdbx_strand_id']).split(',')) > 1
or
len(d_mmCIF['_entity_poly.entity_id']) > 1
):
print pdb
print d_mmCIF['_entity.pdbx_number_of_molecules']
print d_mmCIF['_entity_poly.pdbx_strand_id']
stop
entity_poly_id = int(''.join(d_mmCIF['_entity_poly.entity_id']))
for i_entity_poly in range(len(d_mmCIF['_entity_poly.entity_id'])):
entity_poly_id = d_mmCIF['_entity_poly.entity_id'][i_entity_poly]
entity_poly_type = d_mmCIF['_entity_poly.entity_id'][i_entity_poly]
l_Biso = []
for i_atom_site in range(len(d_mmCIF['_atom_site.id'])):
occupancy = float(d_mmCIF['_atom_site.occupancy'][i_atom_site])
if occupancy != 1:
continue
alt_id = d_mmCIF['_atom_site.label_alt_id'][i_atom_site]
if alt_id != '.':
continue
entity_id = d_mmCIF['_atom_site.label_entity_id'][i_atom_site]
if entity_id != entity_poly_id:
continue
comp_id = d_mmCIF['_atom_site.label_comp_id'][i_atom_site]
if not comp_id in ['MSE','ALA','CYS','ASP','GLU','PHE','GLY','HIS','ILE','LYS','LEU','MET','ASN','PRO','GLN','ARG','SER','THR','VAL','TRP','TYR',]:
continue
type_symbol = d_mmCIF['_atom_site.type_symbol'][i_atom_site]
if type_symbol == 'H':
continue
atom_id = d_mmCIF['_atom_site.label_atom_id'][i_atom_site]
if not atom_id in ['N','CA','C',]:
continue
Biso = float(d_mmCIF['_atom_site.B_iso_or_equiv'][i_atom_site])
l_Biso += [Biso]
year = int(d_mmCIF['_database_PDB_rev.date'][0][:4])
site = ''.join(d_mmCIF['_pdbx_database_status.process_site'])
if len(l_Biso) == 0:
continue
## if l_Biso == len(l_Biso)*[l_Biso[0]]:
## print pdb, year, l_Biso[0:3]
## if year >= 2010:
## stop
## continue
Biso_average = sum(l_Biso)/len(l_Biso)
bool_continue = False
for Biso in set(l_Biso):
count = l_Biso.count(Biso)
if count > 20:
if '_software.name' in d_mmCIF.keys():
print pdb, Biso_average, Biso, count, d_mmCIF['_software.name']
s = '%s %6.2f %4i %6.2f %4i %s %s\n' %(
pdb,Biso,count,Biso_average,year,site,
str(d_mmCIF['_software.name']),
)
else:
print pdb, Biso_average, Biso, count
s = '%s %6.2f %4i %6.2f %4i %s\n' %(
pdb,Biso,count,Biso_average, year, site,
)
bool_continue = True
fd = open('remediation_Biso_duplicates.txt','a')
fd.write(s)
fd.close()
break
if bool_continue == True:
continue
## if Biso_average in [2,3,4,5,6,7,8,9,99,90,50,20,25,1,100,10,0]:
if Biso_average in range(0,100+1):
print l_Biso
print Biso_average
print pdb
print year
stop
if '_refine.pdbx_TLS_residual_ADP_flag' in d_mmCIF.keys():
if ''.join(d_mmCIF['_refine.pdbx_TLS_residual_ADP_flag']) in ['UNVERIFIED','LIKELY RESIDUAL',]:
continue
elif ''.join(d_mmCIF['_refine.pdbx_TLS_residual_ADP_flag']) in ['?',]:
pass
else:
print d_mmCIF['_refine.pdbx_TLS_residual_ADP_flag']
print pdb, Biso_average
stop
if round(Biso_average,4) == round(Biso_average_prev,4):
print pdb, Biso_average, Biso_average_prev
stop
print pdb, round(Biso_average,2), resolution
fd = open('Biso_v_resolution.gnuplotdata','a')
fd.write('%s %s %s %s\n' %(Biso_average,resolution,pdb,year,))
fd.close()
plot()
import matthews_coefficient, parse_mmCIF
for pdb in [
'2hhb',
'1hho',
'1hv4',
'3hl9',
'3hlb',
'3hlc',
'3hld',
'3hle',
'3hlf',
'3hlg',
]:
d_mmCIF = parse_mmCIF.main(pdb)
a = float(d_mmCIF['_cell.length_a'][0])
b = float(d_mmCIF['_cell.length_b'][0])
c = float(d_mmCIF['_cell.length_c'][0])
alpha = float(d_mmCIF['_cell.angle_alpha'][0])
beta = float(d_mmCIF['_cell.angle_beta'][0])
gamma = float(d_mmCIF['_cell.angle_gamma'][0])
Z = int(d_mmCIF['_cell.Z_PDB'][0]) ## number of polymers in unit cell
mw = 0
for i in range(len(d_mmCIF['_entity.id'])):
if d_mmCIF['_entity.type'][i] == 'polymer':
mw += float(d_mmCIF['_entity.formula_weight'][i])
MV = matthews_coefficient.main(
a,
b,
dn,
))
l_fn.sort()
for fn in l_fn:
pdb = fn[:4]
if fn[-3:] == '.gz':
continue
######## if pdb in ['2fl9','3gau','3gav','3gaw',]: ## tmp!!!
######## continue
## print pdb
fd = open('%s/%s/%s' % (path, dn, fn), 'r')
lines = fd.readlines()
fd.close()
d = parse_mmCIF.main(
pdb,
lines,
l_data_categories=l_data_categories,
d_breaks=d_breaks,
)
if d_exclude_subset:
bool_continue = False
for item_exclude, l_values_exclude in d_exclude_subset.items():
if not item_exclude in d.keys():
bool_continue = True
fd = open('%s/remediation_%s.txt' % (
path,
item_exclude,
), 'a')
fd.write('%s\n' % (pdb))
fd.close()
continue
def parse_cifs(
l_pdbs,
ref_seq, l_db_codes,
n_mutations_max,
resolution_min,
bool_multiple_entities = False,
):
print 'parse cifs'
n_mutants = 0
l_wts = []
l_wts_cysfree = []
d_mutants = {}
d_mmCIF_main = {}
for pdb in l_pdbs:
if pdb[:4].lower() in d_mmCIF_main.keys():
continue
d_mmCIF = parse_mmCIF.main(pdb[:4].lower(),)
## not an x-ray structure
if d_mmCIF['_exptl.method'] != ['X-RAY DIFFRACTION']:
print pdb, d_mmCIF['_exptl.method']
continue
## more than one type of polymer present
n_entities = len(d_mmCIF['_entity_poly.entity_id'])
if bool_multiple_entities == False:
if n_entities > 1:
print pdb, 'entities', n_entities #, d_mmCIF['_struct.title']
continue
## low resolution
if d_mmCIF['_refine.ls_d_res_high'] != d_mmCIF['_refine_hist.d_res_high']:
print d_mmCIF['_refine.ls_d_res_high']
print d_mmCIF['_refine_hist.d_res_high']
stop
if resolution_min:
## if float(d_mmCIF['_refine.ls_d_res_high'][0]) >= resolution_min:
if float(d_mmCIF['_refine.ls_d_res_high'][0]) > resolution_min:
print pdb, 'resolution', d_mmCIF['_refine.ls_d_res_high']
continue
## get entity ID from chain ID
for i_entity in range(len(d_mmCIF['_entity_poly.entity_id'])):
entity_id = d_mmCIF['_entity_poly.entity_id'][i_entity]
s_chain_ids = d_mmCIF['_entity_poly.pdbx_strand_id'][i_entity]
if pdb[-1] in s_chain_ids:
break
if pdb[-1] not in s_chain_ids:
print pdb
print s_chain_ids
stop
## get sequence from entity ID
seq = []
for i in range(len(d_mmCIF['_entity_poly_seq.entity_id'])):
if d_mmCIF['_entity_poly_seq.entity_id'][i] == entity_id:
mon_id = d_mmCIF['_entity_poly_seq.mon_id'][i]
if pdb[:4] == '1RCM' and i == 126:
if mon_id != 'CYS':
stop
mon_id = 'CCS'
seq += [mon_id]
## wrong chain length
if ref_seq:
if len(seq) != len(ref_seq):
if ''.join(ref_seq) in ''.join(seq):
print ref_seq
print seq
stop
## unobserved atoms not in seqres
elif ''.join(seq) in ''.join(ref_seq):
pass
## last two residues unobserved
elif len(seq) == 162 and pdb in [
'1KS3_A','1KW5_A','1KW7_A','1KY0_A','1KY1_A','1L0J_A','1LOK_A','1LPY_A','1LW9_A','1LWG_A','1LWK_A',
]:
pass
## last two residues unobserved
elif len(seq) == 162 and seq[-1] == 'LYS':
pass
else:
print pdb, 'seqlen', len(seq)
continue
## not from Gallus gallus
## check not necessary, because sequence checked against ref seq
entity_id = d_mmCIF['_entity_poly.entity_id'][i_entity]
db_code = d_mmCIF['_struct_ref.db_code'][d_mmCIF['_struct_ref.entity_id'].index(entity_id)]
if db_code not in l_db_codes:
print pdb, 'uniprot', db_code
continue
## more than 1 mutation?
if n_mutations_max != None:
l_mutations = []
for i_seq in range(len(seq)):
res_id_mmCIF = seq[i_seq]
res_id_uniprot = ref_seq[i_seq]
if res_id_mmCIF != res_id_uniprot:
l_mutations += ['%3s%i%3s' %(res_id_uniprot,i_seq+1,res_id_mmCIF,)]
## if len(l_mutations) == 1:
if len(l_mutations) > n_mutations_max:
print pdb, 'muts', len(l_mutations)
continue
elif len(l_mutations) > 0:
n_mutants += 1
startmodel = parse_mmCIF_item(d_mmCIF,'_refine.pdbx_starting_model',pdb,)
## append to lists and dictionaries
d_mmCIF_main[pdb[:4]] = d_mmCIF
if len(l_mutations) > 0:
if l_mutations == ['CYS54THR', 'CYS97ALA']:
l_wts_cysfree += [pdb]
d_mutants[pdb] = {'mutations':l_mutations,'startmodel':startmodel}
else:
l_wts += [pdb]
## print 'd_mutants', d_mutants
return d_mmCIF_main, l_wts, d_mutants, l_wts_cysfree
'1u3fA',
'1agyA',
'1zioA',
'1pa9A',
'2tpsA',
'2plcA',
'1qk2A',
'1j53A',
'1m21A',
]
cutoff = 10
for pdb in l_pdbs:
pdb = pdb[:4]
d = parse_mmCIF.main(pdb, )
d_coords, l_coords = mmCIF2coords.main(pdb, d, query_chain=pdb[4:])
matrix_hessian = NMA.hessian_calculation(l_coords, cutoff, verbose=False)
eigenvectors, eigenvalues = NMA.diagonalize_hessian(matrix_hessian,
verbose=False)
visualization.vmd_arrows(pdb, l_coords, eigenvectors)
print pdb
stop
'1czfA', '1thgA', '1booA', '1iu4A', '1bqcA', '206lA', '1cdeA', '1snzA',
'1gq8A', '1aqlA', '1ps1A', '1s95A', '1pylA', '1ra2A', '1b6bA', '1pntA',
'1e1aA', '2f9rA', '1v04A', '2nlrA', '1n29A', '1pbgA', '5cpaA', '1agmA',
'1byaA', '1r76A', '1u5uA', '1vidA', '1h4gA', '1akdA', '1fy2A', '1xqdA',
'1d6oA', '1qv0A', '1qjeA', '1fvaA', '1bp2A', '1ah7A', '2pthA', '2engA',
'2acyA', '1qazA', '2a0nA', '1dl2A', '1gp5A', '1onrA', '1cwyA', '1pudA',
'1bs9A', '1dinA', '1xyzA', '1bwlA', '1eugA', '1idjA', '1g24A', '1oygA',
'1hzfA', '9papA', '1eb6A', '1ghsA', '1rbnA', '1bixA', '1bs4A', '1celA',
'1hkaA', '1b02A', '1qibA', '1u3fA', '1agyA', '1zioA', '1pa9A', '2tpsA',
'2plcA', '1qk2A', '1j53A', '1m21A',
]
cutoff = 10
for pdb in l_pdbs:
pdb = pdb[:4]
d = parse_mmCIF.main(pdb,)
d_coords, l_coords = mmCIF2coords.main(pdb, d, query_chain = pdb[4:])
matrix_hessian = NMA.hessian_calculation(l_coords, cutoff, verbose = False)
eigenvectors, eigenvalues = NMA.diagonalize_hessian(matrix_hessian, verbose = False)
visualization.vmd_arrows(pdb, l_coords, eigenvectors)
print pdb
stop
def unobs_nonterminal_atoms_alpha():
