/usr/bin/bp_genbank2gff3 is in bioperl 1.6.924-3.
This file is owned by root:root, with mode 0o755.
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 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 | #!/usr/bin/perl
eval 'exec /usr/bin/perl -S $0 ${1+"$@"}'
if 0; # not running under some shell
=pod
=head1 NAME
bp_genbank2gff3.pl -- Genbank-E<gt>gbrowse-friendly GFF3
=head1 SYNOPSIS
bp_genbank2gff3.pl [options] filename(s)
# process a directory containing GenBank flatfiles
perl bp_genbank2gff3.pl --dir path_to_files --zip
# process a single file, ignore explicit exons and introns
perl bp_genbank2gff3.pl --filter exon --filter intron file.gbk.gz
# process a list of files
perl bp_genbank2gff3.pl *gbk.gz
# process data from URL, with Chado GFF model (-noCDS), and pipe to database loader
curl ftp://ftp.ncbi.nih.gov/genomes/Saccharomyces_cerevisiae/CHR_X/NC_001142.gbk \
| perl bp_genbank2gff3.pl -noCDS -in stdin -out stdout \
| perl gmod_bulk_load_gff3.pl -dbname mychado -organism fromdata
Options:
--noinfer -r don't infer exon/mRNA subfeatures
--conf -i path to the curation configuration file that contains user preferences
for Genbank entries (must be YAML format)
(if --manual is passed without --ini, user will be prompted to
create the file if any manual input is saved)
--sofile -l path to to the so.obo file to use for feature type mapping
(--sofile live will download the latest online revision)
--manual -m when trying to guess the proper SO term, if more than
one option matches the primary tag, the converter will
wait for user input to choose the correct one
(only works with --sofile)
--dir -d path to a list of genbank flatfiles
--outdir -o location to write GFF files (can be 'stdout' or '-' for pipe)
--zip -z compress GFF3 output files with gzip
--summary -s print a summary of the features in each contig
--filter -x genbank feature type(s) to ignore
--split -y split output to separate GFF and fasta files for
each genbank record
--nolump -n separate file for each reference sequence
(default is to lump all records together into one
output file for each input file)
--ethresh -e error threshold for unflattener
set this high (>2) to ignore all unflattener errors
--[no]CDS -c Keep CDS-exons, or convert to alternate gene-RNA-protein-exon
model. --CDS is default. Use --CDS to keep default GFF gene model,
use --noCDS to convert to g-r-p-e.
--format -f Input format (SeqIO types): GenBank, Swiss or Uniprot, EMBL work
(GenBank is default)
--GFF_VERSION 3 is default, 2 and 2.5 and other Bio::Tools::GFF versions available
--quiet don't talk about what is being processed
--typesource SO sequence type for source (e.g. chromosome; region; contig)
--help -h display this message
=head1 DESCRIPTION
This script uses Bio::SeqFeature::Tools::Unflattener and
Bio::Tools::GFF to convert GenBank flatfiles to GFF3 with gene
containment hierarchies mapped for optimal display in gbrowse.
The input files are assumed to be gzipped GenBank flatfiles for refseq
contigs. The files may contain multiple GenBank records. Either a
single file or an entire directory can be processed. By default, the
DNA sequence is embedded in the GFF but it can be saved into separate
fasta file with the --split(-y) option.
If an input file contains multiple records, the default behaviour is
to dump all GFF and sequence to a file of the same name (with .gff
appended). Using the 'nolump' option will create a separate file for
each genbank record. Using the 'split' option will create separate
GFF and Fasta files for each genbank record.
=head2 Notes
=head3 'split' and 'nolump' produce many files
In cases where the input files contain many GenBank records (for
example, the chromosome files for the mouse genome build), a very
large number of output files will be produced if the 'split' or
'nolump' options are selected. If you do have lists of files E<gt> 6000,
use the --long_list option in bp_bulk_load_gff.pl or
bp_fast_load_gff.pl to load the gff and/ or fasta files.
=head3 Designed for RefSeq
This script is designed for RefSeq genomic sequence entries. It may
work for third party annotations but this has not been tested.
But see below, Uniprot/Swissprot works, EMBL and possibly EMBL/Ensembl
if you don't mind some gene model unflattener errors (dgg).
=head3 G-R-P-E Gene Model
Don Gilbert worked this over with needs to produce GFF3 suited to
loading to GMOD Chado databases. Most of the changes I believe are
suited for general use. One main chado-specific addition is the
--[no]cds2protein flag
My favorite GFF is to set the above as ON by default (disable with --nocds2prot)
For general use it probably should be OFF, enabled with --cds2prot.
This writes GFF with an alternate, but useful Gene model,
instead of the consensus model for GFF3
[ gene > mRNA> (exon,CDS,UTR) ]
This alternate is
gene > mRNA > polypeptide > exon
means the only feature with dna bases is the exon. The others
specify only location ranges on a genome. Exon of course is a child
of mRNA and protein/peptide.
The protein/polypeptide feature is an important one, having all the
annotations of the GenBank CDS feature, protein ID, translation, GO
terms, Dbxrefs to other proteins.
UTRs, introns, CDS-exons are all inferred from the primary exon bases
inside/outside appropriate higher feature ranges. Other special gene
model features remain the same.
Several other improvements and bugfixes, minor but useful are included
* IO pipes now work:
curl ftp://ncbigenomes/... | bp_genbank2gff3 --in stdin --out stdout | gff2chado ...
* GenBank main record fields are added to source feature, e.g. organism, date,
and the sourcetype, commonly chromosome for genomes, is used.
