-
Notifications
You must be signed in to change notification settings - Fork 2
/
DataAnnotation.java
5459 lines (5237 loc) · 272 KB
/
DataAnnotation.java
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
/*
* To change this license header, choose License Headers in Project Properties.
* To change this template file, choose Tools | Templates
* and open the template in the editor.
*/
package tappas;
import javafx.beans.property.SimpleIntegerProperty;
import javafx.beans.property.SimpleStringProperty;
import javafx.collections.FXCollections;
import javafx.collections.ObservableList;
import tappas.DbProject.AFIdStatsData;
import tappas.DbProject.AFStatsData;
import java.io.*;
import java.nio.charset.StandardCharsets;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.*;
//
// TODO: Clean up and move some code to one or more new classes - way too big right now
//
/**
*
* @author Hector del Risco - [email protected] & Pedro Salguero - [email protected]
*/
public class DataAnnotation extends AppObject {
static public final int MIN_GOCNT = 5;
static public final int MAX_GOCNT = 500;
static public final int TRANS_CUTOFF_LEN = 100;
static public final int PROTEIN_CUTOFF_LEN = 10;
static public final int MAX_UTR_LENGTH_DIFF = 60;
static enum AnnotationType { TRANS, PROTEIN, GENOMIC };
static enum DiversityType { LENGTH, COUNT, TYPE_COUNT };
static public enum IsoRegion { ALL, CODING, NONCODING };
static public enum IsoType { ALL, CODING, NONCODING };
public static final String PROVEAN_EXACT = "Exact_Principal_Isoform"; // update if TSV is changed to a value
public static final double PEXACT_SCORE = Double.MAX_VALUE;
static public final String DBCATNOID = "<NO_ID>";
// Internal DB categories
public static final String INTDB = "~Internal";
public static final String INTCAT_FLUSHDATA = "~nt_flushdata";
public static final String INTCAT_NODATA = "~nt_nodata";
public static final String INTCAT_3UTR = "~nt_3UTR";
public static final String INTCAT_5UTR = "~nt_5UTR";
public static final String INTCAT_CDS = "~nt_CDS";
public static final String INTCAT_SPLICEJUNCTION = "~nt_splice_junction";
public static final String INTCAT_EXON = "~nt_exon";
static public enum AnnotFeature {
NONE, TRANSCRIPT, PROTEIN, GENOMIC,
GENE, CDS, EXON, SPLICEJUNCTION
}
public static final String TAPPAS_PROTEIN = "tappASPID_";
public static final String TAPPAS_SOURCE = "tappAS";
public static final String STRUCTURAL_SOURCE = "TranscriptAttributes";
public static final String POLYA_FEATURE = "polyA_Site";
public static final String CDS_FEATURE = "CDS_Length";
public static final String UTRLENGTH3_FEATURE = "3UTR_Length";
public static final String UTRLENGTH5_FEATURE = "5UTR_Length";
AnnotationFileDefs fileDefs;
public ArrayList<AnnotFeatureDef> lstAnnotFeatureDefs = new ArrayList<>();
// gene and protein descriptions
private HashMap<String, String> hmGeneDescriptions = new HashMap<>();
private HashMap<String, String> hmProteinDescriptions = new HashMap<>();
private HashMap<String, HashMap<String, HashMap<String, String>>> hmFeatureDescriptions = new HashMap<>();
// genes with hashmap of transcripts
private HashMap<String, HashMap<String, Object>> hmGeneTrans = new HashMap<>();
// transcripts with TransData
private HashMap<String, TransData> hmTransData = new HashMap<>();
// proteins to transcript map
private HashMap<String, HashMap<String, Object>> hmProteinTrans = new HashMap<>();
//
// Data loaded on a need to basis
//
private HashMap<String, HashMap<String, Object>> hmAllAFs = new HashMap<>();
private HashMap<String, AnnotSourceStats> hmAnnotSourceStats = new HashMap<>();
private HashMap<String, HashMap<String, AFStatsData>> hmAFStats = new HashMap<>();
private HashMap<String, ArrayList<String>> hmAFStatsPositional = new HashMap<>();
private HashMap<String, ArrayList<String>> hmAFStatsPresence = new HashMap<>();
private HashMap<String, HashMap<String, String>> hmAFStatsType = new HashMap<>();
// transcript:source:feature:id:"count:positions string"
// Ex: PB.1606.1:pfam:DOMAIN:PF17121:"2:P3-50;P63-92"
private HashMap<String, HashMap<String, HashMap<String, HashMap<String, String>>>> hmTransAFIdPos = new HashMap<>(); //FEA