## this method is not entirely correct... e.g. 1kwr...
category = fn = '_pdbx_unobs_or_zero_occ_atoms'
fd = open('%s/list%s.txt' %(path,fn))
s = fd.read()
fd.close()
l_pdbs_include = s.split()
## if a whole residue is missing, then all of it's atoms are also missing
fd = open('%s/list_pdbx_unobs_residues__NONTERMINAL.txt' %(path))
s = fd.read()
fd.close()
l_pdbs_exclude = s.split()
l_data_categories = [
'_pdbx_poly_seq_scheme',
'_pdbx_unobs_or_zero_occ_atoms',
'_entity_poly',
'_struct', ## .pdbx_model_type_details
'_exptl',
]
d_breaks = {'_exptl.method':['SOLUTION NMR','SOLID-STATE NMR']}
fn_out = 'list_pdbx_unobs_atoms__CA.txt'
l_pdbs_out = []
for pdb in l_pdbs_include:
## if pdb[1:3] < 'fe':
## continue
## if pdb == '2kzt': ## takes too long...
## continue
if pdb != '3e3d':
continue
if pdb in l_pdbs_exclude:
continue
print pdb
d = parse_mmCIF.main(pdb,l_data_categories=l_data_categories,d_breaks=d_breaks,)
## something has to be missing in the first place for it to be terminal/nonterminal
if not category in d.keys():
continue
## it has to be a polymer in the first place for anything to be terminal/nonterminal
if not '_pdbx_poly_seq_scheme' in d.keys():
continue
## don't deal with NMR models for now... (too many unobs records when hydrogen...)
if d['_exptl.method'] != ['X-RAY DIFFRACTION']:
continue
if '_struct.pdbx_model_type_details' in d.keys():
if d['_struct.pdbx_model_type_details'] in [
['?'],
['minimized average'],
['MINIMIZED AVERAGE'],
]:
pass
## if residues are not missing, and model is CA only, then no CA are missing!!!
elif 'CA ATOMS ONLY' in d['_struct.pdbx_model_type_details'][0]:
continue
else:
print d['_struct.pdbx_model_type_details']
stop
## if not 'CA' in d['_pdbx_unobs_or_zero_occ_atoms.auth_atom_id']:
## continue
bool_append = False
for i_unobs in range(len(d['_pdbx_unobs_or_zero_occ_atoms'])):
if (
d['_pdbx_unobs_or_zero_occ_atoms.auth_atom_id'][i_unobs] == 'CA'
and
d['_pdbx_unobs_or_zero_occ_atoms.polymer_flag'][i_unobs] == 'Y'
and
## unobs (1), zero_occ (0)
d['_pdbx_unobs_or_zero_occ_atoms.occupancy_flag'][i_unobs] == '1'
):
l_pdbs_out += [pdb]
print '***', pdb
break
continue
print l_pdbs_out
stop
fd = open('%s/%s' %(path,fn_out,),'w')
fd.write('\n'.join(l_pdbs_out))
fd.close()
for x in []:
l_indexes_unobs = []
bool_append = False
s = ''.join(d['_pdbx_poly_seq_scheme.pdb_strand_id'])
for i_unobs in range(len(d['_pdbx_unobs_or_zero_occ_atoms'])):
## skip if not alpha carbon
if d['_pdbx_unobs_or_zero_occ_atoms.auth_atom_id'][i_unobs] != 'CA':
continue
## skip if zero occupancy
if d['_pdbx_unobs_or_zero_occ_atoms.occupancy_flag'][i_unobs] == '0':
continue
if 'HA' in d['_pdbx_unobs_or_zero_occ_atoms.auth_atom_id']:
print pdb
print len(d['_pdbx_unobs_or_zero_occ_atoms.auth_seq_id'])
stop2
if d['_pdbx_unobs_or_zero_occ_atoms.polymer_flag'].count('Y') > 800:
print pdb
print len(d['_pdbx_unobs_or_zero_occ_atoms.auth_seq_id'])
stop1
asymID_unobs = d['_pdbx_unobs_or_zero_occ_atoms.auth_asym_id'][i_unobs]
seqID_unobs = d['_pdbx_unobs_or_zero_occ_atoms.auth_seq_id'][i_unobs]
index1 = s.index(asymID_unobs)
index2 = s.rindex(asymID_unobs)+1
for i_poly in range(index1,index2,):
asymID_poly = d['_pdbx_poly_seq_scheme.pdb_strand_id'][i_poly]
seqID_poly = d['_pdbx_poly_seq_scheme.auth_seq_num'][i_poly]
if seqID_poly == seqID_unobs:
if d['_pdbx_poly_seq_scheme.pdb_ins_code'][i_poly] == '.' and d['_pdbx_unobs_or_zero_occ_atoms.PDB_ins_code'][i_unobs] == '?':
pass
elif d['_pdbx_poly_seq_scheme.pdb_ins_code'][i_poly] == d['_pdbx_unobs_or_zero_occ_atoms.PDB_ins_code'][i_unobs]:
pass
elif d['_pdbx_unobs_or_zero_occ_atoms.PDB_ins_code'][i_unobs] == '?' and d['_pdbx_poly_seq_scheme.pdb_ins_code'][i_poly] != '.':
continue
elif not d['_pdbx_unobs_or_zero_occ_atoms.PDB_ins_code'][i_unobs] in d['_pdbx_poly_seq_scheme.pdb_ins_code']:
print d['_pdbx_poly_seq_scheme.pdb_ins_code'][i_poly]
print insCode_unobs
print pdb
print seqID_unobs, asymID_unobs
stop
else:
continue
if asymID_unobs != asymID_poly:
stop_add_with_check_of_identiiical_seqID
## tmp!!! check!!!
if d['_pdbx_unobs_or_zero_occ_atoms.auth_comp_id'][i_unobs] != d['_pdbx_poly_seq_scheme.pdb_mon_id'][i_poly]:
print pdb
stop
## ## last residue
## if index2-i_poly == 0:
## pass ## should append...
## ## first residue
## elif i_poly-index1 == 0:
## pass ## should append...
#### elif i_poly-index1 > 1 and bool_unobs_prev == False:
#### bool_append = True
## previous residues are missing
elif d['_pdbx_poly_seq_scheme.auth_seq_num'][index1:i_poly] == (i_poly-index1)*['?']:
bool_append = True
## next residues are missing
elif d['_pdbx_poly_seq_scheme.auth_seq_num'][i_poly+1:index2] == (index2-i_poly-1)*['?']:
bool_append = True
## zero occupancy residue prior to residue with unobserved atom(s)
elif pdb in ['7adh']:
bool_append = False
pass
else:
if len( set(range(index1,i_poly)) - set(l_indexes_unobs) ) == 0:
l_indexes_unobs += [i_poly]
stop1
pass
elif len( set(range(i_poly+1,index2)) - set(l_indexes_unobs) ) == 0:
l_indexes_unobs += [i_poly]
print pdb
print l_indexes_unobs
print i_poly, index1, index2
stop2
pass
else:
## this method is not entirely correct... e.g. 1kwr...
if i_poly-index1 < 10 or index2-i_poly < 10:
print pdb
print i_poly-index1
## print index2-i_poly
print seqID_unobs
print pdb
print d['_pdbx_poly_seq_scheme.auth_seq_num'][index1:i_poly]
print d['_pdbx_poly_seq_scheme.auth_seq_num'][i_poly:index2]
print pdb
## stop
bool_append = True
break
if bool_append == True:
break
if bool_append == True:
print pdb
l_pdbs_out += [pdb]
continue
if l_indexes_unobs != []:
print l_indexes_unobs
stop
fd = open('%s/%s' %(path,fn_out,),'w')
fd.write('\n'.join(l_pdbs_out))
fd.close()
return
def main():
l_fn_out = [
'_exptl_crystal_grow',
'_exptl_crystal_grow_comp',
]
d = {}
for fn_out in l_fn_out:
fd = open('db%s.txt' %(fn_out),'r')
lines = fd.readlines()
fd.close()
d[fn_out] = {}
for line in lines:
if line == '\n':
continue
pdb = line[:4]
s = line[5:]
d[fn_out][pdb] = s
fd = open('remediation_exptl_crystal_grow.pH.txt','r')
lines = fd.readlines()
fd.close()
l_pdbs = [line[:4] for line in lines]
path = '/media/WDMyBook1TB/2TB/mmCIF'
l_dns = os.listdir(path)
l_dns.sort()
for i in range(len(l_dns)):
dn = l_dns[i]
if dn < sys.argv[-1]:
continue
if not os.path.isdir('%s/%s' %(path,dn)):
continue
print '%s/%s %s' %(i+1,len(l_dns), dn)
l_fns = os.listdir('%s/%s' %(path,dn))
l_fns.sort()
for fn in l_fns:
if fn[-3:] == '.gz':
continue
pdb = fn[0:4]
## continue if already in txt file from previous attempt to run loop
## if pdb in d['_exptl_crystal_grow_comp'].keys():
## continue
## if pdb in d['_exptl_crystal_grow'].keys():
## continue
## print pdb
if not pdb in l_pdbs:
continue
fd = open('%s/%s/%s' %(path, dn, fn), 'r')
lines = fd.readlines()
fd.close()
d_mmCIF = parse_mmCIF.main(
pdb,lines,
d_breaks_negation = {
## break if not x-ray diffraction
'_exptl.method':'X-RAY DIFFRACTION',
},
l_data_categories_break = [
## '_atom',
'_diffrn',
],
l_data_categories = [
## parse selected data categories
'_database_PDB_rev',
'_pdbx_database_status',
'_exptl',
'_exptl_crystal_grow',
'_exptl_crystal_grow_comp',
],
)
## ## no polymers in structure?
## if not '_entity_poly.entity_id' in d_mmCIF.keys():
## continue
if d_mmCIF['_exptl.method'] != ['X-RAY DIFFRACTION']:
continue
## print pdb
##
##
##
year = int(d_mmCIF['_database_PDB_rev.date'][0][:4])
process_site = ''.join(d_mmCIF['_pdbx_database_status.process_site'])
if (
not '_exptl_crystal_grow.pdbx_details' in d_mmCIF.keys()
and
not '_exptl_crystal_grow_comp.name' in d_mmCIF.keys()
