forked from qrefine/qrefine
-
Notifications
You must be signed in to change notification settings - Fork 0
/
completion.py
1140 lines (1093 loc) · 36.7 KB
/
completion.py
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
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
import math
import sys
from string import letters
import iotbx
from mmtbx.monomer_library import server
from scitbx import matrix
from scitbx.math import dihedral_angle
from iotbx.pdb import amino_acid_codes as aac
mon_lib_server = server.server()
get_class = iotbx.pdb.common_residue_names_get_class
from utils import hierarchy_utils
from mmtbx.hydrogens.specialised_hydrogen_atoms import conditional_add_cys_hg_to_atom_group
def d_squared(xyz1, xyz2):
d2 = 0
for i in range(3):
d2 += (xyz2[i]-xyz1[i])**2
return d2
def get_bond_vector(a1,a2,unit=False):
vector = []
l = 0
for i in range(3):
vector.append(a1.xyz[i]-a2.xyz[i])
l+=vector[i]**2
if unit:
l=math.sqrt(l)
for i in range(3):
vector[i] /= l
return tuple(vector)
def construct_xyz(ba, bv,
aa, av,
da, dv,
period=3,
):
assert ba is not None
assert aa is not None
assert da is not None
rn = matrix.col(ba.xyz)
rca = matrix.col(aa.xyz)
rc = matrix.col(da.xyz)
rcca = rc -rca
e0 = (rn - rca).normalize()
e1 = (rcca - (rcca.dot(e0))*e0).normalize()
e2 = e0.cross(e1)
pi = math.pi
alpha = math.radians(av)
phi = math.radians(dv)
rh_list = []
for n in range(0, period):
rh = rn + bv * (math.sin(alpha)*(math.cos(phi + n*2*pi/period)*e1 +
math.sin(phi + n*2*pi/period)*e2) -
math.cos(alpha)*e0)
rh_list.append(rh)
return rh_list
def _add_atom_to_chain(atom, ag, icode=None):
rg = _add_atom_to_residue_group(atom, ag, icode=icode)
chain = ag.parent().parent()
tc = iotbx.pdb.hierarchy.chain()
tc.id = chain.id
tc.append_residue_group(rg)
return tc
def _add_atom_to_residue_group(atom, ag, icode=None):
tag = iotbx.pdb.hierarchy.atom_group()
tag.resname = ag.resname
tag.append_atom(atom)
rg = iotbx.pdb.hierarchy.residue_group()
rg.resseq = ag.parent().resseq
if icode is not None: rg.icode=icode
rg.append_atom_group(tag)
for i, c in enumerate(letters):
if c==ag.parent().parent().id:
break
atom.tmp = i
return rg
def get_atoms_by_names(ag, l=None, all_or_nothing=True):
assert l
rc = []
for name in l:
atom = ag.get_atom(name)
rc.append(atom)
if len(l)!=len(filter(None, rc)): return None
return rc
def add_n_terminal_hydrogens_to_atom_group(ag,
use_capping_hydrogens=False,
append_to_end_of_model=False,
retain_original_hydrogens=True,
n_ca_c=None,
):
rc=[]
if n_ca_c is not None:
n, ca, c = n_ca_c
else:
n = ag.get_atom("N")
if n is None: return 'no N'
ca = ag.get_atom("CA")
if ca is None: return 'no CA'
c = ag.get_atom("C")
if c is None: return 'no C'
atom = ag.get_atom('H')
dihedral=120.
