This repository has been archived by the owner on Jul 8, 2020. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 10
/
Copy pathPathwayGene.pm
executable file
·913 lines (821 loc) · 24.5 KB
/
PathwayGene.pm
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
#!/usr/local/bin/perl
# Copyright SRA International
#
# Distributed under the OSI-approved BSD 3-Clause License.
# See http://ncip.github.com/pathway-interaction-database/LICENSE.txt for details.
use DBI;
use Cache;
use strict;
use constant ORACLE_LIST_LIMIT => 500;
use constant MAX_LONG_LEN => 16384;
use constant CACHE_ROOT => "/share/content/PID/data/cache" ;
use constant PW_CACHE_PREFIX => "PW" ;
use constant DOT_PGM => "/usr/local/bin/dot"; ## on dev
#use constant DOT_PGM => "/share/content/PID/run/dot"; ## on stage, prod
use constant PREDEF_DIR => "/share/content/PID/data/predefined";
my $color_a = "blue";
my $color_b = "red";
my $color_ab = "purple";
######################################################################
sub r_numerically { $b <=> $a; }
######################################################################
sub numerically { $a <=> $b; }
######################################################################
sub HTML_HEAD {
return qq!
<head>
<STYLE TYPE=\"text/css\">
BODY {font-family: Arial}
</STYLE>
</head>
!;
}
######################################################################
sub GetPathwayHitsForEntrezGenes {
my ($db, $schema, $genes, $source, $pd, $gd) = @_;
my $list;
my @genes = keys %{ $genes };
my ($source_name, $pathway_id, $ext_pathway_id, $pathway_name,
$entrez_gene_id);
for(my $i = 0; $i < @genes; $i += ORACLE_LIST_LIMIT) {
if(($i + ORACLE_LIST_LIMIT - 1) < @genes) {
$list = join(",", @genes[$i..$i+ORACLE_LIST_LIMIT-1]);
}
else {
$list = join(",", @genes[$i..@genes-1]);
}
my $sql = qq!
select unique
c.source_name,
p.pathway_id,
p.ext_pathway_id,
p.pathway_name,
pg.entrez_gene_id
from
$schema.pw_pathway_gene pg,
$schema.pw_pathway p,
$schema.pw_source c
where
p.pathway_id = pg.pathway_id
and c.source_id = p.pathway_source_id
and p.pathway_source_id = $source
and pg.entrez_gene_id in ($list)
!;
my $stm = $db->prepare($sql);
if(not $stm) {
print STDERR "$sql\n";
print STDERR "$DBI::errstr\n";
die "prepare call failed\n";
}
if(!$stm->execute()) {
print STDERR "$sql\n";
print STDERR "$DBI::errstr\n";
die "execute call failed\n";
}
while (($source_name, $pathway_id, $ext_pathway_id, $pathway_name,
$entrez_gene_id) = $stm->fetchrow_array()) {
$pd->{gene}{$pathway_id}{$entrez_gene_id} = 1;
$pd->{source}{$pathway_id} = $source_name;
$pd->{ext_id}{$pathway_id} = $ext_pathway_id;
$pd->{name}{$pathway_id} = $pathway_name;
$gd->{pathway}{$entrez_gene_id}{$pathway_id} = 1;
}
}
}
######################################################################
sub GetTotalGenesInPathways {
my ($db, $schema) = @_;
my $sql = qq!
select
count (unique pg.entrez_gene_id)
from
$schema.pw_pathway_gene pg
!;
my $stm = $db->prepare($sql);
if(not $stm) {
print STDERR "$sql\n";
print STDERR "$DBI::errstr\n";
die "prepare call failed\n";
}
if(!$stm->execute()) {
print STDERR "$sql\n";
print STDERR "$DBI::errstr\n";
die "execute call failed\n";
}
my ($total_genes_in_pathways) = $stm->fetchrow_array();
$stm->finish();
return $total_genes_in_pathways;
}
######################################################################
sub MakeSymbolList {
my ($list, $gd) = @_;
my @symbols;
for my $g (@{ $list }) {
if (defined $gd->{symbol}{$g}{OF}) {
push @symbols, $gd->{symbol}{$g}{OF};
} else {
for my $t (keys %{ $gd->{symbol}{$g} }) {
push @symbols, $gd->{symbol}{$g}{$t};
last; ## just take one
}
}
}
return \@symbols;
}
######################################################################
sub CountGenesInPathways {
my ($db, $schema, $pd) = @_;
my $list;
my ($pathway_id, $count);
my @pids = keys %{ $pd->{gene} };
for(my $i = 0; $i < @pids; $i += ORACLE_LIST_LIMIT) {
if(($i + ORACLE_LIST_LIMIT - 1) < @pids) {
$list = join(",", @pids[$i..$i+ORACLE_LIST_LIMIT-1]);
}
else {
$list = join(",", @pids[$i..@pids-1]);
}
my $sql = qq!