## ''.join(d_mmCIF['_exptl_crystal_grow.pdbx_details']).strip() == '?'
):
if process_site != '?':
print pdb, year, process_site
continue
##
if '_exptl_crystal_grow.pdbx_details' in d_mmCIF.keys():
s_grow = ' '.join(d_mmCIF['_exptl_crystal_grow.pdbx_details']).strip()
if (
## pH not given
d_mmCIF['_exptl_crystal_grow.pH'] in [['?'],[''],['.'],]
and
d_mmCIF['_exptl_crystal_grow.pdbx_pH_range'] in [['?'],[''],['.'],]
and
## but pH in growth details
(
' PH ' in s_grow.upper()
or
'PH=' in s_grow.upper()
or
',PH ' in s_grow.upper()
)
):
fd = open('remediation_exptl_crystal_grow.pH.txt','a')
fd.write('%s\t%s\t%s\t%4i\t%s\t%s\n' %(
pdb,
''.join(d_mmCIF['_exptl_crystal_grow.pH']),
''.join(d_mmCIF['_exptl_crystal_grow.pdbx_pH_range']),
year,
process_site,
s_grow,
)
)
fd.close()
if (
not '_exptl_crystal_grow_comp.name' in d_mmCIF.keys()
or
''.join(d_mmCIF['_exptl_crystal_grow_comp.name']) in ['.','','?',]
):
if '_exptl_crystal_grow_comp.name' in d_mmCIF.keys():
name = ''.join(d_mmCIF['_exptl_crystal_grow_comp.name'])
else:
name = 'N/A'
## ## remove end punctuation
## s = s_grow[:-1]+s_grow[-1].replace('.','')
## split
## l_grow_punctuation = s_grow.upper().split('. ')
## l_grow = l_grow_comma = [s_grow.upper().split(',') for s in l_grow_punctuation]
l_grow = s_grow.upper().split(',')
## strip space
l_grow = [x.strip() for x in l_grow]
## remove empty
if '' in l_grow:
l_grow.remove('')
## remove end punctuation
l_grow = [x[:-1]+x[-1].replace('.','') for x in l_grow]
## remove selected words from elements of list
for x in [
'CRYSTALS OBTAINED BY CO-CRYSTALLIZATION AT ',
'PROTEIN SOLUTION (',
]:
for i_grow in range(len(l_grow)):
l_grow[i_grow] = l_grow[i_grow].replace(x,'')
## replace abbreviations
for i_grow in range(len(l_grow)):
l_grow[i_grow] = l_grow[i_grow].replace('MILLIMOLAR','MM')
## remove selected words from list
l_remove = []
for x in [
'VAPOR DIFFUSION',
'VAPOUR DIFFUSION',
'HANGING DROP',
'SITTING DROP',
]:
if x in l_grow:
l_remove += [x]
## removed other selected words from list
for i_grow in range(len(list(l_grow))):
## remove physical conditions
bool_continue = False
for x in [
'TEMPERATURE',
'PH=',
'PH ',
'AT PH ',
]:
if l_grow[i_grow][:len(x)] == x:
l_remove += [l_grow[i_grow]]
bool_continue = True
break
if bool_continue == True:
continue
## remove long words (sentences)
if len(l_grow[i_grow]) > 50:
l_remove += [l_grow[i_grow]]
break
for remove in l_remove:
l_grow.remove(remove)
if len(l_grow) > 0:
## write to file
line = '%s\t%s\t%s\t%4i\t%s\t%s\n' %(
pdb,
name,
l_grow,
year,
process_site,
s_grow,
)
fd = open('remediation_exptl_crystal_grow_comp.name.txt','a')
fd.write(line)
fd.close()
else:
s_grow = ''
##
if '_exptl_crystal_grow_comp.name' in d_mmCIF.keys():
l_grow_comp = d_mmCIF['_exptl_crystal_grow_comp.name']
else:
l_grow_comp = []
## lines_out += [line]
## append to txt file in case loop doesn't finish
d_lines = {}
line = '%s %s\n' %(pdb,s_grow,)
d_lines['_exptl_crystal_grow'] = line
line = '%s %s\n' %(pdb,l_grow_comp,)
d_lines['_exptl_crystal_grow_comp'] = line
for fn_out in l_fn_out:
fd = open('db%s.txt' %(fn_out),'a')
fd.write(d_lines[fn_out])
fd.close()
## append to dic for when loop finishes
d['_exptl_crystal_grow'][pdb] = s_grow
d['_exptl_crystal_grow_comp'][pdb] = l_grow_comp
lines_out = []
for pdb,s in d.items():
line = '%s %s\n' %(pdb,s,)
lines_out += [line]
fd = open(fn_out,'w')
fd.writelines(lines_out)
fd.close()
return
import sys
sys.path.append('/home/tc/svn/tc_sandbox/pdb')
import parse_mmCIF, mmCIF2coords
sys.path.append('/home/tc/svn/GoodVibes')
import NMA, visualization
d_mmCIF = parse_mmCIF.main('2lzm', )
d_coords, l_coords_alpha = mmCIF2coords.main('2lzm', d_mmCIF)
cutoff = 10
matrix_hessian = NMA.hessian_calculation(l_coords_alpha, cutoff)
eigenvectors, eigenvalues = NMA.diagonalize_hessian(matrix_hessian, )
visualization.vmd_trajectory('2lzm', l_coords_alpha, eigenvectors)
def main():
fd = open('db_authors.txt', 'r')
lines = fd.readlines()
fd.close()
d_authors = {}
for line in lines:
l = line.strip().split()
pdb = l[0]
s_authors = l[1:]
d_authors[pdb] = s_authors
lines_out = []
path = '/media/WDMyBook1TB/2TB/mmCIF'
l_dns = os.listdir(path)
l_dns.sort()
for i in range(len(l_dns)):
dn = l_dns[i]
if dn < sys.argv[-1]:
continue
if not os.path.isdir('%s/%s' % (path, dn)):
continue
print '%s/%s %s' % (i + 1, len(l_dns), dn)
l_fns = os.listdir('%s/%s' % (path, dn))
l_fns.sort()
for fn in l_fns:
if fn[-3:] == '.gz':
continue
pdb = fn[0:4]
if pdb in d_authors.keys():
continue
print pdb
fd = open('%s/%s/%s' % (path, dn, fn), 'r')
lines = fd.readlines()
fd.close()
d_mmCIF = parse_mmCIF.main(
pdb,
lines,
l_data_categories=[
'_audit_author',
'_citation_author',
], ## parse selected data categories
l_data_categories_break=[
'_citation_author',
],
)
l_authors = d_mmCIF['_audit_author.name']
s_authors = ';'.join(l_authors)
if d_mmCIF['_audit_author.name'] == []:
print d_mmCIF['_citation_author.name']
print d_mmCIF['_audit_author.name']
stop
line = '%s %s\n' % (
pdb,
s_authors,
)
lines_out += [line]
fd = open('db_authors.txt', 'a')
fd.write(line)
fd.close()
d_authors[pdb] = s_authors
##
## write to file
##
lines_out = []
for pdb, s_authors in d_authors.items():
line = '%s %s\n' % (
pdb,
s_authors,
)
lines_out += [line]
fd = open('db_authors.txt', 'w')
fd.writelines(lines_out)
fd.close()
return
for i_line in range(len(lines)):
if i_line % 100 == 0:
d_coordinates = {}
line = lines[i_line]
l = line.split()
pdb1 = l[0]
pdb2 = l[1]
chain1 = l[4]
chain2 = l[5]
for pdb,chain in [[pdb1,chain1,],[pdb2,chain2,],]:
if pdb in d_coordinates.keys():
continue
d_mmCIF = parse_mmCIF.main(pdb)
if d_mmCIF['_pdbx_poly_seq_scheme.pdb_seq_num'] != d_mmCIF['_pdbx_poly_seq_scheme.author_seq_num']:
print d_mmCIF['_pdbx_poly_seq_scheme.pdb_seq_num']
print d_mmCIF['_pdbx_poly_seq_scheme.author_seq_num']
stop
d_coords = {}
d_ndb_seq_num = {}
for i_seq in range(len(d_mmCIF['_pdbx_poly_seq_scheme.ndb_seq_num'])):
if d_mmCIF['_pdbx_poly_seq_scheme.pdb_strand_id'][i_seq] != chain:
continue
ndb_seq_num = d_mmCIF['_pdbx_poly_seq_scheme.ndb_seq_num'][i_seq]
pdb_seq_num = d_mmCIF['_pdbx_poly_seq_scheme.pdb_seq_num'][i_seq]
d_ndb_seq_num[pdb_seq_num] = ndb_seq_num
def unobs_nonterminal_atoms_alpha():
## this method is not entirely correct... e.g. 1kwr...
category = fn = '_pdbx_unobs_or_zero_occ_atoms'
fd = open('%s/list%s.txt' % (path, fn))
s = fd.read()
fd.close()
l_pdbs_include = s.split()
## if a whole residue is missing, then all of it's atoms are also missing
fd = open('%s/list_pdbx_unobs_residues__NONTERMINAL.txt' % (path))
s = fd.read()
fd.close()
l_pdbs_exclude = s.split()
l_data_categories = [
'_pdbx_poly_seq_scheme',
'_pdbx_unobs_or_zero_occ_atoms',
'_entity_poly',
'_struct', ## .pdbx_model_type_details
'_exptl',
]
d_breaks = {'_exptl.method': ['SOLUTION NMR', 'SOLID-STATE NMR']}
fn_out = 'list_pdbx_unobs_atoms__CA.txt'
l_pdbs_out = []
for pdb in l_pdbs_include:
