Newer
Older
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
while (my @row = $sth->fetchrow_array) {
push @sp, $row[0];
}
$sth->finish;
my $species = join(" ", reverse @sp);
$self->throw("Could not determine species scientific name from database.")
unless $species;
return $species;
}
=head2 species
Arg[1] : (optional) String $species - species name to set
Example : my $species = $support->species;
my $url = "http://vega.sanger.ac.uk/$species/";
Description : Getter/setter for species name (Genus_species). If not set, it's
determined from database's meta table
Return type : String - species name
Exceptions : none
Caller : general
=cut
sub species {
my $self = shift;
$self->{'_species'} = shift if (@_);
# get species name from database if not set
unless ($self->{'_species'}) {
$self->{'_species'} = join('_',
split(/ /, $self->get_species_scientific_name));
}
return $self->{'_species'};
}
=head2 sort_chromosomes
Arg[1] : (optional) Hashref $chr_hashref - Hashref with chr_name as keys
Example : my $chr = { '6-COX' => 1, '1' => 1, 'X' => 1 };
my @sorted = $support->sort_chromosomes($chr);
Description : Sorts chromosomes in an intuitive way (numerically, then
alphabetically). If no chromosome hashref is passed, it's
retrieve by calling $self->get_chrlength()
Return type : List - sorted chromosome names
Exceptions : thrown if no hashref is provided
Caller : general
=cut
sub sort_chromosomes {
my ($self, $chr_hashref) = @_;
$chr_hashref = $self->get_chrlength unless ($chr_hashref);
throw("You have to pass a hashref of your chromosomes")
unless ($chr_hashref and ref($chr_hashref) eq 'HASH');
return (sort _by_chr_num keys %$chr_hashref);
}
=head2 _by_chr_num
Example : my @sorted = sort _by_chr_num qw(X, 6-COX, 14, 7);
Description : Subroutine to use in sort for sorting chromosomes. Sorts
numerically, then alphabetically
Return type : values to be used by sort
Exceptions : none
Caller : internal ($self->sort_chromosomes)
=cut
sub _by_chr_num {
my @awords = split /-/, $a;
my @bwords = split /-/, $b;
my $anum = $awords[0];
my $bnum = $bwords[0];
if ($anum !~ /^[0-9]*$/) {
if ($bnum !~ /^[0-9]*$/) {
return $anum cmp $bnum;
} else {
return 1;
}
}
if ($bnum !~ /^[0-9]*$/) {
return -1;
}
if ($anum <=> $bnum) {
return $anum <=> $bnum;
} else {
if ($#awords == 0) {
return -1;
} elsif ($#bwords == 0) {
return 1;
} else {
return $awords[1] cmp $bwords[1];
}
}
}
=head2 split_chromosomes_by_size
Arg[1] : (optional) Int $cutoff - the cutoff in bp between small and
large chromosomes
Arg[2] : (optional) Boolean to include duplicate regions, ie PAR or not
(default is no)
Arg[3] : (optional) Coordsystem version to retrieve
Example : my $chr_slices = $support->split_chromosomes_by_size;
foreach my $block_size (keys %{ $chr_slices }) {
print "Chromosomes with blocksize $block_size: ";
print join(", ", map { $_->seq_region_name }
@{ $chr_slices->{$block_size} });
}
Description : Determines block sizes for storing DensityFeatures on
chromosomes, and return slices for each chromosome. The block
size is determined so that you have 150 bins for the smallest
chromosome over 5 Mb in length. For chromosomes smaller than 5
Mb, an additional smaller block size is used to yield 150 bins
for the overall smallest chromosome. This will result in
reasonable resolution for small chromosomes and high
Steve Trevanion
committed
performance for big ones. Does not return non-reference seq_regions
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
Return type : Hashref (key: block size; value: Arrayref of chromosome
Bio::EnsEMBL::Slices)
Exceptions : none
Caller : density scripts
=cut
sub split_chromosomes_by_size {
my $self = shift;
my $cutoff = shift || 5000000;
my $dup = shift || 0;
my $cs_version = shift;
my $slice_adaptor = $self->dba->get_SliceAdaptor;
my $top_slices;
if ($self->param('chromosomes')) {
foreach my $chr ($self->param('chromosomes')) {
push @{ $top_slices }, $slice_adaptor->fetch_by_region('chromosome', $chr);
}
} else {
$top_slices = $slice_adaptor->fetch_all('chromosome',$cs_version,0,$dup);
}
