Repository navigation
Expand file tree
/
Copy pathStructureTools.java
More file actions
1893 lines (1664 loc) · 53.8 KB
/
Copy pathStructureTools.java
File metadata and controls
1893 lines (1664 loc) · 53.8 KB
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
/*
* BioJava development code
*
* This code may be freely distributed and modified under the
* terms of the GNU Lesser General Public Licence. This should
* be distributed with the code. If you do not have a copy,
* see:
*
* http://www.gnu.org/copyleft/lesser.html
*
* Copyright for this code is held jointly by the individual
* authors. These should be listed in @author doc comments.
*
* For more information on the BioJava project and its aims,
* or to join the biojava-l mailing list, visit the home page
* at:
*
* http://www.biojava.org/
*
* Created on Jan 4, 2006
*
*/
package org.biojava.nbio.structure;
import java.io.File;
import java.io.FileInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.HashSet;
import java.util.Iterator;
import java.util.LinkedHashSet;
import java.util.List;
import java.util.Map;
import java.util.Set;
import javax.vecmath.Matrix4d;
import org.biojava.nbio.structure.align.util.AtomCache;
import org.biojava.nbio.structure.contact.AtomContactSet;
import org.biojava.nbio.structure.contact.Grid;
import org.biojava.nbio.structure.io.FileParsingParameters;
import org.biojava.nbio.structure.io.PDBFileParser;
import org.biojava.nbio.structure.io.mmcif.chem.PolymerType;
import org.biojava.nbio.structure.io.mmcif.chem.ResidueType;
import org.biojava.nbio.structure.io.mmcif.model.ChemComp;
import org.biojava.nbio.structure.io.util.FileDownloadUtils;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
/**
* A class that provides some tool methods.
*
* @author Andreas Prlic, Jules Jacobsen
* @since 1.0
*/
public class StructureTools {
private static final Logger logger = LoggerFactory
.getLogger(StructureTools.class);
// Amino Acid backbone
/**
* The atom name of the backbone C-alpha atom. Note that this can be
* ambiguous depending on the context since Calcium atoms use the same name
* in PDB.
*/
public static final String CA_ATOM_NAME = "CA";
/**
* The atom name for the backbone amide nitrogen
*/
public static final String N_ATOM_NAME = "N";
/**
* The atom name for the backbone carbonyl
*/
public static final String C_ATOM_NAME = "C";
/**
* The atom name for the backbone carbonyl oxygen
*/
public static final String O_ATOM_NAME = "O";
/**
* The atom name of the side-chain C-beta atom
*/
public static final String CB_ATOM_NAME = "CB";
// Nucleotide backbone
/**
* The atom name of the backbone C1' in RNA
*/
public static final String C1_ATOM_NAME = "C1'";
/**
* The atom name of the backbone C2' in RNA
*/
public static final String C2_ATOM_NAME = "C2'";
/**
* The atom name of the backbone C3' in RNA
*/
public static final String C3_ATOM_NAME = "C3'";
/**
* The atom name of the backbone C4' in RNA
*/
public static final String C4_ATOM_NAME = "C4'";
/**
* The atom name of the backbone O2' in RNA
*/
public static final String O2_ATOM_NAME = "O2'";
/**
* The atom name of the backbone O3' in RNA
*/
public static final String O3_ATOM_NAME = "O3'";
/**
* The atom name of the backbone O4' in RNA
*/
public static final String O4_ATOM_NAME = "O4'";
/**
* The atom name of the backbone O4' in RNA
*/
public static final String O5_ATOM_NAME = "O5'";
/**
* The atom name of the backbone O4' in RNA
*/
public static final String OP1_ATOM_NAME = "OP1";
/**
* The atom name of the backbone O4' in RNA
*/
public static final String OP2_ATOM_NAME = "OP2";
/**
* The atom name of the backbone phosphate in RNA
*/
public static final String P_ATOM_NAME = "P";
/**
* The atom used as representative for nucleotides, equivalent to
* {@link #CA_ATOM_NAME} for proteins
*/
public static final String NUCLEOTIDE_REPRESENTATIVE = P_ATOM_NAME;
/**
* The character to use for unknown compounds in sequence strings