## if pdb[1:3] < 'fe':
## continue
## if pdb == '2kzt': ## takes too long...
## continue
if pdb != '3e3d':
continue
if pdb in l_pdbs_exclude:
continue
print pdb
d = parse_mmCIF.main(
pdb,
l_data_categories=l_data_categories,
d_breaks=d_breaks,
)
## something has to be missing in the first place for it to be terminal/nonterminal
if not category in d.keys():
continue
## it has to be a polymer in the first place for anything to be terminal/nonterminal
if not '_pdbx_poly_seq_scheme' in d.keys():
continue
## don't deal with NMR models for now... (too many unobs records when hydrogen...)
if d['_exptl.method'] != ['X-RAY DIFFRACTION']:
continue
if '_struct.pdbx_model_type_details' in d.keys():
if d['_struct.pdbx_model_type_details'] in [
['?'],
['minimized average'],
['MINIMIZED AVERAGE'],
]:
pass
## if residues are not missing, and model is CA only, then no CA are missing!!!
elif 'CA ATOMS ONLY' in d['_struct.pdbx_model_type_details'][0]:
continue
else:
print d['_struct.pdbx_model_type_details']
stop
## if not 'CA' in d['_pdbx_unobs_or_zero_occ_atoms.auth_atom_id']:
## continue
bool_append = False
for i_unobs in range(len(d['_pdbx_unobs_or_zero_occ_atoms'])):
if (d['_pdbx_unobs_or_zero_occ_atoms.auth_atom_id'][i_unobs]
== 'CA' and
d['_pdbx_unobs_or_zero_occ_atoms.polymer_flag'][i_unobs]
== 'Y' and
## unobs (1), zero_occ (0)
d['_pdbx_unobs_or_zero_occ_atoms.occupancy_flag'][i_unobs]
== '1'):
l_pdbs_out += [pdb]
print '***', pdb
break
continue
print l_pdbs_out
stop
fd = open('%s/%s' % (
path,
fn_out,
), 'w')
fd.write('\n'.join(l_pdbs_out))
fd.close()
for x in []:
l_indexes_unobs = []
bool_append = False
s = ''.join(d['_pdbx_poly_seq_scheme.pdb_strand_id'])
for i_unobs in range(len(d['_pdbx_unobs_or_zero_occ_atoms'])):
## skip if not alpha carbon
if d['_pdbx_unobs_or_zero_occ_atoms.auth_atom_id'][i_unobs] != 'CA':
continue
## skip if zero occupancy
if d['_pdbx_unobs_or_zero_occ_atoms.occupancy_flag'][
i_unobs] == '0':
continue
if 'HA' in d['_pdbx_unobs_or_zero_occ_atoms.auth_atom_id']:
print pdb
print len(d['_pdbx_unobs_or_zero_occ_atoms.auth_seq_id'])
stop2
if d['_pdbx_unobs_or_zero_occ_atoms.polymer_flag'].count(
'Y') > 800:
print pdb
print len(d['_pdbx_unobs_or_zero_occ_atoms.auth_seq_id'])
stop1
asymID_unobs = d['_pdbx_unobs_or_zero_occ_atoms.auth_asym_id'][
i_unobs]
seqID_unobs = d['_pdbx_unobs_or_zero_occ_atoms.auth_seq_id'][
i_unobs]
index1 = s.index(asymID_unobs)
index2 = s.rindex(asymID_unobs) + 1
for i_poly in range(
index1,
index2,
):
asymID_poly = d['_pdbx_poly_seq_scheme.pdb_strand_id'][i_poly]
seqID_poly = d['_pdbx_poly_seq_scheme.auth_seq_num'][i_poly]
if seqID_poly == seqID_unobs:
if d['_pdbx_poly_seq_scheme.pdb_ins_code'][
i_poly] == '.' and d[
'_pdbx_unobs_or_zero_occ_atoms.PDB_ins_code'][
i_unobs] == '?':
pass
elif d['_pdbx_poly_seq_scheme.pdb_ins_code'][i_poly] == d[
'_pdbx_unobs_or_zero_occ_atoms.PDB_ins_code'][
i_unobs]:
pass
elif d['_pdbx_unobs_or_zero_occ_atoms.PDB_ins_code'][
i_unobs] == '?' and d[
'_pdbx_poly_seq_scheme.pdb_ins_code'][
i_poly] != '.':
continue
elif not d['_pdbx_unobs_or_zero_occ_atoms.PDB_ins_code'][
i_unobs] in d['_pdbx_poly_seq_scheme.pdb_ins_code']:
print d['_pdbx_poly_seq_scheme.pdb_ins_code'][i_poly]
print insCode_unobs
print pdb
print seqID_unobs, asymID_unobs
stop
else:
continue
if asymID_unobs != asymID_poly:
stop_add_with_check_of_identiiical_seqID
## tmp!!! check!!!
if d['_pdbx_unobs_or_zero_occ_atoms.auth_comp_id'][
i_unobs] != d['_pdbx_poly_seq_scheme.pdb_mon_id'][
i_poly]:
print pdb
stop
## ## last residue
## if index2-i_poly == 0:
## pass ## should append...
## ## first residue
## elif i_poly-index1 == 0:
## pass ## should append...
#### elif i_poly-index1 > 1 and bool_unobs_prev == False:
#### bool_append = True
## previous residues are missing
elif d['_pdbx_poly_seq_scheme.auth_seq_num'][
index1:i_poly] == (i_poly - index1) * ['?']:
bool_append = True
## next residues are missing
elif d['_pdbx_poly_seq_scheme.auth_seq_num'][
i_poly +
1:index2] == (index2 - i_poly - 1) * ['?']:
bool_append = True
## zero occupancy residue prior to residue with unobserved atom(s)
elif pdb in ['7adh']:
bool_append = False
pass
else:
if len(
set(range(index1, i_poly)) -
set(l_indexes_unobs)) == 0:
l_indexes_unobs += [i_poly]
stop1
pass
elif len(
set(range(i_poly + 1, index2)) -
set(l_indexes_unobs)) == 0:
l_indexes_unobs += [i_poly]
print pdb
print l_indexes_unobs
print i_poly, index1, index2
stop2
pass
else:
## this method is not entirely correct... e.g. 1kwr...
if i_poly - index1 < 10 or index2 - i_poly < 10:
print pdb
print i_poly - index1
## print index2-i_poly
print seqID_unobs
print pdb
print d['_pdbx_poly_seq_scheme.auth_seq_num'][
index1:i_poly]
print d['_pdbx_poly_seq_scheme.auth_seq_num'][
i_poly:index2]
print pdb
## stop
bool_append = True
break
if bool_append == True:
break
if bool_append == True:
print pdb
l_pdbs_out += [pdb]
continue
if l_indexes_unobs != []:
print l_indexes_unobs
stop
fd = open('%s/%s' % (
path,
fn_out,
), 'w')
fd.write('\n'.join(l_pdbs_out))
fd.close()
return
import sys
sys.path.append('/home/tc/svn/tc_sandbox/pdb')
import parse_mmCIF, mmCIF2coords
sys.path.append('/home/tc/svn/GoodVibes')
import NMA, visualization
d_mmCIF = parse_mmCIF.main('2lzm',)
d_coords, l_coords_alpha = mmCIF2coords.main('2lzm',d_mmCIF)
cutoff = 10
matrix_hessian = NMA.hessian_calculation(l_coords_alpha, cutoff)
eigenvectors, eigenvalues = NMA.diagonalize_hessian(matrix_hessian,)
visualization.vmd_trajectory('2lzm',l_coords_alpha,eigenvectors)
def parse_coords(pdb):
d_mmCIF = parse_mmCIF.main(pdb,)
d_coords, l_coords_alpha = mmCIF2coords.main(pdb,d_mmCIF)
return d_mmCIF, l_coords_alpha
def main():
fd = open('radius_of_gyration.txt', 'r')
lines = fd.readlines()
fd.close()
d_radii = {}
for line in lines:
l = line.strip().split()
pdb = l[0]
r = l[1]
d_radii[pdb] = r
lines_out = []
path = '/media/WDMyBook1TB/2TB/mmCIF'
l_dns = os.listdir(path)
l_dns.sort()
for i in range(len(l_dns)):
dn = l_dns[i]
if dn < sys.argv[-1]:
continue
if not os.path.isdir('%s/%s' % (path, dn)):
continue
print '%s/%s %s' % (i + 1, len(l_dns), dn)
l_fns = os.listdir('%s/%s' % (path, dn))
l_fns.sort()
for fn in l_fns:
if fn[-3:] == '.gz':
continue
pdb = fn[0:4]
if pdb in d_radii.keys():
continue
print pdb
fd = open('%s/%s/%s' % (path, dn, fn), 'r')
lines = fd.readlines()
fd.close()
d_mmCIF = parse_mmCIF.main(
pdb,
lines,
d_breaks={
## break if multiple polymer types (not monomeric)
'_entity_poly.entity_id': '2',
## '_exptl.method':'SOLUTION NMR', ## break if e.g. _exptl.method = SOLUTION NMR
## break if multiple chains
'_entity_poly.pdbx_strand_id': ',',
},
d_breaks_negation={
## break if not x-ray diffraction
'_exptl.method': 'X-RAY DIFFRACTION',
## break if not monomeric
'_pdbx_struct_assembly.oligomeric_details': 'monomeric',
},
l_data_categories=[
'_atom_site',
'_entity_poly',
'_pdbx_struct_assembly',
], ## parse selected data categories
)
## some unknown temporary error... or break before reaching this part when parsing...
if not '_pdbx_struct_assembly.oligomeric_details' in d_mmCIF.keys(
):
continue
## NMR structure?
if d_mmCIF['_exptl.method'] != ['X-RAY DIFFRACTION']:
stop2
continue
## no polymers in structure?
if not '_entity_poly.entity_id' in d_mmCIF.keys():
continue
## polymer(s) is/are not polypeptide(s)
if d_mmCIF['_entity_poly.type'] != len(
d_mmCIF['_entity_poly.type']) * ['polypeptide(L)']:
continue
## biounit not monomeric
if d_mmCIF['_pdbx_struct_assembly.oligomeric_details'] != len(
d_mmCIF['_pdbx_struct_assembly.oligomeric_details']) * [
'monomeric'
]:
continue
## one polymer in assymetric unit
if len(d_mmCIF['_entity_poly.entity_id']) > 1:
continue
print pdb
##
## calculate center of mass
##
center_of_mass = numpy.array([
0.,
0.,
0.,
])
l_coords = []
l_masses = []
for i_atom_site in range(len(d_mmCIF['_atom_site.id'])):
if d_mmCIF['_atom_site.label_entity_id'][
i_atom_site] not in d_mmCIF['_entity_poly.entity_id']:
continue
element = d_mmCIF['_atom_site.type_symbol'][i_atom_site]
## only do heavy atoms
if element == 'H':
continue
if element not in d_mass.keys():
print pdb, d_mmCIF['_atom_site.type_symbol'][i_atom_site]
continue
mass = d_mass[element]
l_masses += [mass]
x = float(d_mmCIF['_atom_site.Cartn_x'][i_atom_site])
y = float(d_mmCIF['_atom_site.Cartn_y'][i_atom_site])
z = float(d_mmCIF['_atom_site.Cartn_z'][i_atom_site])
coord = numpy.array([
x,
y,
z,
])
l_coords += [coord]
center_of_mass += mass * coord
center_of_mass /= sum(l_masses)
##
## calculate radius of gyration
##
sum_r = 0
for i_coord in range(len(l_coords)):
coord = l_coords[i_coord]
mass = l_masses[i_coord]
sq_dist_from_center_of_mass = sum((coord - center_of_mass)**2)
sum_r += mass * sq_dist_from_center_of_mass
radius_of_gyration = math.sqrt(sum_r / sum(l_masses))
print pdb, center_of_mass, radius_of_gyration
line = '%s %s\n' % (
pdb,
radius_of_gyration,
)
lines_out += [line]
fd = open('radius_of_gyration.txt', 'a')
fd.write(line)
fd.close()
d_radii[pdb] = radius_of_gyration
##
## write calculated radii of gyration to file
##
lines_out = []
for pdb, radius_of_gyration in d_radii.items():
line = '%s %s\n' % (
pdb,
radius_of_gyration,
)
lines_out += [line]
fd = open('radius_of_gyration.txt', 'w')
fd.writelines(lines_out)
fd.close()
return
def main():
l_fn_out = [
'_exptl_crystal_grow',
'_exptl_crystal_grow_comp',
]
d = {}
for fn_out in l_fn_out:
fd = open('db%s.txt' % (fn_out), 'r')
lines = fd.readlines()
fd.close()
d[fn_out] = {}
for line in lines:
if line == '\n':
continue
pdb = line[:4]
s = line[5:]
d[fn_out][pdb] = s
fd = open('remediation_exptl_crystal_grow.pH.txt', 'r')
lines = fd.readlines()
fd.close()
l_pdbs = [line[:4] for line in lines]
path = '/media/WDMyBook1TB/2TB/mmCIF'
l_dns = os.listdir(path)
l_dns.sort()
for i in range(len(l_dns)):
dn = l_dns[i]
if dn < sys.argv[-1]:
continue
if not os.path.isdir('%s/%s' % (path, dn)):
continue
print '%s/%s %s' % (i + 1, len(l_dns), dn)
l_fns = os.listdir('%s/%s' % (path, dn))
l_fns.sort()
for fn in l_fns:
if fn[-3:] == '.gz':
continue
pdb = fn[0:4]
## continue if already in txt file from previous attempt to run loop
## if pdb in d['_exptl_crystal_grow_comp'].keys():
## continue
## if pdb in d['_exptl_crystal_grow'].keys():
## continue
## print pdb
if not pdb in l_pdbs:
continue
fd = open('%s/%s/%s' % (path, dn, fn), 'r')
lines = fd.readlines()
fd.close()
d_mmCIF = parse_mmCIF.main(
pdb,
lines,
d_breaks_negation={
## break if not x-ray diffraction
'_exptl.method': 'X-RAY DIFFRACTION',
},
l_data_categories_break=[
## '_atom',
'_diffrn',
],
l_data_categories=[
## parse selected data categories
'_database_PDB_rev',
'_pdbx_database_status',
'_exptl',
'_exptl_crystal_grow',
'_exptl_crystal_grow_comp',
],
)