if atom:
dihedral = dihedral_angle(sites=[atom.xyz,
n.xyz,
ca.xyz,
c.xyz,
],
deg=True)
if retain_original_hydrogens: pass
else:
if ag.get_atom("H"): # maybe needs to be smarter or actually work
ag.remove_atom(ag.get_atom('H'))
#if use_capping_hydrogens and 0:
# for i, atom in enumerate(ag.atoms()):
# if atom.name == ' H3 ':
# ag.remove_atom(i)
# break
# add H1
rh3 = construct_xyz(n, 0.9,
ca, 109.5,
c, dihedral,
)
# this could be smarter
possible = ['H', 'H1', 'H2', 'H3', 'HT1', 'HT2']
h_count = 0
for h in possible:
if ag.get_atom(h): h_count+=1
number_of_hydrogens=3
if use_capping_hydrogens:
number_of_hydrogens-=1
#if ag.atoms()[0].parent().resname=='PRO':
# number_of_hydrogens=-1
# # should name the hydrogens correctly
if h_count>=number_of_hydrogens: return []
for i in range(0, number_of_hydrogens):
name = " H%d " % (i+1)
if retain_original_hydrogens:
if i==0 and ag.get_atom('H'): continue
if ag.get_atom(name.strip()): continue
if ag.resname=='PRO':
if i==0:
continue
atom = iotbx.pdb.hierarchy.atom()
atom.name = name
atom.element = "H"
atom.xyz = rh3[i]
atom.occ = n.occ
atom.b = n.b
atom.segid = ' '*4
if append_to_end_of_model and i+1==number_of_hydrogens:
rg = _add_atom_to_chain(atom,
ag,
icode=n.parent().parent().icode)
rc.append(rg)
else:
ag.append_atom(atom)
return rc
def add_n_terminal_hydrogens_to_residue_group(residue_group,
use_capping_hydrogens=False,
append_to_end_of_model=False,
):
rc=[]
for ag, (n, ca, c) in generate_atom_group_atom_names(residue_group,
['N', 'CA', 'C'],
):
tmp = add_n_terminal_hydrogens_to_atom_group(
ag,
use_capping_hydrogens=use_capping_hydrogens,
append_to_end_of_model=append_to_end_of_model,
n_ca_c=[n,ca,c],
)
assert type(tmp)!=type(''), 'not string "%s" %s' % (tmp, type(tmp))
rc += tmp
return rc
def add_n_terminal_hydrogens(hierarchy,
#residue_selection=None,
add_to_chain_breaks=False,
):
assert 0
# add N terminal hydrogens because Reduce only does it to resseq=1
# needs to be alt.loc. aware for non-quantum-refine
for chain_i, chain in enumerate(hierarchy.chains()):
for res_i, residue_group in enumerate(chain.residue_groups()):
if len(residue_group.atom_groups())>1: continue
atom_group = residue_group.atom_groups()[0]
if get_class(atom_group.resname) not in ["common_amino_acid",
"modified_amino_acid",
]:
continue
if res_i==0: # need better switch
add_n_terminal_hydrogens_to_atom_group(atom_group)
hierarchy.atoms_reset_serial()
hierarchy.atoms().reset_i_seq()
return hierarchy
def add_c_terminal_oxygens_to_atom_group(ag,
use_capping_hydrogens=False,
append_to_end_of_model=False,
c_ca_n=None,
):
#
# do we need ANISOU
#
rc = []
atom_name=' OXT'
atom_element = 'O'
bond_length=1.231
if use_capping_hydrogens:
if ag.get_atom(atom_name.strip()): return []
atom_name=" HC "
atom_element="H"
bond_length=1.
if ag.get_atom(atom_name.strip()): return []
if c_ca_n is not None:
c, ca, n = c_ca_n
else:
c = ag.get_atom("C")
if c is None: return
ca = ag.get_atom("CA")
if ca is None: return
n = ag.get_atom("N")
if n is None: return
atom = ag.get_atom('O')
dihedral = dihedral_angle(sites=[atom.xyz,
c.xyz,
ca.xyz,
n.xyz,
],
deg=True)
ro2 = construct_xyz(c, bond_length,
ca, 120.,
n, dihedral,
period=2,
)
oxys = [' O ', atom_name]
for i in range(0,2):
name = oxys[i]
atom = ag.get_atom(name.strip())
if atom:
pass #atom.xyz = ro2[i]
else:
atom = iotbx.pdb.hierarchy.atom()
atom.name = name
atom.element = atom_element
atom.occ = c.occ
atom.b = c.b
atom.segid = ' '*4
atom.xyz = ro2[i]
if append_to_end_of_model:
chain = _add_atom_to_chain(atom,
ag,
icode=c.parent().parent().icode)
rc.append(chain)
else:
# add the atom to the hierarchy
ag.append_atom(atom)
return rc
def add_c_terminal_oxygens_to_residue_group(residue_group,
use_capping_hydrogens=False,
append_to_end_of_model=False,
):
rc=[]
for ag, (c, ca, n) in generate_atom_group_atom_names(residue_group,