* Gene Model handling for ncRNA, pseudogenes are added.
* GFF header is cleaner, more informative.
--GFF_VERSION flag allows choice of v2 as well as default v3
* GFF ##FASTA inclusion is improved, and
CDS translation sequence is moved to FASTA records.
* FT -> GFF attribute mapping is improved.
* --format choice of SeqIO input formats (GenBank default).
Uniprot/Swissprot and EMBL work and produce useful GFF.
* SeqFeature::Tools::TypeMapper has a few FT -> SOFA additions
and more flexible usage.
=head1 TODO
=head2 Are these additions desired?
* filter input records by taxon (e.g. keep only organism=xxx or taxa level = classYYY
* handle Entrezgene, other non-sequence SeqIO structures (really should change
those parsers to produce consistent annotation tags).
=head2 Related bugfixes/tests
These items from Bioperl mail were tested (sample data generating
errors), and found corrected:
From: Ed Green <green <at> eva.mpg.de>
Subject: genbank2gff3.pl on new human RefSeq
Date: 2006-03-13 21:22:26 GMT
-- unspecified errors (sample data works now).
From: Eric Just <e-just <at> northwestern.edu>
Subject: genbank2gff3.pl
Date: 2007-01-26 17:08:49 GMT
-- bug fixed in genbank2gff3 for multi-record handling
This error is for a /trans_splice gene that is hard to handle, and
unflattner/genbank2 doesn't
From: Chad Matsalla <chad <at> dieselwurks.com>
Subject: genbank2gff3.PLS and the unflatenner - Inconsistent order?
Date: 2005-07-15 19:51:48 GMT
=head1 AUTHOR
Sheldon McKay (mckays@cshl.edu)
Copyright (c) 2004 Cold Spring Harbor Laboratory.
=head2 AUTHOR of hacks for GFF2Chado loading
Don Gilbert (gilbertd@indiana.edu)
=cut
use strict;
use warnings;
use lib "$ENV{HOME}/bioperl-live";
# chad put this here to enable situations when this script is tested
# against bioperl compiled into blib along with other programs using blib
BEGIN {
unshift(@INC,'blib/lib');
};
use Pod::Usage;
use Bio::Root::RootI;
use Bio::SeqIO;
use File::Spec;
use Bio::SeqFeature::Tools::Unflattener;
use Bio::SeqFeature::Tools::TypeMapper;
use Bio::SeqFeature::Tools::IDHandler;
use Bio::Location::SplitLocationI;
use Bio::Location::Simple;
use Bio::Tools::GFF;
use Getopt::Long;
use List::Util qw(first);
use Bio::OntologyIO;
use YAML qw(Dump LoadFile DumpFile);
use File::Basename;
use vars qw/$split @filter $zip $outdir $help $ethresh
$ONTOLOGY %FEATURES %DESCENDANTS @RETURN $MANUAL @GFF_LINE_FEAT
$CONF $YAML $TYPE_MAP $SYN_MAP $noinfer $SO_FILE
$file @files $dir $summary $nolump
$source_type %proteinfa %exonpar $didheader $verbose $DEBUG $GFF_VERSION
$gene_id $rna_id $tnum $ncrna_id $rnum %method %id %seen/;
use constant SO_URL =>
'http://song.cvs.sourceforge.net/viewvc/*checkout*/song/ontology/so.obo';
use constant ALPHABET => [qw(a b c d e f g h i j k l m n o p q r s t u v w x y z)];
use constant ALPHABET_TO_NUMBER => {
a => 0, b => 1, c => 2, d => 3, e => 4, f => 5, g => 6, h => 7, i => 8,
j => 9, k => 10, l => 11, m => 12, n => 13, o => 14, p => 15, q => 16,
r => 17, s => 18, t => 19, u => 20, v => 21, w => 22, x => 23, y => 24,
z => 25,
};
use constant ALPHABET_DIVISOR => 26;
use constant GM_NEW_TOPLEVEL => 2;
use constant GM_NEW_PART => 1;
use constant GM_DUP_PART => 0;
use constant GM_NOT_PART => -1;
# Options cycle in multiples of 2 because of left side/right side pairing.
# You can make this number odd, but displayed matches will still round up
use constant OPTION_CYCLE => 6;
$GFF_VERSION = 3; # allow v2 ...
$verbose = 1; # right default? -nov to turn off
# dgg: change the gene model to Gene/mRNA/Polypeptide/exons...
my $CDSkeep= 1; # default should be ON (prior behavior), see gene_features()
my $PROTEIN_TYPE = 'polypeptide'; # for noCDSkeep;
# protein = flybase chado usage; GMOD Perls use 'polypeptide' with software support
my $FORMAT="GenBank"; # swiss ; embl; genbank ; ** guess from SOURCEID **
my $SOURCEID= $FORMAT; # "UniProt" "GenBank" "EMBL" should work
# other Bio::SeqIO formats may work. TEST: EntrezGene < problematic tags; InterPro KEGG
my %TAG_MAP = (
db_xref => 'Dbxref',
name => 'Name',
note => 'Note', # also pull GO: ids into Ontology_term
synonym => 'Alias',
symbol => 'Alias', # is symbol still used?