## ## no polymers in structure?
## if not '_entity_poly.entity_id' in d_mmCIF.keys():
## continue
if d_mmCIF['_exptl.method'] != ['X-RAY DIFFRACTION']:
continue
## print pdb
##
##
##
year = int(d_mmCIF['_database_PDB_rev.date'][0][:4])
process_site = ''.join(
d_mmCIF['_pdbx_database_status.process_site'])
if (not '_exptl_crystal_grow.pdbx_details' in d_mmCIF.keys()
and not '_exptl_crystal_grow_comp.name' in d_mmCIF.keys()
## ''.join(d_mmCIF['_exptl_crystal_grow.pdbx_details']).strip() == '?'
):
if process_site != '?':
print pdb, year, process_site
continue
##
if '_exptl_crystal_grow.pdbx_details' in d_mmCIF.keys():
s_grow = ' '.join(
d_mmCIF['_exptl_crystal_grow.pdbx_details']).strip()
if (
## pH not given
d_mmCIF['_exptl_crystal_grow.pH'] in [
['?'],
[''],
['.'],
] and d_mmCIF['_exptl_crystal_grow.pdbx_pH_range'] in [
['?'],
[''],
['.'],
] and
## but pH in growth details
(' PH ' in s_grow.upper() or 'PH=' in s_grow.upper()
or ',PH ' in s_grow.upper())):
fd = open('remediation_exptl_crystal_grow.pH.txt', 'a')
fd.write('%s\t%s\t%s\t%4i\t%s\t%s\n' % (
pdb,
''.join(d_mmCIF['_exptl_crystal_grow.pH']),
''.join(d_mmCIF['_exptl_crystal_grow.pdbx_pH_range']),
year,
process_site,
s_grow,
))
fd.close()
if (not '_exptl_crystal_grow_comp.name' in d_mmCIF.keys() or
''.join(d_mmCIF['_exptl_crystal_grow_comp.name']) in [
'.',
'',
'?',
]):
if '_exptl_crystal_grow_comp.name' in d_mmCIF.keys():
name = ''.join(
d_mmCIF['_exptl_crystal_grow_comp.name'])
else:
name = 'N/A'
## ## remove end punctuation
## s = s_grow[:-1]+s_grow[-1].replace('.','')
## split
## l_grow_punctuation = s_grow.upper().split('. ')
## l_grow = l_grow_comma = [s_grow.upper().split(',') for s in l_grow_punctuation]
l_grow = s_grow.upper().split(',')
## strip space
l_grow = [x.strip() for x in l_grow]
## remove empty
if '' in l_grow:
l_grow.remove('')
## remove end punctuation
l_grow = [x[:-1] + x[-1].replace('.', '') for x in l_grow]
## remove selected words from elements of list
for x in [
'CRYSTALS OBTAINED BY CO-CRYSTALLIZATION AT ',
'PROTEIN SOLUTION (',
]:
for i_grow in range(len(l_grow)):
l_grow[i_grow] = l_grow[i_grow].replace(x, '')
## replace abbreviations
for i_grow in range(len(l_grow)):
l_grow[i_grow] = l_grow[i_grow].replace(
'MILLIMOLAR', 'MM')
## remove selected words from list
l_remove = []
for x in [
'VAPOR DIFFUSION',
'VAPOUR DIFFUSION',
'HANGING DROP',
'SITTING DROP',
]:
if x in l_grow:
l_remove += [x]
## removed other selected words from list
for i_grow in range(len(list(l_grow))):
## remove physical conditions
bool_continue = False
for x in [
'TEMPERATURE',
'PH=',
'PH ',
'AT PH ',
]:
if l_grow[i_grow][:len(x)] == x:
l_remove += [l_grow[i_grow]]
bool_continue = True
break
if bool_continue == True:
continue
## remove long words (sentences)
if len(l_grow[i_grow]) > 50:
l_remove += [l_grow[i_grow]]
break
for remove in l_remove:
l_grow.remove(remove)
if len(l_grow) > 0:
## write to file
line = '%s\t%s\t%s\t%4i\t%s\t%s\n' % (
pdb,
name,
l_grow,
year,
process_site,
s_grow,
)
fd = open(
'remediation_exptl_crystal_grow_comp.name.txt',
'a')
fd.write(line)
fd.close()
else:
s_grow = ''
##
if '_exptl_crystal_grow_comp.name' in d_mmCIF.keys():
l_grow_comp = d_mmCIF['_exptl_crystal_grow_comp.name']
else:
l_grow_comp = []
## lines_out += [line]
## append to txt file in case loop doesn't finish
d_lines = {}
line = '%s %s\n' % (
pdb,
s_grow,
)
d_lines['_exptl_crystal_grow'] = line
line = '%s %s\n' % (
pdb,
l_grow_comp,
)
d_lines['_exptl_crystal_grow_comp'] = line
for fn_out in l_fn_out:
fd = open('db%s.txt' % (fn_out), 'a')
fd.write(d_lines[fn_out])
fd.close()
## append to dic for when loop finishes
d['_exptl_crystal_grow'][pdb] = s_grow
d['_exptl_crystal_grow_comp'][pdb] = l_grow_comp
lines_out = []
for pdb, s in d.items():
line = '%s %s\n' % (
pdb,
s,
)
lines_out += [line]
fd = open(fn_out, 'w')
fd.writelines(lines_out)
fd.close()
return
def exclude(l_chainIDs):
##
## exclude obsolete structures and theoretical structures
##
print 'obsolete/theoretical'
print len(l_chainIDs)
l_exclude = []
for chainID in l_chainIDs:
if not os.path.isfile('/data/mmCIF/%s/%s.cif' % (
chainID[1:3],
chainID[0:4],
)):
l_exclude += [chainID]
for chainID in l_exclude:
l_chainIDs.remove(chainID)
print len(l_chainIDs)
print
##
## exclude multidomain structures
##
print 'multidomain'
print len(l_chainIDs)
fd = open('../CathDomall', 'r')
lines = fd.readlines()
fd.close()
l_single_domain_chains = []
for line in lines:
chainID = line[:5]
if not chainID in l_chainIDs:
continue
n_domains = int(line[7:9])
if n_domains == 1:
l_single_domain_chains += [chainID]
l_chainIDs = list(set(l_chainIDs) & set(l_single_domain_chains))
print len(l_chainIDs)
print
##
## exclude multichain biological units
## exclude non-x-ray structures
##
print 'multichain'
print len(l_chainIDs)
l_exclude = []
l_pdbs_parsed = []
d_resolutions = {}
for i_chainID in range(len(l_chainIDs)):
chainID = l_chainIDs[i_chainID]
print i_chainID, len(l_chainIDs), chainID
pdbID = chainID[:4]
if pdbID in l_pdbs_parsed:
continue
d_mmCIF = parse_mmCIF.main(pdbID)
l_pdbs_parsed += [pdbID]
if d_mmCIF['_exptl.method'] != ['X-RAY DIFFRACTION']:
l_exclude += [pdbID]
continue
try:
l_oligomeric_counts = d_mmCIF[
'_pdbx_struct_assembly.oligomeric_count']
except:
print chainID
continue
if l_oligomeric_counts != len(l_oligomeric_counts) * ['1']:
l_exclude += [pdbID]
try:
d_resolutions[pdbID] = float(''.join(
d_mmCIF['_refine_hist.d_res_high']))
except:
print chainID
stop
for chainID in list(l_chainIDs):
if chainID[:4] in l_exclude:
l_chainIDs.remove(chainID)
print len(l_chainIDs)
print
##
## exclude redundancies
##
print 'redunant'
print len(l_chainIDs)
fd = open('../bc-50.out', 'r')
lines = fd.readlines()
fd.close()
d = {}
for i_line in range(len(lines)):
line = lines[i_line]
l_cluster = line.split()
for i in range(len(l_cluster)):
l_cluster[i] = l_cluster[i][:4].lower() + l_cluster[i][-1]
l = list(set(l_cluster) & set(l_chainIDs))
if len(l) > 1:
max_resolution = [
'',
None,
]
l.sort()
for chainID in l:
pdbID = chainID[:4]
resolution = d_resolutions[pdbID]
if resolution < max_resolution[0]:
max_resolution = [
resolution,
chainID,
]
for chainID in l:
if chainID != max_resolution[1]:
l_chainIDs.remove(chainID)
print len(l_chainIDs)
print
return l_chainIDs
def parse_GoodVibes_exclude_flexible(pdb,path,):
##
## calculate amplitudes
##
d_mmCIF = parse_mmCIF.main(pdb[:4],)
d_coords, l_coords_alpha = mmCIF2coords.main(pdb[:4],d_mmCIF,query_chain=pdb[-1])
print len(l_coords_alpha)
##
## eigenvector
##
cutoff = 10
matrix_hessian = NMA.hessian_calculation(l_coords_alpha,cutoff,)
eigenvectors, eigenvalues = NMA.diagonalize_hessian(matrix_hessian)
l_amplitudes = [
math.sqrt(
eigenvectors[6][i]**2+eigenvectors[6][i+1]**2+eigenvectors[6][i+2]**2
)
for i in range(0,len(eigenvectors[6]),3)
]
## ## write pdb (color by bfactor)
## l_bfactors = [100*(l_amplitudes[i]-min(l_amplitudes))/(max(l_amplitudes)-min(l_amplitudes)) for i in range(len(l_amplitudes))]
## fd = open('output/%s/%s_%s_probe.pdb' %(path,pdb[:4],pdb[-1],),'r')
## lines = fd.readlines()
## fd.close()
## index = [-1,None,]
## lines_out = []
## for line in lines:
## record = line[:6].strip()
## if record != 'ATOM':
## lines_out += [line]
## else:
## res_no = int(line[22:26])
## if res_no != index[1]:
## index = [index[0]+1,res_no,]
## bfactor = l_bfactors[index[0]]
## line_out = '%s%6.2f%s' %(line[:60],bfactor,line[66:],)
## lines_out += [line_out]
## fd = open('output/%s/%s_%s_probe_color_by_amplitude.pdb' %(path,pdb[:4],pdb[-1],),'w')
## fd.writelines(lines_out)
## fd.close()
## average amplitude
average = sum(l_amplitudes)/len(l_amplitudes)
average,stddev = statistics.do_stddev(l_amplitudes)
##
l_coords_rigid = []
for i in range(len(l_coords_alpha)):
if l_amplitudes[i] < average:
l_coords_rigid += [l_coords_alpha[i]]
l_coords_flexible = []
for i in range(len(l_coords_alpha)):
if l_amplitudes[i] > average+0.5*stddev:
l_coords_flexible += [l_coords_alpha[i]]
## parse output
fd = open('output/%s/%s_%s_probe.pdb' %(path,pdb[:4],pdb[-1],),'r')
lines = fd.readlines()
fd.close()
max_bfactor = None
coord = None
for line in lines:
record = line[:6].strip()
if record not in ['ATOM','HETATM',]:
continue
res_name = line[17:20]
if res_name != 'EXT':
continue
bfactor = float(line[60:66])
if bfactor > max_bfactor:
x = float(line[30:38])
y = float(line[38:46])
z = float(line[46:54])