['C', 'CA', 'N'],
):
tmp = add_c_terminal_oxygens_to_atom_group(
ag,
use_capping_hydrogens=use_capping_hydrogens,
append_to_end_of_model=append_to_end_of_model,
c_ca_n = [c, ca, n],
)
rc += tmp
return rc
def add_c_terminal_oxygens(hierarchy,
):
assert 0
for chain_i, chain in enumerate(hierarchy.chains()):
for res_i, residue_group in enumerate(chain.residue_groups()):
if len(residue_group.atom_groups())>1: continue
atom_group = residue_group.atom_groups()[0]
if get_class(atom_group.resname) not in ["common_amino_acid",
"modified_amino_acid",
]:
continue
if capping_hydrogens:
assert 0
if res_i==len(chain.residue_groups())-1: # need better switch
add_c_terminal_oxygens_to_atom_group(atom_group)
hierarchy.atoms_reset_serial()
hierarchy.atoms().reset_i_seq()
return hierarchy
def _add_hydrogens_to_atom_group_using_bad(ag,
atom_name,
atom_element,
bond_atom,
angle_atom,
dihedral_atom,
bond_length,
angle,
dihedral,
append_to_end_of_model=False,
):
rc = []
if ag.get_atom(atom_name.strip()): return []
if type(bond_atom)==type(''):
ba = ag.get_atom(bond_atom.strip())
#print bond_atom,ba.quote()
if ba is None: return
else: ba = bond_atom
if type(angle_atom)==type(''):
aa = ag.get_atom(angle_atom.strip())
#print angle_atom,aa.quote()
if aa is None: return
else: aa = angle_atom
if type(dihedral_atom)==type(''):
da = ag.get_atom(dihedral_atom.strip())
#print dihedral_atom, da.quote()
if da is None: return
else: da = dihedral_atom
ro2 = construct_xyz(ba, bond_length,
aa, angle,
da, dihedral,
period=1,
)
atom = iotbx.pdb.hierarchy.atom()
atom.name = atom_name
atom.element = atom_element
atom.occ = ba.occ
atom.b = ba.b
# altloc???
atom.hetero = ba.hetero
atom.segid = ' '*4
atom.xyz = ro2[0]
if append_to_end_of_model:
chain = _add_atom_to_chain(atom,
ag,
icode=ba.parent().parent().icode)
rc.append(chain)
else:
ag.append_atom(atom)
return rc
def add_cys_hg_to_atom_group(ag,
append_to_end_of_model=False,
):
#
# do we need ANISOU
#
rc = _add_hydrogens_to_atom_group_using_bad(
ag,
' HG ',
'H',
'SG',
'CB',
'CA',
1.2,
120.,
160.,
append_to_end_of_model=append_to_end_of_model,
)
return rc
def add_cys_hg_to_residue_group(rg,
append_to_end_of_model=False,
):
rc=[]
for ag in rg.atom_groups():
if ag.resname not in ['CYS']: continue
rc += add_cys_hg_to_atom_group(
ag,
append_to_end_of_model=append_to_end_of_model,
)
return rc
def remove_cys_hg_from_residue_group(rg):
for ag in rg.atom_groups():
if ag.resname not in ['CYS']: continue
for atom in ag.atoms():
if atom.name==' HG ':
ag.remove_atom(atom)
break
def conditional_remove_cys_hg_to_atom_group(geometry_restraints_manager,
rg,
):
sgs = None
for atom in rg.atoms():
if atom.name.strip()=='SG' and atom.parent().resname=='CYS':
sgs = atom.i_seq
break
if sgs:
sg_bonds = generate_bonded_i_seqs(geometry_restraints_manager, rg, sgs)
if len(sg_bonds)>2:
remove_cys_hg_from_residue_group(rg)
def generate_bonded_i_seqs(geometry_restraints_manager, rg, j_seq):
def _not_j_seq(j_seq, i_seqs):
i_seqs.remove(j_seq)
return i_seqs[0]
bonds = []
for bond in geometry_restraints_manager.pair_proxies().bond_proxies.simple:
if j_seq in bond.i_seqs:
bonds.append(_not_j_seq(j_seq, list(bond.i_seqs)))
for bond in geometry_restraints_manager.pair_proxies().bond_proxies.asu:
if j_seq in [bond.i_seq, bond.j_seq]:
bonds.append(_not_j_seq(j_seq, [bond.i_seq, bond.j_seq]))
return bonds
def iterate_over_threes(hierarchy,
geometry_restraints_manager,
use_capping_hydrogens=False,
append_to_end_of_model=False,
verbose=False,
):
atoms = hierarchy.atoms()
###
def get_residue_group(residue):
for atom in residue.atoms():
atom = atoms[atom.i_seq]
break
return atom.parent().parent()
###
additional_hydrogens=hierarchy_utils.smart_add_atoms()
for three in hierarchy_utils.generate_protein_fragments(
hierarchy,
geometry_restraints_manager,
backbone_only=False,
use_capping_hydrogens=use_capping_hydrogens,