select unique
pg.pathway_id,
count (unique pg.entrez_gene_id)
from
$schema.pw_pathway_gene pg
where
pg.pathway_id in ($list)
group by
pg.pathway_id
!;
my $stm = $db->prepare($sql);
if(not $stm) {
print STDERR "$sql\n";
print STDERR "$DBI::errstr\n";
die "prepare call failed\n";
}
if(!$stm->execute()) {
print STDERR "$sql\n";
print STDERR "$DBI::errstr\n";
die "execute call failed\n";
}
while (($pathway_id, $count) = $stm->fetchrow_array()) {
$pd->{genecount}{$pathway_id} = $count;
}
}
}
######################################################################
sub RankPathwaysByGeneHits {
my ($db, $schema, $format, $source, $terms_a, $terms_b) = @_;
my %terms;
for my $t (keys %{ $terms_a }) {
$terms{$t} = 1;
}
for my $t (keys %{ $terms_b }) {
$terms{$t} = 1;
}
print STDERR "In RankPathways $schema $format $source\n";
my @terms = keys %terms;
if (@terms == 0) {
return;
}
my ($sql, $stm, $list);
my ($source_name, $pathway_id, $ext_pathway_id, $pathway_name,
$entrez_gene_id, $count, $symbol, $symbol_type);
$source_name = 'BioCarta data';
if ($source == 5) {
$source_name = 'NCI-Nature Curated data';
}
if ($source == 7) {
$source_name = 'Reactome data';
}
if ($source_name eq 'BioCarta data') {
$source = 2;
}
my %pd; ## pathway data
my %gd; ## gene data
my $total_genes_in_pathways = GetTotalGenesInPathways($db, $schema);
print STDERR "After GetTotalGenesInPathways\n";
my ($genes_a, $genes_b) = GetEntrezGeneIds($db, $schema, $terms_a, $terms_b, $source, \%gd);
my $genelist='';
for my $gtest (keys % {$genes_a}) {
$genelist = $genelist . ' ' .$gtest;
}
print STDERR "Before GetPathwayHitsForEntrezGenes $genelist\n";
GetPathwayHitsForEntrezGenes($db, $schema, $genes_a, $source, \%pd, \%gd);
GetPathwayHitsForEntrezGenes($db, $schema, $genes_b, $source, \%pd, \%gd);
my @genes = keys %{ $gd{pathway} };
my $n_query = scalar(@genes);
CountGenesInPathways($db, $schema, \%pd);
my $n = 0;
my (%tmp, %pval_cache);
for my $pid (keys %{ $pd{gene} }) {
my (@alist, @blist);
my $hits_target = 0;
for my $g (keys %{ $pd{gene}{$pid} }) {
if (defined $$genes_a{$g}) {
push @alist, $g;
}
if (defined $$genes_b{$g}) {
push @blist, $g;
}
}
for my $g (@genes) {
if (defined $pd{gene}{$pid}{$g}) {
$hits_target++;
}
}
my $pval;
my $good = $pd{genecount}{$pid};
if (defined $pval_cache{"$good,$hits_target"}) {
$pval = $pval_cache{"$good,$hits_target"};
} else {
$pval = hypergeom(
$good,
$total_genes_in_pathways - $good,
$n_query,
$hits_target
);
$pval = sprintf("%.2e", $pval);
$pval_cache{"$good,$hits_target"} = $pval;
}
print STDERR "pval: $pval\n";
## remove any possible duplicate gene ids (from multiple symbols)
my %cull;
for my $g (@alist) {
$cull{$g} = 1;
}
undef @alist;
@alist = keys %cull;
my %cull;
for my $g (@blist) {
$cull{$g} = 1;
}
undef @blist;
@blist = keys %cull;
## make symbol lists
my @a_syms = @{ MakeSymbolList(\@alist, \%gd) };
my @b_syms = @{ MakeSymbolList(\@blist, \%gd) };
if ($format eq "text") {
push @{ $tmp{$pval} }, join("\t",
$pval,
$good,
$total_genes_in_pathways - $good,
$n_query,
$hits_target,
join(",", @alist),
join(",", @a_syms),
join(",", @blist),
join(",", @b_syms),