*/
public static final char UNKNOWN_GROUP_LABEL = 'X';
/**
* Below this ratio of aminoacid/nucleotide residues to the sequence total,
* we use simple majority of aminoacid/nucleotide residues to decide the
* character of the chain (protein/nucleotide)
*/
public static final double RATIO_RESIDUES_TO_TOTAL = 0.95;
// there is a file format change in PDB 3.0 and nucleotides are being
// renamed
private static final Map<String, Character> nucleotides30;
private static final Map<String, Character> nucleotides23;
// amino acid 3 and 1 letter code definitions
private static final Map<String, Character> aminoAcids;
private static final Set<Element> hBondDonorAcceptors;
static {
nucleotides30 = new HashMap<String, Character>();
nucleotides30.put("DA", 'A');
nucleotides30.put("DC", 'C');
nucleotides30.put("DG", 'G');
nucleotides30.put("DT", 'T');
nucleotides30.put("DI", 'I');
nucleotides30.put("A", 'A');
nucleotides30.put("G", 'G');
nucleotides30.put("C", 'C');
nucleotides30.put("U", 'U');
nucleotides30.put("I", 'I');
// the DNA linkers - the +C , +G, +A +T +U and +I have been replaced
// with these:
nucleotides30.put("TAF", UNKNOWN_GROUP_LABEL); // Fluorinated Thymine
nucleotides30.put("TC1", UNKNOWN_GROUP_LABEL); // Furanosyl
nucleotides30.put("TFE", UNKNOWN_GROUP_LABEL); // Fluorinated Thymine
nucleotides30.put("TFO", UNKNOWN_GROUP_LABEL); // Tenofovir (3'
// terminator)
nucleotides30.put("TGP", UNKNOWN_GROUP_LABEL); // Guanine variant
nucleotides30.put("THX", UNKNOWN_GROUP_LABEL); // 5' terminator
nucleotides30.put("TLC", UNKNOWN_GROUP_LABEL); // Thymine with dicyclic
// sugar
nucleotides30.put("TLN", UNKNOWN_GROUP_LABEL); // locked Thymine
nucleotides30.put("LCG", UNKNOWN_GROUP_LABEL); // locked Guanine
nucleotides30.put("TP1", UNKNOWN_GROUP_LABEL); // Thymine peptide
// nucleic acid, with
// added methyl
nucleotides30.put("CP1", UNKNOWN_GROUP_LABEL); // Cytidine peptide
// nucleic acid, with
// added methyl
nucleotides30.put("TPN", UNKNOWN_GROUP_LABEL); // Thymine peptide
// nucleic acid
nucleotides30.put("CPN", UNKNOWN_GROUP_LABEL); // Cytidine peptide
// nucleic acid
nucleotides30.put("GPN", UNKNOWN_GROUP_LABEL); // Guanine peptide
// nucleic acid
nucleotides30.put("APN", UNKNOWN_GROUP_LABEL); // Adenosine peptide
// nucleic acid
nucleotides30.put("TPC", UNKNOWN_GROUP_LABEL); // Thymine variant
// store nucleic acids (C, G, A, T, U, and I), and
// the modified versions of nucleic acids (+C, +G, +A, +T, +U, and +I),
// and
nucleotides23 = new HashMap<String, Character>();
String[] names = { "C", "G", "A", "T", "U", "I", "+C", "+G", "+A",
"+T", "+U", "+I" };
for (String n : names) {
nucleotides23.put(n, n.charAt(n.length() - 1));
}
aminoAcids = new HashMap<String, Character>();
aminoAcids.put("GLY", 'G');
aminoAcids.put("ALA", 'A');
aminoAcids.put("VAL", 'V');
aminoAcids.put("LEU", 'L');
aminoAcids.put("ILE", 'I');
aminoAcids.put("PHE", 'F');
aminoAcids.put("TYR", 'Y');
aminoAcids.put("TRP", 'W');
aminoAcids.put("PRO", 'P');
aminoAcids.put("HIS", 'H');
aminoAcids.put("LYS", 'K');
aminoAcids.put("ARG", 'R');
aminoAcids.put("SER", 'S');
aminoAcids.put("THR", 'T');
aminoAcids.put("GLU", 'E');
aminoAcids.put("GLN", 'Q');
aminoAcids.put("ASP", 'D');
aminoAcids.put("ASN", 'N');
aminoAcids.put("CYS", 'C');
aminoAcids.put("MET", 'M');
// MSE is only found as a molecular replacement for MET
aminoAcids.put("MSE", 'M');
// 'non-standard', genetically encoded
// http://www.chem.qmul.ac.uk/iubmb/newsletter/1999/item3.html
// IUBMB recommended name is 'SEC' but the wwPDB currently use 'CSE'
// likewise 'PYL' (IUBMB) and 'PYH' (PDB)
aminoAcids.put("CSE", 'U');
aminoAcids.put("SEC", 'U');
aminoAcids.put("PYH", 'O');
aminoAcids.put("PYL", 'O');
hBondDonorAcceptors = new HashSet<Element>();
hBondDonorAcceptors.add(Element.N);
hBondDonorAcceptors.add(Element.O);
hBondDonorAcceptors.add(Element.S);
}
/**
* Count how many Atoms are contained within a Structure object.