):
if verbose: print three
if not len(three): continue
ptr=0
assert three.are_linked()
if use_capping_hydrogens:
for i in range(len(three)):
rg = get_residue_group(three[i])
conditional_add_cys_hg_to_atom_group(geometry_restraints_manager, rg)
else:
for i in range(len(three)):
rg = get_residue_group(three[i])
conditional_remove_cys_hg_to_atom_group(geometry_restraints_manager, rg)
# check if N-term residue - FVA
n_term_done = False
if three[0].resname in ['FVA',
]:
n_term_done = True
ptr+=1
assert ptr==1, 'ptr (%d) is not 1' % ptr
if three.start and not n_term_done:
ptr+=1
assert ptr==1, 'ptr (%d) is not 1' % ptr
rg = get_residue_group(three[0])
rc = add_n_terminal_hydrogens_to_residue_group(
rg,
use_capping_hydrogens=use_capping_hydrogens,
append_to_end_of_model=append_to_end_of_model,
)
if rc: additional_hydrogens.append(rc)
#hierarchy.reset_i_seq_if_necessary()
c_term_done = False
if three[-1].resname in ['ETA',
]:
c_term_done = True
ptr-=1
assert ptr==0, 'ptr (%d) is not 0' % ptr
if three.end and not c_term_done:
ptr-=1
assert ptr==0, 'ptr (%d) is not 0' % ptr
rg = get_residue_group(three[-1])
rc = add_c_terminal_oxygens_to_residue_group(
rg,
use_capping_hydrogens=use_capping_hydrogens,
append_to_end_of_model=append_to_end_of_model,
)
if rc: additional_hydrogens.append(rc)
#hierarchy.reset_i_seq_if_necessary()
else:
pass
return additional_hydrogens
def iterate_using_original(hierarchy,
geometry_restraints_manager,
original_hierarchy,
use_capping_hydrogens=False,
append_to_end_of_model=False,
):
slots=[]
start=18
assert len(original_hierarchy.models())==1
assert len(hierarchy.models())==1
for chain in original_hierarchy.chains():
for org in chain.residue_groups():
protein = True
for atom_group in org.atom_groups():
if(get_class(atom_group.resname) not in ["common_amino_acid",
"modified_amino_acid",
] and
atom_group.resname not in aac.three_letter_l_given_three_letter_d):
protein=False
break
if not protein:
slots.append(False)
continue
org_atom1_quote = org.atoms()[0].quote()[start:]
for rg in hierarchy.residue_groups():
if rg.atoms()[0].quote()[start:]==org_atom1_quote:
slots.append(rg)
break
else:
slots.append(0)
slots.append(None)
ptr=0
additional_hydrogens=[]
for i in range(len(slots)):
start=False
end=False
if slots[i]:
if i==0: start=True
elif not slots[i-1]: start=True
if i==len(slots)-1: end=True
elif not slots[i+1]: end=True
# does not work for chain ends
else: continue
rg = slots[i]
conditional_add_cys_hg_to_atom_group(geometry_restraints_manager,
rg)
if start:
ptr+=1
assert ptr==1
if hierarchy_utils.is_n_terminal_residue(rg):
rc = None
else:
rc = add_n_terminal_hydrogens_to_residue_group(
rg,
use_capping_hydrogens=use_capping_hydrogens,
append_to_end_of_model=append_to_end_of_model,
)
if rc: additional_hydrogens.append(rc)
if end:
ptr-=1
assert ptr==0
rc = add_c_terminal_oxygens_to_residue_group(
rg,
use_capping_hydrogens=use_capping_hydrogens,
append_to_end_of_model=append_to_end_of_model,
)
if rc: additional_hydrogens.append(rc)
else:
pass
return additional_hydrogens
def use_electrons_to_add_hdyrogens(hierarchy,
geometry_restraints_manager,
use_capping_hydrogens=False,
append_to_end_of_model=False,
):
if not use_capping_hydrogens: return
from qrefine.utils import electrons
rc=[]
raw_records = hierarchy_utils.get_raw_records(
pdb_hierarchy=hierarchy,
crystal_symmetry=geometry_restraints_manager.crystal_symmetry,
)
charges = electrons.run(pdb_filename=None,
raw_records=raw_records,
return_formal_charges=True,
)
charged_atoms = charges.get_charged_atoms()
remove=[]
for atom, electrons in charged_atoms:
atom_group = atom.parent()
#if atom_group.resname=='CYS' and atom.name==' SG ':
# if electrons==-1 and atom_group.get_atom('HG'):
# remove.append(atom_group.get_atom('HG'))
if atom.element_is_hydrogen() and electrons==1:
#print 'REMOVING', atom.quote()
