/usr/lib/python2.7/dist-packages/chempy/protein.py is in pymol 1.8.4.0+dfsg-1.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 | #A* -------------------------------------------------------------------
#B* This file contains source code for the PyMOL computer program
#C* copyright 1998-2000 by Warren Lyford Delano of DeLano Scientific.
#D* -------------------------------------------------------------------
#E* It is unlawful to modify or remove this copyright notice.
#F* -------------------------------------------------------------------
#G* Please see the accompanying LICENSE file for further information.
#H* -------------------------------------------------------------------
#I* Additional authors of this source file include:
#-*
#-*
#-*
#Z* -------------------------------------------------------------------
#
#
#
from __future__ import print_function
from . import bond_amber
from . import protein_residues
from . import protein_amber
from chempy.neighbor import Neighbor
from chempy.models import Connected
from chempy import Bond,place,feedback
from chempy.cpv import *
MAX_BOND_LEN = 2.2
PEPT_CUTOFF = 1.7
N_TERMINAL_ATOMS = ('HT','HT1','HT2','HT3','H1','H2','H3',
'1H','2H','3H','1HT','2HT','3HT')
C_TERMINAL_ATOMS = ('OXT','O2','OT1','OT2')
#---------------------------------------------------------------------------------
# NOTE: right now, the only way to get N-terminal residues is to
# submit a structure which contains at least one N_TERMINAL hydrogens
def generate(model, forcefield = protein_amber, histidine = 'HIE',
skip_sort=None, bondfield = bond_amber ):
strip_atom_bonds(model) # remove bonds between non-hetatms (ATOM)
add_bonds(model,forcefield=forcefield)
connected = model.convert_to_connected()
add_hydrogens(connected,forcefield=forcefield,skip_sort=skip_sort)
place.simple_unknowns(connected,bondfield = bondfield)
return connected.convert_to_indexed()
#---------------------------------------------------------------------------------
def strip_atom_bonds(model):
new_bond = []
matom = model.atom
for a in model.bond:
if matom[a.index[0]].hetatm or matom[a.index[1]].hetatm:
new_bond.append(a)
model.bond = new_bond
#---------------------------------------------------------------------------------
def assign_types(model, forcefield = protein_amber, histidine = 'HIE' ):
'''
assigns types: takes HIS -> HID,HIE,HIP and CYS->CYX where appropriate
but does not add any bonds!
'''
if feedback['actions']:
print(" "+str(__name__)+": assigning types...")
if str(model.__class__) != 'chempy.models.Indexed':
raise ValueError('model is not an "Indexed" model object')
if model.nAtom:
crd = model.get_coord_list()
nbr = Neighbor(crd,MAX_BOND_LEN)
res_list = model.get_residues()
if len(res_list):
for a in res_list:
base = model.atom[a[0]]
if not base.hetatm:
resn = base.resn
if resn == 'HIS':
for c in range(a[0],a[1]): # this residue
model.atom[c].resn = histidine
resn = histidine
if resn == 'N-M': # N-methyl from Insight II,
for c in range(a[0],a[1]): # this residue
model.atom[c].resn = 'NME'
resn = 'NME'
# find out if this is n or c terminal residue
names = []
for b in range(a[0],a[1]):
names.append(model.atom[b].name)
tmpl = protein_residues.normal
if forcefield:
ffld = forcefield.normal
for b in N_TERMINAL_ATOMS:
if b in names:
tmpl = protein_residues.n_terminal
if forcefield:
ffld = forcefield.n_terminal
break
for b in C_TERMINAL_ATOMS:
if b in names:
tmpl = protein_residues.c_terminal
if forcefield:
