/usr/share/perl5/Bio/SeqIO/chadoxml.pm is in libbio-perl-perl 1.7.2-2.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
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 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 1120 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 1513 1514 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 1554 1555 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 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 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 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 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 | #
# BioPerl module for Bio::SeqIO::chadoxml
#
# Peili Zhang <peili@morgan.harvard.edu>
#
# You may distribute this module under the same terms as perl itself
# POD documentation - main docs before the code
=head1 NAME
Bio::SeqIO::chadoxml - chadoxml sequence output stream
=head1 SYNOPSIS
It is probably best not to use this object directly, but
rather go through the SeqIO handler system:
$writer = Bio::SeqIO->new(-file => ">chado.xml",
-format => 'chadoxml');
# assume you already have Sequence or SeqFeature objects
$writer->write_seq($seq_obj);
#after writing all seqs
$writer->close_chadoxml();
=head1 DESCRIPTION
This object can transform Bio::Seq objects to chadoxml flat
file databases (for chadoxml DTD, see
http://gmod.cvs.sourceforge.net/gmod/schema/chado/dat/chado.dtd).
This is currently a write-only module.
$seqio = Bio::SeqIO->new(-file => '>outfile.xml',
-format => 'chadoxml'
-suppress_residues => 1,
-allow_residues => 'chromosome',
);
# we have a Bio::Seq object $seq which is a gene located on
# chromosome arm 'X', to be written out to chadoxml
# before converting to chadoxml, $seq object B<must> be transformed
# so that all the coordinates in $seq are against the source
# feature to be passed into Bio::SeqIO::chadoxml->write_seq()
# -- chromosome arm X in the example below.
$seqio->write_seq(-seq=>$seq,
-genus => 'Homo',
-species => 'sapiens',
-seq_so_type=>'gene',
-src_feature=>'X',
-src_feat_type=>'chromosome_arm',
-nounflatten=>1,
-is_analysis=>'true',
-data_source=>'GenBank');
The chadoxml output of Bio::SeqIO::chadoxml-E<gt>write_seq() method can be
passed to the loader utility in XORT package
(http://gmod.cvs.sourceforge.net/gmod/schema/XMLTools/XORT/)
to be loaded into chado.
This object is currently implemented to work with sequence and
annotation data from whole genome projects deposited in GenBank. It
may not be able to handle all different types of data from all
different sources.
In converting a Bio::Seq object into chadoxml, a top-level feature is
created to represent the object and all sequence features inside the
Bio::Seq object are treated as subfeatures of the top-level
feature. The Bio::SeqIO::chadoxml object calls
Bio::SeqFeature::Tools::Unflattener to unflatten the flat feature list
contained in the subject Bio::Seq object, to build gene model
containment hierarchy conforming to chado central dogma model: gene
--E<gt> mRNA --E<gt> exons and protein.
Destination of data in the subject Bio::Seq object $seq is as following:
*$seq->display_id: name of the top-level feature;
*$seq->accession_number: if defined, uniquename and
feature_dbxref of the top-level
feature if not defined,
$seq->display_id is used as the
uniquename of the top-level feature;
*$seq->molecule: transformed to SO type, used as the feature
type of the top-level feature if -seq_so_type
argument is supplied, use the supplied SO type
as the feature type of the top-level feature;
*$seq->species: organism of the top-level feature;
*$seq->seq: residues of the top-level feature;
*$seq->is_circular, $seq->division: feature_cvterm;
*$seq->keywords, $seq->desc, comments: featureprop;
*references: pub and feature_pub;
medline/pubmed ids: pub_dbxref;
comments: pubprop;
*feature "source" span: featureloc for top-level feature;
*feature "source" db_xref: feature_dbxref for top-level feature;
*feature "source" other tags: featureprop for top-level feature;
*subfeature 'symbol' or 'label' tag: feature uniquename, if
none of these is present, the chadoxml object
generates feature uniquenames as:
<gene>-<feature_type>-<span>
(e.g. foo-mRNA--1000..3000);
*gene model: feature_relationship built based on the
containment hierarchy;
*feature span: featureloc;
*feature accession numbers: feature_dbxref;
*feature tags (except db_xref, symbol and gene): featureprop;
Things to watch out for:
*chado schema change: this version works with the chado
version tagged chado_1_01 in GMOD CVS.
*feature uniquenames: especially important if using XORT
loader to do incremental load into
chado. may need pre-processing of the
source data to put the correct
uniquenames in place.
*pub uniquenames: chadoxml->write_seq() has the FlyBase policy
on pub uniquenames hard-coded, it assigns
pub uniquenames in the following way: for
journals and books, use ISBN number; for
published papers, use MEDLINE ID; for
everything else, use FlyBase unique
identifier FBrf#. need to modify the code to
implement your policy. look for the comments
in the code.
*for pubs possibly existing in chado but with no knowledge of
its uniquename:put "op" as "match", then need to run the
output chadoxml through a special filter that
talks to chado database and tries to find the
pub by matching with the provided information
instead of looking up by the unique key. after
matching, the filter also resets the "match"
operation to either "force" (default), or
"lookup", or "insert", or "update". the
"match" operation is for a special FlyBase use
case. please modify to work according to your
rules.
*chado initialization for loading:
cv & cvterm: in the output chadoxml, all cv's and
cvterm's are lookup only. Therefore,
before using XORT loader to load the
output into chado, chado must be
pre-loaded with all necessary CVs and
CVterms, including "SO" , "property
type", "relationship type", "pub type",
"pubprop type", "pub relationship type",
"sequence topology", "GenBank feature
qualifier", "GenBank division". A pub by
the uniquename 'nullpub' of type 'null
pub' needs to be inserted.
=head1 FEEDBACK
=head2 Mailing Lists
User feedback is an integral part of the evolution of this and other
Bioperl modules. Send your comments and suggestions preferably to one
of the Bioperl mailing lists. Your participation is much appreciated.
bioperl-l@bioperl.org - General discussion
http://bioperl.org/wiki/Mailing_lists - About the mailing lists
=head2 Support
Please direct usage questions or support issues to the mailing list:
I<bioperl-l@bioperl.org>
rather than to the module maintainer directly. Many experienced and
reponsive experts will be able look at the problem and quickly
address it. Please include a thorough description of the problem
with code and data examples if at all possible.
=head2 Reporting Bugs
Report bugs to the Bioperl bug tracking system to help us keep track
the bugs and their resolution.