my ($big_chr, $small_chr, $min_big_chr, $min_small_chr);
foreach my $slice (@{ $top_slices }) {
next if ($slice->length eq 10000); #hack for chrY pseudoslice
if ($slice->length < $cutoff) {
if (! $min_small_chr or ($min_small_chr > $slice->length)) {
$min_small_chr = $slice->length;
}
# push small chromosomes onto $small_chr
push @{ $small_chr }, $slice;
}
elsif (! $min_big_chr or ($min_big_chr > $slice->length) ){
$min_big_chr = $slice->length;
}
# push _all_ chromosomes onto $big_chr
push @{ $big_chr }, $slice;
}
my $chr_slices;
$chr_slices->{int($min_big_chr/150)} = $big_chr if $min_big_chr;
$chr_slices->{int($min_small_chr/150)} = $small_chr if $min_small_chr;
return $chr_slices;
}
=head2 log
Arg[1] : String $txt - the text to log
Arg[2] : Int $indent - indentation level for log message
Example : my $log = $support->log_filehandle;
$support->log('Log foo.\n', 1);
Description : Logs a message to the filehandle initialised by calling
$self->log_filehandle(). You can supply an indentation level
to get nice hierarchical log messages.
Return type : true on success
Exceptions : thrown when no filehandle can be obtained
Caller : general
=cut
sub log {
my ($self, $txt, $indent) = @_;
$indent ||= 0;
# strip off leading linebreaks so that indenting doesn't break
$txt =~ s/^(\n*)//;
$txt = $1." "x$indent . $txt;
my $fh = $self->{'_log_filehandle'};
throw("Unable to obtain log filehandle") unless $fh;
print $fh "$txt";
return(1);
}
=head2 log_warning
Arg[1] : String $txt - the warning text to log
Arg[2] : Int $indent - indentation level for log message
Arg[3] : Bool - add a line break before warning if true
Example : my $log = $support->log_filehandle;
$support->log_warning('Log foo.\n', 1);
Description : Logs a message via $self->log and increases the warning counter.
Return type : true on success
Exceptions : none
Caller : general
=cut
sub log_warning {
my ($self, $txt, $indent, $break) = @_;
$txt = "WARNING: " . $txt;
$txt = "\n$txt" if ($break);
$self->log($txt, $indent);
$self->{'_warnings'}++;
return(1);
}
=head2 log_error
Arg[1] : String $txt - the error text to log
Arg[2] : Int $indent - indentation level for log message
Example : my $log = $support->log_filehandle;
$support->log_error('Log foo.\n', 1);
Description : Logs a message via $self->log and exits the script.
Return type : none
Exceptions : none
Caller : general
=cut
sub log_error {
my ($self, $txt, $indent) = @_;
$txt = "ERROR: ".$txt;
$self->log($txt, $indent);
$self->log("Exiting.\n");
exit;
}
=head2 log_verbose
Arg[1] : String $txt - the warning text to log
Arg[2] : Int $indent - indentation level for log message
Example : my $log = $support->log_filehandle;
$support->log_verbose('Log this verbose message.\n', 1);
Description : Logs a message via $self->log if --verbose option was used
Return type : TRUE on success, FALSE if not verbose
Exceptions : none
Caller : general
=cut
sub log_verbose {
my ($self, $txt, $indent) = @_;
return(0) unless $self->param('verbose');
$self->log($txt, $indent);
return(1);
}
=head2 log_stamped
Arg[1] : String $txt - the warning text to log
Arg[2] : Int $indent - indentation level for log message
Example : my $log = $support->log_filehandle;
$support->log_stamped('Log this stamped message.\n', 1);
Description : Appends timestamp and memory usage to a message and logs it via
$self->log
Return type : TRUE on success
Exceptions : none
Caller : general
=cut
sub log_stamped {
my ($self, $txt, $indent) = @_;
# append timestamp and memory usage to log text
$txt =~ s/(\n*)$//;
$txt .= " ".$self->date_and_mem.$1;
$self->log($txt, $indent);
return(1);
}
=head2 log_filehandle
Arg[1] : (optional) String $mode - file access mode
Example : my $log = $support->log_filehandle;
# print to the filehandle
print $log 'Lets start logging...\n';
# log via the wrapper $self->log()
$support->log('Another log message.\n');
Description : Returns a filehandle for logging (STDERR by default, logfile if
set from config or commandline). You can use the filehandle
directly to print to, or use the smart wrapper $self->log().