## coord_tmp = numpy.array([x,y,z,])
## bool_vicinal_to_rigid = False
## for coord_rigid in l_coords_rigid:
## dist_from_rigid = math.sqrt(sum((coord_rigid-coord_tmp)**2))
## if dist_from_rigid < 6:
## bool_vicinal_to_rigid = True
## break
## if bool_vicinal_to_rigid == False:
## continue
## bool_vicinal_to_flexible = False
## for coord_flexible in l_coords_flexible:
## dist_from_flexible = math.sqrt(sum((coord_flexible-coord_tmp)**2))
## if dist_from_flexible < 6:
## bool_vicinal_to_flexible = True
## break
## if bool_vicinal_to_flexible == True:
## continue
## min_dist = [1000.,None,]
## for i_coord_alpha in range(len(l_coords_alpha)):
## coord_alpha = l_coords_alpha[i_coord_alpha]
## dist_from_alpha = math.sqrt(sum((coord_alpha-coord_tmp)**2))
## if dist_from_alpha < min_dist[0]:
## min_dist = [dist_from_alpha,i_coord_alpha,]
## if l_amplitudes[min_dist[1]] > average+stddev:
## continue
coord = numpy.array([x,y,z,])
max_bfactor = bfactor
return coord
def one_polysaccharide(pdb, ):
l_data_categories = [
'_entity',
'_chem_comp',
'_entity_poly',
]
d = parse_mmCIF.main(
pdb,
l_data_categories=l_data_categories,
)
bool_append = False
bool_polysaccharide = False
if '_chem_comp.type' in d.keys():
for chem_comp_type in d['_chem_comp.type']:
if chem_comp_type.lower() in [
'd-saccharide 1,4 and 1,4 linking', # 3amm
'l-saccharide',
'd-saccharide',
'saccharide'
]:
bool_polysaccharide = True
break
## elif 'acchar' in chem_comp_type.lower():
## print d
## print chem_comp_type
## print pdb
## print set(['D-saccharide','saccharide'])&set(d['_chem_comp.type'])
## stop
## else:
## print pdb
## stop
count_polymer_sugar = 0
bool_monosaccharide = False ## included to exclude 1a14 which contains polymers and monomers
for i in range(len(d['_entity.type'])):
entity_type = d['_entity.type'][i]
if entity_type in [
'polymer',
]:
if d['_entity.pdbx_description'][i][:7] == 'SUGAR (':
count_polymer_sugar += int(
d['_entity.pdbx_number_of_molecules'][i])
continue
## ## polypeptide or polynucleotide (just a check)
## elif d['_entity.pdbx_description'][i][:5] == 'SUGAR': ## eg 2c49
## if d['_entity.id'][i] not in d['_entity_poly.entity_id']:
## print pdb
## stop
elif entity_type == 'non-polymer' and d['_entity.pdbx_description'][
i][:5] == 'SUGAR':
bool_monosaccharide = True
## ## just a check
## if d['_entity.pdbx_description'][i][:7] != 'SUGAR (' and pdb not in ['1iuc',]:
## print pdb
## print d['_entity.pdbx_description'][i]
## stop
## ## anything else named SUGAR? just a check
## elif entity_type != 'non-polymer' and d['_entity.pdbx_description'][i][:5] == 'SUGAR':
## print d
## print pdb
## print entity_type
## print d['_entity.pdbx_description'][i]
## stop
if bool_monosaccharide == False and bool_polysaccharide == True and count_polymer_sugar == 1:
bool_append = True
## elif pdb in ['3gvj','3gvk','3gvl','3hmy','3msg','1v0f',]:
## bool_append = False
## ## error check
## elif bool_polysaccharide == False and count_polymer_sugar > 0:
## print d
## print bool_polysaccharide
## print d['_entity.pdbx_description']
## print count_polymer_sugar
## print pdb
## stop_no_poly_but_poly
if pdb == '1dl2':
print count_polymer_sugar
print bool_append
stop
return bool_append
def main():
l_pdbs = []
fd = open('Biso_v_resolution.gnuplotdata', 'r')
lines = fd.readlines()
fd.close()
for line in lines:
l = line.split()
resolution = float(l[1])
Biso = float(l[0])
if resolution > 3.5 and Biso < 10:
print line
if resolution > 2.5 and Biso < 10:
print line
if resolution > 2.0 and Biso < 5:
print line
## if resolution > 1.5 and Biso < 5:
## print line
pdb = l[2]
l_pdbs += [pdb]
Biso_average_prev = 0
l_dn = os.listdir(path)
l_dn.sort()
for dn in l_dn:
if dn < sys.argv[-2]:
continue
if dn > sys.argv[-1]:
continue
if not os.path.isdir('%s/%s' % (path, dn)):
continue
l_fns = os.listdir('%s/%s' % (path, dn))
l_fns.sort()
for fn in l_fns:
if fn[-3:] == '.gz':
continue
pdb = fn[0:4]
if pdb in l_pdbs:
continue
if pdb in [
'3bfn', ## PISA left out chains from biological unit
'2jjg',
'1qjb', ## _pdbx_struct_assembly missing
]:
continue
##
## parse header
##
d_mmCIF = parse_mmCIF.main(
pdb,
l_data_categories=[
'_pdbx_struct_assembly',
'_entity_poly',
'_citation',
'_pdbx_database_related',
], ## parse selected data categories
d_breaks_negation={
## break if not x-ray diffraction
'_exptl.method': 'X-RAY DIFFRACTION',
})
if d_mmCIF['_exptl.method'] != ['X-RAY DIFFRACTION']:
continue
if not 'polypeptide(L)' in d_mmCIF['_entity_poly.type']:
continue
if '_pdbx_database_related.content_type' in d_mmCIF.keys():
if 'split' in d_mmCIF['_pdbx_database_related.content_type']:
continue
try:
if d_mmCIF['_pdbx_struct_assembly.oligomeric_details'] != [
'monomeric'
]:
continue
except:
print pdb
stop
if not '_citation.id' in d_mmCIF.keys():
continue
##
## parse coordinate section
##
d_mmCIF = parse_mmCIF.main(
pdb,
l_data_categories=[
'_database_PDB_rev',
'_refine',
'_refine_hist',
'_atom_site',
'_software',
'_entity',
'_entity_poly',
'_pdbx_struct_assembly',
'_pdbx_database_status',
], ## parse selected data categories
d_breaks_negation={
## break if not x-ray diffraction
'_exptl.method': 'X-RAY DIFFRACTION',
})
if d_mmCIF['_exptl.method'] != ['X-RAY DIFFRACTION']:
continue
if not 'polypeptide(L)' in d_mmCIF['_entity_poly.type']:
continue
if d_mmCIF['_pdbx_struct_assembly.oligomeric_details'] != [
'monomeric'
]:
continue
resolution = float(''.join(d_mmCIF['_refine.ls_d_res_high']))
if (int(d_mmCIF['_entity.pdbx_number_of_molecules'][0]) != 1
or len(d_mmCIF['_entity_poly.pdbx_strand_id']) > 1
or len(''.join(
d_mmCIF['_entity_poly.pdbx_strand_id']).split(',')) > 1
or len(d_mmCIF['_entity_poly.entity_id']) > 1):
print pdb
print d_mmCIF['_entity.pdbx_number_of_molecules']
print d_mmCIF['_entity_poly.pdbx_strand_id']
stop
entity_poly_id = int(''.join(d_mmCIF['_entity_poly.entity_id']))
for i_entity_poly in range(len(d_mmCIF['_entity_poly.entity_id'])):
entity_poly_id = d_mmCIF['_entity_poly.entity_id'][
i_entity_poly]
entity_poly_type = d_mmCIF['_entity_poly.entity_id'][
i_entity_poly]
l_Biso = []
for i_atom_site in range(len(d_mmCIF['_atom_site.id'])):
occupancy = float(d_mmCIF['_atom_site.occupancy'][i_atom_site])
if occupancy != 1:
continue
alt_id = d_mmCIF['_atom_site.label_alt_id'][i_atom_site]
if alt_id != '.':
continue
entity_id = d_mmCIF['_atom_site.label_entity_id'][i_atom_site]
if entity_id != entity_poly_id:
continue
comp_id = d_mmCIF['_atom_site.label_comp_id'][i_atom_site]
if not comp_id in [
'MSE',
'ALA',
'CYS',
'ASP',
'GLU',
'PHE',
'GLY',
'HIS',
'ILE',
'LYS',
'LEU',
'MET',
'ASN',
'PRO',
'GLN',
'ARG',
'SER',
'THR',
'VAL',
'TRP',
'TYR',
]:
continue
type_symbol = d_mmCIF['_atom_site.type_symbol'][i_atom_site]
if type_symbol == 'H':
continue
atom_id = d_mmCIF['_atom_site.label_atom_id'][i_atom_site]
if not atom_id in [
'N',
'CA',
'C',
]:
continue
Biso = float(d_mmCIF['_atom_site.B_iso_or_equiv'][i_atom_site])
l_Biso += [Biso]
year = int(d_mmCIF['_database_PDB_rev.date'][0][:4])
site = ''.join(d_mmCIF['_pdbx_database_status.process_site'])
if len(l_Biso) == 0:
continue
## if l_Biso == len(l_Biso)*[l_Biso[0]]:
## print pdb, year, l_Biso[0:3]
## if year >= 2010:
## stop
## continue
Biso_average = sum(l_Biso) / len(l_Biso)
bool_continue = False
for Biso in set(l_Biso):
count = l_Biso.count(Biso)
if count > 20:
if '_software.name' in d_mmCIF.keys():
print pdb, Biso_average, Biso, count, d_mmCIF[
'_software.name']
s = '%s %6.2f %4i %6.2f %4i %s %s\n' % (
pdb,
Biso,
count,
Biso_average,
year,
site,
str(d_mmCIF['_software.name']),
)
else:
print pdb, Biso_average, Biso, count
s = '%s %6.2f %4i %6.2f %4i %s\n' % (
pdb,
Biso,
count,
Biso_average,
year,
site,
)
bool_continue = True
fd = open('remediation_Biso_duplicates.txt', 'a')
fd.write(s)
fd.close()
break
if bool_continue == True:
continue
## if Biso_average in [2,3,4,5,6,7,8,9,99,90,50,20,25,1,100,10,0]:
if Biso_average in range(0, 100 + 1):
print l_Biso
print Biso_average
print pdb
print year
stop
if '_refine.pdbx_TLS_residual_ADP_flag' in d_mmCIF.keys():
if ''.join(d_mmCIF['_refine.pdbx_TLS_residual_ADP_flag']) in [
'UNVERIFIED',
'LIKELY RESIDUAL',
]:
continue
elif ''.join(
d_mmCIF['_refine.pdbx_TLS_residual_ADP_flag']) in [
'?',
]:
pass
else:
print d_mmCIF['_refine.pdbx_TLS_residual_ADP_flag']
print pdb, Biso_average
stop
if round(Biso_average, 4) == round(Biso_average_prev, 4):
print pdb, Biso_average, Biso_average_prev
stop
print pdb, round(Biso_average, 2), resolution
fd = open('Biso_v_resolution.gnuplotdata', 'a')
fd.write('%s %s %s %s\n' % (
Biso_average,
resolution,
pdb,
year,
))
fd.close()
plot()
def unobs_nonterminal_residues():