Bug reports can be submitted via the web:
https://github.com/bioperl/bioperl-live/issues
=head1 AUTHOR - Peili Zhang
Email peili@morgan.harvard.edu
=head1 APPENDIX
The rest of the documentation details each of the object
methods. Internal methods are usually preceded with a _
=cut
# Let the code begin...
package Bio::SeqIO::chadoxml;
use strict;
use English;
use Carp;
use Data::Dumper;
use XML::Writer;
use IO::File;
use IO::Handle;
use Bio::Seq;
use Bio::Seq::RichSeq;
use Bio::SeqIO::FTHelper;
use Bio::Species;
use Bio::Seq::SeqFactory;
use Bio::Factory::SequenceStreamI;
use Bio::SeqFeature::Generic;
use Bio::Annotation::Collection;
use Bio::Annotation::Comment;
use Bio::Annotation::Reference;
use Bio::Annotation::DBLink;
use Bio::SeqFeature::Tools::Unflattener;
#global variables
undef(my %finaldatahash); #data from Bio::Seq object stored in a hash
undef(my %datahash); #data from Bio::Seq object stored in a hash
my $chadotables = 'feature featureprop feature_relationship featureloc feature_cvterm cvterm cv feature_pub pub pub_dbxref pub_author author pub_relationship pubprop feature_dbxref dbxref db synonym feature_synonym';
my %fkey = (
"cvterm.cv_id" => "cv",
"cvterm.dbxref_id" => "dbxref",
"dbxref.db_id" => "db",
"feature.type_id" => "cvterm",
"feature.organism_id" => "organism",
"feature.dbxref_id" => "dbxref",
"featureprop.type_id" => "cvterm",
"feature_pub.pub_id" => "pub",
"feature_cvterm.cvterm_id" => "cvterm",
"feature_cvterm.pub_id" => "pub",
"feature_cvterm.feature_id" => "feature",
"feature_dbxref.dbxref_id" => "dbxref",
"feature_relationship.object_id" => "feature",
"feature_relationship.subject_id" => "feature",
"feature_relationship.type_id" => "cvterm",
"featureloc.srcfeature_id" => "feature",
"pub.type_id" => "cvterm",
"pub_dbxref.dbxref_id" => "dbxref",
"pub_author.author_id" => "author",
"pub_relationship.obj_pub_id" => "pub",
"pub_relationship.subj_pub_id" => "pub",
"pub_relationship.type_id" => "cvterm",
"pubprop.type_id" => "cvterm",
"feature_synonym.feature_id" => "feature",
"feature_synonym.synonym_id" => "synonym",
"feature_synonym.pub_id" => "pub",
"synonym.type_id" => "cvterm",
);
my %cv_name = (
'relationship' => 'relationship',
'sequence' => 'sequence',
'feature_property' => 'feature_property',
);
my %feattype_args2so = (
"aberr" => "aberration_junction",
# "conflict" => "sequence_difference",
# "polyA_signal" => "polyA_signal_sequence",
"variation" => "sequence_variant",
"mutation1" => "point_mutation", #for single-base mutation
"mutation2" => "sequence_variant", #for multi-base mutation
"rescue" => "rescue_fragment",
# "rfrag" => "restriction_fragment",
"protein_bind" => "protein_binding_site",
"misc_feature" => "region",
# "prim_transcript" => "primary_transcript",
"CDS" => "polypeptide",
"reg_element" => "regulatory_region",
"seq_variant" => "sequence_variant",
"mat_peptide" => "mature_peptide",
"sig_peptide" => "signal_peptide",
);
undef(my %organism);
use base qw(Bio::SeqIO);
sub _initialize {
my($self,%args) = @_;
$self->SUPER::_initialize(%args);
unless( defined $self->sequence_factory ) {
$self->sequence_factory(Bio::Seq::SeqFactory->new
(-verbose => $self->verbose(),
-type => 'Bio::Seq::RichSeq'));
}
#optional arguments that can be passed in
$self->suppress_residues($args{'-suppress_residues'})
if defined $args{'-suppress_residues'};
$self->allow_residues($args{'-allow_residues'})
if defined $args{'-allow_residues'};
return;
}
=head2 write_seq
Title : write_seq
Usage : $stream->write_seq(-seq=>$seq, -seq_so_type=>$seqSOtype,
-src_feature=>$srcfeature,
-src_feat_type=>$srcfeattype,
-nounflatten=>0 or 1,
-is_analysis=>'true' or 'false',
-data_source=>$datasource)
Function: writes the $seq object (must be seq) into chadoxml.
Returns : 1 for success and 0 for error
Args : A Bio::Seq object $seq, optional $seqSOtype, $srcfeature,
$srcfeattype, $nounflatten, $is_analysis and $data_source.
When $srcfeature (a string, the uniquename of the source feature) is given, the
location and strand information of the top-level feature against the source
feature will be derived from the sequence feature called 'source' of the $seq
object, a featureloc record is generated for the top -level feature on
$srcfeature. when $srcfeature is given, $srcfeattype must also be present. All
feature coordinates in $seq should be against $srcfeature. $seqSOtype is the
optional SO term to use as the type of the top-level feature. For example, a
GenBank data file for a Drosophila melanogaster genome scaffold has the molecule
type of "DNA", when converting to chadoxml, a $seqSOtype argument of
"golden_path_region" can be supplied to save the scaffold as a feature of type
"golden_path_region" in chadoxml, instead of "DNA". a feature with primary tag
of 'source' must be present in the sequence feature list of $seq, to describe the
whole sequence record.
In the current implementation:
=over 3
=item *
non-mRNA records
A top-level feature of type $seq-E<gt>alphabet is generated for the whole GenBank
record, features listed are unflattened for DNA records to build gene model
feature graph, and for the other types of records all features in $seq are
treated as subfeatures of the top-level feature.
=item *
mRNA records
If a 'gene' feature is present, it B<must> have a /symbol or /label tag to
contain the uniquename of the gene. a top-level feature of type 'gene' is
generated. the mRNA is written as a subfeature of the top-level gene feature,
and the other sequence features listed in $seq are treated as subfeatures of the
mRNA feature.
=back
=cut
sub write_seq {
my $usage = <<EOUSAGE;
Bio::SeqIO::chadoxml->write_seq()
Usage : \$stream->write_seq(-seq=>\$seq,
-seq_so_type=>\$SOtype,
-src_feature=>\$srcfeature,
-src_feat_type=>\$srcfeattype,
-nounflatten=>0 or 1,
-is_analysis=>'true' or 'false',
-data_source=>\$datasource)
Args : \$seq : a Bio::Seq object
\$SOtype : the SO term to use as the feature type of
the \$seq record, optional
\$srcfeature : unique name of the source feature, a string
containing at least one alphabetical letter
(a-z, A-Z), optional
\$srcfeattype : feature type of \$srcfeature. one of SO terms.
optional
when \$srcfeature is given, \$srcfeattype becomes mandatory,
\$datasource : source of the sequence annotation data,
e.g. 'GenBank' or 'GFF'.
EOUSAGE
my ($self,@args) = @_;
my ($seq, $seq_so_type, $srcfeature, $srcfeattype, $nounflatten, $isanalysis, $datasource, $genus, $species) =
$self->_rearrange([qw(SEQ
SEQ_SO_TYPE
SRC_FEATURE
SRC_FEAT_TYPE
NOUNFLATTEN
IS_ANALYSIS
DATA_SOURCE
GENUS
SPECIES
)],
@args);
#print "$seq_so_type, $srcfeature, $srcfeattype\n";
if( !defined $seq ) {
$self->throw("Attempting to write with no seq!");
}
if( ! ref $seq || ! $seq->isa('Bio::Seq::RichSeqI') ) {
## FIXME $self->warn(" $seq is not a RichSeqI compliant module. Attempting to dump, but may fail!");
}
# try to get the srcfeature from the seqFeature object
# for this to work, the user has to pass in the srcfeature type
if (!$srcfeature) {
if ($seq->can('seq_id')) {
$srcfeature=$seq->seq_id if ($seq->seq_id ne $seq->display_name);
}
}
#$srcfeature, when provided, should contain at least one alphabetical letter
if (defined $srcfeature)
{
if ($srcfeature =~ /[a-zA-Z]/)
{
chomp($srcfeature);
} else {
$self->throw( $usage );
}
#check for mandatory $srcfeattype
if (! defined $srcfeattype)
{
$self->throw( $usage );
#$srcfeattype must be a string of non-whitespace characters
} else {
if ($srcfeattype =~ /\S+/) {
chomp($srcfeattype);
} else {
$self->throw( $usage );
}
}
}
# variables local to write_seq()
my $div = undef;
my $hkey = undef;
undef(my @top_featureprops);
undef(my @featuresyns);
undef(my @top_featurecvterms);
my $name = $seq->display_id if $seq->can('display_id');
$name = $seq->display_name if $seq->can('display_name');
undef(my @feature_cvterms);
undef(my %sthash);
undef(my %dvhash);
undef(my %h1);
undef(my %h2);
my $temp = undef;
my $ann = undef;
undef(my @references);
undef(my @feature_pubs);
my $ref = undef;
my $location = undef;
my $fbrf = undef;
my $journal = undef;
my $issue = undef;
my $volume = undef;
my $volumeissue = undef;
my $pages = undef;
my $year = undef;
my $pubtype = undef;
# my $miniref= undef;
my $uniquename = undef;
my $refhash = undef;
my $feat = undef;
my $tag = undef;
my $tag_cv = undef;
my $ftype = undef;
my $subfeatcnt = undef;
undef(my @top_featrels);
undef (my %srcfhash);
local($^W) = 0; # suppressing warnings about uninitialized fields.