Logging mode (truncate or append) can be set by passing the
mode as an argument to log_filehandle(), or with the
--logappend commandline option (default: truncate)
Return type : Filehandle - the filehandle to log to
Exceptions : thrown if logfile can't be opened
Caller : general
=cut
sub log_filehandle {
my ($self, $mode) = @_;
$mode ||= '>';
$mode = '>>' if ($self->param('logappend'));
my $fh = \*STDERR;
if (my $logfile = $self->param('logfile')) {
if (my $logpath = $self->param('logpath')) {
unless (-e $logpath) {
system("mkdir $logpath") == 0 or
$self->log_error("Can't create log dir $logpath: $!\n");
}
$logfile = "$logpath/$logfile";
}
open($fh, "$mode", $logfile) or throw(
"Unable to open $logfile for writing: $!");
}
$self->{'_log_filehandle'} = $fh;
return $self->{'_log_filehandle'};
}
=head2 filehandle
Arg[1] : String $mode - file access mode
Arg[2] : String $file - input or output file
Example : my $fh = $support->filehandle('>>', '/path/to/file');
# print to the filehandle
print $fh 'Your text goes here...\n';
Description : Returns a filehandle (*STDOUT for writing, *STDIN for reading
by default) to print to or read from.
Return type : Filehandle - the filehandle
Exceptions : thrown if file can't be opened
Caller : general
=cut
sub filehandle {
my ($self, $mode, $file) = @_;
$mode ||= ">";
my $fh;
if ($file) {
open($fh, "$mode", $file) or throw(
"Unable to open $file for writing: $!");
} elsif ($mode =~ />/) {
$fh = \*STDOUT;
} elsif ($mode =~ /</) {
$fh = \*STDIN;
}
return $fh;
}
=head2 init_log
Example : $support->init_log;
Description : Opens a filehandle to the logfile and prints some header
information to this file. This includes script name, date, user
running the script and parameters the script will be running
with.
Return type : Filehandle - the log filehandle
Exceptions : none
Caller : general
=cut
sub init_log {
my $self = shift;
# get a log filehandle
my $log = $self->log_filehandle;
# print script name, date, user who is running it
my $hostname = `hostname`;
chomp $hostname;
my $script = "$hostname:$Bin/$Script";
my $user = `whoami`;
chomp $user;
$self->log("Script: $script\nDate: ".$self->date."\nUser: $user\n");
# print parameters the script is running with
$self->log("Parameters:\n\n");
$self->log($self->list_all_params);
# remember start time
$self->{'_start_time'} = time;
return $log;
}
=head2 finish_log
Example : $support->finish_log;
Description : Writes footer information to a logfile. This includes the
number of logged warnings, timestamp and memory footprint.
Return type : TRUE on success
Exceptions : none
Caller : general
=cut
sub finish_log {
my $self = shift;
$self->log("\nAll done. ".$self->warnings." warnings. ");
if ($self->{'_start_time'}) {
$self->log("Runtime ");
my $diff = time - $self->{'_start_time'};
my $sec = $diff % 60;
$diff = ($diff - $sec) / 60;
my $min = $diff % 60;
my $hours = ($diff - $min) / 60;
$self->log("${hours}h ${min}min ${sec}sec ");
}
$self->log($self->date_and_mem."\n\n");
return(1);
}
=head2 date_and_mem
Example : print LOG "Time, memory usage: ".$support->date_and_mem."\n";
Description : Prints a timestamp and the memory usage of your script.