# protein_id => 'Dbxref', also seen Dbxref tags: EC_number
# translation: handled in gene_features
);
$| = 1;
my $quiet= !$verbose;
my $ok= GetOptions( 'd|dir|input:s' => \$dir,
'z|zip' => \$zip,
'h|help' => \$help,
's|summary' => \$summary,
'r|noinfer' => \$noinfer,
'i|conf=s' => \$CONF,
'sofile=s' => \$SO_FILE,
'm|manual' => \$MANUAL,
'o|outdir|output:s'=> \$outdir,
'x|filter:s'=> \@filter,
'y|split' => \$split,
"ethresh|e=s"=>\$ethresh,
'c|CDS!' => \$CDSkeep,
'f|format=s' => \$FORMAT,
'typesource=s' => \$source_type,
'GFF_VERSION=s' => \$GFF_VERSION,
'quiet!' => \$quiet, # swap quiet to verbose
'DEBUG!' => \$DEBUG,
'n|nolump' => \$nolump);
my $lump = 1 unless $nolump || $split;
$verbose= !$quiet;
# look for help request
pod2usage(2) if $help || !$ok;
# keep SOURCEID as-is and change FORMAT for SeqIO types;
# note SeqIO uses file.suffix to guess type; not useful here
$SOURCEID= $FORMAT;
$FORMAT = "swiss" if $FORMAT =~/UniProt|trembl/;
$verbose =1 if($DEBUG);
# initialize handlers
my $unflattener = Bio::SeqFeature::Tools::Unflattener->new; # for ensembl genomes (-trust_grouptag=>1);
$unflattener->error_threshold($ethresh) if $ethresh;
$unflattener->verbose(1) if($DEBUG);
# $unflattener->group_tag('gene') if($FORMAT =~ /embl/i) ; #? ensembl only?
# ensembl parsing is still problematic, forget this
my $tm = Bio::SeqFeature::Tools::TypeMapper->new;
my $idh = Bio::SeqFeature::Tools::IDHandler->new;
# dgg
$source_type ||= "region"; # should really parse from FT.source contents below
#my $FTSOmap = $tm->FT_SO_map();
my $FTSOmap;
my $FTSOsynonyms;
if (defined($SO_FILE) && $SO_FILE eq 'live') {
print "\nDownloading the latest SO file from ".SO_URL."\n\n";
use LWP::UserAgent;
my $ua = LWP::UserAgent->new(timeout => 30);
my $request = HTTP::Request->new(GET => SO_URL);
my $response = $ua->request($request);
if ($response->status_line =~ /200/) {
use File::Temp qw/ tempfile /;
my ($fh, $fn) = tempfile();
print $fh $response->content;
$SO_FILE = $fn;
} else {
print "Couldn't download SO file online...skipping validation.\n"
. "HTTP Status was " . $response->status_line . "\n"
and undef $SO_FILE
}
}
if ($SO_FILE) {
my (%terms, %syn);
my $parser = Bio::OntologyIO->new( -format => "obo", -file => $SO_FILE );
$ONTOLOGY = $parser->next_ontology();
for ($ONTOLOGY->get_all_terms) {
my $feat = $_;
$terms{$feat->name} = $feat->name;
#$terms{$feat->name} = $feat;
my @syn = $_->each_synonym;
push @{$syn{$_}}, $feat->name for @syn;
#push @{$syn{$_}}, $feat for @syn;
}
$FTSOmap = \%terms;
$FTSOsynonyms = \%syn;
my %hardTerms = %{ $tm->FT_SO_map() };
map { $FTSOmap->{$_} ||= $hardTerms{$_} } keys %hardTerms;
} else {
my %terms = %{ $tm->FT_SO_map() };
while (my ($k,$v) = each %terms) {
$FTSOmap->{$k} = ref($v) ? shift @$v : $v;
}
}
$TYPE_MAP = $FTSOmap;
$SYN_MAP = $FTSOsynonyms;
# #convert $FTSOmap undefined to valid SO : moved to TypeMapper->map_types( -undefined => "region")
# stringify filter list if applicable
my $filter = join ' ', @filter if @filter;
# determine input files
my $stdin=0; # dgg: let dir == stdin == '-' for pipe use
if ($dir && ($dir eq '-' || $dir eq 'stdin')) {
$stdin=1; $dir=''; @files=('stdin');
} elsif ( $dir ) {
if ( -d $dir ) {
opendir DIR, $dir or die "could not open $dir for reading: $!";
@files = map { "$dir/$_";} grep { /\.gb.*/ } readdir DIR;
closedir DIR;
}
else {
die "$dir is not a directory\n";
}
}
else {
@files = @ARGV;
$dir = '';
}
# we should have some files by now
pod2usage(2) unless @files;
my $stdout=0; # dgg: let outdir == stdout == '-' for pipe use
if($outdir && ($outdir eq '-' || $outdir eq 'stdout')) {
warn("std. output chosen: cannot split\n") if($split);
warn("std. output chosen: cannot zip\n") if($zip);
warn("std. output chosen: cannot nolump\n") if($nolump);
$stdout=1; $lump=1; $split= 0; $zip= 0; # unless we pipe stdout thru gzip
} elsif ( $outdir && !-e $outdir ) {
mkdir($outdir) or die "could not create directory $outdir: $!\n";
}
elsif ( !$outdir ) {
$outdir = $dir || '.';