$pid,
$pd{source_name}{$pid},
$pd{ext_id}{$pid},
$pd{name}{$pid}
);
} elsif ($format eq "html") {
my $a_syms;
if (@a_syms == 0) {
$a_syms = " ";
} else {
$a_syms = join(", ", sort @a_syms);
}
my $b_syms;
if (@b_syms == 0) {
$b_syms = " ";
} else {
$b_syms = join(", ", sort @b_syms);
}
push @{ $tmp{$pval} }, join("\t",
"<td><a href=\"/search/pathway_landing.shtml?" .
"what=graphic\&" .
"pathway_id=$pid\&" .
"jpg=on\&" .
"source=$pd{source}{$pid}\&" .
"genes_a=" . join(",", @alist) . "\&" .
"genes_b=" . join(",", @blist) .
"\" target=_>$pd{name}{$pid}</a></td>",
"<td>$a_syms</td>",
"<td>$b_syms</td>",
"<td>$pval</td>",
"</tr>"
);
}
}
my @rows;
# for my $pval (sort numerically keys %tmp) {
# for my $r (@{ $tmp{$pval} }) {
# push @rows, $r;
# }
#}
print STDERR "Before assigning rows\n";
if ($format eq "html") {
unshift @rows, "<h1 class=\"pagetitle\">Batch query results for $source_name </h1> " .
"<table class=\"data\" >" .
"<thead> ".
"<th scope=\"colgroup\" class=\"colspan\">Pathway Name</th><th scope=\"colgroup\" class=\"colspan\">Biomolecules in Group 1</th><th scope=\"colgroup\" class=\"colspan\">Biomolecules in Group 2</th><th scope=\"colgroup\" class=\"colspan\">P-value <div class=\"helpbox\"> " .
"<a href=\"/index.shtml#\" class=\"help\">Help</a> " .
"<div class=\"description\"> " .
"<p class=\"norm\">The pathways are ranked by the probability that they include biomolecules from the query list. The lower the p-value the greater the probability that the query list is biased towards a given pathway. The parameters for generating the p-value are the size of the query set, the number of biomolecules in a given pathway and the number of molecules in the database as a whole.</p></div></div></th></tr> ";
push @rows, "</thead>";
push @rows, "<tbody>";
for my $pval (sort numerically keys %tmp) {
for my $r (@{ $tmp{$pval} }) {
push @rows, ($n %2 == 0) ? "<tr>" : "<tr class=\"odd\">";
$n++;
push @rows, $r;
}
}
push @rows, "</tbody>";
push @rows, "</table>";
} elsif ($format eq "text") {
unshift @rows, join("\t",
"P-value",
"N genes in pathway",
"N genes NOT in pathway",
"N genes in Query",
"N Hits",
"Gene ids in A list",
"Gene symbols in A list",
"Gene ids in B list",
"Gene symbols in B list",
"Pathway id",
"Pathway source",
"Pathway ext id",
"Pathway name");
}
return join("\n", @rows, "");
}
#####################################################################
sub GetEntrezGeneIds {
my ($db, $schema, $terms_a, $terms_b, $source, $gd) = @_;
## limit the search to Entrez Gene ids that are in some pathway
my %terms;
my (%genes_a, %genes_b);
for my $t (keys %{ $terms_a }, keys %{ $terms_b }) {
$terms{$t} = 1;
print STDERR "Terms: $t\n";
}
my (@numeric_terms, @non_numeric_terms);
for my $t (keys %terms) {
if ($t =~ /^\d+$/) {
push @numeric_terms, $t;
} else {
push @non_numeric_terms, $t;
}
}
## do numeric
my $list;
for(my $i = 0; $i < @numeric_terms; $i += ORACLE_LIST_LIMIT) {
if(($i + ORACLE_LIST_LIMIT - 1) < @numeric_terms) {
$list = join(",", @numeric_terms[$i..$i+ORACLE_LIST_LIMIT-1]);
}
else {
$list = join(",", @numeric_terms[$i..@numeric_terms-1]);
}
my $sql = qq!