remove.append(atom)
if get_class(atom.parent().resname) in ['common_amino_acid',
]:
continue
atom = hierarchy.atoms()[atom.i_seq]
# this does not even work
rc = _add_hydrogens_to_atom_group_using_bad(
atom.parent(),
' H1 ',
'H',
atom.name.strip(),
'C4',
'C3',
1.,
120.,
160.,
append_to_end_of_model=append_to_end_of_model,
)
def _atom_i_seq(a1, a2):
if a1.i_seq<a2.i_seq: return -1
return 1
if remove:
remove.sort(_atom_i_seq)
remove.reverse()
for atom in remove:
# this is a kludge
name = atom.name
atom = hierarchy.atoms()[atom.i_seq]
atom_group = atom.parent()
atom = atom_group.get_atom(name.strip())
atom_group.remove_atom(atom)
return rc
def add_terminal_hydrogens(
hierarchy,
geometry_restraints_manager,
add_to_chain_breaks=False,
use_capping_hydrogens=False, # instead of terminal H
append_to_end_of_model=False, # useful for Q|R
#use_capping_only_on_chain_breaks=False,
original_hierarchy=None,
occupancy=1.,
verbose=False,
):
# add N terminal hydrogens because Reduce only does it to resseq=1
# needs to be alt.loc. aware for non-quantum-refine
if original_hierarchy:
additional_hydrogens = iterate_using_original(
hierarchy,
geometry_restraints_manager,
original_hierarchy,
use_capping_hydrogens=use_capping_hydrogens,
append_to_end_of_model=append_to_end_of_model,
)
else:
additional_hydrogens=iterate_over_threes(
hierarchy,
geometry_restraints_manager,
use_capping_hydrogens=use_capping_hydrogens,
append_to_end_of_model=append_to_end_of_model,
)
# add hydrogens to non-protein
non_protein = False
for atom_group in hierarchy.atom_groups():
if get_class(atom_group.resname) not in ['common_amino_acid']:
non_protein=True
break
if non_protein or 1:
rc = use_electrons_to_add_hdyrogens(
hierarchy,
geometry_restraints_manager,
use_capping_hydrogens=use_capping_hydrogens,
append_to_end_of_model=append_to_end_of_model,
)
if rc: additional_hydrogens += [rc]
if append_to_end_of_model and additional_hydrogens:
tmp = []
for group in additional_hydrogens:
for chain in group:
tmp.append(chain)
_add_atoms_from_chains_to_end_of_hierarchy(hierarchy, tmp)
def _add_atoms_from_chains_to_end_of_hierarchy(hierarchy, chains):
lookup = {}
for chain in chains:
lookup.setdefault(chain.id, [])
lookup[chain.id].append(chain)
model = hierarchy.models()[0]
for i, chain_group in sorted(lookup.items()):
tc = iotbx.pdb.hierarchy.chain()
tc.id = i
for chain in chain_group:
for rg in chain.residue_groups():
tc.append_residue_group(rg.detached_copy())
model.append_chain(tc)
def _add_atoms_from_residue_groups_to_end_of_hierarchy(hierarchy, rgs):
assert 0
chains = {}
for rg in rgs:
for atom in rg.atoms():
# this is a bad idea
cid = atom.tmp
if cid not in chains:
chains[cid] = iotbx.pdb.hierarchy.chain()
chains[cid].id = letters[cid]
chains[cid].append_residue_group(rg)
model = hierarchy.models()[0]
for i, chain in sorted(chains.items()):
model.append_chain(chain)
def remove_acid_side_chain_hydrogens(hierarchy):
removes = {"GLU" : "HE2",
"ASP" : "HD2",
}
for ag in hierarchy.atom_groups():
r = removes.get(ag.resname, None)
if r is None: continue
atom = ag.get_atom(r)
if atom:
ag.remove_atom(atom)
hierarchy.atoms_reset_serial()
hierarchy.atoms().reset_i_seq()
return hierarchy
def _eta_peptide_h(hierarchy,
geometry_restraints_manager,
verbose=False,
):
atoms = hierarchy.atoms()
###
def get_residue_group(residue):
for atom in residue.atoms():
atom = atoms[atom.i_seq]
break
return atom.parent().parent()
###
for three in hierarchy_utils.generate_protein_fragments(
hierarchy,
geometry_restraints_manager,
backbone_only=False,
#use_capping_hydrogens=use_capping_hydrogens,
):
if len(three)==1: continue
if three[-1].resname!='ETA': continue
print three
eta = get_residue_group(three[-1])
print dir(eta)
previous = get_residue_group(three[-2])
print previous
print dir(previous)
for ag in previous.atom_groups(): # smarter?