*
* @param s
* the structure object
* @return the number of Atoms in this Structure
*/
public static final int getNrAtoms(Structure s) {
int nrAtoms = 0;
Iterator<Group> iter = new GroupIterator(s);
while (iter.hasNext()) {
Group g = iter.next();
nrAtoms += g.size();
}
return nrAtoms;
}
/**
* Count how many groups are contained within a structure object.
*
* @param s
* the structure object
* @return the number of groups in the structure
*/
public static final int getNrGroups(Structure s) {
int nrGroups = 0;
List<Chain> chains = s.getChains(0);
for (Chain c : chains) {
nrGroups += c.getAtomLength();
}
return nrGroups;
}
/**
* Returns an array of the requested Atoms from the Structure object.
* Iterates over all groups and checks if the requested atoms are in this
* group, no matter if this is a {@link AminoAcid} or {@link HetatomImpl}
* group. If the group does not contain all requested atoms then no atoms
* are added for that group. For structures with more than one model, only
* model 0 will be used.
*
* @param s
* the structure to get the atoms from
*
* @param atomNames
* contains the atom names to be used.
* @return an Atom[] array
*/
public static final Atom[] getAtomArray(Structure s, String[] atomNames) {
List<Chain> chains = s.getModel(0);
List<Atom> atoms = new ArrayList<Atom>();
extractAtoms(atomNames, chains, atoms);
return atoms.toArray(new Atom[atoms.size()]);
}
/**
* Returns an array of the requested Atoms from the Structure object. In
* contrast to {@link #getAtomArray(Structure, String[])} this method
* iterates over all chains. Iterates over all chains and groups and checks
* if the requested atoms are in this group, no matter if this is a
* {@link AminoAcid} or {@link HetatomImpl} group. If the group does not
* contain all requested atoms then no atoms are added for that group. For
* structures with more than one model, only model 0 will be used.
*
* @param s
* the structure to get the atoms from
*
* @param atomNames
* contains the atom names to be used.
* @return an Atom[] array
*/
public static final Atom[] getAtomArrayAllModels(Structure s,
String[] atomNames) {
List<Atom> atoms = new ArrayList<Atom>();
for (int i = 0; i < s.nrModels(); i++) {
List<Chain> chains = s.getModel(i);
extractAtoms(atomNames, chains, atoms);
}
return atoms.toArray(new Atom[atoms.size()]);
}
/**
* Convert all atoms of the structure (first model) into an Atom array
*
* @param s
* input structure
* @return all atom array
*/
public static final Atom[] getAllAtomArray(Structure s) {
List<Atom> atoms = new ArrayList<Atom>();
AtomIterator iter = new AtomIterator(s);
while (iter.hasNext()) {
Atom a = iter.next();
atoms.add(a);
}
return atoms.toArray(new Atom[atoms.size()]);
}
/**
* Returns and array of all atoms of the chain (first model), including
* Hydrogens (if present) and all HETATOMs. Waters are not included.
*
* @param c
* input chain
* @return all atom array
*/
public static final Atom[] getAllAtomArray(Chain c) {
List<Atom> atoms = new ArrayList<Atom>();
for (Group g : c.getAtomGroups()) {
if (g.isWater())
continue;
for (Atom a : g.getAtoms()) {
atoms.add(a);
}
}
return atoms.toArray(new Atom[atoms.size()]);
}
/**
* List of groups from the structure not included in ca (e.g. ligands).