if (!$name && $seq->can('attributes') ) {
($name) = $seq->attributes('Alias');
}
if ($seq->can('accession_number') && defined $seq->accession_number && $seq->accession_number ne 'unknown') {
$uniquename = $seq->accession_number;
} elsif ($seq->can('accession') && defined $seq->accession && $seq->accession ne 'unknown') {
$uniquename = $seq->accession;
} elsif ($seq->can('attributes')) {
($uniquename) = $seq->attributes('load_id');
} else {
$uniquename = $name;
}
my $len = $seq->length();
if ($len == 0) {
$len = undef;
}
undef(my $gb_type);
if (!$seq->can('molecule') || ! defined ($gb_type = $seq->molecule()) ) {
$gb_type = $seq->can('alphabet') ? $seq->alphabet : 'DNA';
}
$gb_type = 'DNA' if $ftype eq 'dna';
$gb_type = 'RNA' if $ftype eq 'rna';
if(length $seq_so_type > 0) {
if (defined $seq_so_type) {
$ftype = $seq_so_type;
}
elsif ($seq->type) {
$ftype = ($seq->type =~ /(.*):/)
? $1
: $seq->type;
}
else {
$ftype = $gb_type;
}
}
else {
$ftype = $gb_type;
}
my %ftype_hash = $self->return_ftype_hash($ftype);
if ($species) {
%organism = ("genus"=>$genus, "species" => $species);
}
else {
my $spec = $seq->species();
if (!defined $spec) {
$self->throw("$seq does not know what organism it is from, which is required by chado. cannot proceed!\n");
} else {
%organism = ("genus"=>$spec->genus(), "species" => $spec->species());
}
}
my $residues;
if (!$self->suppress_residues ||
($self->suppress_residues && $self->allow_residues eq $ftype)) {
$residues = $seq->seq->isa('Bio::PrimarySeq')
? $seq->seq->seq
: $seq->seq;
}
else {
$residues = '';
}
#set is_analysis flag for gene model features
undef(my $isanal);
if ($ftype eq 'gene' || $ftype eq 'mRNA' || $ftype eq 'exon' || $ftype eq 'protein' || $ftype eq 'polypeptide') {
$isanal = $isanalysis;
$isanal = 'false' if !defined $isanal;
}
%datahash = (
"name" => $name,
"uniquename" => $uniquename,
"seqlen" => $len,
"residues" => $residues,
"type_id" => \%ftype_hash,
"organism_id" => \%organism,
"is_analysis" => $isanal || 'false',
);
if (defined $srcfeature) {
%srcfhash = $self->_srcf_hash($srcfeature,
$srcfeattype,
\%organism);
my ($phase,$strand);
if ($seq->can('phase')) {
$phase = $seq->phase;
}
if ($seq->can('strand')) {
$strand = $seq->strand;
}
my %fl = (
"srcfeature_id" => \%srcfhash,
"fmin" => $seq->start - 1,
"fmax" => $seq->end,
"strand" => $strand,
"phase" => $phase,
);
$datahash{'featureloc'} = \%fl;
}
#if $srcfeature is not given, use the Bio::Seq object itself as the srcfeature for featureloc's
if (!defined $srcfeature) {
$srcfeature = $uniquename;
$srcfeattype = $ftype;
}
#default data source is 'GenBank'
if (!defined $datasource) {
$datasource = 'GenBank';
}
if ($datasource =~ /GenBank/i) {
#sequence topology as feature_cvterm
if ($seq->can('is_circular') && $seq->is_circular) {
%sthash = (
"cvterm_id" => {'name' => 'circular',
'cv_id' => {
'name' => 'sequence topology',
},
},
"pub_id" => {'uniquename' => 'nullpub',
'type_id' => {
'name' => 'null pub',
'cv_id' => {
'name'=> 'pub type',
},
},
},
);
} else {
%sthash = (
"cvterm_id" => { 'name' => 'linear',
'cv_id' => {
'name' => 'sequence topology',
}
},
"pub_id" => {'uniquename' => 'nullpub',
'type_id' => {
'name' => 'null pub',
'cv_id' => {
'name'=> 'pub type',
},
},
},
);
}
push(@feature_cvterms, \%sthash);
#division as feature_cvterm
if ($seq->can('division') && defined $seq->division()) {
$div = $seq->division();
%dvhash = (
"cvterm_id" => {'name' => $div,
'cv_id' => {
'name' => 'GenBank division'}},
"pub_id" => {'uniquename' => 'nullpub',
'type_id' => {
'name' => 'null pub',
'cv_id' => {
'name'=> 'pub type'},
}},
);
push(@feature_cvterms, \%dvhash);
}
$datahash{'feature_cvterm'} = \@feature_cvterms;
} # closes if GenBank
#featureprop's
#DEFINITION
if ($seq->can('desc') && defined $seq->desc()) {
$temp = $seq->desc();
my %prophash = (
"type_id" => {'name' => 'description',
'cv_id' => {
'name' =>
$cv_name{'feature_property'}
},
},
"value" => $temp,
);
push(@top_featureprops, \%prophash);
}
#KEYWORDS
if ($seq->can('keywords')) {
$temp = $seq->keywords();
if (defined $temp && $temp ne '.' && $temp ne '') {
my %prophash = (
"type_id" => {'name' => 'keywords',
'cv_id' => {
'name' =>
$cv_name{'feature_property'}
}
},
"value" => $temp,
);
push(@top_featureprops, \%prophash);
}
}
#COMMENT
if ($seq->can('annotation')) {
$ann = $seq->annotation();
foreach my $comment ($ann->get_Annotations('comment')) {
$temp = $comment->as_text();
#print "fcomment: $temp\n";
my %prophash = (
"type_id" => {'name' => 'comment',
'cv_id' => {
'name' =>
$cv_name{'feature_property'}
}
},
"value" => $temp,
);
push(@top_featureprops, \%prophash);
}
}
my @top_dbxrefs = ();
#feature object from Bio::DB::SeqFeature::Store
if ($seq->can('attributes')) {
my %attributes = $seq->attributes;
for my $key (keys %attributes) {
next if ($key eq 'parent_id');
next if ($key eq 'load_id');
if ($key eq 'Alias') {
@featuresyns = $self->handle_Alias_tag($seq,@featuresyns);
}
###FIXME deal with Dbxref, Ontology_term,source,
elsif ($key eq 'Ontology_term') {
@top_featurecvterms = $self->handle_Ontology_tag($seq,@top_featurecvterms);
}
elsif ($key eq 'dbxref' or $key eq 'Dbxref') {
@top_dbxrefs = $self->handle_dbxref($seq, $key, @top_dbxrefs);
}
elsif ($key =~ /^[a-z]/) {
@top_featureprops
= $self->handle_unreserved_tags($seq,$key,@top_featureprops);
}
}
}
$datahash{'feature_synonym'} = \@featuresyns;
if ($seq->can('source')) {
@top_dbxrefs = $self->handle_source($seq,@top_dbxrefs);