Return type : String - timestamp and memory usage
Exceptions : none
Caller : general
=cut
sub date_and_mem {
my $date = strftime "%Y-%m-%d %T", localtime;
my $mem = `ps -p $$ -o vsz |tail -1`;
chomp $mem;
return "[$date, mem $mem]";
}
=head2 date
Example : print "Date: " . $support->date . "\n";
Description : Prints a nicely formatted timestamp (YYYY-DD-MM hh:mm:ss)
Return type : String - the timestamp
Exceptions : none
Caller : general
=cut
sub date {
return strftime "%Y-%m-%d %T", localtime;
}
=head2 format_time
Example : print $support->format_time($gene->modifed_date) . "\n";
Description : Prints timestamps from the database
Return type : String - nicely formatted time stamp
Exceptions : none
Caller : general
=cut
sub date_format {
my( $self, $time, $format ) = @_;
my( $d,$m,$y) = (localtime($time))[3,4,5];
my %S = ('d'=>sprintf('%02d',$d),'m'=>sprintf('%02d',$m+1),'y'=>$y+1900);
(my $res = $format ) =~s/%(\w)/$S{$1}/ge;
return $res;
}
=head2 mem
Example : print "Memory usage: " . $support->mem . "\n";
Description : Prints the memory used by your script. Not sure about platform
dependence of this call ...
Return type : String - memory usage
Exceptions : none
Caller : general
=cut
sub mem {
my $mem = `ps -p $$ -o vsz |tail -1`;
chomp $mem;
return $mem;
}
=head2 commify
Arg[1] : Int $num - a number to commify
Example : print "An easy to read number: ".$self->commify(100000000);
# will print 100,000,000
Description : put commas into a number to make it easier to read
Return type : a string representing the commified number
Exceptions : none
Caller : general
Status : stable
=cut
sub commify {
my $self = shift;
my $num = shift;
$num = reverse($num);
$num =~ s/(\d\d\d)(?=\d)(?!\d*\.)/$1,/g;
return scalar reverse $num;
}
=head2 fetch_non_hidden_slices
Arg[1] : B::E::SliceAdaptor
Arg[2] : B::E::AttributeAdaptor
Arg[3] : string $coord_system_name (optional) - 'chromosome' by default
Arg[4] : string $coord_system_version (optional) - 'otter' by default
Example : $chroms = $support->fetch_non_hidden_slice($sa,$aa);
Steve Trevanion
committed
Description : retrieve all slices from a loutre database that don't have a hidden attribute.
Doesn't retrieve non-reference slices
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
Return type : arrayref
Caller : general
Status : stable
=cut
sub fetch_non_hidden_slices {
my $self = shift;
my $aa = shift or throw("You must supply an attribute adaptor");
my $sa = shift or throw("You must supply a slice adaptor");
my $cs = shift || 'chromosome';
my $cv = shift || 'Otter';
my $visible_chroms;
foreach my $chrom ( @{$sa->fetch_all($cs,$cv)} ) {
my $chrom_name = $chrom->name;
my $attribs = $aa->fetch_all_by_Slice($chrom,'hidden');
if ( scalar(@$attribs) > 1 ) {
$self->log_warning("More than one hidden attribute for chromosome $chrom_name\n");
}
elsif ($attribs->[0]->value == 0) {
push @$visible_chroms, $chrom;
}
elsif ($attribs->[0]->value == 1) {
$self->log_verbose("chromosome $chrom_name is hidden\n");
}
else {
$self->log_warning("No hidden attribute for chromosome $chrom_name\n");
}
}
return $visible_chroms;
}
=head2 get_non_hidden_slice_names
Arg[1] : B::E::SliceAdaptor
Arg[2] : B::E::AttributeAdaptor
Arg[3] : string $coord_system_name (optional) - 'chromosome' by default
Arg[4] : string $coord_system_version (optional) - 'otter' by default
Example : $chrom_names = $support->get_non_hidden_slice_names($sa,$aa);
Steve Trevanion
committed
Description : retrieve names of all slices from a loutre database that don't have a hidden attribute.