ffld = forcefield.c_terminal
break
if resn not in tmpl:
raise RuntimeError("unknown residue type '"+resn+"'")
else:
# reassign atom names and build dictionary
dict = {}
aliases = tmpl[resn]['aliases']
for b in range(a[0],a[1]):
at = model.atom[b]
if at.name in aliases:
at.name = aliases[at.name]
dict[at.name] = b
if forcefield:
k = (resn,at.name)
if k in ffld:
at.text_type = ffld[k]['type']
at.partial_charge = ffld[k]['charge']
else:
raise RuntimeError("no parameters for '"+str(k)+"'")
if 'SG' in dict: # cysteine
cur = dict['SG']
at = model.atom[cur]
lst = nbr.get_neighbors(at.coord)
for b in lst:
if b>cur: # only do this once (only when b>cur - i.e. this is 1st CYS)
at2 = model.atom[b]
if at2.name=='SG':
if not at2.in_same_residue(at):
dst = distance(at.coord,at2.coord)
if dst<=MAX_BOND_LEN:
if forcefield:
for c in range(a[0],a[1]): # this residue
atx = model.atom[c]
atx.resn = 'CYX'
resn = atx.resn
if (c<=b):
k = ('CYX',atx.name)
if k in ffld:
atx.text_type = ffld[k]['type']
atx.partial_charge = ffld[k]['charge']
else:
raise RuntimeError("no parameters for '"+str(k)+"'")
for d in res_list: # other residue
if (b>=d[0]) and (b<d[1]):
for c in range(d[0],d[1]):
atx = model.atom[c]
atx.resn = 'CYX'
# since b>cur, assume assignment later on
break
#---------------------------------------------------------------------------------
def add_bonds(model, forcefield = protein_amber, histidine = 'HIE' ):
'''
add_bonds(model, forcefield = protein_amber, histidine = 'HIE' )
(1) fixes aliases, assigns types, makes HIS into HIE,HID, or HIP
and changes cystine to CYX
(2) adds bonds between existing atoms
'''
if feedback['actions']:
print(" "+str(__name__)+": assigning types and bonds...")
if str(model.__class__) != 'chempy.models.Indexed':
raise ValueError('model is not an "Indexed" model object')
if model.nAtom:
crd = model.get_coord_list()
nbr = Neighbor(crd,MAX_BOND_LEN)
res_list = model.get_residues()
if len(res_list):
for a in res_list:
base = model.atom[a[0]]
if not base.hetatm:
resn = base.resn
if resn == 'HIS':
for c in range(a[0],a[1]): # this residue
model.atom[c].resn = histidine
resn = histidine
if resn == 'N-M': # N-methyl from Insight II,
for c in range(a[0],a[1]): # this residue
model.atom[c].resn = 'NME'
resn = 'NME'
# find out if this is n or c terminal residue
names = []
for b in range(a[0],a[1]):
names.append(model.atom[b].name)
tmpl = protein_residues.normal
if forcefield:
ffld = forcefield.normal
for b in N_TERMINAL_ATOMS:
if b in names:
tmpl = protein_residues.n_terminal
if forcefield:
ffld = forcefield.n_terminal
break
for b in C_TERMINAL_ATOMS:
if b in names:
tmpl = protein_residues.c_terminal
if forcefield:
ffld = forcefield.c_terminal
break
if resn not in tmpl:
raise RuntimeError("unknown residue type '"+resn+"'")
else:
# reassign atom names and build dictionary
dict = {}
aliases = tmpl[resn]['aliases']
for b in range(a[0],a[1]):
at = model.atom[b]
if at.name in aliases:
at.name = aliases[at.name]
dict[at.name] = b
if forcefield:
k = (resn,at.name)
if k in ffld:
at.text_type = ffld[k]['type']
at.partial_charge = ffld[k]['charge']
else:
raise RuntimeError("no parameters for '"+str(k)+"'")
# now add bonds for atoms which are present
bonds = tmpl[resn]['bonds']
mbond = model.bond
for b in list(bonds.keys()):
if b[0] in dict and b[1] in dict:
bnd = Bond()
bnd.index = [ dict[b[0]], dict[b[1]] ]
bnd.order = bonds[b]['order']
mbond.append(bnd)
if 'N' in dict: # connect residues N-C based on distance