}
#accession and version as feature_dbxref
if ($seq->can('accession_number') && defined $seq->accession_number && $seq->accession_number ne 'unknown') {
my $db = $self->_guess_acc_db($seq, $seq->accession_number);
my %acchash = (
"db_id" => {'name' => $db},
"accession" => $seq->accession_number,
"version" => $seq->seq_version,
);
my %fdbx = ('dbxref_id' => \%acchash);
push(@top_dbxrefs, \%fdbx);
}
if( $seq->isa('Bio::Seq::RichSeqI') && defined $seq->get_secondary_accessions() ) {
my @secacc = $seq->get_secondary_accessions();
my $acc;
foreach $acc (@secacc) {
my %acchash = (
"db_id" => {'name' => 'GB'},
"accession" => $acc,
);
my %fdbx = ('dbxref_id' => \%acchash);
push(@top_dbxrefs, \%fdbx);
}
}
#GI number
if( $seq->isa('Bio::Seq::RichSeqI') && defined ($seq->pid)) {
my $id = $seq->pid;
#print "reftype: ", ref($id), "\n";
#if (ref($id) eq 'HASH') {
my %acchash = (
"db_id" => {'name' => 'GI'},
"accession" => $id,
);
my %fdbx = ('dbxref_id' => \%acchash);
push (@top_dbxrefs, \%fdbx);
}
#REFERENCES as feature_pub
if (defined $ann) {
#get the references
@references = $ann->get_Annotations('reference');
foreach $ref (@references) {
undef(my %pubhash);
$refhash = $ref->hash_tree();
$location = $ref->location || $refhash->{'location'};
#print "location: $location\n";
#get FBrf#, special for FlyBase SEAN loading
if (index($location, ' ==') >= 0) {
$location =~ /\s==/;
#print "match: $MATCH\n";
#print "prematch: $PREMATCH\n";
#print "postmatch: $POSTMATCH\n";
$fbrf = $PREMATCH;
$location = $POSTMATCH;
$location =~ s/^\s//;
}
#print "location: $location\n";
#unpublished reference
if ($location =~ /Unpublished/) {
$pubtype = 'unpublished';
%pubhash = (
"title" => $ref->title || $refhash->{'title'},
#"miniref" => substr($location, 0, 255),
#"uniquename" => $fbrf,
"type_id" => {'name' => $pubtype, 'cv_id' => {'name' =>'pub type'}}
);
}
#submitted
elsif ($location =~ /Submitted/) {
$pubtype = 'submitted';
%pubhash = (
"title" => $ref->title || $refhash->{'title'},
#"miniref" => substr($location, 0, 255),
#"uniquename" => $fbrf,
"type_id" => {'name' => $pubtype, 'cv_id' => {'name' =>'pub type'}}
);
undef(my $pyear);
$pyear = $self->_getSubmitYear($location);
if (defined $pyear) {
$pubhash{'pyear'} = $pyear;
}
}
#published journal paper
elsif ($location =~ /\D+\s\d+\s\((\d+|\d+-\d+)\),\s(\d+-\d+|\d+--\d+)\s\(\d\d\d\d\)$/) {
$pubtype = 'paper';
#parse location to get journal, volume, issue, pages & year
$location =~ /\(\d\d\d\d\)$/;
$year = $MATCH;
my $stuff = $PREMATCH;
$year =~ s/\(//; #remove the leading parenthesis
$year =~ s/\)//; #remove the trailing parenthesis
$stuff =~ /,\s(\d+-\d+|\d+--\d+)\s$/;
$pages = $MATCH;
$stuff = $PREMATCH;
$pages =~ s/^, //; #remove the leading comma and space
$pages =~ s/ $//; #remove the last space
$stuff =~ /\s\d+\s\((\d+|\d+-\d+)\)$/;
$volumeissue = $MATCH;
$journal = $PREMATCH;
$volumeissue =~ s/^ //; #remove the leading space
$volumeissue =~ /\((\d+|\d+-\d+)\)$/;
$issue = $MATCH;
$volume = $PREMATCH;
$issue =~ s/^\(//; #remove the leading parentheses
$issue =~ s/\)$//; #remove the last parentheses
$volume =~ s/^\s//; #remove the leading space
$volume =~ s/\s$//; #remove the last space
%pubhash = (
"title" => $ref->title || $refhash->{'title'},
"volume" => $volume,
"issue" => $issue,
"pyear" => $year,
"pages" => $pages,
#"miniref" => substr($location, 0, 255),
#"miniref" => ' ',
#"uniquename" => $fbrf,
"type_id" => {'name' => $pubtype, 'cv_id' => {'name' =>'pub type'}},
"pub_relationship" => {
'obj_pub_id' => {
'uniquename' => $journal,
'title' => $journal,
#'miniref' => substr($journal, 0, 255),
'type_id' =>{'name' => 'journal',
'cv_id' =>
{'name' => 'pub type'
},
},
#'pubprop' =>{'value'=> $journal,
# 'type_id'=>{'name' => 'abbreviation', 'cv_id' => {'name' => 'pubprop type'}},
# },
},
'type_id' => {
'name' => 'published_in',
'cv_id' => {
'name' => 'pub relationship type'},
},
},
);
}
#other references
else {
$pubtype = 'other';
%pubhash = (
"title" => $ref->title || $refhash->{'title'},
#"miniref" => $fbrf,
"type_id" => {
'name' => $pubtype,
'cv_id' => {'name' =>'pub type'}
}
);
}
#pub_author
my $autref = $self->_getRefAuthors($ref);
if (defined $autref) {
$pubhash{'pub_author'} = $autref;
}
# if no author and is type 'submitted' and has submitter address, use the first 100 characters of submitter address as the author lastname.
else {
if ($pubtype eq 'submitted') {
my $autref = $self->_getSubmitAddr($ref);
if (defined $autref) {
$pubhash{'pub_author'} = $autref;
}
}
}
#$ref->comment as pubprop
#print "ref comment: ", $ref->comment, "\n";
#print "ref comment: ", $refhash->{'comment'}, "\n";
if (defined $ref->comment || defined $refhash->{'comment'}) {
my $comnt = $ref->comment || $refhash->{'comment'};
#print "remark: ", $comnt, "\n";
$pubhash{'pubprop'} = {
"type_id" => {'name' => 'comment', 'cv_id' => {'name' => 'pubprop type'}},
"value" => $comnt,
};
}
#pub_dbxref
undef(my @pub_dbxrefs);
if (defined $fbrf) {
push(@pub_dbxrefs, {dbxref_id => {accession => $fbrf, db_id => {'name' => 'FlyBase'}}});
}
if (defined ($temp = $ref->medline)) {
push(@pub_dbxrefs, {dbxref_id => {accession => $temp, db_id => {'name' => 'MEDLINE'}}});
#use medline # as the pub's uniquename
$pubhash{'uniquename'} = $temp;
}
if (defined ($temp = $ref->pubmed)) {
push(@pub_dbxrefs, {dbxref_id => {accession => $temp, db_id => {'name' => 'PUBMED'}}});
}
$pubhash{'pub_dbxref'} = \@pub_dbxrefs;