Doesn't retrieve non-reference slices
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
Return type : arrayref of names of all non-hidden slices
Caller : general
Status : stable
=cut
sub get_non_hidden_slice_names {
my $self = shift;
my $aa = shift or throw("You must supply an attribute adaptor");
my $sa = shift or throw("You must supply a slice adaptor");
my $cs = shift || 'chromosome';
my $cv = shift || 'Otter';
my $visible_chrom_names;
foreach my $chrom ( @{$sa->fetch_all($cs,$cv)} ) {
my $chrom_name = $chrom->seq_region_name;
my $attribs = $aa->fetch_all_by_Slice($chrom,'hidden');
if ( scalar(@$attribs) > 1 ) {
$self->log_warning("More than one hidden attribute for chromosome $chrom_name\n");
}
elsif ($attribs->[0]->value == 0) {
push @$visible_chrom_names, $chrom_name;
}
elsif ($attribs->[0]->value == 1) {
$self->log_verbose("chromosome $chrom_name is hidden\n");
}
else {
$self->log_warning("No hidden attribute for chromosome $chrom_name\n");
}
}
return $visible_chrom_names;
}
=head2 get_wanted_chromosomes
Steve Trevanion
committed
Arg[1] : B::E::SliceAdaptor
Arg[2] : B::E::AttributeAdaptor
Arg[3] : string $coord_system_name (optional) - 'chromosome' by default
Arg[4] : string $coord_system_version (optional) - 'otter' by default
Example : $chr_names = $support->get_wanted_chromosomes($laa,$lsa);
Description : retrieve names of slices from a lutra database that are ready for dumping to Vega.
Deals with list of names to ignore (ignore_chr = LIST)
Return type : arrayref of slices
Caller : general
Status : stable
=cut
sub get_wanted_chromosomes {
my $self = shift;
my $aa = shift or throw("You must supply an attribute adaptor");
my $sa = shift or throw("You must supply a slice adaptor");
my $cs = shift || 'chromosome';
my $cv = shift || 'Otter';
my $export_mode = $self->param('release_type');
my $release = $self->param('vega_release');
my $names;
my $chroms = $self->fetch_non_hidden_slices($aa,$sa,$cs,$cv);
CHROM:
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
foreach my $chrom (@$chroms) {
my $attribs = $aa->fetch_all_by_Slice($chrom);
my $vals = $self->get_attrib_values($attribs,'vega_export_mod');
if (scalar(@$vals > 1)) {
$self->log_warning ("Multiple attribs for \'vega_export_mod\', please fix before continuing");
exit;
}
next CHROM if (! grep { $_ eq $export_mode} @$vals);
$vals = $self->get_attrib_values($attribs,'vega_release',$release);
if (scalar(@$vals > 1)) {
$self->log_warning ("Multiple attribs for \'vega_release\' value = $release , please fix before continuing");
exit;
}
next CHROM if (! grep { $_ eq $release} @$vals);
my $name = $chrom->seq_region_name;
if (my @ignored = $self->param('ignore_chr')) {
next CHROM if (grep {$_ eq $name} @ignored);
}
push @{$names}, $name;
}
return $names;
}
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
=head2 is_haplotype
Arg[1] : B::E::Slice
Arg[2]: : B::E::DBAdaptor (optional, if you don't supply one then the *first* one you generated is returned, which may or may not be what you want!)
Description : Is the slice a Vega haplotype? At the moment this is
implemented by testing for presence of vega_ref_chrom but non_ref
which is correct in practice, but really misses the prupose of
vega_ref_chrom, so this might bite us if that changes.
Return type : boolean
=cut
sub is_haplotype {
my ($self,$slice,$dba) = @_;
$dba ||= $self->dba;
my $aa = $dba->get_adaptor('Attribute');
my $attribs = $aa->fetch_all_by_Slice($slice);
return (@{$self->get_attrib_values($attribs,'vega_ref_chrom')} and
@{$self->get_attrib_values($attribs,'non_ref',1)});
}
Steve Trevanion
committed
=head2 get_unique_genes
Arg[1] : B::E::Slice
Arg[2] : B::E::DBAdaptor (optional, if you don't supply one then the *first* one you generated is returned, which may or may not be what you want!)