##
## unobs or zero occup not at terminals!!! (combination...)
## eg dont exlude 200l w 163,164 missing
## dont exclude 201l w 163,164 missing, but internally in _pdbx_poly_seq_scheme because 2 chains
##
category = fn = '_pdbx_unobs_or_zero_occ_residues'
fd = open('%s/list%s.txt' % (path, fn))
s = fd.read()
fd.close()
l_pdbs_in = s.split()
l_data_categories = [
'_pdbx_poly_seq_scheme',
'_pdbx_unobs_or_zero_occ_residues',
'_entity_poly',
]
fn_out = 'list_pdbx_unobs_residues__NONTERMINAL'
loop_residues(
category,
fn_out,
)
l_pdbs_out = []
for pdb in l_pdbs_in:
## if pdb[1:3] < 'oa':
## continue
## if pdb != '2hub':
## continue
## no residues are present! (e.g. 1oax, 1oay)
if pdb in [
'1oax',
'1oay',
]:
continue
d = parse_mmCIF.main(
pdb,
l_data_categories=l_data_categories,
)
## print pdb
if not category in d.keys():
continue
bool_append = False
s = ''.join(d['_pdbx_poly_seq_scheme.pdb_strand_id'])
for chains in d['_entity_poly.pdbx_strand_id']:
for chain in chains.split(','):
index1 = s.index(chain)
index2 = s.rindex(chain)
## print chain
l_auth_seq_num = d['_pdbx_poly_seq_scheme.auth_seq_num'][
index1:index2 + 1]
while l_auth_seq_num[0] == '?':
l_auth_seq_num = l_auth_seq_num[1:]
while l_auth_seq_num[-1] == '?':
l_auth_seq_num = l_auth_seq_num[:-1]
## non-terminal residues missing?
if '?' in l_auth_seq_num:
print '****', pdb
bool_append = True
break
if bool_append == True:
break
if bool_append == True:
print pdb
l_pdbs_out += [pdb]
## continue
fd = open('%s/%s' % (
path,
fn_out,
), 'w')
fd.write('\n'.join(l_pdbs_out))
fd.close()
return
def main():
fn_out = 'db_MatthewsCoefficient.txt'
fd = open(fn_out, 'r')
lines = fd.readlines()
fd.close()
d = {}
for line in lines:
l = line.strip().split()
pdb = l[0]
v = l[1]
if pdb == '2p51':
v = '1.72610466393'
d[pdb] = v
lines_out = []
path = '/media/WDMyBook1TB/2TB/mmCIF'
l_dns = os.listdir(path)
l_dns.sort()
for i in range(len(l_dns)):
dn = l_dns[i]
if dn < sys.argv[-1]:
continue
if not os.path.isdir('%s/%s' % (path, dn)):
continue
print '%s/%s %s' % (i + 1, len(l_dns), dn)
l_fns = os.listdir('%s/%s' % (path, dn))
l_fns.sort()
for fn in l_fns:
if fn[-3:] == '.gz':
continue
pdb = fn[0:4]
if pdb in d.keys():
continue
## Matthews Coefficient not calculated...
if pdb in [
'1vh7',
'1vho',
'1vhu',
'1vi3',
'1vi4',
'1vis',
]:
continue
## Matthews Coefficient *wrong*
if pdb in [
'2p51',
## too high
'1c5v',
'1q9i',
'1ut6',
'1x6x',
'1x6y',
'1xdn',
'1y63',
'1zix',
## too low
'1t95',
'1jih',
'1t95',
'1d5t',
'1c7k',
'1dbo',
'1d9x',
'1qt9',
'1ia5',
'1dcq',
]:
continue
fd = open('%s/%s/%s' % (path, dn, fn), 'r')
lines = fd.readlines()
fd.close()
d_mmCIF = parse_mmCIF.main(
pdb,
lines,
d_breaks={
## break if multiple polymer types (not monomeric)
'_entity_poly.entity_id': '2',
## '_exptl.method':'SOLUTION NMR', ## break if e.g. _exptl.method = SOLUTION NMR
## break if multiple chains
'_entity_poly.pdbx_strand_id': ',',
},
d_breaks_negation={
## break if not x-ray diffraction
'_exptl.method': 'X-RAY DIFFRACTION',
## break if not monomeric
'_pdbx_struct_assembly.oligomeric_details': 'monomeric',
},
l_data_categories=[
'_exptl_crystal',
], ## parse selected data categories
l_data_categories_break=['_exptl_crystal'])
## some unknown temporary error... or break before reaching this part when parsing...
if not '_pdbx_struct_assembly.oligomeric_details' in d_mmCIF.keys(
):
continue
## NMR structure?
if d_mmCIF['_exptl.method'] != ['X-RAY DIFFRACTION']:
stop2
continue
## no polymers in structure?
if not '_entity_poly.entity_id' in d_mmCIF.keys():
continue
## polymer(s) is/are not polypeptide(s)
if d_mmCIF['_entity_poly.type'] != len(
d_mmCIF['_entity_poly.type']) * ['polypeptide(L)']:
continue
## biounit not monomeric
if d_mmCIF['_pdbx_struct_assembly.oligomeric_details'] != len(
d_mmCIF['_pdbx_struct_assembly.oligomeric_details']) * [
'monomeric'
]:
continue
## one polymer in assymetric unit
if len(d_mmCIF['_entity_poly.entity_id']) > 1:
continue
if d_mmCIF['_exptl_crystal.density_Matthews'] == ['?']:
v = VM = calc_matthews_coefficient.main(pdb)
## continue
else:
v = float(''.join(d_mmCIF['_exptl_crystal.density_Matthews']))
line = '%s %s\n' % (
pdb,
v,
)
fd = open(fn_out, 'a')
fd.write(line)
fd.close()
d[pdb] = v
##
## write calculated radii of gyration to file
##
lines_out = []
for pdb, v in d.items():
line = '%s %s\n' % (
pdb,
v,
)
lines_out += [line]
fd = open(fn_out, 'w')
fd.writelines(lines_out)
fd.close()
return
def main():
d = {}
if os.path.isfile('db_resolution.txt'):
fd = open('db_resolution.txt','r')
lines = fd.readlines()
fd.close()
for line in lines:
l = line.strip().split()
pdb = l[0]
v = l[1]
d[pdb] = v
path = '/media/WDMyBook1TB/2TB/mmCIF'
l_dns = os.listdir(path)
l_dns.sort()
lines_out = []
for i in range(len(l_dns)):
dn = l_dns[i]
if dn < sys.argv[-1]:
continue
if not os.path.isdir('%s/%s' %(path,dn)):
continue
print '%s/%s %s' %(i+1,len(l_dns), dn)
l_fns = os.listdir('%s/%s' %(path,dn))
l_fns.sort()
for fn in l_fns:
if fn[-3:] == '.gz':
continue
pdb = fn[0:4]
if pdb in d.keys():
continue
print pdb
fd = open('%s/%s/%s' %(path, dn, fn), 'r')
lines = fd.readlines()
fd.close()
d_mmCIF = parse_mmCIF.main(
pdb,lines,
l_data_categories = [
'_refine',
'_refine_hist',
], ## parse selected data categories
l_data_categories_break = [
'_refine',
## '_refine_hist',
],
d_breaks_negation = {
## break if not x-ray diffraction
'_exptl.method':'X-RAY DIFFRACTION',
}
)
if d_mmCIF['_exptl.method'] != ['X-RAY DIFFRACTION']:
continue
resolution = d_mmCIF['_refine.ls_d_res_high']
line = '%s %s\n' %(pdb,resolution,)
lines_out += [line]
fd = open('db_resolution.txt','a')
fd.write(line)
fd.close()
d[pdb] = resolution
##
## write to file
##
lines_out = []
for pdb,resolution in d.items():
line = '%s %s\n' %(pdb,resolution,)
lines_out += [line]
fd = open('db_resolution.txt','w')
fd.writelines(lines_out)
fd.close()
d = {}
fd = open('db_resolution.txt','r')
lines = fd.readlines()
fd.close()
lines_out = []
for line in lines:
resolution = line.strip().split()[1][2:-2]
if resolution == '.':
continue
resolution = float(resolution)
resolution = round(resolution,2)
if not resolution in d.keys():
d[resolution] = 0
d[resolution] += 1
lines_out += ['%s\n' %(resolution,)]
fd = open('histogram_resolution.txt','w')
fd.writelines(lines_out)
fd.close()
stop
lines_out = []
l_resolutions = d.keys()
l_resolutions.sort()
## for resolution,count in d.items():
for resolution in l_resolutions:
count = d[resolution]
lines_out += ['%s %s\n' %(resolution,count,)]
fd = open('histogram_resolution.txt','w')
fd.writelines(lines_out)
fd.close()
return
def exclude(l_chainIDs):
##
## exclude obsolete structures and theoretical structures
##
print 'obsolete/theoretical'
print len(l_chainIDs)
l_exclude = []
for chainID in l_chainIDs:
if not os.path.isfile('/data/mmCIF/%s/%s.cif' %(chainID[1:3],chainID[0:4],)):
l_exclude += [chainID]
for chainID in l_exclude:
l_chainIDs.remove(chainID)
print len(l_chainIDs)
print
##
## exclude multidomain structures
##
print 'multidomain'
print len(l_chainIDs)
fd = open('../CathDomall','r')
lines = fd.readlines()
fd.close()
l_single_domain_chains = []
for line in lines:
chainID = line[:5]
if not chainID in l_chainIDs:
continue
n_domains = int(line[7:9])
if n_domains == 1:
l_single_domain_chains += [chainID]
l_chainIDs = list( set(l_chainIDs) & set(l_single_domain_chains) )
print len(l_chainIDs)
print
##
## exclude multichain biological units
## exclude non-x-ray structures
##
print 'multichain'
print len(l_chainIDs)
l_exclude = []
l_pdbs_parsed = []
d_resolutions = {}
for i_chainID in range(len(l_chainIDs)):
chainID = l_chainIDs[i_chainID]
print i_chainID, len(l_chainIDs), chainID
pdbID = chainID[:4]
if pdbID in l_pdbs_parsed:
continue
d_mmCIF = parse_mmCIF.main(pdbID)
l_pdbs_parsed += [pdbID]
if d_mmCIF['_exptl.method'] != ['X-RAY DIFFRACTION']:
l_exclude += [pdbID]
continue
try:
l_oligomeric_counts = d_mmCIF['_pdbx_struct_assembly.oligomeric_count']
except:
print chainID
continue
if l_oligomeric_counts != len(l_oligomeric_counts)*['1']:
l_exclude += [pdbID]
try:
d_resolutions[pdbID] = float(''.join(d_mmCIF['_refine_hist.d_res_high']))
except:
print chainID
stop
for chainID in list(l_chainIDs):
if chainID[:4] in l_exclude:
l_chainIDs.remove(chainID)
print len(l_chainIDs)
print
##
## exclude redundancies
##
print 'redunant'
print len(l_chainIDs)
fd = open('../bc-50.out','r')
lines = fd.readlines()
fd.close()
d = {}
for i_line in range(len(lines)):
line = lines[i_line]
l_cluster = line.split()
for i in range(len(l_cluster)):
l_cluster[i] = l_cluster[i][:4].lower()+l_cluster[i][-1]
l = list( set(l_cluster) & set(l_chainIDs) )
if len(l) > 1:
max_resolution = ['',None,]
l.sort()
for chainID in l:
pdbID = chainID[:4]
resolution = d_resolutions[pdbID]
if resolution < max_resolution[0]:
max_resolution = [resolution,chainID,]
for chainID in l:
if chainID != max_resolution[1]:
l_chainIDs.remove(chainID)
print len(l_chainIDs)
print
return l_chainIDs
print dn
l_fn = os.listdir('%s/%s' %(path,dn,))
l_fn.sort()
for fn in l_fn:
pdb = fn[:4]
if fn[-3:] == '.gz':
continue
######## if pdb in ['2fl9','3gau','3gav','3gaw',]: ## tmp!!!