previous_c = ag.get_atom('C')
previous_o = ag.get_atom('O')
for ag in eta.atom_groups(): # needs to be conformers...
atom_name = ' H '
if ag.get_atom(atom_name):
assert 0
else:
for atom in ag.atoms(): print atom.format_atom_record()
rc = _add_hydrogens_to_atom_group_using_bad(
ag,
atom_name,
'H',
'N',
previous_c, #'CA',
previous_o, #'CB',
1.,
120.,
180.,
#append_to_end_of_model=append_to_end_of_model,
)
assert rc is not None
print '-'*80
for atom in ag.atoms(): print atom.format_atom_record()
# hierarchy.show()
#assert 0
def generate_atom_group_atom_names(rg, names):
'''
Generate all alt. loc. groups of names
'''
atom_groups = rg.atom_groups()
atom_altlocs = {}
for ag in atom_groups:
for atom in ag.atoms():
atom_altlocs.setdefault(atom.parent().altloc, [])
atom_altlocs[atom.parent().altloc].append(atom)
keys = atom_altlocs.keys()
if len(keys)>1 and '' in keys:
for key in keys:
if key=='': continue
for atom in atom_altlocs['']:
atom_altlocs[key].append(atom)
del atom_altlocs['']
for key, item in atom_altlocs.items():
atoms=[]
for name in names:
for atom in item:
if atom.name.strip()==name.strip():
atoms.append(atom)
break
else:
assert 0, 'atoms not found %s' % names
yield atoms[0].parent(), atoms
def _h_h2_on_N(hierarchy,
geometry_restraints_manager,
verbose=False,
):
atoms = hierarchy.atoms()
###
def get_residue_group(residue):
for atom in residue.atoms():
atom = atoms[atom.i_seq]
break
return atom.parent().parent()
###
def get_atom_from_residue_group(residue, label):
h = None
for ag in residue.atom_groups():
h = ag.get_atom(label)
if h: break
return h
###
n_done = []
for three in hierarchy_utils.generate_protein_fragments(
hierarchy,
geometry_restraints_manager,
backbone_only=False,
#use_capping_hydrogens=use_capping_hydrogens,
):
if len(three)==1: continue
for i, residue in enumerate(three):
if not i: continue
residue = get_residue_group(residue)
h = get_atom_from_residue_group(residue, 'H')
if h is None:
for ag, (n, ca, c) in generate_atom_group_atom_names(residue,
['N', 'CA', 'C'],
):
if ag.resname in ['PRO']: continue
if n in n_done: continue
n_done.append(n)
dihedral = 0
rh3 = construct_xyz(n, 0.9,
ca, 109.5,
c, dihedral,
)
atom = iotbx.pdb.hierarchy.atom()
atom.name = ' H '
atom.element = "H"
atom.xyz = rh3[0]
atom.occ = n.occ
atom.b = n.b
atom.segid = ' '*4
ag.append_atom(atom)
assert ag.resname!='PRO'
def special_case_hydrogens(hierarchy,
geometry_restraints_manager,
verbose=False,
):
for special_case in [
#_eta_peptide_h,
_h_h2_on_N,
]:
rc = special_case(hierarchy,
geometry_restraints_manager,
verbose=verbose,
)
hierarchy.sort_atoms_in_place()
def complete_pdb_hierarchy(hierarchy,
geometry_restraints_manager,
use_capping_hydrogens=False,
append_to_end_of_model=False,
pdb_filename=None,
pdb_inp=None,
original_pdb_filename=None,
verbose=False,
debug=False,
):
"""Complete PDB hierarchy with hydrogen atoms as needed
This needs to move to Phenix with better functionality
Args:
hierarchy (hierarchy): Starting model
geometry_restraints_manager (GRM): Starting restraints
use_capping_hydrogens (bool, optional): Capping or not
append_to_end_of_model (bool, optional): Added atoms go to end of atom list