private HashMap<String, HashMap<String, HashMap<String, HashMap<String, String>>>> hmTransAFIdGenPos = new HashMap<>(); //NewGenomicPos
public DataAnnotation(Project project) {
super(project, null);
}
public void initialize() {
clearData();
// populate reserved source/feature list
fileDefs = project.data.getAnnotationFileDefs();
lstAnnotFeatureDefs.clear();
lstAnnotFeatureDefs.add(new AnnotFeatureDef(AnnotFeature.TRANSCRIPT, fileDefs.transcript.source, fileDefs.transcript.feature));
lstAnnotFeatureDefs.add(new AnnotFeatureDef(AnnotFeature.PROTEIN, fileDefs.protein.source, fileDefs.protein.feature));
lstAnnotFeatureDefs.add(new AnnotFeatureDef(AnnotFeature.GENOMIC, fileDefs.genomic.source, fileDefs.genomic.feature));
lstAnnotFeatureDefs.add(new AnnotFeatureDef(AnnotFeature.GENE, fileDefs.gene.source, fileDefs.gene.feature));
lstAnnotFeatureDefs.add(new AnnotFeatureDef(AnnotFeature.CDS, fileDefs.cds.source, fileDefs.cds.feature));
lstAnnotFeatureDefs.add(new AnnotFeatureDef(AnnotFeature.EXON, fileDefs.exon.source, fileDefs.exon.feature));
lstAnnotFeatureDefs.add(new AnnotFeatureDef(AnnotFeature.SPLICEJUNCTION, fileDefs.sj.source, fileDefs.sj.feature));
}
//
// Source:Feature Functions
//
public boolean isRsvdNoDiversityFeature(String db, String cat) {
return (getRsvdAnnotFeature(db, cat).equals(AnnotFeature.GENE) || getRsvdAnnotFeature(db, cat).equals(AnnotFeature.GENOMIC) ||
getRsvdAnnotFeature(db, cat).equals(AnnotFeature.PROTEIN) || getRsvdAnnotFeature(db, cat).equals(AnnotFeature.CDS) ||
getRsvdAnnotFeature(db, cat).equals(AnnotFeature.TRANSCRIPT) || getRsvdAnnotFeature(db, cat).equals(AnnotFeature.EXON));
}
public boolean isRsvdFeature(String db, String cat) { return (!getRsvdAnnotFeature(db, cat).equals(AnnotFeature.NONE) || isInternalFeature(db, cat)); }
public boolean isInternalFeature(String db, String cat) { return cat.startsWith("~nt_"); }
public AnnotFeatureDef getRsvdAnnotFeatureDef(AnnotFeature id) {
AnnotFeatureDef def = null;
for(AnnotFeatureDef d : lstAnnotFeatureDefs) {
if(d.id.equals(id)) {
def = new AnnotFeatureDef(d.id, d.source, d.feature);
break;
}
}
return def;
}
public AnnotFeature getRsvdAnnotFeature(String source, String feature) {
AnnotFeature id = AnnotFeature.NONE;
for(AnnotFeatureDef d : lstAnnotFeatureDefs) {
if(d.source.equals(source) && d.feature.equals(feature)) {
id = d.id;
break;
}
}
return id;
}
//
// Public Functions
//
// Note: this is run on a background thread when a project is first opened
// no direct GUI access is allowed from any of these functions
// It is the responsibility of higher level code to make sure none of
// the relevant functions in this class are called before the data is loaded
public boolean loadBaseData() {
boolean result = false;
long tstart = System.nanoTime();
clearData();
System.out.println("Loading base project annotation data...");
hmGeneTrans = project.data.loadGeneTrans();
DbProject.TransDataResults trd = project.data.loadTransData();
//System.out.println("Assigning transcript values...");
hmTransData = trd.hmTransData;
//System.out.println("Assigning gene descriptions...");
hmGeneDescriptions = trd.hmGeneDescriptions;
//System.out.println("Assigning protein descriptions...");
hmProteinDescriptions = trd.hmProteinDescriptions;
hmFeatureDescriptions = project.data.loadFeatureDescriptions();
hmAFStatsPresence = project.data.loadAFStatsPresence();
hmAFStatsPositional = project.data.loadAFStatsPositional();
hmAFStats = project.data.loadAFStats();
hmAFStatsType = project.data.loadAFStatsType();
if(!hmGeneTrans.isEmpty() && !hmTransData.isEmpty()) {
// build protein to transcript map
for(TransData td : hmTransData.values()) {
if(!td.protein.isEmpty()) {
if(!hmProteinTrans.containsKey(td.protein)) {
HashMap<String, Object> hm = new HashMap<>();
hm.put(td.trans, null);
hmProteinTrans.put(td.protein, hm);
}
else
hmProteinTrans.get(td.protein).put(td.trans, null);
}
}
result = true;
}
//result = true;
long tend = System.nanoTime();
long duration = (tend - tstart)/1000000;
System.out.println("Total time: " + duration + " ms");
return result;
}
public void clearData() {
hmGeneTrans.clear();
hmTransData.clear();
hmProteinTrans.clear();
hmGeneDescriptions.clear();
hmTransAFIdPos.clear();
hmAFStats.clear();