select unique
pg.entrez_gene_id,
lower(e.symbol),
e.symbol,
e.symbol_type
from
$schema.pw_pathway_gene pg,
$schema.pw_pathway p,
cgap.ll_gene e
where
pg.entrez_gene_id = e.ll_id
and e.organism = 'Hs'
and pg.pathway_id = p.pathway_id
and p.pathway_source_id = $source
and e.ll_id in ($list)
!;
my $stm = $db->prepare($sql);
if(not $stm) {
print STDERR "$sql\n";
print STDERR "$DBI::errstr\n";
die "prepare call failed\n";
}
if(!$stm->execute()) {
print STDERR "$sql\n";
print STDERR "$DBI::errstr\n";
die "execute call failed\n";
}
my ($entrez_gene_id, $lc_symbol, $symbol, $symbol_type);
while (($entrez_gene_id, $lc_symbol, $symbol, $symbol_type) =
$stm->fetchrow_array()) {
$gd->{symbol}{$entrez_gene_id}{$symbol_type} = $symbol;
if (defined $$terms_a{$entrez_gene_id}) {
$genes_a{$entrez_gene_id} = 1;
}
if (defined $$terms_b{$entrez_gene_id}) {
$genes_b{$entrez_gene_id} = 1;
}
}
}
## do non_numeric, gene symbols
my $list;
my $sqlsearch = "in";
if ($#non_numeric_terms < 1) {
$sqlsearch = "like";
}
my $number = $#non_numeric_terms;
print STDERR "Nonnumeric: $number\n";
for(my $i = 0; $i < @non_numeric_terms; $i += ORACLE_LIST_LIMIT) {
if(($i + ORACLE_LIST_LIMIT - 1) < @non_numeric_terms) {
$list = lc("'" . join("','", @non_numeric_terms[$i..$i+ORACLE_LIST_LIMIT-1]) . "'");
}
else {
$list = lc("'" . join("','", @non_numeric_terms[$i..@non_numeric_terms-1]) . "'");
}
my $sql = qq!
select unique
pg.entrez_gene_id,
lower(e.symbol),
e.symbol,
e.symbol_type,
lower(ms.map_name)
from
$schema.pw_pathway_gene pg,
$schema.pw_pathway p,
$schema.pw_mol_srch ms,
$schema.pw_mol_srch ms2,
cgap.ll_gene e
where
pg.entrez_gene_id = e.ll_id
and pg.pathway_id = p.pathway_id
and p.pathway_source_id = $source
and e.organism = 'Hs'
and ms.mol_id = ms2.mol_id
and lower(e.symbol) = lower(ms2.map_name)
and lower(ms.map_name) $sqlsearch ($list)
!;
print STDERR "List: $list\n";
print STDERR "Query: $sql\n";
my $stm = $db->prepare($sql);
if(not $stm) {
print STDERR "$sql\n";
print STDERR "$DBI::errstr\n";
die "prepare call failed\n";
}
if(!$stm->execute()) {
print STDERR "$sql\n";
print STDERR "$DBI::errstr\n";
die "execute call failed\n";
}
my ($entrez_gene_id, $lc_symbol, $symbol, $symbol_type, $map_name);
while (($entrez_gene_id, $lc_symbol, $symbol, $symbol_type, $map_name) =
$stm->fetchrow_array()) {
$gd->{symbol}{$entrez_gene_id}{$symbol_type} = $symbol;
my $lengtha = length($list);
my $teststring = substr($list,$lengtha-2,1);
print STDERR "Lengthtest: $teststring $lengtha $list\n";
if ((substr($list,$lengtha-2,1) eq '%') || (defined $$terms_a{$map_name})) {
$genes_a{$entrez_gene_id} = 1;
}
if (defined $$terms_b{$map_name}) {
$genes_b{$entrez_gene_id} = 1;
}
}
}
## do non_numeric, UniProt ids (we still have significantly more
## UP-to-EG associations in ll2sp than in ll2acc)
my $list;
for(my $i = 0; $i < @non_numeric_terms; $i += ORACLE_LIST_LIMIT) {
if(($i + ORACLE_LIST_LIMIT - 1) < @non_numeric_terms) {
$list = lc("'" . join("','", @non_numeric_terms[$i..$i+ORACLE_LIST_LIMIT-1]) . "'");
}
else {
$list = lc("'" . join("','", @non_numeric_terms[$i..@non_numeric_terms-1]) . "'");
}
my $sql = qq!