pdb_filename (None, optional): Description
pdb_inp (None, optional): Description
original_pdb_filename (None, optional): Description
verbose (bool, optional): Description
debug (bool, optional): Description
Returns:
TYPE: Description
Raises:
Sorry: Description
"""
for ag in hierarchy.atom_groups():
if get_class(ag.resname) in ['common_rna_dna']:
raise Sorry('')
from mmtbx.building import extend_sidechains
params=None
original_hierarchy = None
if use_capping_hydrogens:
params = hierarchy_utils.get_pdb_interpretation_params()
params.link_distance_cutoff=1.8 # avoid linking across a single missing AA
if original_pdb_filename:
original_pdb_inp = iotbx.pdb.input(original_pdb_filename)
original_hierarchy = original_pdb_inp.construct_hierarchy()
if debug:
output = hierarchy_utils.write_hierarchy(pdb_filename,
pdb_inp,
hierarchy,
'temp1',
)
#
# assume model is heavy-atom complete
#
if not use_capping_hydrogens:
if debug:
ppf = hierarchy_utils.get_processed_pdb(pdb_filename=output)
else:
raw_records = hierarchy_utils.get_raw_records(pdb_inp, hierarchy)
ppf = hierarchy_utils.get_processed_pdb(raw_records=raw_records,
params=params,
)
sites_cart = hierarchy.atoms().extract_xyz()
ppf.all_chain_proxies.pdb_hierarchy.atoms().set_xyz(sites_cart)
n_changed = extend_sidechains.extend_protein_model(
ppf.all_chain_proxies.pdb_hierarchy,
mon_lib_server,
add_hydrogens=False,
)
if debug:
print 'number of side chains changed',n_changed
output = hierarchy_utils.write_hierarchy(pdb_filename,
pdb_inp,
ppf.all_chain_proxies.pdb_hierarchy,
'temp2',
)
#
# need to use Reduce/ReadySet! to add hydrogens
#
if not use_capping_hydrogens:
output = hierarchy_utils.write_hierarchy(
pdb_filename,
pdb_inp,
ppf.all_chain_proxies.pdb_hierarchy,
'readyset_input',
)
hierarchy = hierarchy_utils.add_hydrogens_using_ReadySet(output)
#
# remove side chain acid hydrogens - maybe not required since recent changes
#
if debug:
ppf = hierarchy_utils.get_processed_pdb(pdb_filename=output,
params=params,
)
else:
raw_records = hierarchy_utils.get_raw_records(pdb_inp, hierarchy)
ppf = hierarchy_utils.get_processed_pdb(raw_records=raw_records,
params=params,
)
sites_cart = hierarchy.atoms().extract_xyz()
ppf.all_chain_proxies.pdb_hierarchy.atoms().set_xyz(sites_cart)
remove_acid_side_chain_hydrogens(ppf.all_chain_proxies.pdb_hierarchy)
#
# add hydrogens in special cases
# eg ETA
# eg N - H, H2
#
if debug:
ppf = hierarchy_utils.get_processed_pdb(pdb_filename=output,
params=params,
)
else:
hierarchy = ppf.all_chain_proxies.pdb_hierarchy
raw_records = hierarchy_utils.get_raw_records(pdb_inp, hierarchy)
ppf = hierarchy_utils.get_processed_pdb(raw_records=raw_records,
params=params,
)
sites_cart = hierarchy.atoms().extract_xyz()
ppf.all_chain_proxies.pdb_hierarchy.atoms().set_xyz(sites_cart)
special_case_hydrogens(ppf.all_chain_proxies.pdb_hierarchy,
ppf.geometry_restraints_manager(),
#use_capping_hydrogens=use_capping_hydrogens,
#append_to_end_of_model=append_to_end_of_model,
#original_hierarchy=original_hierarchy,
verbose=verbose,
)
#
# add terminals atoms including hydrogens and OXT - more docs here...
#
if debug:
output = hierarchy_utils.write_hierarchy(
pdb_filename,
pdb_inp,