hmAnnotSourceStats.clear();
}
public void clearFilteredData() {
// clear statistical data
hmAFStats.clear();
hmAnnotSourceStats.clear();
}
// get annotation summary data for given transcript group filter - database:category:[entries, uniqueIds]
public SummaryData getSummaryData(HashMap<String, HashMap<String, Object>> hmTGFilter, boolean includeReserved) {
HashMap<String, String> hmTFilter = new HashMap<>();
HashMap<String, Object> hmGeneCount = new HashMap<>();
HashMap<String, Object> hmTransCount = new HashMap<>();
boolean filter = (hmTGFilter != null && !hmTGFilter.isEmpty());
if(filter) {
for(String gene : hmTGFilter.keySet()) {
HashMap<String, Object> hm = hmTGFilter.get(gene);
for(String trans : hm.keySet())
hmTFilter.put(trans, gene);
}
}
// this can take a few secs to load if not already loaded
loadTransAFIdPos();
HashMap<String, HashMap<String, HashMap<String, Integer>>> hmDBCatIdCounts = new HashMap<>();
for(String trans : hmTransAFIdPos.keySet()) {
if(!filter || hmTFilter.containsKey(trans)) {
HashMap<String, HashMap<String, HashMap<String, String>>> hmTransDB = hmTransAFIdPos.get(trans);
for(String db : hmTransDB.keySet()) {
HashMap<String, HashMap<String, String>> hmTransDBCat = hmTransDB.get(db);
for(String cat : hmTransDBCat.keySet()) {
if(includeReserved || !isRsvdFeature(db, cat)) {
// only update the gene/trans count hashmaps if we include the db cat
hmTransCount.put(trans, null);
hmGeneCount.put(hmTFilter.get(trans), null);
HashMap<String, String> hmTransDBCatId = hmTransDBCat.get(cat);
for(String id : hmTransDBCatId.keySet()) {
if(hmDBCatIdCounts.containsKey(db)) {
HashMap<String, HashMap<String, Integer>> hmCat = hmDBCatIdCounts.get(db);
if(hmCat.containsKey(cat)) {
HashMap<String, Integer> hmId = hmCat.get(cat);
if(hmId.containsKey(id))
hmId.put(id, hmId.get(id) + TransFeatureIdValues.getCount(hmTransDBCatId.get(id)));
else
hmId.put(id, TransFeatureIdValues.getCount(hmTransDBCatId.get(id)));
}
else {
HashMap<String, Integer> hmId = new HashMap<>();
hmId.put(id, TransFeatureIdValues.getCount(hmTransDBCatId.get(id)));
hmCat.put(cat, hmId);
}
}
else {
HashMap<String, HashMap<String, Integer>> hmCat = new HashMap<>();
HashMap<String, Integer> hmId = new HashMap<>();
hmId.put(id, TransFeatureIdValues.getCount(hmTransDBCatId.get(id)));
hmCat.put(cat, hmId);
hmDBCatIdCounts.put(db, hmCat);
}
}
}
}
}
}
}
SummaryData data = new SummaryData(hmGeneCount.size(), hmTransCount.size(), hmDBCatIdCounts);
return data;
}
public HashMap<String, AFStatsData> getSummaryDBStatsData(String dbFilter, HashMap<String, HashMap<String, Object>> hmTGFilter, boolean includeReserved) {
HashMap<String, AFStatsData> hmDBCatStats = new HashMap<>();
HashMap<String, String> hmTFilter = new HashMap<>();
boolean filter = (hmTGFilter != null && !hmTGFilter.isEmpty());
if(filter) {
for(String gene : hmTGFilter.keySet()) {
HashMap<String, Object> hm = hmTGFilter.get(gene);
for(String trans : hm.keySet())
hmTFilter.put(trans, gene);
}
}
loadTransAFIdPos();
for(String trans : hmTransAFIdPos.keySet()) {
if(!filter || hmTFilter.containsKey(trans)) {
HashMap<String, HashMap<String, HashMap<String, String>>> hmDB = hmTransAFIdPos.get(trans);
for(String db : hmDB.keySet()) {
if(db.equals(dbFilter)) {
HashMap<String, HashMap<String, String>> hmCat = hmDB.get(db);
for(String cat : hmCat.keySet()) {
if(includeReserved || !isRsvdFeature(db, cat)) {
boolean updcnt = true;
HashMap<String, String> hmIds = hmCat.get(cat);
for(String id : hmIds.keySet()) {
if(hmDBCatStats.containsKey(cat)) {
// we are only going to track the category transcripts in the loop
// we will use the end results to set the counts and idcounts
AFStatsData sd = hmDBCatStats.get(cat);
if(updcnt) {
sd.transCount++;
updcnt = false;
}
if(sd.hmIds.containsKey(id)) {
// we found an existing category id, add entries for this transcript
// and increment transcript count by one
sd.hmIds.get(id).count += TransFeatureIdValues.getCount(hmIds.get(id));
sd.hmIds.get(id).transCount++;
}
else
sd.hmIds.put(id, new AFIdStatsData("", "", TransFeatureIdValues.getCount(hmIds.get(id)), 1));
}
else {
AFStatsData sd = new AFStatsData(1, 1, 1);
sd.hmIds.put(id, new AFIdStatsData("", "", TransFeatureIdValues.getCount(hmIds.get(id)), 1));