}
for my $file ( @files ) {
# dgg ; allow 'stdin' / '-' input ?
chomp $file;
die "$! $file" unless($stdin || -e $file);
print "# Input: $file\n" if($verbose);
my ($lump_fh, $lumpfa_fh, $outfile, $outfa);
if ($stdout) {
$lump_fh= *STDOUT; $lump="stdout$$";
$outfa= "stdout$$.fa"; # this is a temp file ... see below
open $lumpfa_fh, ">$outfa" or die "Could not create a lump outfile called ($outfa) because ($!)\n";
} elsif ( $lump ) {
my ($vol,$dirs,$fileonly) = File::Spec->splitpath($file);
$lump = File::Spec->catfile($outdir, $fileonly.'.gff');
($outfa = $lump) =~ s/\.gff/\.fa/;
open $lump_fh, ">$lump" or die "Could not create a lump outfile called ($lump) because ($!)\n";
open $lumpfa_fh, ">$outfa" or die "Could not create a lump outfile called ($outfa) because ($!)\n";
}
# open input file, unzip if req'd
if ($stdin) {
*FH = *STDIN;
} elsif ( $file =~ /\.gz/ ) {
open FH, "gunzip -c $file |";
}
else {
open FH, '<', $file;
}
my $in = Bio::SeqIO->new(-fh => \*FH, -format => $FORMAT, -debug=>$DEBUG);
my $gffio = Bio::Tools::GFF->new( -noparse => 1, -gff_version => $GFF_VERSION );
while ( my $seq = $in->next_seq() ) {
my $seq_name = $seq->accession_number;
my $end = $seq->length;
my @to_print;
# arrange disposition of GFF output
$outfile = $lump || File::Spec->catfile($outdir, $seq_name.'.gff');
my $out;
if ( $lump ) {
$outfile = $lump;
$out = $lump_fh;
}
else {
$outfile = File::Spec->catfile($outdir, $seq_name.'.gff');
open $out, ">$outfile";
}
# filter out unwanted features
my $source_feat= undef;
my @source= filter($seq); $source_feat= $source[0];
($source_type,$source_feat)=
getSourceInfo( $seq, $source_type, $source_feat ) ;
# always; here we build main prot $source_feat; # if @source;
# abort if there are no features
warn "$seq_name has no features, skipping\n" and next
if !$seq->all_SeqFeatures;
$FTSOmap->{'source'} = $source_type;
## $FTSOmap->{'CDS'}= $PROTEIN_TYPE; # handle this in gene_features
# construct a GFF header
# add: get source_type from attributes of source feature? chromosome=X tag
# also combine 1st ft line here with source ft from $seq ..
my($header,$info)= gff_header($seq_name, $end, $source_type, $source_feat);
print $out $header;
print "# working on $info\n" if($verbose);
# unflatten gene graphs, apply SO types, etc; this also does TypeMapper ..
unflatten_seq($seq);
# Note that we use our own get_all_SeqFeatures function
# to rescue cloned exons
@GFF_LINE_FEAT = ();
for my $feature ( get_all_SeqFeatures($seq) ) {
my $method = $feature->primary_tag;
next if($SOURCEID =~/UniProt|swiss|trembl/i && $method ne $source_type);
$feature->seq_id($seq->id) unless($feature->seq_id);
$feature->source_tag($SOURCEID);
# dgg; need to convert some Genbank to GFF tags: note->Note; db_xref->Dbxref;
## also, pull any GO:000 ids from /note tag and put into Ontology_term
maptags2gff($feature);
# current gene name. The unflattened gene features should be in order so any
# exons, CDSs, etc that follow will belong to this gene
my $gene_name;
if ( $method eq 'gene' || $method eq 'pseudogene' ) {
@to_print= print_held($out, $gffio, \@to_print);
$gene_id = $gene_name= gene_name($feature);
} else {
$gene_name= gene_name($feature);
}
#?? should gene_name from /locus_tag,/gene,/product,/transposon=xxx
# be converted to or added as Name=xxx (if not ID= or as well)
## problematic: convert_to_name ($feature); # drops /locus_tag,/gene, tags
convert_to_name($feature);
## dgg: extended to protein|polypeptide
## this test ($feature->has_tag('gene') ||) is not good: repeat_regions over genes
## in yeast have that genbank tag; why?
## these include pseudogene ...
## Note we also have mapped types to SO, so these RNA's are now transcripts:
# pseudomRNA => "pseudogenic_transcript",
# pseudotranscript" => "pseudogenic_transcript",
# misc_RNA=>'processed_transcript',
warn "#at: $method $gene_id/$gene_name\n" if $DEBUG;
if ( $method =~ /(gene|RNA|CDS|exon|UTR|protein|polypeptide|transcript)/
|| ( $gene_id && $gene_name eq $gene_id ) ) {
my $action = gene_features($feature, $gene_id, $gene_name); # -1, 0, 1, 2 result
if ($action == GM_DUP_PART) {
# ignore, this is dupl. exon with new parent ...
} elsif ($action == GM_NOT_PART) {
add_generic_id( $feature, $gene_name, "nocount");
my $gff = $gffio->gff_string($feature);
push @GFF_LINE_FEAT, $feature;
#print $out "$gff\n" if $gff;
} elsif ($action > 0) {
# hold off print because exon etc. may get 2nd, 3rd parents
@to_print= print_held($out, $gffio, \@to_print) if ($action == GM_NEW_TOPLEVEL);
push(@to_print, $feature);
}
}
# otherwise handle as generic feats with IDHandler labels
else {
add_generic_id( $feature, $gene_name, "");
my $gff= $gffio->gff_string($feature);
push @GFF_LINE_FEAT, $feature;
#print $out "$gff\n" if $gff;