#if the pub uniquename is not defined or blank, put its FBrf# as its uniquename
#this is unique to FlyBase
#USERS OF THIS MODULE: PLEASE MODIFY HERE TO IMPLEMENT YOUR POLICY
# ON PUB UNIQUENAME!!!
if (!defined $pubhash{'uniquename'} || $pubhash{'uniquename'} eq '') {
if (defined $fbrf) {
$pubhash{'uniquename'} = $fbrf;
}
#else {
# $pubhash{'uniquename'} = $self->_CreatePubUname($ref);
#}
}
#add to collection of references
#if the pub covers the entire sequence of the top-level feature, add it to feature_pubs
if (($ref->start == 1 && $ref->end == $len) || (!defined $ref->start && !defined $ref->end)) {
push(@feature_pubs, {"pub_id" => \%pubhash});
}
#the pub is about a sub-sequence of the top-level feature
#create a feature for the sub-sequence and add pub as its feature_pub
#featureloc of this sub-sequence is against the top-level feature, in interbase coordinates.
else {
my %parf = (
'uniquename' => $uniquename . ':' . $ref->start . "\.\." . $ref->end,
'organism_id' =>\%organism,
'type_id' =>{'name' =>'region', 'cv_id' => {'name' => $cv_name{'sequence'} }},
);
my %parfsrcf = (
'uniquename' => $uniquename,
'organism_id' =>\%organism,
);
my %parfloc = (
'srcfeature_id' => \%parfsrcf,
'fmin' => $ref->start - 1,
'fmax' => $ref->end,
);
$parf{'featureloc'} = \%parfloc;
$parf{'feature_pub'} = {'pub_id' => \%pubhash};
my %ffr = (
'subject_id' => \%parf,
'type_id' => { 'name' => 'partof', 'cv_id' => { 'name' => $cv_name{'relationship'}}},
);
push(@top_featrels, \%ffr);
}
}
$datahash{'feature_pub'} = \@feature_pubs;
}
##construct srcfeature hash for use in featureloc
if (defined $srcfeature) {
%srcfhash = $self->_srcf_hash($srcfeature,
$srcfeattype,
\%organism);
# my %fr = (
# "object_id" => \%srcfhash,
# "type_id" => { 'name' => 'partof', 'cv_id' => { 'name' => 'relationship type'}},
# );
# push (@top_featrels, \%fr);
}
#unflatten the seq features in $seq if $seq is a gene or a DNA sequence
if (($gb_type eq 'gene' || $gb_type eq 'DNA') &&
!$nounflatten) {
my $u = Bio::SeqFeature::Tools::Unflattener->new;
$u->unflatten_seq(-seq=>$seq, -use_magic=>1);
}
my @top_sfs = $seq->get_SeqFeatures;
#print $#top_sfs, "\n";
#SUBFEATURES
if ($datasource =~ /GenBank/i) {
$tag_cv = 'GenBank feature qualifier';
} elsif ($datasource =~ /GFF/i) {
$tag_cv = 'feature_property';
} else {
$tag_cv = $cv_name{'feature_property'};
}
my $si = 0;
foreach $feat (@top_sfs) {
#$feat = $top_sfs[$si];
#print "si: $si\n";
my $prim_tag = $feat->primary_tag;
#print $prim_tag, "\n";
# get all qualifiers of the 'source' feature, load these as top_featureprops of the top level feature
if ($prim_tag eq 'source') {
foreach $tag ($feat->all_tags()) {
#db_xref
if ($tag eq 'db_xref'
or $tag eq 'Dbxref'
or $tag eq 'dbxref') {
my @t1 = $feat->each_tag_value($tag);
foreach $temp (@t1) {
$temp =~ /([^:]*?):(.*)/;
my $db = $1;
my $xref = $2;
#PRE/POST very inefficent
#my $db = $PREMATCH;
#my $xref = $POSTMATCH;
my %acchash = (
"db_id" => {'name' => $db},
"accession" => $xref,
);
my %fdbx = ('dbxref_id' => \%acchash);
push (@top_dbxrefs, \%fdbx);
}
#Ontology_term
} elsif ($tag eq 'Ontology_term') {
my @t1 = $feat->each_tag_value($tag);
foreach $temp (@t1) {
###FIXME
}
#other tags as featureprop
} elsif ($tag ne 'gene') {
my %prophash = undef;
%prophash = (
"type_id" => {'name' => $tag, 'cv_id' => {'name' => $tag_cv}},
"value" => join(' ',$feat->each_tag_value($tag)),
);
push(@top_featureprops, \%prophash);
}
}
if ($feat->can('source')) {
my $source = $feat->source();
@top_dbxrefs = $self->handle_source($feat, @top_dbxrefs);
}
#featureloc for the top-level feature
my $fmin = undef;
my $fmax = undef;
my $strand = undef;
my $phase = undef;
my %fl = undef;
$fmin = $feat->start - 1;
$fmax = $feat->end;
$strand = $feat->strand;
if ($feat->can('phase')) {
$phase = $feat->phase;
}
%fl = (
"srcfeature_id" => \%srcfhash,
"fmin" => $fmin,
"fmax" => $fmax,
"strand" => $strand,
"phase" => $phase,
);
$datahash{'featureloc'} = \%fl;
#delete 'source' feature from @top_sfs
splice(@top_sfs, $si, 1);
}
$si ++;
#close loop over top_sfs
}
#the top-level features other than 'source'
foreach $feat (@top_sfs) {
#print $feat->primary_tag, "\n";
my $r = $self->_subfeat2featrelhash($name, $ftype, $feat, \%srcfhash, $tag_cv, $isanalysis);
if (!($ftype eq 'mRNA' && $feat->primary_tag eq 'gene')) {
my %fr = %$r;
push(@top_featrels, \%fr);
} else {
%finaldatahash = %$r;
}
}
if (@top_dbxrefs) {
$datahash{'feature_dbxref'} = \@top_dbxrefs;
}
if (@top_featureprops) {
$datahash{'featureprop'} = \@top_featureprops;
}
if (@top_featrels) {
$datahash{'feature_relationship'} = \@top_featrels;
}
if (@top_featurecvterms) {
$datahash{'feature_cvterm'} = \@top_featurecvterms;
}
if ($ftype eq 'mRNA' && %finaldatahash) {
$finaldatahash{'feature_relationship'} = {
'subject_id' => \%datahash,
'type_id' => { 'name' => 'partof', 'cv_id' => { 'name' => $cv_name{'relationship'} }},
};
} else {
%finaldatahash = %datahash;
}
my $mainTag = 'feature';
$self->_hash2xml(undef, $mainTag, \%finaldatahash);
return 1;
}
sub _hash2xml {
my $self = shift;
my $isMatch = undef;
$isMatch = shift;
my $ult = shift;
my $ref = shift;
my %mh = %$ref;
my $key;
my $v;
my $sh;
my $xx;
my $yy;
my $nt;
my $ntref;
my $output;
my $root = shift if (@_);
#print "ult: $ult\n";
if (!defined $self->{'writer'}) {
$root = 1;
$self->_create_writer();
}
my $temp;
my %subh = undef;
#start opeing tag
#if pub record of type 'journal', form the 'ref' attribute for special pub lookup
#requires that the journal name itself is also stored as a pubprop record for the journal with value equal
#to the journal name and type of 'abbreviation'.