select unique
pg.entrez_gene_id,
lower(e.symbol),
e.symbol,
e.symbol_type
from
$schema.pw_pathway_gene pg,
$schema.pw_pathway p,
cgap.ll_gene e,
cgap.ll2sp s,
cgap.sp_primary p
where
pg.entrez_gene_id = e.ll_id
and pg.pathway_id = p.pathway_id
and p.pathway_source_id = $source
and e.organism = 'Hs'
and e.ll_id = s.ll_id
and s.sp_primary = p.sp_primary
and lower(p.sp_id_or_secondary) in ($list)
!;
my $stm = $db->prepare($sql);
if(not $stm) {
print STDERR "$sql\n";
print STDERR "$DBI::errstr\n";
die "prepare call failed\n";
}
if(!$stm->execute()) {
print STDERR "$sql\n";
print STDERR "$DBI::errstr\n";
die "execute call failed\n";
}
my ($entrez_gene_id, $lc_symbol, $symbol, $symbol_type);
while (($entrez_gene_id, $lc_symbol, $symbol, $symbol_type) =
$stm->fetchrow_array()) {
$gd->{symbol}{$entrez_gene_id}{$symbol_type} = $symbol;
if (defined $$terms_a{$lc_symbol}) {
$genes_a{$entrez_gene_id} = 1;
}
if (defined $$terms_b{$lc_symbol}) {
$genes_b{$entrez_gene_id} = 1;
}
}
}
return (\%genes_a, \%genes_b);
}
#####################################################################
sub oldGetEntrezGeneIds {
my ($db, $schema, $terms_a, $terms_b, $gd) = @_;
## limit the search to Entrez Gene ids that are in some pathway
my %terms;
my (%genes_a, %genes_b);
for my $t (keys %{ $terms_a }, keys %{ $terms_b }) {
$terms{$t} = 1;
}
my @terms = keys %terms;
my $list;
for(my $i = 0; $i < @terms; $i += ORACLE_LIST_LIMIT) {
if(($i + ORACLE_LIST_LIMIT - 1) < @terms) {
$list = lc("'" . join("','", @terms[$i..$i+ORACLE_LIST_LIMIT-1]) . "'");
}
else {
$list = lc("'" . join("','", @terms[$i..@terms-1]) . "'");
}
my $sql = qq!
select unique
m1.map_name,
pg.entrez_gene_id,
e.symbol,
e.symbol_type
from
$schema.pw_pathway_gene pg,
cgap.ll_gene e,
$schema.pw_mol_srch m1,
$schema.pw_mol_srch m2
where
pg.entrez_gene_id = e.ll_id
and e.organism = 'Hs'
and to_char(pg.entrez_gene_id) = m2.map_name
and m1.mol_id not in (select family_mol_id from $schema.pw_family_member)
and m1.mol_id = m2.mol_id
and m1.map_name in ($list)
!;
my $stm = $db->prepare($sql);
if(not $stm) {
print STDERR "$sql\n";
print STDERR "$DBI::errstr\n";
die "prepare call failed\n";
}
if(!$stm->execute()) {
print STDERR "$sql\n";
print STDERR "$DBI::errstr\n";
die "execute call failed\n";
}
my ($term, $entrez_gene_id, $symbol, $symbol_type);
while (($term, $entrez_gene_id, $symbol, $symbol_type) =
$stm->fetchrow_array()) {
$gd->{symbol}{$entrez_gene_id}{$symbol_type} = $symbol;
if (defined $$terms_a{$term}) {
$genes_a{$entrez_gene_id} = 1;
}
if (defined $$terms_b{$term}) {
$genes_b{$entrez_gene_id} = 1;
}
}
}
return (\%genes_a, \%genes_b);
}
#####################################################################
sub CreateGraphicFile {
my ($db, $schema, $pid, $source, $mols_a, $mols_b, $format) = @_;
my %source_map = (
"NATURE" => "nature",
"BioCarta" => "biocarta",
"Reactome" => "reactome"
);
my %nice_source = (
"NATURE" => "NCI-Nature Curated",
"BioCarta" => "BioCarta",
"Reactome" => "Reactome"
);
my $sql = qq!