cur_n = dict['N']
at = model.atom[cur_n]
lst = nbr.get_neighbors(at.coord)
for b in lst:
at2 = model.atom[b]
if at2.name=='C':
if not at2.in_same_residue(at):
dst = distance(at.coord,at2.coord)
if dst<=PEPT_CUTOFF:
bnd=Bond()
bnd.index = [cur_n,b]
bnd.order = 1
mbond.append(bnd)
break
if 'SG' in dict: # cysteine
cur = dict['SG']
at = model.atom[cur]
lst = nbr.get_neighbors(at.coord)
for b in lst:
if b>cur: # only do this once (only when b>cur - i.e. this is 1st CYS)
at2 = model.atom[b]
if at2.name=='SG':
if not at2.in_same_residue(at):
dst = distance(at.coord,at2.coord)
if dst<=MAX_BOND_LEN:
bnd=Bond()
bnd.index = [cur,b]
bnd.order = 1
mbond.append(bnd)
if forcefield:
for c in range(a[0],a[1]): # this residue
atx = model.atom[c]
atx.resn = 'CYX'
resn = atx.resn
k = ('CYX',atx.name)
if k in ffld:
atx.text_type = ffld[k]['type']
atx.partial_charge = ffld[k]['charge']
else:
raise RuntimeError("no parameters for '"+str(k)+"'")
for d in res_list:
if (b>=d[0]) and (b<d[1]): # find other residue
for c in range(d[0],d[1]):
atx = model.atom[c]
atx.resn = 'CYX'
# since b>cur, assume assignment later on
break
#---------------------------------------------------------------------------------
def add_hydrogens(model,forcefield=protein_amber,skip_sort=None):
# assumes no bonds between non-hetatms
if feedback['actions']:
print(" "+str(__name__)+": adding hydrogens...")
if str(model.__class__) != 'chempy.models.Connected':
raise ValueError('model is not a "Connected" model object')
if model.nAtom:
if not model.index:
model.update_index()
res_list = model.get_residues()
if len(res_list):
for a in res_list:
base = model.atom[a[0]]
if not base.hetatm:
resn = base.resn
# find out if this is n or c terminal residue
names = []
for b in range(a[0],a[1]):
names.append(model.atom[b].name)
tmpl = protein_residues.normal
if forcefield:
ffld = forcefield.normal
for b in N_TERMINAL_ATOMS:
if b in names:
tmpl = protein_residues.n_terminal
if forcefield:
ffld = forcefield.n_terminal
break
for b in C_TERMINAL_ATOMS:
if b in names:
tmpl = protein_residues.c_terminal
if forcefield:
ffld = forcefield.c_terminal
break
if resn not in tmpl:
raise RuntimeError("unknown residue type '"+resn+"'")
else:
# build dictionary
dict = {}
for b in range(a[0],a[1]):
at = model.atom[b]
dict[at.name] = b
# find missing bonds with hydrogens
bonds = tmpl[resn]['bonds']
mbond = model.bond
for b in list(bonds.keys()):
if b[0] in dict and (b[1] not in dict):
at = model.atom[dict[b[0]]]
if at.symbol != 'H':
name = b[1]
symbol = tmpl[resn]['atoms'][name]['symbol']
if symbol == 'H':
newat = at.new_in_residue()
newat.name = name
newat.symbol = symbol
k = (resn,newat.name)
newat.text_type = ffld[k]['type']
newat.partial_charge = ffld[k]['charge']
idx1 = model.index[id(at)]
idx2 = model.add_atom(newat)
bnd = Bond()
bnd.index = [ idx1, idx2 ]
bnd.order = bonds[b]['order']
mbond[idx1].append(bnd)
mbond[idx2].append(bnd)
if (b[0] not in dict) and b[1] in dict:
at = model.atom[dict[b[1]]]
if at.symbol != 'H':
name = b[0]
symbol = tmpl[resn]['atoms'][name]['symbol']
if symbol == 'H':
newat = at.new_in_residue()
newat.name = name
newat.symbol = symbol
k = (resn,newat.name)
newat.text_type = ffld[k]['type']
newat.partial_charge = ffld[k]['charge']
idx1 = model.index[id(at)]
idx2 = model.add_atom(newat)
bnd = Bond()
bnd.index = [ idx1, idx2 ]
bnd.order = bonds[b]['order']
mbond[idx1].append(bnd)
mbond[idx2].append(bnd)
if not skip_sort:
model.sort()
|