}
}
# don't like doing this after others; do after each new gene id?
@to_print= print_held($out, $gffio, \@to_print);
gff_validate(@GFF_LINE_FEAT);
for my $feature (@GFF_LINE_FEAT) {
my $gff= $gffio->gff_string($feature);
print $out "$gff\n" if $gff;
}
# deal with the corresponding DNA
my ($fa_out,$fa_outfile);
my $dna = $seq->seq;
if($dna || %proteinfa) {
$method{'RESIDUES'} += length($dna);
$dna =~ s/(\S{60})/$1\n/g;
$dna .= "\n";
if ($split) {
$fa_outfile = $outfile;
$fa_outfile =~ s/gff$/fa/;
open $fa_out, ">$fa_outfile" or die $!;
print $fa_out ">$seq_name\n$dna" if $dna;
foreach my $aid (sort keys %proteinfa) {
my $aa= delete $proteinfa{$aid};
$method{'RESIDUES(tr)'} += length($aa);
$aa =~ s/(\S{60})/$1\n/g;
print $fa_out ">$aid\n$aa\n";
}
}
else {
## problem here when multiple GB Seqs in one file; all FASTA needs to go at end of $out
## see e.g. Mouse: mm_ref_chr19.gbk has NT_082868 and NT_039687 parts in one .gbk
## maybe write this to temp .fa then cat to end of lumped gff $out
print $lumpfa_fh ">$seq_name\n$dna" if $dna;
foreach my $aid (sort keys %proteinfa) {
my $aa= delete $proteinfa{$aid};
$method{'RESIDUES(tr)'} += length($aa);
$aa =~ s/(\S{60})/$1\n/g;
print $lumpfa_fh ">$aid\n$aa\n";
}
}
%proteinfa=();
}
if ( $zip && !$lump ) {
system "gzip -f $outfile";
system "gzip -f $fa_outfile" if($fa_outfile);
$outfile .= '.gz';
$fa_outfile .= '.gz' if $split;
}
# print "\n>EOF\n" if($stdout); #?? need this if summary goes to stdout after FASTA
print "# GFF3 saved to $outfile" unless( !$verbose || $stdout || $lump);
print ($split ? "; DNA saved to $fa_outfile\n" : "\n") unless($stdout|| $lump);
# dgg: moved to after all inputs; here it prints cumulative sum for each record
#if ( $summary ) {
# print "# Summary:\n# Feature\tCount\n# -------\t-----\n";
#
# for ( keys %method ) {
# print "# $_ $method{$_}\n";
# }
# print "# \n";
# }
}
print "# GFF3 saved to $outfile\n" if( $verbose && $lump);
if ( $summary ) {
print "# Summary:\n# Feature\tCount\n# -------\t-----\n";
for ( keys %method ) {
print "# $_ $method{$_}\n";
}
print "# \n";
}
## FIXME for piped output w/ split FA files ...
close($lumpfa_fh) if $lumpfa_fh;
if (!$split && $outfa && $lump_fh) {
print $lump_fh "##FASTA\n"; # GFF3 spec
open $lumpfa_fh, $outfa or warn "reading FA $outfa: $!";
while( <$lumpfa_fh>) {
print $lump_fh $_;
} # is $lump_fh still open?
close($lumpfa_fh);
unlink($outfa);
}
if ( $zip && $lump ) {
system "gzip -f $lump";
}
close FH;
}
sub typeorder {
return 1 if ($_[0] =~ /gene/);
return 2 if ($_[0] =~ /RNA|transcript/);
return 3 if ($_[0] =~ /protein|peptide/);
return 4 if ($_[0] =~ /exon|CDS/);
return 3; # default before exon (smallest part)
}
sub sort_by_feattype {
my($at,$bt)= ($a->primary_tag, $b->primary_tag);
return (typeorder($at) <=> typeorder($bt))
or ($at cmp $bt);
## or ($a->name() cmp $b->name());
}
sub print_held {
my($out,$gffio,$to_print)= @_;
return unless(@$to_print);
@$to_print = sort sort_by_feattype @$to_print; # put exons after mRNA, otherwise chado loader chokes
while ( my $feature = shift @$to_print) {
my $gff= $gffio->gff_string($feature); # $gff =~ s/\'/./g; # dang bug in encode
push @GFF_LINE_FEAT, $feature;
#print $out "$gff\n";
}
return (); # @to_print
}
sub maptags2gff {
my $f = shift;
## should copy/move locus_tag to Alias, if not ID/Name/Alias already
# but see below /gene /locus_tag usage
foreach my $tag (keys %TAG_MAP) {
if ($f->has_tag($tag)) {
my $newtag= $TAG_MAP{$tag};
my @v= $f->get_tag_values($tag);
$f->remove_tag($tag);
$f->add_tag_value($newtag,@v);
## also, pull any GO:000 ids from /note tag and put into Ontology_term
## ncbi syntax in CDS /note is now '[goid GO:0005886]' OR '[goid 0005624]'
if ($tag eq 'note') {
map { s/\[goid (\d+)/\[goid GO:$1/g; } @v;
my @go= map { m/(GO:\d+)/g } @v;
$f->add_tag_value('Ontology_term',@go) if(@go);
}
}
}
}
sub getSourceInfo {
my ($seq, $source_type, $sf) = @_;
my $is_swiss= ($SOURCEID =~/UniProt|swiss|trembl/i);
my $is_gene = ($SOURCEID =~/entrezgene/i);
my $is_rich = (ref($seq) =~ /RichSeq/);
my $seq_name= $seq->accession_number();
unless($sf) { # make one
$source_type= $is_swiss ? $PROTEIN_TYPE
: $is_gene ? "eneg" # "gene" # "region" #
: $is_rich ? $seq->molecule : $source_type;
$sf = Bio::SeqFeature::Generic->direct_new();
my $len = $seq->length(); $len=1 if($len<1); my $start = 1; ##$start= $len if ($len<1);
my $loc= $seq->can('location') ? $seq->location()
: new Bio::Location::Simple( -start => $start, -end => $len);
$sf->location( $loc );
$sf->primary_tag($source_type);
$sf->source_tag($SOURCEID);
$sf->seq_id( $seq_name);
#? $sf->display_name($seq->id()); ## Name or Alias ?