hmDBCatStats.put(cat, sd);
updcnt = false;
}
}
}
}
}
}
}
}
// update the category counts and idCounts from results
for(String cat : hmDBCatStats.keySet()) {
AFStatsData sd = hmDBCatStats.get(cat);
sd.idCount = sd.hmIds.size();
sd.count = 0;
for(AFIdStatsData idd : sd.hmIds.values())
sd.count += idd.count;
}
return hmDBCatStats;
}
public HashMap<String, AnnotSourceStats> getAnnotSourceStats(HashMap<String, Object> hmFilterTrans) {
if(hmAnnotSourceStats.isEmpty())
hmAnnotSourceStats = project.data.loadAnnotSourceStats();
return hmAnnotSourceStats;
}
public ArrayList<String[]> getAnnotationData(String gene, HashMap<String, Object> hmTransFilter) {
long tstart = System.nanoTime();
ArrayList<String[]> lst = new ArrayList<>();
try {
System.out.println("Annotation data requested for gene '" + gene + "'");
String fields[];
String line, transid;
ArrayList<String> lstAnnotations = project.data.loadGeneAnnotations(gene);
int cnt = lstAnnotations.size();
boolean findStart = false;
boolean errflg = false;
for(int lstidx = 0; lstidx < cnt && !errflg; lstidx++) {
line = lstAnnotations.get(lstidx);
fields = line.split("\t");
//10 because I add length field
if(fields.length == 10) {
AnnotFeature dbcatid = project.data.getRsvdAnnotFeature(fields[1], fields[2]);
if(dbcatid == AnnotFeature.TRANSCRIPT) {
transid = fields[0];
if(hmTransFilter != null && !hmTransFilter.containsKey(transid)) {
// set to find next transcript
findStart = true;
continue;
}
lst.add(fields);
}
else {
// check if we are looking for start of transcript annotations
if(findStart)
continue;
else {
lst.clear();
errflg = true;
logger.logError("Bad annotation entry: " + line);
break;
}
}
for(++lstidx; lstidx < cnt && !errflg; lstidx++) {
line = lstAnnotations.get(lstidx);
fields = line.split("\t");
if(fields.length == 10) {
AnnotFeature afid = project.data.getRsvdAnnotFeature(fields[1], fields[2]);
if(afid == AnnotFeature.TRANSCRIPT) {
lstidx--;
break;
}
else {
if(transid.equals(fields[0]))
lst.add(fields);
else
break;
}
}
}
}
}
}
catch (Exception e) {
logger.logError("Unable to get gene annotation data: " + e.getMessage());
lst.clear();
}
System.out.println("Returning " + lst.size() + " annotation entries.");
long tend = System.nanoTime();
long duration = (tend - tstart)/1000000;
System.out.println("Total time: " + duration + " ms");
return lst;
}
// Get transcripts annotations for the given transcripts list all belonging to the given gene
public ArrayList<AnnotationDataEntry> getTransAnnotationData(String gene, ArrayList<String> transcripts) {
HashMap<String, Object> hmTransFilter = new HashMap<>();
for(String trans : transcripts)
hmTransFilter.put(trans, null);
ArrayList<String[]> lad = getAnnotationData(gene, hmTransFilter);
// get gene annotation data
long tstart = System.nanoTime();
ArrayList<AnnotationDataEntry> lst = new ArrayList<>();
ArrayList<AnnotationDataEntry> alst = new ArrayList<>();
try {
String[] fields;
int cnt = lad.size();
for(int lstidx = 0; lstidx < cnt; lstidx++) {
fields = lad.get(lstidx);
int start = 0;
int end = 0;
int length = 0;
try { start = Integer.parseInt(fields[3]); } catch(Exception e) {}
try { end = Integer.parseInt(fields[4]); } catch(Exception e) {}
try { length = Integer.parseInt(fields[9]); } catch(Exception e) {}
lst.clear();
lst.add(new AnnotationDataEntry(fields[0], fields[1], fields[2], start, end, fields[5], fields[6], fields[7], fields[8], length));
for(++lstidx; lstidx < cnt; lstidx++) {
fields = lad.get(lstidx);
AnnotFeature afid = project.data.getRsvdAnnotFeature(fields[1], fields[2]);
if(afid == AnnotFeature.TRANSCRIPT) {
lstidx--;
break;
}
else {
start = 0;
end = 0;
try { start = Integer.parseInt(fields[3]); } catch(Exception e) {}
try { end = Integer.parseInt(fields[4]); } catch(Exception e) {}
try { length = Integer.parseInt(fields[9]); } catch(Exception e) {}
lst.add(new AnnotationDataEntry(fields[0], fields[1], fields[2], start, end, fields[5], fields[6], fields[7], fields[8], length));
}
}
// some items are required to be in order so do it just in case
// tsv is required to have the transcript section first followed by the genomic section and then protein section
for(AnnotationDataEntry a : lst) {