Example : $genes = $support->get_unique_genes($slice,$dba);
Steve Trevanion
committed
Description : Retrieve genes that are only on the slice itself - used for human where assembly patches
are in the assembly_exception table. Needs the PATCHes to have 'non_ref' seq_region_attributes.
Return type : arrayref of genes
Caller : general
Status : stable
=cut
sub get_unique_genes {
my $self = shift;
my ($slice,$dba) = @_;
$slice or throw("You must supply a slice");
$dba ||= $self->dba;
my $sa = $dba->get_adaptor('Slice');
my $ga = $dba->get_adaptor('Gene');
my $patch = 0;
my $genes = [];
if ( ! $slice->is_reference() and ! $self->is_haplotype($slice,$dba) ) {
Steve Trevanion
committed
$patch = 1;
my $slices = $sa->fetch_by_region_unique( $slice->coord_system_name(),$slice->seq_region_name() );
foreach my $slice ( @{$slices} ) {
push @$genes,@{$ga->fetch_all_by_Slice($slice)};
# my $start = $slice->start;
Steve Trevanion
committed
}
}
else {
$genes = $ga->fetch_all_by_Slice($slice);
}
return ($genes, $patch);
}
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
=head2 get_attrib_values
Arg[1] : Arrayref of B::E::Attributes
Arg[2] : 'code' to search for
Arg[3] : 'value' to search for (optional)
Example : my $c = $self->get_attrib_values($attribs,'name'));
Description : (i) In the absence of an attribute value argument, examines an arrayref
of B::E::Attributes for a particular attribute type, returning the values
for each attribute of that type. Can therefore be used to test for the
number of attributes of that type.
(ii) In the presence of the optional value argument it returns all
attributes with that value ie can be used to test for the presence of an
attribute with that particular value.
Return type : arrayref of values for that attribute
Caller : general
Status : stable
=cut
sub get_attrib_values {
my $self = shift;
my $attribs = shift;
my $code = shift;
my $value = shift;
if (my @atts = grep {$_->code eq $code } @$attribs) {
my $r = [];
if ($value) {
if (my @values = grep {$_->value eq $value} @atts) {
foreach (@values) {
push @$r, $_->value;
}
return $r;
}
else {
return [];
}
}
else {
foreach (@atts) {
push @$r, $_->value;
}
return $r;
}
}
else {
return [];
}
}
=head2 fix_attrib_value
Arg[1] : Arrayref of existing B::E::Attributes
Arg[2] : dbID of object
Arg[3] : name of object (just for reporting)
Arg[4] : attrib_type.code
Arg[5] : attrib_type.value
Arg[6] : interactive ? (0 by default)
Arg[7] : table
Example : $support->fix_attrib_value($attribs,$chr_id,$chr_name,'vega_export_mod','N',1);
Description : adds a new attribute to an object, or updates an existing attribute with a new value
Can be run in interactive or non-interactive mode (default)
Return type : arrayref of results
Caller : general
Status : only ever tested with seq_region_attributes to date
=cut
sub fix_attrib_value {
my $self = shift;
my $attribs = shift;
my $id = shift;
my $name = shift;
my $code = shift;
my $value = shift;
my $interact = shift || 0;
my $table = shift || 'seq_region_attrib';
#transiently set interactive parameter to zero
my $int_before;
if (! $interact) {
$int_before = $self->param('interactive');
$self->param('interactive',0);
}
#get any existing value(s) for this attribute
my $existings = $self->get_attrib_values($attribs,$code);
#add a new attribute if there is none...
if (! @$existings ) {
if ($self->user_proceed("Do you want to set $name attrib (code = $code) to value $value ?")) {
my $r = $self->store_new_attribute($id,$code,$value);
#reset interactive parameter
$self->param('interactive',$int_before) if (! $interact);
return $r;
}
}
#...warn and exit if you're trying to update more than one value for the same attribute...
elsif (scalar @$existings > 1) {
$self->log_warning("You shouldn't be trying to update multiple attributes with the same code at once ($name:$code,$value), looks like you have duplicate entries in the (seq_region_)attrib table\n");
exit;
}
#...or update an attribute with new values...