$sf->add_tag_value( Alias => $seq->id()); # unless id == accession
$seq->add_SeqFeature($sf);
## $source_feat= $sf;
}
if ($sf->has_tag("chromosome")) {
$source_type= "chromosome";
my ($chrname) = $sf->get_tag_values("chromosome");
## PROBLEM with Name <> ID, RefName for Gbrowse; use Alias instead
## e.g. Mouse chr 19 has two IDs in NCBI genbank now
$sf->add_tag_value( Alias => $chrname );
}
# pull GB Comment, Description for source ft ...
# add reference - can be long, not plain string...
warn "# $SOURCEID:$seq_name fields = ", join(",", $seq->annotation->get_all_annotation_keys()),"\n" if $DEBUG;
# GenBank fields: keyword,comment,reference,date_changed
# Entrezgene fields 850293 =ALIAS_SYMBOL,RefSeq status,chromosome,SGD,dblink,Entrez Gene Status,OntologyTerm,LOCUS_SYNONYM
# is this just for main $seq object or for all seqfeatures ?
my %AnnotTagMap= (
'gene_name' => 'Alias',
'ALIAS_SYMBOL' => 'Alias', # Entrezgene
'LOCUS_SYNONYM' => 'Alias', #?
'symbol' => 'Alias',
'synonym' => 'Alias',
'dblink' => 'Dbxref',
'product' => 'product',
'Reference' => 'reference',
'OntologyTerm' => 'Ontology_term',
'comment' => 'Note',
'comment1' => 'Note',
# various map-type locations
# gene accession tag is named per source db !??
# 'Index terms' => keywords ??
);
my ($desc)= $seq->annotation->get_Annotations("desc") || ( $seq->desc() );
my ($date)= $seq->annotation->get_Annotations("dates")
|| $seq->annotation->get_Annotations("update-date")
|| $is_rich ? $seq->get_dates() : ();
my ($comment)= $seq->annotation->get_Annotations("comment");
my ($species)= $seq->annotation->get_Annotations("species");
if (!$species
&& $seq->can('species')
&& defined $seq->species()
&& $seq->species()->can('binomial') ) {
$species= $seq->species()->binomial();
}
# update source feature with main GB fields
$sf->add_tag_value( ID => $seq_name ) unless $sf->has_tag('ID');
$sf->add_tag_value( Note => $desc ) if($desc && ! $sf->has_tag('Note'));
$sf->add_tag_value( organism => $species ) if($species && ! $sf->has_tag('organism'));
$sf->add_tag_value( comment1 => $comment ) if(!$is_swiss && $comment && ! $sf->has_tag('comment1'));
$sf->add_tag_value( date => $date ) if($date && ! $sf->has_tag('date'));
$sf->add_tag_value( Dbxref => $SOURCEID.':'.$seq_name ) if $is_swiss || $is_gene;
foreach my $atag (sort keys %AnnotTagMap) {
my $gtag= $AnnotTagMap{$atag}; next unless($gtag);
my @anno = map{
if (ref $_ && $_->can('get_all_values')) {
split( /[,;] */, join ";", $_->get_all_values)
}
elsif (ref $_ && $_->can('display_text')) {
split( /[,;] */, $_->display_text)
}
elsif (ref $_ && $_->can('value')) {
split( /[,;] */, $_->value)
}
else {
();
}
} $seq->annotation->get_Annotations($atag);
foreach(@anno) { $sf->add_tag_value( $gtag => $_ ); }
}
#my @genes = map{ split( /[,;] */, "$_"); } $seq->annotation->get_Annotations('gene_name');
#$sf->add_tag_value( Alias => $_ ) foreach(@genes);
#
#my @dblink= map { "$_"; } $seq->annotation->get_Annotations("dblink"); # add @all
#$sf->add_tag_value( Dbxref => $_ ) foreach(@dblink);
return (wantarray)? ($source_type,$sf) : $source_type; #?
}
sub gene_features {
my ($f, $gene_id, $genelinkID) = @_;
local $_ = $f->primary_tag;
$method{$_}++;
if ( /gene/ ) {
$f->add_tag_value( ID => $gene_id ) unless($f->has_tag('ID')); # check is same value!?
$tnum = $rnum= 0; $ncrna_id= $rna_id = '';
return GM_NEW_TOPLEVEL;
} elsif ( /mRNA/ ) {
return GM_NOT_PART unless $gene_id;
return GM_NOT_PART if($genelinkID && $genelinkID ne $gene_id);
($rna_id = $gene_id ) =~ s/gene/mRNA/;
$rna_id .= '.t0' . ++$tnum;
$f->add_tag_value( ID => $rna_id );
$f->add_tag_value( Parent => $gene_id );