select
p.pathway_name
from
$schema.pw_pathway p
where
p.pathway_id = $pid
!;
my $stm = $db->prepare($sql);
if(not $stm) {
print STDERR "$sql\n";
exit;
}
if(!$stm->execute()) {
print STDERR "$sql\n";
exit;
}
my ($pathway_name) = $stm->fetchrow_array();
$stm->finish();
my $map_file;
my $inf = PREDEF_DIR . "/" . "$source_map{$source}/$pid.dot";
if ($format ne 'svg') {
$inf = PREDEF_DIR . "/" . "$source_map{$source}/$pid.dotg";
}
open(INF, $inf) or die "cannot open $inf";
my $cache = new Cache(CACHE_ROOT, PW_CACHE_PREFIX);
my ($cache_id, $filename) = $cache->MakeCacheFile();
if ($cache_id != $CACHE_FAIL) {
open(OUTF, ">$filename.dot");
while (<INF>) {
s/[\r\n]+//;
if (/^ *\/\//) {
next;
}
if (/^ *M_(\d+)/ && ! / -> /) {
my $mol = $1;
if (defined $$mols_a{$mol}) {
if (defined $$mols_b{$mol}) {
if (/fontcolor="([^"]+)"/) {
s/fontcolor="[^"]+"/fontcolor="$color_ab"/;
} else {
s/\];/ fontcolor="$color_ab"];/;
}
} else {
if (/fontcolor="([^"]+)"/) {
s/fontcolor="[^"]+"/fontcolor="$color_a"/;
} else {
s/\];/ fontcolor="$color_a"];/;
}
}
} elsif (defined $$mols_b{$mol}) {
if (/fontcolor="([^"]+)"/) {
s/fontcolor="[^"]+"/fontcolor="$color_b"/;
} else {
s/\];/ fontcolor="$color_b"];/;
}
}
}
print OUTF "$_\n";
}
close(OUTF);
chmod 0666, "$filename.dot";
print STDERR "Format: $format\n";
if ($format ne 'svg') {
$format = 'jpg';
}
my $cmd = DOT_PGM . " $filename.dot -T$format > $filename";
system($cmd);
chmod 0666, $filename;
if ($format eq "jpg") {
my $cmd = DOT_PGM . " $filename.dot -Tcmap > $filename.map";
system($cmd);
chmod 0666, "$filename.map";
$map_file = "$filename.map"
}
unlink("$filename.dot");
}
my @tmp;
push @tmp, "<html>";
push @tmp, HTML_HEAD();
push @tmp, "<body>";
push @tmp, "<p>";
if ($format eq "svg") {
push @tmp,
"<embed type=\"image/svg-xml\" height=800 width=1000 " .
"src=\"/pidcgi/GetPwImage.pl?" .
"GID=$cache_id&FORMAT=SVG\" alt = \"Image of Pathway\">";
} elsif ($format eq "jpg") {
push @tmp, "<img " .
"src=\"/pidcgi/GetPwImage.pl?" .