if ($ult eq 'pub' && $mh{'type_id'}->{'name'} eq 'journal') {
$self->{'writer'}->startTag($ult, 'ref' => $mh{'title'} . ':journal:abbreviation');
}
#special pub match if pub uniquename not known
elsif ($ult eq 'pub' && !defined $mh{'uniquename'}) {
$self->{'writer'}->startTag($ult, 'op' => 'match');
#set the match flag, all the sub tags should also have "op"="match"
$isMatch = 1;
}
#if cvterm or cv, lookup only
elsif (($ult eq 'cvterm') || ($ult eq 'cv')) {
$self->{'writer'}->startTag($ult, 'op' => 'lookup');
}
#if nested tables of match table, match too
elsif ($isMatch) {
$self->{'writer'}->startTag($ult, 'op' => 'match');
}
else {
$self->{'writer'}->startTag($ult);
}
#first loop to produce xml for all the table columns
foreach $key (keys %mh)
{
#print "key: $key\n";
$xx = ' ' . $key;
$yy = $key . ' ';
if (index($chadotables, $xx) < 0 && index($chadotables, $yy) < 0)
{
if ($isMatch) {
$self->{'writer'}->startTag($key, 'op' => 'match');
} else {
$self->{'writer'}->startTag($key);
}
my $x = $ult . '.' . $key;
#the column is a foreign key
if (defined $fkey{$x})
{
$nt = $fkey{$x};
$sh = $mh{$key};
$self->_hash2xml($isMatch, $nt, $sh, 0);
} else
{
#print "$key: $mh{$key}\n";
$self->{'writer'}->characters($mh{$key});
}
$self->{'writer'}->endTag($key);
}
}
#second loop to produce xml for all the nested tables
foreach $key (keys %mh)
{
#print "key: $key\n";
$xx = ' ' . $key;
$yy = $key . ' ';
#a nested table
if (index($chadotables, $xx) > 0 || index($chadotables, $yy) > 0)
{
#$writer->startTag($key);
$ntref = $mh{$key};
#print "$key: ", ref($ntref), "\n";
if (ref($ntref) =~ 'HASH') {
$self->_hash2xml($isMatch, $key, $ntref, 0);
} elsif (ref($ntref) =~ 'ARRAY') {
#print "array dim: ", $#$ntref, "\n";
foreach $ref (@$ntref) {
#print "\n";
$self->_hash2xml($isMatch, $key, $ref, 0);
}
}
#$writer->endTag($key);
}
}
#end tag
$self->{'writer'}->endTag($ult);
#if ($root == 1) {
# $self->{'writer'}->endTag('chado');
# }
}
sub _guess_acc_db {
my $self = shift;
my $seq = shift;
my $acc = shift;
#print "acc: $acc\n";
if ($acc =~ /^NM_\d{6}/ || $acc =~ /^NP_\d{6}/ || $acc =~ /^NT_\d{6}/ || $acc =~ /^NC_\d{6}/) {
return "RefSeq";
} elsif ($acc =~ /^XM_\d{6}/ || $acc =~ /^XP_\d{6}/ || $acc =~ /^XR_\d{6}/) {
return "RefSeq";
} elsif ($acc =~ /^[a-zA-Z]{1,2}\d{5,6}/) {
return "GB";
} elsif ($seq->molecule() eq 'protein' && $acc =~ /^[a-zA-z]\d{5}/) {
return "PIR";
} elsif ($seq->molecule() eq 'protein' && $acc =~ /^\d{6,7}[a-zA-Z]/) {
return "PRF";
} elsif ($acc =~ /\d+/ && $acc !~ /[a-zA-Z]/) {
return "LocusID";
} elsif ($acc =~ /^CG\d+/ || $acc =~ /^FB[a-z][a-z]\d+/) {
return "FlyBase";
} else {
return "unknown";
}
}
sub _subfeat2featrelhash {
my $self = shift;
my $genename = shift;
my $seqtype = shift;
my $feat = shift;
my $r = shift;
my %srcf = %$r; #srcfeature hash for featureloc.srcfeature_id
my $tag_cv = shift;
my $isanalysis = shift;
my $prim_tag = $feat->primary_tag;
my $sfunique = undef; #subfeature uniquename
my $sfname = undef; #subfeature name
my $sftype = undef; #subfeature type
if ($feat->has_tag('symbol')) {
($sfunique) = $feat->each_tag_value("symbol");
} elsif ($feat->has_tag('label')) {
($sfunique) = $feat->each_tag_value("label");
} else {
#$self->throw("$prim_tag at " . $feat->start . "\.\." . $feat->end . " does not have symbol or label! To convert into chadoxml, a seq feature must have a /symbol or /label tag holding its unique name.");
#generate feature unique name as <genename>-<feature-type>-<span>
$sfunique = $self->_genFeatUniqueName($genename, $feat);
}
if ($feat->has_tag('Name')) {
($sfname) = $feat->each_tag_value("Name");
}
#feature type translation
if (defined $feattype_args2so{$prim_tag}) {
$sftype = $feattype_args2so{$prim_tag};
} else {
$sftype = $prim_tag;
}
if ($prim_tag eq 'mutation') {
if ($feat->start == $feat->end) {
$sftype = $feattype_args2so{'mutation1'};
} else {
$sftype = $feattype_args2so{'mutation2'};
}
}
#set is_analysis flag for gene model features
undef(my $isanal);
if ($sftype eq 'gene' || $sftype eq 'mRNA' || $sftype eq 'exon' || $sftype eq 'protein' || $sftype eq 'polypeptide') {
$isanal = $isanalysis;
}
my %sfhash = (
"name" => $sfname,
"uniquename" => $sfunique,
"organism_id" => \%organism,
"type_id" => { 'name' => $sftype, 'cv_id' => { 'name' => $cv_name{'sequence'} }},
"is_analysis" => $isanal || 'false',
);
#make a copy of %sfhash for passing to this method when recursively called
#my %srcfeat = (
# "name" => $sfname,
# "uniquename" => $sfunique,
# "organism_id" => \%organism,
# "type_id" => { 'name' => $sftype, 'cv_id' => { 'name' => 'SO'}},
# );
#featureloc for subfeatures
undef(my $sfmin);
undef(my $sfmax);
undef(my $is_sfmin_partial);
undef(my $is_sfmax_partial);
undef(my $sfstrand);
undef(my $sfphase);
$sfmin = $feat->start - 1;
$sfmax = $feat->end;
$sfstrand = $feat->strand();
if ($feat->can('phase')) {
$sfphase = $feat->phase;
}
#if the gene feature in an mRNA record, cannot use its coordinates, omit featureloc
if ($seqtype eq 'mRNA' && $sftype eq 'gene') {
} else {
if ($feat->location->isa('Bio::Location::FuzzyLocationI')) {
if ($feat->location->start_pos_type() ne 'EXACT') {
$is_sfmin_partial = 'true';
}
if ($feat->location->end_pos_type() ne 'EXACT') {
$is_sfmax_partial = 'true';
}
}
my %sfl = (
"srcfeature_id" => \%srcf,
"fmin" => $sfmin,
"is_fmin_partial" => $is_sfmin_partial || 'false',
"fmax" => $sfmax,
"is_fmax_partial" => $is_sfmax_partial || 'false',
"strand" => $sfstrand,
"phase" => $sfphase,
);
$sfhash{'featureloc'} = \%sfl;
}
#subfeature tags
undef(my @sfdbxrefs); #subfeature dbxrefs
undef(my @sub_featureprops); #subfeature props
undef(my @sub_featuresyns); #subfeature synonyms
undef(my @sub_featurecvterms); #subfeature cvterms
foreach my $tag ($feat->all_tags()) {
#feature_dbxref for features
if ($tag eq 'db_xref' or $tag eq 'dbxref' or $tag eq 'Dbxref') {
my @t1 = $feat->each_tag_value($tag);
#print "# of dbxref: @t1\n";
for my $temp (@t1) {
$temp =~ /:/;
my $db = $PREMATCH;
my $xref = $POSTMATCH;