} elsif ( /RNA|transcript/) {
## misc_RNA here; missing exons ... flattener problem?
# all of {t,nc,sn}RNA can have gene models now
## but problem in Worm chr: mRNA > misc_RNA > CDS with same locus tag
## CDS needs to use mRNA, not misc_RNA, rna_id ...
## also need to fix cases where tRNA,... lack a 'gene' parent: make this one top-level
if($gene_id) {
return GM_NOT_PART if($genelinkID && $genelinkID ne $gene_id);
($ncrna_id = $gene_id) =~ s/gene/ncRNA/;
$ncrna_id .= '.r0' . ++$rnum;
$f->add_tag_value( Parent => $gene_id );
$f->add_tag_value( ID => $ncrna_id );
} else {
unless ($f->has_tag('ID')) {
if($genelinkID) {
$f->add_tag_value( ID => $genelinkID ) ;
} else {
$idh->generate_unique_persistent_id($f);
}
}
($ncrna_id)= $f->get_tag_values('ID');
return GM_NEW_TOPLEVEL;
# this feat now acts as gene-top-level; need to print @to_print to flush prior exons?
}
} elsif ( /exon/ ) { # can belong to any kind of RNA
return GM_NOT_PART unless ($rna_id||$ncrna_id);
return GM_NOT_PART if($genelinkID && $genelinkID ne $gene_id);
## we are getting duplicate Parents here, which chokes chado loader, with reason...
## problem is when mRNA and ncRNA have same exons, both ids are active, called twice
## check all Parents
for my $expar ($rna_id, $ncrna_id) {
next unless($expar);
if ( $exonpar{$expar} and $f->has_tag('Parent') ) {
my @vals = $f->get_tag_values('Parent');
next if (grep {$expar eq $_} @vals);
}
$exonpar{$expar}++;
$f->add_tag_value( Parent => $expar);
# last; #? could be both
}
# now we can skip cloned exons
# dgg note: multiple parents get added and printed for each unique exon
return GM_DUP_PART if ++$seen{$f} > 1;
} elsif ( /CDS|protein|polypeptide/ ) {
return GM_NOT_PART unless $rna_id; ## ignore $ncrna_id ??
return GM_NOT_PART if($genelinkID && $genelinkID ne $gene_id); #??
(my $pro_id = $rna_id) =~ s/\.t/\.p/;
if( ! $CDSkeep && /CDS/) {
$f->primary_tag($PROTEIN_TYPE);
## duplicate problem is Location ..
if ($f->location->isa("Bio::Location::SplitLocationI")) {
# my($b,$e)=($f->start, $f->end); # is this all we need?
my($b,$e)=(-1,0);
foreach my $l ($f->location->each_Location) {
$b = $l->start if($b<0 || $b > $l->start);
$e = $l->end if($e < $l->end);
}
$f->location( Bio::Location::Simple->new(
-start => $b, -end => $e, -strand => $f->strand) );
}
$f->add_tag_value( Derives_from => $rna_id );
}
else {
$f->add_tag_value( Parent => $rna_id );
}
$f->add_tag_value( ID => $pro_id );
move_translation_fasta($f, $pro_id);
#if( $f->has_tag('translation')) {
# my ($aa) = $f->get_tag_values("translation");
# $proteinfa{$pro_id}= $aa;
# $f->remove_tag("translation");
# $f->add_tag_value("translation","length.".length($aa)); # hack for odd chado gbl problem
#}
} elsif ( /region/ ) {
$f->primary_tag('gene_component_region');
$f->add_tag_value( Parent => $gene_id );
} else {
return GM_NOT_PART unless $gene_id;
$f->add_tag_value( Parent => $gene_id );
}
## return GM_DUP_PART if /exon/ && ++$seen{$f} > 1;
return GM_NEW_PART;
}
## was generic_features > add_generic_id
sub add_generic_id {
my ($f, $ft_name, $flags) = @_;
my $method = $f->primary_tag;
$method{$method}++ unless($flags =~ /nocount/); ## double counts GM_NOT_PART from above
if ($f->has_tag('ID')) {
}
elsif ( $f->has_tag($method) ) {
my ($name) = $f->get_tag_values($method);
$f->add_tag_value( ID => "$method:$name" );
}
elsif($ft_name) { # is this unique ?
$f->add_tag_value( ID => $ft_name );
}
else {
$idh->generate_unique_persistent_id($f);
}
move_translation_fasta( $f, ($f->get_tag_values("ID"))[0] )
if($method =~ /CDS/);
# return $io->gff_string($f);
}
sub move_translation_fasta {
my ($f, $ft_id) = @_;
if( $ft_id && $f->has_tag('translation') ) {
my ($aa) = $f->get_tag_values("translation");
if($aa && $aa !~ /^length/) {
$proteinfa{$ft_id}= $aa;
$f->remove_tag("translation");
$f->add_tag_value("translation","length.".length($aa)); # hack for odd chado gbl problem
}
}
}
sub gff_header {
my ($name, $end, $source_type, $source_feat) = @_;
$source_type ||= "region";
my $info = "$source_type:$name";
my $head = "##gff-version $GFF_VERSION\n".
"##sequence-region $name 1 $end\n".
"# conversion-by bp_genbank2gff3.pl\n";
if ($source_feat) {
## dgg: these header comment fields are not useful when have multi-records, diff organisms
for my $key (qw(organism Note date)) {
my $value;
if ($source_feat->has_tag($key)) {
($value) = $source_feat->get_tag_values($key);
}
if ($value) {
$head .= "# $key $value\n";
$info .= ", $value";
}
}
$head = "" if $didheader;
} else {
$head .= "$name\t$SOURCEID\t$source_type\t1\t$end\t.\t.\t.\tID=$name\n";
}
$didheader++;
return (wantarray) ? ($head,$info) : $head;
}
sub unflatten_seq {
my $seq = shift;
## print "# working on $source_type:", $seq->accession, "\n";
my $uh_oh = "Possible gene unflattening error with" . $seq->accession_number .