if(getRsvdAnnotFeature(a.db, a.category).equals(AnnotFeature.TRANSCRIPT)) {
alst.add(a);
break;
}
}
for(AnnotationDataEntry a : lst) {
if(getRsvdAnnotFeature(a.db, a.category).equals(AnnotFeature.GENE)) {
alst.add(a);
break;
}
}
for(AnnotationDataEntry a : lst) {
if(getRsvdAnnotFeature(a.db, a.category).equals(AnnotFeature.CDS)) {
alst.add(a);
break;
}
}
for(AnnotationDataEntry a : lst) {
if(getRsvdAnnotFeature(a.db, a.category).equals(AnnotFeature.EXON))
alst.add(a);
}
for(AnnotationDataEntry a : lst) {
if(!getRsvdAnnotFeature(a.db, a.category).equals(AnnotFeature.TRANSCRIPT) &&
!getRsvdAnnotFeature(a.db, a.category).equals(AnnotFeature.GENE) &&
!getRsvdAnnotFeature(a.db, a.category).equals(AnnotFeature.CDS) &&
!getRsvdAnnotFeature(a.db, a.category).equals(AnnotFeature.EXON))
alst.add(a);
}
}
}
catch (Exception e) {
logger.logError("Unable to get gene transcripts annotation data: " + e.getMessage());
alst.clear();
}
System.out.println("Returning " + alst.size() + " entries.");
long tend = System.nanoTime();
long duration = (tend - tstart)/1000000;
System.out.println("Total time: " + duration + " ms");
return alst;
}
//
// Get Transcript Information Functions
// this information is loaded at initialization for all transcripts
//
public HashMap<String, Object> getGeneTrans(String gene) {
HashMap<String, Object> hmResults = new HashMap<>();
if(hmGeneTrans.containsKey(gene)) {
HashMap<String, Object> hm = hmGeneTrans.get(gene);
for(String trans : hm.keySet())
hmResults.put(trans, null);
}
return hmResults;
}
public HashMap<String, HashMap<String, Object>> getGeneTrans(boolean multipleOnly) {
HashMap<String, HashMap<String, Object>> hmResults = new HashMap<>();
for(String gene : hmGeneTrans.keySet()) {
HashMap<String, Object> hm = new HashMap<>();
if(!multipleOnly || hmGeneTrans.get(gene).size() > 1) {
for(String trans : hmGeneTrans.get(gene).keySet())
hm.put(trans, null);
hmResults.put(gene, hm);
}
}
return hmResults;
}
public boolean hasGene(String gene) {
return hmGeneTrans.containsKey(gene);
}
public boolean hasProtein(String protein) {
return hmProteinTrans.containsKey(protein);
}
public boolean hasTranscript(String trans) {
return hmTransData.containsKey(trans);
}
public String getGeneChromo(String gene) {
String chromo = "";
if(hmGeneTrans.containsKey(gene)) {
for(String trans : hmGeneTrans.get(gene).keySet()) {
TransData td = hmTransData.get(trans);
if(td != null) {
chromo = td.chromo;
break;
}
}
}
return chromo;
}
public String getGeneStrand(String gene) {
String strand = "";
if(hmGeneTrans.containsKey(gene)) {
for(String trans : hmGeneTrans.get(gene).keySet()) {
TransData td = hmTransData.get(trans);
if(td != null) {
strand = td.negStrand? "-" : "+";
break;
}
}
}
return strand;
}
public int getGeneProteinsCount(String gene) {
int count = 0;
if(hmGeneTrans.containsKey(gene))
count = getTransProteinCount(hmGeneTrans.get(gene));
return count;
}
public int getGeneTransCount(String gene) {
int count = 0;
if(hmGeneTrans.containsKey(gene))
count = hmGeneTrans.get(gene).size();
return count;
}
// Note: will return counts of 0 for genes that do not have the requested type
public HashMap<String, Integer> getGeneTransCount(IsoType type) {
HashMap<String, Integer> hmResults = new HashMap<>();
HashMap<String, Object> hm;
boolean coding;
for(String gene : hmGeneTrans.keySet()) {
int cnt = 0;
hm = hmGeneTrans.get(gene);
if(type == IsoType.ALL)
cnt = hm.size();
else {
for(String trans : hm.keySet()) {
coding = isTransCoding(trans);
if((coding && type == IsoType.CODING) || (!coding && type == IsoType.NONCODING))
cnt++;
}
}
hmResults.put(gene, cnt);
}
return hmResults;
}
public HashMap<String, HashMap<String, Object>> getAssignedProteinGenes() {
HashMap<String, HashMap<String, Object>> hmResults = new HashMap<>();
HashMap<String, Object> hm;
String prot;
boolean coding;
for(String gene : hmGeneTrans.keySet()) {
hm = hmGeneTrans.get(gene);
for(String trans : hm.keySet()) {
coding = isTransCoding(trans);
if(coding) {
prot = getTransAssignedProtein(trans);
if(!hmResults.containsKey(prot))
hmResults.put(prot, new HashMap<>());
HashMap<String, Object> hmGenes = hmResults.get(prot);
if(!hmGenes.containsKey(gene))