else {
my $existing = $existings->[0];
if ($existing ne $value) {
if ($self->user_proceed("Do you want to reset $name attrib (code = $code) from $existing to $value ?")) {
my $r = $self->update_attribute($id,$code,$value);
$self->param('interactive',$int_before) if (! $interact);
push @$r, $existing;
return $r;
}
}
#...or make no change
else {
$self->param('interactive',$int_before) if (! $interact);
return [];
}
}
}
=head2 _get_attrib_id
Arg[1] : attrib_type.code
Arg[2] : database handle
Example : $self->_get_attrib_id('name',$dbh)
Description : get attrib_type.attrib_type_id from a attrib_type.code
Return type : attrib_type.attrib_type_id
Caller : internal
Status : stable
=cut
sub _get_attrib_id {
my $self = shift;
my $attrib_code = shift;
my $dbh = shift;
my ($attrib_id) = $dbh->selectrow_array(
qq(select attrib_type_id
from attrib_type
where code = ?),
{},
($attrib_code)
);
if (! $attrib_id) {
$self->log_warning("There is no attrib_type_id for code $attrib_code, please patch the attrib_table\n");
exit;
}
else {
return $attrib_id;
}
}
=head2 store_new_attribute
Arg[1] : seq_region.seq_region_id
Arg[2] : attrib_type.code
Arg[3] : attrib_type.value
ARG[4] : table to update (seq_region_attribute by default)
Example : $support->store_new_attribute(23,name,5);
Description : uses MySQL to store an entry (code and value) in an attribute table
(seq_region_attrib by default)
Return type : array_ref
Caller : general
Status : stable
=cut
sub store_new_attribute {
my $self = shift;
my $sr_id = shift;
my $attrib_code = shift;
my $attrib_value = shift || '';
my $table = shift || 'seq_region_attrib';
#get database handle
my $dbh = $self->get_dbconnection('loutre');
#get attrib_type_id for this particular attribute
my $attrib_id = $self->_get_attrib_id($attrib_code,$dbh);
#store
my $r = $dbh->do(
qq(insert into $table
values (?,?,?)),
{},
($sr_id,$attrib_id,$attrib_value)
);
return ['Stored',$r];
}
=head2 update_attribute
Arg[1] : seq_region.seq_region_id
Arg[2] : attrib_type.code
Arg[3] : attrib_type.value
ARG[4] : table to update (seq_region_attribute by default)
Example : $support->update_attribute(23,name,5);
Description : uses MySQL to update an attribute table (seq_region_attrib by default)
Return type : array_ref
Caller : general
Status : stable
=cut
sub update_attribute {
my $self = shift;
my $sr_id = shift;
my $attrib_code = shift;
my $attrib_value = shift;
my $table = shift || 'seq_region_attrib';
my $dbh = $self->get_dbconnection('loutre');
my $attrib_id = $self->_get_attrib_id($attrib_code,$dbh);
#update
my $r = $dbh->do(
qq(update $table
set value = ?
where seq_region_id = $sr_id
and attrib_type_id = $attrib_id),
{},
($attrib_value)
);
return ['Updated',$r];
}
Steve Trevanion
committed
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
=head2 remove_duplicate_attribs
Arg[1] : db handle
Arg[2] : table
Example : $support->remove_duplicate_attribs($dbh,'gene');
Description : uses MySQL to remove duplicate entries from an attribute table
Return type : none
Caller : general
Status : stable
=cut
sub remove_duplicate_attribs {
my $self = shift;
my $dbh = shift;
my $table = shift;
$dbh->do(qq(create table nondup_${table}_attrib like ${table}_attrib));
$dbh->do(qq(insert into nondup_${table}_attrib (select ${table}_id, attrib_type_id, value from ${table}_attrib group by ${table}_id, attrib_type_id, value)));
$dbh->do(qq(delete from ${table}_attrib));
$dbh->do(qq(insert into ${table}_attrib (select ${table}_id, attrib_type_id, value from nondup_${table}_attrib)));
$dbh->do(qq(drop table nondup_${table}_attrib));
}