######## continue
## print pdb
fd = open('%s/%s/%s' %(path,dn,fn), 'r')
lines = fd.readlines()
fd.close()
d = parse_mmCIF.main(
pdb,lines,
l_data_categories = l_data_categories,
d_breaks = d_breaks,
)
if d_exclude_subset:
bool_continue = False
for item_exclude,l_values_exclude in d_exclude_subset.items():
if not item_exclude in d.keys():
bool_continue = True
fd = open('%s/remediation_%s.txt' %(path,item_exclude,),'a')
fd.write('%s\n' %(pdb))
fd.close()
continue
if len( set(d[item_exclude]) & set(l_values_exclude) ) > 0:
bool_continue = True
break
def parse_cifs(
l_pdbs,
ref_seq,
l_db_codes,
n_mutations_max,
resolution_min,
bool_multiple_entities=False,
):
print 'parse cifs'
n_mutants = 0
l_wts = []
l_wts_cysfree = []
d_mutants = {}
d_mmCIF_main = {}
for pdb in l_pdbs:
if pdb[:4].lower() in d_mmCIF_main.keys():
continue
d_mmCIF = parse_mmCIF.main(pdb[:4].lower(), )
## not an x-ray structure
if d_mmCIF['_exptl.method'] != ['X-RAY DIFFRACTION']:
print pdb, d_mmCIF['_exptl.method']
continue
## more than one type of polymer present
n_entities = len(d_mmCIF['_entity_poly.entity_id'])
if bool_multiple_entities == False:
if n_entities > 1:
print pdb, 'entities', n_entities #, d_mmCIF['_struct.title']
continue
## low resolution
if d_mmCIF['_refine.ls_d_res_high'] != d_mmCIF[
'_refine_hist.d_res_high']:
print d_mmCIF['_refine.ls_d_res_high']
print d_mmCIF['_refine_hist.d_res_high']
stop
if resolution_min:
## if float(d_mmCIF['_refine.ls_d_res_high'][0]) >= resolution_min:
if float(d_mmCIF['_refine.ls_d_res_high'][0]) > resolution_min:
print pdb, 'resolution', d_mmCIF['_refine.ls_d_res_high']
continue
## get entity ID from chain ID
for i_entity in range(len(d_mmCIF['_entity_poly.entity_id'])):
entity_id = d_mmCIF['_entity_poly.entity_id'][i_entity]
s_chain_ids = d_mmCIF['_entity_poly.pdbx_strand_id'][i_entity]
if pdb[-1] in s_chain_ids:
break
if pdb[-1] not in s_chain_ids:
print pdb
print s_chain_ids
stop
## get sequence from entity ID
seq = []
for i in range(len(d_mmCIF['_entity_poly_seq.entity_id'])):
if d_mmCIF['_entity_poly_seq.entity_id'][i] == entity_id:
mon_id = d_mmCIF['_entity_poly_seq.mon_id'][i]
if pdb[:4] == '1RCM' and i == 126:
if mon_id != 'CYS':
stop
mon_id = 'CCS'
seq += [mon_id]
## wrong chain length
if ref_seq:
if len(seq) != len(ref_seq):
if ''.join(ref_seq) in ''.join(seq):
print ref_seq
print seq
stop
## unobserved atoms not in seqres
elif ''.join(seq) in ''.join(ref_seq):
pass
## last two residues unobserved
elif len(seq) == 162 and pdb in [
'1KS3_A',
'1KW5_A',
'1KW7_A',
'1KY0_A',
'1KY1_A',
'1L0J_A',
'1LOK_A',
'1LPY_A',
'1LW9_A',
'1LWG_A',
'1LWK_A',
]:
pass
## last two residues unobserved
elif len(seq) == 162 and seq[-1] == 'LYS':
pass
else:
print pdb, 'seqlen', len(seq)
continue
## not from Gallus gallus
## check not necessary, because sequence checked against ref seq
entity_id = d_mmCIF['_entity_poly.entity_id'][i_entity]
db_code = d_mmCIF['_struct_ref.db_code'][
d_mmCIF['_struct_ref.entity_id'].index(entity_id)]
if db_code not in l_db_codes:
print pdb, 'uniprot', db_code
continue
## more than 1 mutation?
if n_mutations_max != None:
l_mutations = []
for i_seq in range(len(seq)):
res_id_mmCIF = seq[i_seq]
res_id_uniprot = ref_seq[i_seq]
if res_id_mmCIF != res_id_uniprot:
l_mutations += [
'%3s%i%3s' % (
res_id_uniprot,
i_seq + 1,
res_id_mmCIF,
)
]
## if len(l_mutations) == 1:
if len(l_mutations) > n_mutations_max:
print pdb, 'muts', len(l_mutations)
continue
elif len(l_mutations) > 0:
n_mutants += 1
startmodel = parse_mmCIF_item(
d_mmCIF,
'_refine.pdbx_starting_model',
pdb,
)
## append to lists and dictionaries
d_mmCIF_main[pdb[:4]] = d_mmCIF
if len(l_mutations) > 0:
if l_mutations == ['CYS54THR', 'CYS97ALA']:
l_wts_cysfree += [pdb]
d_mutants[pdb] = {
'mutations': l_mutations,
'startmodel': startmodel
}
else:
l_wts += [pdb]
## print 'd_mutants', d_mutants
return d_mmCIF_main, l_wts, d_mutants, l_wts_cysfree
def parse_GoodVibes_exclude_flexible(
pdb,
path,
):
##
## calculate amplitudes
##
d_mmCIF = parse_mmCIF.main(pdb[:4], )
d_coords, l_coords_alpha = mmCIF2coords.main(pdb[:4],
d_mmCIF,
query_chain=pdb[-1])
print len(l_coords_alpha)
##
## eigenvector
##
cutoff = 10
matrix_hessian = NMA.hessian_calculation(
l_coords_alpha,
cutoff,
)
eigenvectors, eigenvalues = NMA.diagonalize_hessian(matrix_hessian)
l_amplitudes = [
math.sqrt(eigenvectors[6][i]**2 + eigenvectors[6][i + 1]**2 +
eigenvectors[6][i + 2]**2)
for i in range(0, len(eigenvectors[6]), 3)
]
## ## write pdb (color by bfactor)
## l_bfactors = [100*(l_amplitudes[i]-min(l_amplitudes))/(max(l_amplitudes)-min(l_amplitudes)) for i in range(len(l_amplitudes))]
## fd = open('output/%s/%s_%s_probe.pdb' %(path,pdb[:4],pdb[-1],),'r')
## lines = fd.readlines()
## fd.close()
## index = [-1,None,]
## lines_out = []
## for line in lines:
## record = line[:6].strip()
## if record != 'ATOM':
## lines_out += [line]
## else:
## res_no = int(line[22:26])
## if res_no != index[1]:
## index = [index[0]+1,res_no,]
## bfactor = l_bfactors[index[0]]
## line_out = '%s%6.2f%s' %(line[:60],bfactor,line[66:],)
## lines_out += [line_out]
## fd = open('output/%s/%s_%s_probe_color_by_amplitude.pdb' %(path,pdb[:4],pdb[-1],),'w')
## fd.writelines(lines_out)
## fd.close()
## average amplitude
average = sum(l_amplitudes) / len(l_amplitudes)
average, stddev = statistics.do_stddev(l_amplitudes)
##
l_coords_rigid = []
for i in range(len(l_coords_alpha)):
if l_amplitudes[i] < average:
l_coords_rigid += [l_coords_alpha[i]]
l_coords_flexible = []
for i in range(len(l_coords_alpha)):
if l_amplitudes[i] > average + 0.5 * stddev:
l_coords_flexible += [l_coords_alpha[i]]
## parse output
fd = open('output/%s/%s_%s_probe.pdb' % (
path,
pdb[:4],
pdb[-1],
), 'r')
lines = fd.readlines()
fd.close()
max_bfactor = None
coord = None
for line in lines:
record = line[:6].strip()
if record not in [
'ATOM',
'HETATM',
]:
continue
res_name = line[17:20]
if res_name != 'EXT':
continue
bfactor = float(line[60:66])
if bfactor > max_bfactor:
x = float(line[30:38])
y = float(line[38:46])
z = float(line[46:54])
## coord_tmp = numpy.array([x,y,z,])
## bool_vicinal_to_rigid = False
## for coord_rigid in l_coords_rigid:
## dist_from_rigid = math.sqrt(sum((coord_rigid-coord_tmp)**2))
## if dist_from_rigid < 6:
## bool_vicinal_to_rigid = True
## break
## if bool_vicinal_to_rigid == False:
## continue
## bool_vicinal_to_flexible = False
## for coord_flexible in l_coords_flexible:
## dist_from_flexible = math.sqrt(sum((coord_flexible-coord_tmp)**2))
## if dist_from_flexible < 6:
## bool_vicinal_to_flexible = True
## break
## if bool_vicinal_to_flexible == True:
## continue
## min_dist = [1000.,None,]
## for i_coord_alpha in range(len(l_coords_alpha)):
## coord_alpha = l_coords_alpha[i_coord_alpha]
## dist_from_alpha = math.sqrt(sum((coord_alpha-coord_tmp)**2))
## if dist_from_alpha < min_dist[0]:
## min_dist = [dist_from_alpha,i_coord_alpha,]
## if l_amplitudes[min_dist[1]] > average+stddev:
## continue
coord = numpy.array([
x,
y,
z,
])
max_bfactor = bfactor
return coord
def identify_CH_bonds():
##
## identify all C-H single bonds in the standard residues
##
d_atoms = {}
for residue in [
'ALA',
## 'ALA','CYS','ASP','GLU','PHE',
## 'GLY','HIS','ILE','LYS','LEU',
## 'MET','ASN','PRO','GLN','ARG',
## 'SER','THR','VAL','TRP','TYR',
]:
lines = urllib2.urlopen('http://www.pdb.org/pdb/files/ligand/%s.cif' %(residue)).readlines()
d = parse_mmCIF.main(residue,lines)
d_atoms[residue] = []
for i in range(len(d['_chem_comp_bond.comp_id'])):
if d['_chem_comp_bond.value_order'][i] != 'SING':
continue
atom1 = d['_chem_comp_bond.atom_id_1'][i]
atom2 = d['_chem_comp_bond.atom_id_2'][i]
## heavy element is always listed before hydrogen
if atom1[0] != 'C' or atom2[0] != 'H':
continue
print residue, d['_chem_comp_bond.atom_id_1'][i], d['_chem_comp_bond.atom_id_2'][i]
d_atoms[residue] += [atom1]
return d_atoms