"GID=$cache_id&FORMAT=JPG\" usemap=#map_$cache_id alt = \"Image of Network Search Map\" >";
push @tmp, "<map name=map_$cache_id>";
open(MAP, $map_file) or die "cannot open $map_file";
while (<MAP>) {
chomp;
push @tmp, "$_";
}
close(MAP);
push @tmp, "</map>";
# Need to add map information here
}
return join("\n", @tmp, "");
}
######################################################################
sub GetMolIdsForEntrezGene {
my ($db, $pathway_id, $genes) = @_;
print STDERR "In GetMolIdsForEntrezGene\n";
my @genearray = keys %{ $genes };
my $gene_number = $#genearray;
print STDERR "Gene 0: $genearray[0]\n";
print STDERR "Gene 1: $genearray[1]\n";
print STDERR "Genes: $gene_number\n";
if ($#genearray == -1) {
print STDERR "Empty genes\n";
return {};
}
my ($mol, %mols, $list);
for(my $i = 0; $i <= $#genearray; $i += ORACLE_LIST_LIMIT) {
if(($i + ORACLE_LIST_LIMIT - 1) <= $gene_number) {
$list = join("','", $genearray[$i..$i+ORACLE_LIST_LIMIT-1]);
}
else {
for (my $j = 0; $j <= $#genearray; $j++) {
$list = $list . "'" . $genearray[$j] . "'";
if ($j < $#genearray) {
$list = $list . ",";
}
}
# $list = join("','", $genearray[$i..$gene_number]);
}
# $list = "'" . $list . "'";
print STDERR "List: $list\n";
my $sql = qq!/*
(mol_id_1, mol_id_2, relation):
identity: (mol, mol, 'i')
complex component: (component, complex, 'c')
family member: (family, member, 'm')
protein subunit: (whole, part, 's')
Have to allow for cases where a component is a family and cases
where a family is a complex with a component that is a family.
When collecting mols for an interaction, find components in a complex
and find members of a family, but do not find families with a member or
complexes with a component.
*/
select unique
mm_outer_family.mol_id_1
from
pid.pw_pathway_atom pa,
pid.pw_edge e,
pid.pw_mol_mol mm_outer_family,
pid.pw_mol_mol mm_inner_family,
pid.pw_mol_mol mm_complex,
pid.pw_mol_srch s,
cgap.ll_gene g
where
mm_outer_family.mol_id_2 = mm_complex.mol_id_2
and mm_complex.mol_id_1 = mm_inner_family.mol_id_1
and e.mol_id = mm_outer_family.mol_id_1
and mm_complex.relation in ('s','c','i')
and mm_outer_family.relation in ('s','m','i')
and mm_inner_family.relation in ('s','m','i')
and e.atom_id = pa.atom_id
and pa.pathway_id = $pathway_id
and mm_inner_family.mol_id_2 = s.mol_id
and s.map_name in ($list)
and to_char(g.ll_id) = s.map_name
!;
# print STDERR "SQL: $sql\n";
my $stm = $db->prepare($sql);
if(not $stm) {
print STDERR "$sql\n";
exit;
}
if(!$stm->execute()) {
print STDERR "$sql\n";
exit;
}
while (($mol) = $stm->fetchrow_array()) {
$mols{$mol} = 1;
}
}
return \%mols;
}
######################################################################
sub logfact {
return gammln(shift(@_) + 1.0);
}
sub hypergeom {
# There are m "bad" and n "good" balls in an urn.
# Pick N of them. The probability of i or more successful selections:
# (m!n!N!(m+n-N)!)/(i!(n-i)!(m+i-N)!(N-i)!(m+n)!)
my ($n, $m, $N, $i) = @_;
my $loghyp1 = logfact($m)+logfact($n)+logfact($N)+logfact($m+$n-$N);
my $loghyp2 = logfact($i)+logfact($n-$i)+logfact($m+$i-$N)+logfact(+$N-$i)+logfact($m+$n);
return exp($loghyp1 - $loghyp2);
}
sub gammln {
my $xx = shift;
my @cof = (76.18009172947146, -86.50532032941677,
24.01409824083091, -1.231739572450155,
0.12086509738661e-2, -0.5395239384953e-5);
my $y = my $x = $xx;
my $tmp = $x + 5.5;
$tmp -= ($x + .5) * log($tmp);
my $ser = 1.000000000190015;
for my $j (0..5) {
$ser += $cof[$j]/++$y;
}
-$tmp + log(2.5066282746310005*$ser/$x);
}
######################################################################
1;
######################################################################