*
* Unaligned groups are searched from all chains referenced in ca, as well
* as any chains in the first model of the structure from ca[0], if any.
*
* @param ca an array of atoms
* @return
*/
public static List<Group> getUnalignedGroups(Atom[] ca) {
Set<Chain> chains = new HashSet<Chain>();
Set<Group> caGroups = new HashSet<Group>();
// Create list of all chains in this structure
Structure s = null;
if (ca.length > 0) {
Group g = ca[0].getGroup();
if (g != null) {
Chain c = g.getChain();
if (c != null) {
s = c.getStructure();
}
}
}
if (s != null) {
// Add all chains from the structure
for (Chain c : s.getChains(0)) {
chains.add(c);
}
}
// Add groups and chains from ca
for (Atom a : ca) {
Group g = a.getGroup();
if (g != null) {
caGroups.add(g);
Chain c = g.getChain();
if (c != null) {
chains.add(c);
}
}
}
// Iterate through all chains, finding groups not in ca
List<Group> unadded = new ArrayList<Group>();
for (Chain c : chains) {
for (Group g : c.getAtomGroups()) {
if (!caGroups.contains(g)) {
unadded.add(g);
}
}
}
return unadded;
}
/**
* Returns and array of all non-Hydrogen atoms in the given Structure,
* optionally including HET atoms or not. Waters are not included.
*
* @param s
* @param hetAtoms
* if true HET atoms are included in array, if false they are not
* @return
*/
public static final Atom[] getAllNonHAtomArray(Structure s, boolean hetAtoms) {
List<Atom> atoms = new ArrayList<Atom>();
AtomIterator iter = new AtomIterator(s);
while (iter.hasNext()) {
Atom a = iter.next();
if (a.getElement() == Element.H)
continue;
Group g = a.getGroup();
if (g.isWater())
continue;
if (!hetAtoms && g.getType().equals(GroupType.HETATM))
continue;
atoms.add(a);
}
return atoms.toArray(new Atom[atoms.size()]);
}
/**
* Returns and array of all non-Hydrogen atoms in the given Chain,
* optionally including HET atoms or not Waters are not included.
*
* @param c
* @param hetAtoms
* if true HET atoms are included in array, if false they are not
* @return
*/
public static final Atom[] getAllNonHAtomArray(Chain c, boolean hetAtoms) {
List<Atom> atoms = new ArrayList<Atom>();
for (Group g : c.getAtomGroups()) {
if (g.isWater())
continue;
for (Atom a : g.getAtoms()) {
if (a.getElement() == Element.H)
continue;
if (!hetAtoms && g.getType().equals(GroupType.HETATM))
continue;
atoms.add(a);
}
}
return atoms.toArray(new Atom[atoms.size()]);
}
/**
* Adds to the given atoms list, all atoms of groups that contained all
* requested atomNames, i.e. if a group does not contain all of the
* requested atom names, its atoms won't be added.
*
* @param atomNames
* @param chains
* @param atoms
*/
private static void extractAtoms(String[] atomNames, List<Chain> chains,
List<Atom> atoms) {
for (Chain c : chains) {
for (Group g : c.getAtomGroups()) {
// a temp container for the atoms of this group
List<Atom> thisGroupAtoms = new ArrayList<Atom>();
// flag to check if this group contains all the requested atoms.
boolean thisGroupAllAtoms = true;
for (String atomName : atomNames) {
Atom a = g.getAtom(atomName);
if (a == null) {
// this group does not have a required atom, skip it...
thisGroupAllAtoms = false;
break;
}
thisGroupAtoms.add(a);
}
if (thisGroupAllAtoms) {
// add the atoms of this group to the array.
for (Atom a : thisGroupAtoms) {
atoms.add(a);
}
}
}
}
}
/**
* Returns an array of the requested Atoms from the Chain object. Iterates
* over all groups and checks if the requested atoms are in this group, no
* matter if this is a AminoAcid or Hetatom group. If the group does not
* contain all requested atoms then no atoms are added for that group.
*
* @param c
* the Chain to get the atoms from
*
* @param atomNames
* contains the atom names to be used.