hmGenes.put(gene, null);
}
}
}
return hmResults;
}
public String getGeneDescription(String gene) {
String desc = "";
if(hmGeneDescriptions.containsKey(gene))
desc= hmGeneDescriptions.get(gene);
return desc;
}
public String getProteinDescription(String protein) {
String desc = "";
if(hmProteinDescriptions.containsKey(protein))
desc= hmProteinDescriptions.get(protein);
return desc;
}
public String getFeatureDescription(String source, String feature, String ID) {
String desc = "";
if(hmFeatureDescriptions.containsKey(source)){
HashMap<String, HashMap<String, String>> hmFeature = hmFeatureDescriptions.get(source);
if(hmFeature.containsKey(feature)){
HashMap<String, String> hmID = hmFeature.get(feature);
if(hmID.containsKey(ID)){
desc = hmID.get(ID);
}
}
}
return desc;
}
public HashMap<String, HashMap<String, Object>> getGeneAssignedProteins(HashMap<String, HashMap<String, Object>> hmFilterGeneTrans) {
HashMap<String, HashMap<String, Object>> hmResults = new HashMap<>();
HashMap<String, Object> hm;
boolean coding;
if(hmFilterGeneTrans == null)
hmFilterGeneTrans = new HashMap<>();
boolean filter = !hmFilterGeneTrans.isEmpty();
for(String gene : hmGeneTrans.keySet()) {
if(!filter || hmFilterGeneTrans.containsKey(gene)) {
String prot;
hm = hmGeneTrans.get(gene);
for(String trans : hm.keySet()) {
if(!filter || hmFilterGeneTrans.get(gene).containsKey(trans)) {
coding = isTransCoding(trans);
if(coding) {
prot = getTransAssignedProtein(trans);
if(!hmResults.containsKey(gene))
hmResults.put(gene, new HashMap<>());
HashMap<String, Object> hmGenes = hmResults.get(gene);
if(!hmGenes.containsKey(prot))
hmGenes.put(prot, null);
}
}
}
}
}
return hmResults;
}
// Note: will return counts of 0 for genes that do not have any assigned proteins
public HashMap<String, Integer> getGeneAssignedProteinsCount(HashMap<String, HashMap<String, Object>> hmFilterGeneTrans) {
HashMap<String, Integer> hmResults = new HashMap<>();
HashMap<String, Object> hm;
boolean coding;
if(hmFilterGeneTrans == null)
hmFilterGeneTrans = new HashMap<>();
boolean filter = !hmFilterGeneTrans.isEmpty();
for(String gene : hmGeneTrans.keySet()) {
if(!filter || hmFilterGeneTrans.containsKey(gene)) {
String prot;
hm = hmGeneTrans.get(gene);
HashMap<String, Object> hmProts = new HashMap<>();
for(String trans : hm.keySet()) {
if(!filter || hmFilterGeneTrans.get(gene).containsKey(trans)) {
coding = isTransCoding(trans);
if(coding) {
prot = getTransAssignedProtein(trans);
if(!hmProts.containsKey(prot))
hmProts.put(prot, null);
}
}
}
hmResults.put(gene, hmProts.size());
}
}
return hmResults;
}
public int getAssignedProteinsCount(HashMap<String, HashMap<String, Object>> hmFilterGeneTrans) {
HashMap<String, Object> hm;
HashMap<String, String> hmDupProts = new HashMap<>();
HashMap<String, Object> hmProts = new HashMap<>();
String prot;
boolean coding;
if(hmFilterGeneTrans == null)
hmFilterGeneTrans = new HashMap<>();
boolean filter = !hmFilterGeneTrans.isEmpty();
for(String gene : hmGeneTrans.keySet()) {
if(!filter || hmFilterGeneTrans.containsKey(gene)) {
hm = hmGeneTrans.get(gene);
for(String trans : hm.keySet()) {
if(!filter || hmFilterGeneTrans.get(gene).containsKey(trans)) {
coding = isTransCoding(trans);
if(coding) {
prot = getTransAssignedProtein(trans);
if(!hmProts.containsKey(prot))
hmProts.put(prot, null);
else
hmDupProts.put(gene + "\t" + trans, prot);
}
}
}
}
}
for(String key : hmDupProts.keySet())
System.out.println(key + "\t" + hmDupProts.get(key));
System.out.println("Dup proteins: " + hmDupProts.size());
return hmProts.size();
}
public HashMap<String, Integer> getAssignedProteinsLength(HashMap<String, HashMap<String, Object>> hmFilterGeneTrans) {
int cnt = 0;
HashMap<String, Object> hm;
HashMap<String, Integer> hmProts = new HashMap<>();
String prot;
SeqAlign.Position pos;
boolean coding;
if(hmFilterGeneTrans == null)
hmFilterGeneTrans = new HashMap<>();
boolean filter = !hmFilterGeneTrans.isEmpty();
for(String gene : hmGeneTrans.keySet()) {
if(!filter || hmFilterGeneTrans.containsKey(gene)) {
hm = hmGeneTrans.get(gene);
for(String trans : hm.keySet()) {
if(!filter || hmFilterGeneTrans.get(gene).containsKey(trans)) {
coding = isTransCoding(trans);
if(coding) {
prot = getTransAssignedProtein(trans);