#print "db: $db; xref: $xref\n";
my %acchash = (
"db_id" => {'name' => $db},
"accession" => $xref,
);
my %sfdbx = ('dbxref_id' => \%acchash);
push (@sfdbxrefs, \%sfdbx);
}
#Alias tags
} elsif ($tag eq 'Alias') {
@sub_featuresyns = $self->handle_Alias_tag($feat, @sub_featuresyns);
} elsif ($tag eq 'Ontology_term') {
@sub_featurecvterms = $self->handle_Ontology_tag($feat, @sub_featurecvterms);
#featureprop for features, excluding GFF Name & Parent tags
} elsif ($tag ne 'gene' && $tag ne 'symbol' && $tag ne 'Name' && $tag ne 'Parent') {
next if ($tag eq 'parent_id');
next if ($tag eq 'load_id');
foreach my $val ($feat->each_tag_value($tag)) {
my %prophash = undef;
%prophash = (
"type_id" => {'name' => $tag, 'cv_id' => {'name' => $tag_cv}},
"value" => $val,
);
push(@sub_featureprops, \%prophash);
}
}
}
if ($feat->can('source')) {
@sfdbxrefs = $self->handle_source($feat,@sfdbxrefs);
}
if (@sub_featureprops) {
$sfhash{'featureprop'} = \@sub_featureprops;
}
if (@sfdbxrefs) {
$sfhash{'feature_dbxref'} = \@sfdbxrefs;
}
if (@sub_featuresyns) {
$sfhash{'feature_synonym'} = \@sub_featuresyns;
}
if (@sub_featurecvterms) {
$sfhash{'feature_cvterm'} = \@sub_featurecvterms;
}
undef(my @ssfeatrel);
if ($feat->has_tag('locus_tag')) {
($genename)= $feat->each_tag_value('locus_tag');
} elsif ($feat->has_tag('gene')) {
($genename)= $feat->each_tag_value('gene');
}
foreach my $sf ($feat->get_SeqFeatures()) {
#print $sf->primary_tag, "\n";
my $rref = $self->_subfeat2featrelhash($genename, $sftype, $sf, \%srcf, $tag_cv, $isanalysis);
if (defined $rref) {
push(@ssfeatrel, $rref);
}
}
if (@ssfeatrel) {
$sfhash{'feature_relationship'} = \@ssfeatrel;
}
#subj-obj relationship type
undef(my $reltypename);
$reltypename = return_reltypename($sftype);
my %fr = (
"subject_id" => \%sfhash,
"type_id" => { 'name' => $reltypename,
'cv_id' => { 'name' => $cv_name{'relationship'} }},
);
if ($seqtype eq 'mRNA' && $sftype eq 'gene') {
return \%sfhash;
} else {
return \%fr;
}
}
#generate uniquename for feature as: <genename>-<feature-type>-<span> (foo-mRNA-10..1000)
sub _genFeatUniqueName {
my $self = shift;
my $genename = shift;
my $feat = shift;
undef(my $uniquename);
my $ftype = $feat->primary_tag;
my $start = $feat->start;
my $end = $feat->end;
if ($feat->has_tag('locus_tag')) {
($genename) = $feat->each_tag_value("locus_tag");
} elsif ($feat->has_tag('gene')) {
($genename) = $feat->each_tag_value("gene");
}
$uniquename = $genename . '-' . $ftype . '-' . $start . "\.\." . $end;
return $uniquename;
}
#create uniquename for pubs with no medline id and no FBrf#
#use "<authors>, <year>, <type>" as the uniquename (same as miniref)
#<authors> is <sole-author-surname> if one author,
# or <first-author-surname> and <second-author-surname> if two,
# or <first-author-surname> et al. if more
#sub _CreatePubUname {
# my $self = shift;
# my $pub = shift;
# undef(my $pubuname);
#
# return $pubuname;
#}
#get authors of a reference
#returns ref to the array of author hashes
sub _getRefAuthors {
my $self = shift;
my $ref = shift;
my $temp = $ref->authors;
undef(my @authors);
undef(my @aut);
#there are authors
if ($temp ne '.') {
if (index($temp, ' and ') > 0) {
$temp =~ / and /;
my $lastauthor = $POSTMATCH;
@authors = split(/\, /, $PREMATCH);
push (@authors, $lastauthor);
} else {
@authors = split(/\, /, $temp);
}
my $a;
my $i = 0;
foreach $a (@authors) {
$i ++;
#parse the author lastname and givennames
undef(my $last);
undef(my $given);
if (index($a, ',') > 0) { #genbank format, last,f.m.
($last, $given) = split(/\,/, $a);
} elsif (index($a, ' ') > 0) { #embl format, last f.m.
($last, $given) = split(/ /, $a);
}
my %au = (
'surname' => $last,
'givennames' => $given,
);
push(@aut, {author_id => \%au, arank => $i});
}
return \@aut;
}
#no authors, Bio::SeqIO::genbank doesn't pick up 'CONSRTM' line.
else {
return;
}
}
#extract submission year from the citation of the submitted reference
#genbank format for the submitted citation: JOURNAL Submitted (DD-MON-YYYY) submitter address
sub _getSubmitYear {
my $self = shift;
my $citation = shift;
if ($citation !~ /Submitted/) {
$self->warn("not citation for a submitted reference. cannot extract submission year.");
return;
} else {
$citation =~ /Submitted \(\d\d-[a-zA-Z]{3}-\d{4}\)/;
my $a = $MATCH;
$a =~ /\d{4}/;
my $year = $MATCH;
return $year;
}
}
sub _getSubmitAddr {
my $self = shift;
my $ref = shift;
undef(my %author);
my $citation = $ref->location;
if ($citation !~ /Submitted/) {
$self->warn("not citation for a submitted reference. cannot extract submission year.");
return;
} else {
$citation =~ /Submitted \(\d\d-[a-zA-Z]{3}-\d{4}\)/;
my $a = $POSTMATCH;
if (defined $a) {
$a =~ s/^\s//;
%author = (
'author_id' => {'surname' => substr($a, 0, 100)},
);
return \%author;
} else {
return;
}
}
}
=head2 suppress_residues
Title : suppress_residues
Usage : $obj->suppress_residues() #get existing value
$obj->suppress_residues($newval) #set new value
Function : Keep track of the flag to suppress printing of residues in the
chadoxml file. The default it to allow all residues to go into the
file.
Returns : value of suppress_residues (a scalar)
Args : new value of suppress_residues (to set)
=cut
sub suppress_residues {
my $self = shift;
my $suppress_residues = shift if @_;
return $self->{'suppress_residues'} = $suppress_residues if defined($suppress_residues);
return $self->{'suppress_residues'};
}
=head2 allow_residues
Title : allow_residues
Usage : $obj->allow_residues() #get existing value
$obj->allow_residues($feature_type) #set new value
Function : Track the allow_residues type. This can be used in conjunction
with the suppress_residues flag to only allow residues from a
specific feature type to be printed in the xml file, for example,
only printing chromosome residues. When suppress_residues is set to
true, then only chromosome features would would go into the xml
file. If suppress_residues is not set, this function has no effect
(since the default is to put all residues in the xml file).