* @return an Atom[] array
*/
public static final Atom[] getAtomArray(Chain c, String[] atomNames) {
List<Atom> atoms = new ArrayList<Atom>();
for (Group g : c.getAtomGroups()) {
// a temp container for the atoms of this group
List<Atom> thisGroupAtoms = new ArrayList<Atom>();
// flag to check if this group contains all the requested atoms.
boolean thisGroupAllAtoms = true;
for (String atomName : atomNames) {
Atom a = g.getAtom(atomName);
if (a == null) {
logger.debug("Group " + g.getResidueNumber() + " ("
+ g.getPDBName()
+ ") does not have the required atom '" + atomName
+ "'");
// this group does not have a required atom, skip it...
thisGroupAllAtoms = false;
break;
}
thisGroupAtoms.add(a);
}
if (thisGroupAllAtoms) {
// add the atoms of this group to the array.
for (Atom a : thisGroupAtoms) {
atoms.add(a);
}
}
}
return atoms.toArray(new Atom[atoms.size()]);
}
/**
* Returns an Atom array of the C-alpha atoms. Any atom that is a carbon and
* has CA name will be returned.
*
* @param c
* the structure object
* @return an Atom[] array
* @see #getRepresentativeAtomArray(Chain)
*/
public static final Atom[] getAtomCAArray(Chain c) {
List<Atom> atoms = new ArrayList<Atom>();
for (Group g : c.getAtomGroups()) {
if (g.hasAtom(CA_ATOM_NAME)
&& g.getAtom(CA_ATOM_NAME).getElement() == Element.C) {
atoms.add(g.getAtom(CA_ATOM_NAME));
}
}
return atoms.toArray(new Atom[atoms.size()]);
}
/**
* Gets a representative atom for each group that is part of the chain
* backbone. Note that modified aminoacids won't be returned as part of the
* backbone if the {@link org.biojava.nbio.structure.io.mmcif.ReducedChemCompProvider} was used to load the
* structure.
*
* For amino acids, the representative is a CA carbon. For nucleotides, the
* representative is the {@value #NUCLEOTIDE_REPRESENTATIVE}. Other group
* types will be ignored.
*
* @param c
* @return representative Atoms of the chain backbone
* @since Biojava 4.1.0
*/
public static final Atom[] getRepresentativeAtomArray(Chain c) {
List<Atom> atoms = new ArrayList<Atom>();
for (Group g : c.getAtomGroups()) {
switch (g.getType()) {
case AMINOACID:
if (g.hasAtom(CA_ATOM_NAME)
&& g.getAtom(CA_ATOM_NAME).getElement() == Element.C) {
atoms.add(g.getAtom(CA_ATOM_NAME));
}
break;
case NUCLEOTIDE:
if (g.hasAtom(NUCLEOTIDE_REPRESENTATIVE)) {
atoms.add(g.getAtom(NUCLEOTIDE_REPRESENTATIVE));
}
break;
default:
// don't add
}
}
return atoms.toArray(new Atom[atoms.size()]);
}
/**
* Provides an equivalent copy of Atoms in a new array. Clones everything,
* starting with parent groups and chains. The chain will only contain
* groups that are part of the input array.
*
* @param ca
* array of representative atoms, e.g. CA atoms
* @return Atom array
* @deprecated Use the better-named {@link #cloneAtomArray(Atom[])} instead
*/
@Deprecated
public static final Atom[] cloneCAArray(Atom[] ca) {
return cloneAtomArray(ca);
}
/**
* Provides an equivalent copy of Atoms in a new array. Clones everything,
* starting with parent groups and chains. The chain will only contain
* groups that are part of the input array.