if(!hmProts.containsKey(prot)) {
pos = hmTransData.get(trans).posCDS;
int len = pos.end - pos.start + 1;
if(pos.start == 0 || pos.end == 0)
len = 0;
hmProts.put(prot, len/3);
}
}
}
}
}
}
return hmProts;
}
// will return a transcript length of 0 for transcripts not found in transcript length list
public HashMap<String, HashMap<String, Integer>> getGeneTransLength(HashMap<String, HashMap<String, Object>> hmFilterGeneTrans) {
HashMap<String, HashMap<String, Integer>> hmResults = new HashMap<>();
HashMap<String, Object> hmGT;
HashMap<String, Integer> hm;
if(hmFilterGeneTrans == null)
hmFilterGeneTrans = new HashMap<>();
boolean filter = !hmFilterGeneTrans.isEmpty();
for(String gene : hmGeneTrans.keySet()) {
if(!filter || hmFilterGeneTrans.containsKey(gene)) {
hmGT = hmGeneTrans.get(gene);
hm = new HashMap<>();
hmResults.put(gene, hm);
for(String trans : hmGT.keySet()) {
if(!filter || hmFilterGeneTrans.get(gene).containsKey(trans)) {
if(hmTransData.containsKey(trans))
hm.put(trans, hmTransData.get(trans).length);
else
hm.put(trans, 0);
}
}
}
}
return hmResults;
}
// will not include proteins for any transcript not in list
public HashMap<String, HashMap<String, Integer>> getGeneProteinsLength(HashMap<String, HashMap<String, Object>> hmFilterGeneTrans) {
HashMap<String, HashMap<String, Integer>> hmResults = new HashMap<>();
HashMap<String, Object> hmGT;
HashMap<String, Integer> hm;
if(hmFilterGeneTrans == null)
hmFilterGeneTrans = new HashMap<>();
boolean filter = hmFilterGeneTrans.isEmpty();
for(String gene : hmGeneTrans.keySet()) {
if(!filter || hmFilterGeneTrans.containsKey(gene)) {
hmGT = hmGeneTrans.get(gene);
hm = new HashMap<>();
hmResults.put(gene, hm);
for(String trans : hmGT.keySet()) {
if(!filter || hmFilterGeneTrans.get(gene).containsKey(trans)) {
if(hmTransData.containsKey(trans)) {
TransData td = hmTransData.get(trans);
if(td.coding)
hm.put(td.protein, td.protLength);
}
}
}
}
}
return hmResults;
}
public int getTransLength(String trans) {
int len = 0;
if(hmTransData.containsKey(trans))
len = hmTransData.get(trans).length;
return len;
}
public int getTransGenomicLength(String trans) {
int len = 0;
if(hmTransData.containsKey(trans)) {
ArrayList<SeqAlign.Position> lst = hmTransData.get(trans).lstExons;
if(lst != null && !lst.isEmpty()) {
int strpos = lst.get(0).start;
int endpos = lst.get(lst.size() - 1).end;
len = Math.abs(endpos - strpos) + 1;
}
}
return len;
}
public int getTransProteinLength(String trans) {
int len = 0;
if(hmTransData.containsKey(trans)) {
if(hmTransData.get(trans).coding) {
SeqAlign.Position pos = hmTransData.get(trans).posCDS;
if(pos.start != 0 && pos.end != 0) {
len = Math.floorDiv((pos.end - pos.start + 1), 3);
// need to adjust for stop codon
if(len > 0)
len--;
}
}
}
return len;
}
// only the length of transcripts found is returned in the list, i.e. it does not return 0 if not found
// Warning: the lengths are not in any reliable order - this is meant for distribution computations
public ArrayList<Integer> getTransLengthArray(HashMap<String, HashMap<String, Object>> hmFilterGeneTrans) {
ArrayList<Integer> lst = new ArrayList<>();
HashMap<String, Object> hmGT;
if(hmFilterGeneTrans == null)
hmFilterGeneTrans = new HashMap<>();
boolean filter = !hmFilterGeneTrans.isEmpty();
for(String gene : hmGeneTrans.keySet()) {
if(!filter || hmFilterGeneTrans.containsKey(gene)) {
hmGT = hmGeneTrans.get(gene);
for(String trans : hmGT.keySet()) {
if(!filter || hmFilterGeneTrans.get(gene).containsKey(trans)) {
if(hmTransData.containsKey(trans))
lst.add(hmTransData.get(trans).length);
}
}
}
}
return lst;
}
// only the CDS length of transcripts found is returned in the list, i.e. it does not return 0 if not found
public ArrayList<Integer> getProteinsLengthArray(HashMap<String, HashMap<String, Object>> hmFilterGeneTrans) {
ArrayList<Integer> lst = new ArrayList<>();
HashMap<String, Object> hmGT;
if(hmFilterGeneTrans == null)
hmFilterGeneTrans = new HashMap<>();
boolean filter = !hmFilterGeneTrans.isEmpty();
for(String gene : hmGeneTrans.keySet()) {
if(!filter || hmFilterGeneTrans.containsKey(gene)) {
hmGT = hmGeneTrans.get(gene);
for(String trans : hmGT.keySet()) {