Returns : value of allow_residues (string that corresponds to a feature type)
Args : new value of allow_residues (to set)
Status :
=cut
sub allow_residues {
my $self = shift;
my $allow_residues = shift if @_;
return $self->{'allow_residues'} = $allow_residues if defined($allow_residues);
return $self->{'allow_residues'};
}
=head2 return_ftype_hash
Title : return_ftype_hash
Usage : $obj->return_ftype_hash()
Function : A simple hash where returning it has be factored out of the main
code to allow subclasses to override it.
Returns : A hash that indicates what the name of the SO term is and what
the name of the Sequence Ontology is in the cv table.
Args : The string that represents the SO term.
Status :
=cut
sub return_ftype_hash {
my $self = shift;
my $ftype = shift;
my %ftype_hash = ( "name" => $ftype,
"cv_id" => {"name" => $cv_name{'sequence'} });
return %ftype_hash;
}
=head2 return_reltypename
Title : return_reltypename
Usage : $obj->return_reltypename
Function : Return the appropriate relationship type name depending on the
feature type (typically part_of, but derives_from for polypeptide).
Returns : A relationship type name.
Args : A SO type name.
Status :
=cut
sub return_reltypename {
my $self = shift;
my $sftype = shift;
my $reltypename;
if ($sftype eq 'protein' || $sftype eq 'polypeptide') {
$reltypename = 'derives_from';
} else {
$reltypename = 'part_of';
}
return $reltypename;
}
=head2 next_seq
Title : next_seq
Usage : $obj->next_seq
Function :
Returns :
Args :
Status : Not implemented (write only adaptor)
=cut
sub next_seq {
my ($self, %argv) = @_;
$self->throw('next_seq is not implemented; this is a write-only adapter.');
}
=head2 _create_writer
Title : _create_writer
Usage : $obj->_create_writer
Function : Creates XML::Writer object and writes start tag
Returns : Nothing, though the writer persists as part of the chadoxml object
Args : None
Status :
=cut
sub _create_writer {
my $self = shift;
$self->{'writer'} = XML::Writer->new(OUTPUT => $self->_fh,
DATA_MODE => 1,
DATA_INDENT => 3);
#print header
$self->{'writer'}->xmlDecl("UTF-8");
$self->{'writer'}->comment("created by Peili Zhang, Flybase, Harvard University\n".
"and Scott Cain, GMOD, Cold Spring Harbor Laboratory");
#start chadoxml
$self->{'writer'}->startTag('chado');
return;
}
=head2 close_chadoxml
Title : close_chadoxml
Usage : $obj->close_chadoxml
Function : Writes the closing xml tag
Returns : None
Args : None
Status :
=cut
sub close_chadoxml {
my $self = shift;
$self->{'writer'}->endTag('chado');
return;
}
=head2 handle_unreserved_tags
Title : handle_unreserved_tags
Usage : $obj->handle_unreserved_tags
Function : Converts tag value pairs to xml-ready hashrefs
Returns : The array containing the hashrefs
Args : In order: the Seq or SeqFeature object, the key, and the hasharray
Status :
=cut
sub handle_unreserved_tags {
my $self = shift;
my $seq = shift;
my $key = shift;
my @arr = @_;
my @values = $seq->attributes($key);
for my $value (@values) {
my %prophash = (
"type_id" => {'name' => $key,
'cv_id' => { 'name' => $cv_name{'feature_property'} }
},
"value" => $value,
);
push(@arr, \%prophash);
}
return @arr;
}
=head2 handle_Alias_tag
Title : handle_Alias_tag
Usage : $obj->handle_Alias_tag
Function : Convert Alias values to synonym hash refs
Returns : An array of synonym hash tags
Args : The seq or seqFeature object and the synonym hash array
Status :
=cut
sub handle_Alias_tag {
my $self = shift;
my $seq = shift;
my @arr = @_;
my @Aliases = $seq->attributes('Alias');
for my $Alias (@Aliases) {
my %synhash = (
"type_id" => { 'name' => 'exact',
'cv_id' => { 'name' => 'synonym_type' } },
"name" => $Alias,
"synonym_sgml" => $Alias,
);
push(@arr, {'synonym_id' => \%synhash,
'pub_id' => {'uniquename' => 'null',
'type_id' => { 'name' => 'null',
'cv_id' => {
'name' => 'null',
},
},
},
});
}
return @arr;
}
=head2 handle_Ontology_tag
Title : handle_Ontology_tag
Usage : $obj->handle_Ontology_tag
Function : Convert Ontology_term values to ontology term hash refs
Returns : An array of ontology term hash refs
Args : The seq or seqFeature object and the ontology term array
Status :
=cut
sub handle_Ontology_tag {
my $self = shift;
my $seq = shift;
my @arr = @_;
my @terms = $seq->attributes('Ontology_term');
for my $term (@terms) {
my $hashref;
if ($term =~ /(\S+):(\S+)/) {
my $db = $1;
my $acc = $2;
$hashref = {
'cvterm_id' => {
'dbxref_id' => {
'db_id' => { 'name' => $db },
'accession' => $acc
},
},
};
}
push(@arr, {cvterm_id => $hashref});
}
return @arr;
}
=head2 handle_dbxref
Title : handle_dbxref
Usage : $obj->handle_dbxref
Function : Convert Dbxref values to dbxref hashref
Returns : An array of dbxref hashrefs
Args : A seq or seqFeature object and the dbxref array
Status :
=cut
sub handle_dbxref {
my $self = shift;
my $seq = shift;
my $tag = shift;
my @arr = @_;
my @terms = $seq->attributes($tag);
for my $term (@terms) {
my $hashref;
if ($term =~ /(\S+):(\S+)/) {
my $db = $1;
my $acc= $2;
my $version = 1;
if ($acc =~ /(\S+)\.(\S+)/) {
$acc = $1;
$version = $2;
}
$hashref = {
'dbxref_id' => {
'db_id' => { 'name' => $db },
'accession' => $acc,
'version' => $version,
},
};
}
else {
$self->throw("I don't know how to handle a dbxref like $term");
}
push(@arr, {'dbxref_id' => $hashref});
}
return @arr;
}
=head2 handle_source
Title : handle_source
Usage : $obj->handle_source
Function :
Returns :
Args :
Status :
=cut
sub handle_source {
my $self = shift;
my $seq = shift;
my @arr = @_;
my $source = $seq->source();
return @arr unless $source;
my $hashref = {
'dbxref_id' => {
'db_id' => {'name' => 'GFF_source'},
'accession' => $source,
}
};
push(@arr, {'dbxref_id' => $hashref});
return @arr;
}
=head2 _srcf_hash
Title : _srcf_hash
Usage : $obj->_srcf_hash
Function : Creates the srcfeature hash for use in featureloc hashes
Returns : The srcfeature hash
Args : The srcfeature name, the srcfeature type and a reference to the
organism hash.
Status :
=cut
sub _srcf_hash {
my $self = shift;
my $srcf = shift;
my $stype= shift;
my $orgref = shift;
my %hash = ('uniquename' => $srcf,
'organism_id' => $orgref,
'type_id' => {'name' => $stype,
'cv_id' =>
{'name' => $cv_name{'sequence'} }},
);
return %hash;
}
1;
|