*
* @param ca
* array of representative atoms, e.g. CA atoms
* @return Atom array
* @since Biojava 4.1.0
*/
public static final Atom[] cloneAtomArray(Atom[] ca) {
Atom[] newCA = new Atom[ca.length];
List<Chain> model = new ArrayList<Chain>();
int apos = -1;
for (Atom a : ca) {
apos++;
Group parentG = a.getGroup();
Chain parentC = parentG.getChain();
Chain newChain = null;
for (Chain c : model) {
if (c.getName().equals(parentC.getName())) {
newChain = c;
break;
}
}
if (newChain == null) {
newChain = new ChainImpl();
newChain.setId(parentC.getId());
newChain.setName(parentC.getName());
model.add(newChain);
}
Group parentN = (Group) parentG.clone();
newCA[apos] = parentN.getAtom(a.getName());
try {
// if the group doesn't exist yet, this produces a StructureException
newChain.getGroupByPDB(parentN.getResidueNumber());
} catch (StructureException e) {
// the group doesn't exist yet in the newChain, let's add it
newChain.addGroup(parentN);
}
}
return newCA;
}
/**
* Clone a set of representative Atoms, but returns the parent groups
*
* @param ca
* Atom array
* @return Group array
*/
public static Group[] cloneGroups(Atom[] ca) {
Group[] newGroup = new Group[ca.length];
List<Chain> model = new ArrayList<Chain>();
int apos = -1;
for (Atom a : ca) {
apos++;
Group parentG = a.getGroup();
Chain parentC = parentG.getChain();
Chain newChain = null;
for (Chain c : model) {
if (c.getName().equals(parentC.getName())) {
newChain = c;
break;
}
}
if (newChain == null) {
newChain = new ChainImpl();
newChain.setName(parentC.getName());
model.add(newChain);
}
Group ng = (Group) parentG.clone();
newGroup[apos] = ng;
newChain.addGroup(ng);
}
return newGroup;
}
/**
* Utility method for working with circular permutations. Creates a
* duplicated and cloned set of Calpha atoms from the input array.
*
* @param ca2
* atom array
* @return cloned and duplicated set of input array
*/
public static Atom[] duplicateCA2(Atom[] ca2) {
// we don't want to rotate input atoms, do we?
Atom[] ca2clone = new Atom[ca2.length * 2];
int pos = 0;
Chain c = null;
String prevChainId = "";
for (Atom a : ca2) {
Group g = (Group) a.getGroup().clone(); // works because each group
// has only a single atom
if (c == null) {
c = new ChainImpl();
Chain orig = a.getGroup().getChain();
c.setId(orig.getId());
c.setName(orig.getName());
} else {
Chain orig = a.getGroup().getChain();
if (!orig.getId().equals(prevChainId)) {
c = new ChainImpl();
c.setId(orig.getId());
c.setName(orig.getName());
}
}
c.addGroup(g);
ca2clone[pos] = g.getAtom(a.getName());
pos++;
}
// Duplicate ca2!
c = null;
prevChainId = "";
for (Atom a : ca2) {
Group g = (Group) a.getGroup().clone();
if (c == null) {
c = new ChainImpl();
Chain orig = a.getGroup().getChain();
c.setId(orig.getId());
c.setName(orig.getName());
} else {
Chain orig = a.getGroup().getChain();
if (!orig.getId().equals(prevChainId)) {
c = new ChainImpl();
c.setId(orig.getId());
c.setName(orig.getName());
}
}
c.addGroup(g);
ca2clone[pos] = g.getAtom(a.getName());
pos++;
}
return ca2clone;
}
/**
* Return an Atom array of the C-alpha atoms. Any atom that is a carbon and
* has CA name will be returned.
*
* @param s
* the structure object
* @return an Atom[] array
* @see #getRepresentativeAtomArray(Structure)
*/
public static Atom[] getAtomCAArray(Structure s) {
List<Atom> atoms = new ArrayList<Atom>();
for (Chain c : s.getChains()) {
for (Group g : c.getAtomGroups()) {
if (g.hasAtom(CA_ATOM_NAME)
&& g.getAtom(CA_ATOM_NAME).getElement() == Element.C) {
atoms.add(g.getAtom(CA_ATOM_NAME));
}
}
}
return atoms.toArray(new Atom[atoms.size()]);
}
/**
* Gets a representative atom for each group that is part of the chain
* backbone. Note that modified aminoacids won't be returned as part of the
* backbone if the {@link org.biojava.nbio.structure.io.mmcif.ReducedChemCompProvider} was used to load the
* structure.
*
* For amino acids, the representative is a CA carbon. For nucleotides, the
* representative is the {@value #NUCLEOTIDE_REPRESENTATIVE}. Other group
* types will be ignored.