if(!filter || hmFilterGeneTrans.get(gene).containsKey(trans)) {
if(hmTransData.containsKey(trans)) {
SeqAlign.Position pos = hmTransData.get(trans).posCDS;
if(pos.start != 0 && pos.end != 0) {
int protlen = Math.floorDiv((pos.end - pos.start + 1), 3);
// adjust for stop codon
if(protlen > 0)
protlen--;
lst.add(protlen);
}
}
}
}
}
}
return lst;
}
// Warning: will use the first transcript asigned to protein, there could be multiple ones
public int getProteinLength(String protein, HashMap<String, Object> hmFilterTrans) {
int protlen = 0;
ArrayList<String> lstTrans = getProteinTrans(protein, hmFilterTrans);
if(!lstTrans.isEmpty()) {
TransData td = getTransData(lstTrans.get(0));
SeqAlign.Position pos = td.posCDS;
if(pos.start != 0 && pos.end != 0) {
protlen = Math.floorDiv((pos.end - pos.start + 1), 3);
// adjust for stop codon
if(protlen > 0)
protlen--;
}
}
return protlen;
}
public HashMap<String, HashMap<String, Integer>> getProteinTransLengths(HashMap<String, Object> hmProteins, HashMap<String, Object> hmFilterTrans) {
HashMap<String, HashMap<String, Integer>> hmProtTrans = new HashMap<>();
for(String protein : hmProteins.keySet()) {
ArrayList<String> lstTrans = getProteinTrans(protein, hmFilterTrans);
for(String trans : lstTrans) {
if(hmProtTrans.containsKey(protein))
hmProtTrans.get(protein).put(trans, getTransData(trans).length);
else {
HashMap<String, Integer> hm = new HashMap<>();
hm.put(trans, getTransData(trans).length);
hmProtTrans.put(protein, hm);
}
}
}
return hmProtTrans;
}
public int getTransGeneCount(List<String> lstTrans, HashMap<String, Object> hmGeneFilter) {
String gene;
HashMap<String, Object> hmResults = new HashMap<>();
for(String trans : lstTrans) {
gene = getTransGene(trans);
if(!gene.isEmpty() && hmGeneFilter.containsKey(gene)) {
if(!hmResults.containsKey(gene))
hmResults.put(gene, null);
}
}
return hmResults.size();
}
// multiple transcripts can code for the same protein
// this returns the number of unique proteins not the number of coding transcripts
public int getTransProteinCount(HashMap<String, Object> hmFilterTrans) {
HashMap<String, Object> hmProteins = new HashMap<>();
if(hmFilterTrans == null)
hmFilterTrans = new HashMap<>();
boolean filter = !hmFilterTrans.isEmpty();
for(String trans : hmTransData.keySet()) {
if(!filter || hmFilterTrans.containsKey(trans)) {
String protein = getTransProtein(trans);
if(!protein.isEmpty())
hmProteins.put(protein, null);
}
}
return hmProteins.size();
}
// will return 0 count for genes with no proteins
public HashMap<String, Integer> getGeneProteinCounts(HashMap<String, Object> hmFilterTrans) {
HashMap<String, Integer> hmGeneProteinCounts = new HashMap<>();
HashMap<String, HashMap<String, Object>> hmGeneProteins = getGeneProteins(hmFilterTrans);
for(String gene : hmGeneProteins.keySet())
hmGeneProteinCounts.put(gene, hmGeneProteins.get(gene).size());
return hmGeneProteinCounts;
}
public HashMap<String, HashMap<String, Object>> getGeneProteins(HashMap<String, Object> hmFilterTrans) {
HashMap<String, HashMap<String, Object>> hmGeneProteins = new HashMap<>();
if(hmFilterTrans == null)
hmFilterTrans = new HashMap<>();
boolean filter = !hmFilterTrans.isEmpty();
for(String trans : hmTransData.keySet()) {
if(!filter || hmFilterTrans.containsKey(trans)) {
String gene = getTransGene(trans);
if(!hmGeneProteins.containsKey(gene))
hmGeneProteins.put(gene, new HashMap());
String protein = getTransProtein(trans);
if(!protein.isEmpty()) {
HashMap<String, Object> hm = hmGeneProteins.get(gene);
hm.put(protein, null);
}
}
}
return hmGeneProteins;
}
public SeqAlign.Position getLocusPosition(DataApp.DataType dataType, String id) {
SeqAlign.Position pos = new SeqAlign.Position(0, 0);
HashMap<String, Object> hm;
SeqAlign.Position posTrans;
ArrayList<String> lst;
switch(dataType) {
case TRANS:
if(hmTransData.containsKey(id))
pos = hmTransData.get(id).pos;
break;
case PROTEIN:
lst = getProteinTrans(id, null);
for(String trans : lst) {
if(hmTransData.containsKey(trans)) {
// using the first transcript that codes for this protein
// use getLocusPositions if all needed
pos = hmTransData.get(trans).pos;
break;
}
}
break;
case GENE:
hm = getGeneTrans(id);
pos.start = Integer.MAX_VALUE;
for(String trans : hm.keySet()) {