*
* @param s
* Input structure
* @return representative Atoms of the structure backbone
* @since Biojava 4.1.0
*/
public static Atom[] getRepresentativeAtomArray(Structure s) {
List<Atom> atoms = new ArrayList<Atom>();
for (Chain c : s.getChains()) {
Atom[] chainAtoms = getRepresentativeAtomArray(c);
for (Atom a : chainAtoms) {
atoms.add(a);
}
}
return atoms.toArray(new Atom[atoms.size()]);
}
/**
* Return an Atom array of the main chain atoms: CA, C, N, O Any group that
* contains those atoms will be included, be it a standard aminoacid or not
*
* @param s
* the structure object
* @return an Atom[] array
*/
public static Atom[] getBackboneAtomArray(Structure s) {
List<Atom> atoms = new ArrayList<Atom>();
for (Chain c : s.getChains()) {
for (Group g : c.getAtomGroups()) {
if (g.hasAminoAtoms()) {
// this means we will only take atoms grom groups that have
// complete backbones
for (Atom a : g.getAtoms()) {
switch (g.getType()) {
case NUCLEOTIDE:
// Nucleotide backbone
if (a.getName().equals(C1_ATOM_NAME))
atoms.add(a);
if (a.getName().equals(C2_ATOM_NAME))
atoms.add(a);
if (a.getName().equals(C3_ATOM_NAME))
atoms.add(a);
if (a.getName().equals(C4_ATOM_NAME))
atoms.add(a);
if (a.getName().equals(O2_ATOM_NAME))
atoms.add(a);
if (a.getName().equals(O3_ATOM_NAME))
atoms.add(a);
if (a.getName().equals(O4_ATOM_NAME))
atoms.add(a);
if (a.getName().equals(O5_ATOM_NAME))
atoms.add(a);
if (a.getName().equals(OP1_ATOM_NAME))
atoms.add(a);
if (a.getName().equals(OP2_ATOM_NAME))
atoms.add(a);
if (a.getName().equals(P_ATOM_NAME))
atoms.add(a);
// TODO Allow C4* names as well as C4'? -SB 3/2015
break;
case AMINOACID:
default:
// we do it this way instead of with g.getAtom() to
// be sure we always use the same order as original
if (a.getName().equals(CA_ATOM_NAME))
atoms.add(a);
if (a.getName().equals(C_ATOM_NAME))
atoms.add(a);
if (a.getName().equals(N_ATOM_NAME))
atoms.add(a);
if (a.getName().equals(O_ATOM_NAME))
atoms.add(a);
break;
}
}
}
}
}
return atoms.toArray(new Atom[atoms.size()]);
}
/**
* Convert three character amino acid codes into single character e.g.
* convert CYS to C. Valid 3-letter codes will be those of the standard 20
* amino acids plus MSE, CSE, SEC, PYH, PYL (see the {@link #aminoAcids}
* map)
*
* @return the 1 letter code, or null if the given 3 letter code does not
* correspond to an amino acid code
* @param groupCode3
* a three character amino acid representation String
* @see {@link #get1LetterCode(String)}
*/
public static final Character get1LetterCodeAmino(String groupCode3) {
return aminoAcids.get(groupCode3);
}
/**
*
* @param code3
* @return
* @deprecated Use {@link #get1LetterCodeAmino(String)} instead
*/
@Deprecated
public static final Character convert_3code_1code(String code3) {
return get1LetterCodeAmino(code3);
}
/**
* Convert a three letter amino acid or nucleotide code into a single
* character code. If the code does not correspond to an amino acid or
* nucleotide, returns {@link #UNKNOWN_GROUP_LABEL}.
*
* Returned null for nucleotides prior to version 4.0.1.
*
* @param groupCode3
* three letter representation
* @return The 1-letter abbreviation
*/
public static final Character get1LetterCode(String groupCode3) {
Character code1;
// is it a standard amino acid ?
code1 = get1LetterCodeAmino(groupCode3);
if (code1 == null) {
// hm groupCode3 is not standard
// perhaps it is a nucleotide?
groupCode3 = groupCode3.trim();
if (isNucleotide(groupCode3)) {
code1 = nucleotides30.get(groupCode3);
if (code1 == null) {
code1 = nucleotides23.get(groupCode3);