": consult STDERR\n";
eval {
$unflattener->unflatten_seq( -seq => $seq,
-noinfer => $noinfer,
-use_magic => 1 );
};
# deal with unflattening errors
if ( $@ ) {
warn $seq->accession_number . " Unflattening error:\n";
warn "Details: $@\n";
print "# ".$uh_oh;
}
return 0 if !$seq || !$seq->all_SeqFeatures;
# map feature types to the sequence ontology
## $tm->map_types_to_SO( -seq => $seq );
#$tm->map_types( -seq => $seq, -type_map => $FTSOmap, -undefined => "region" ); #dgg
map_types(
$tm,
-seq => $seq,
-type_map => $FTSOmap,
-syn_map => $FTSOsynonyms,
-undefined => "region"
); #nml
}
sub filter {
my $seq = shift;
## return unless $filter;
my @feats;
my @sources; # dgg; pick source features here; only 1 always?
if ($filter) {
for my $f ( $seq->remove_SeqFeatures ) {
my $m = $f->primary_tag;
push @sources, $f if ($m eq 'source'); # dgg? but leave in @feats ?
push @feats, $f unless $filter =~ /$m/i;
}
$seq->add_SeqFeature($_) foreach @feats;
} else {
for my $f ( $seq->get_SeqFeatures ){
my $m = $f->primary_tag;
push @sources, $f if ($m eq 'source'); # dgg? but leave in @feats ?
}
}
return @sources;
}
# The default behaviour of Bio::FeatureHolderI:get_all_SeqFeatures
# changed to filter out cloned features. We have to implement the old
# method. These two subroutines were adapted from the v1.4 Bio::FeatureHolderI
sub get_all_SeqFeatures {
my $seq = shift;
my @flatarr;
foreach my $feat ( $seq->get_SeqFeatures ){
push(@flatarr,$feat);
_add_flattened_SeqFeatures(\@flatarr,$feat);
}
return @flatarr;
}
sub gene_name {
my $g = shift;
my $gene_id = ''; # zero it;
if ($g->has_tag('locus_tag')) {
($gene_id) = $g->get_tag_values('locus_tag');
}
elsif ($g->has_tag('gene')) {
($gene_id) = $g->get_tag_values('gene');
}
elsif ($g->has_tag('ID')) { # for non-Genbank > Entrezgene
($gene_id) = $g->get_tag_values('ID');
}
## See Unflattener comment:
# on rare occasions, records will have no /gene or /locus_tag
# but it WILL have /product tags. These serve the same purpose
# for grouping. For an example, see AY763288 (also in t/data)
# eg. product=tRNA-Asp ; product=similar to crooked neck protein
elsif ($g->has_tag('product')) {
my ($name)= $g->get_tag_values('product');
($gene_id) = $name unless($name =~ / /); # a description not name
}
## dgg; also handle transposon=xxxx ID/name
# ID=GenBank:repeat_region:NC_004353:1278337:1281302;transposon=HeT-A{}1685;Dbxref=FLYBASE:FBti0059746
elsif ($g->has_tag('transposon')) {
my ($name)= $g->get_tag_values('transposon');
($gene_id) = $name unless($name =~ / /); # a description not name
}
return $gene_id;
}
# same list as gene_name .. change tag to generic Name
sub convert_to_name {
my $g = shift;
my $gene_id = ''; # zero it;
if ($g->has_tag('gene')) {
($gene_id) = $g->get_tag_values('gene');
$g->remove_tag('gene');
$g->add_tag_value('Name', $gene_id);
}
elsif ($g->has_tag('locus_tag')) {
($gene_id) = $g->get_tag_values('locus_tag');
$g->remove_tag('locus_tag');
$g->add_tag_value('Name', $gene_id);
}
elsif ($g->has_tag('product')) {
my ($name)= $g->get_tag_values('product');
($gene_id) = $name unless($name =~ / /); # a description not name
## $g->remove_tag('product');
$g->add_tag_value('Name', $gene_id);
}
elsif ($g->has_tag('transposon')) {
my ($name)= $g->get_tag_values('transposon');
($gene_id) = $name unless($name =~ / /); # a description not name
## $g->remove_tag('transposon');
$g->add_tag_value('Name', $gene_id);
}
elsif ($g->has_tag('ID')) {
my ($name)= $g->get_tag_values('ID');
$g->add_tag_value('Name', $name);
}
return $gene_id;
}
sub _add_flattened_SeqFeatures {
my ($arrayref,$feat) = @_;
my @subs = ();
if ($feat->isa("Bio::FeatureHolderI")) {
@subs = $feat->get_SeqFeatures;
}
elsif ($feat->isa("Bio::SeqFeatureI")) {
@subs = $feat->sub_SeqFeature;
}
else {
warn ref($feat)." is neither a FeatureHolderI nor a SeqFeatureI. ".
"Don't know how to flatten.";
}
for my $sub (@subs) {
push(@$arrayref,$sub);
_add_flattened_SeqFeatures($arrayref,$sub);
}
}
sub map_types {
my ($self, @args) = @_;
my($sf, $seq, $type_map, $syn_map, $undefmap) =
$self->_rearrange([qw(FEATURE
SEQ
TYPE_MAP
SYN_MAP
UNDEFINED
)],
@args);
if (!$sf && !$seq) {
$self->throw("you need to pass in either -feature or -seq");
}
my @sfs = ($sf);
if ($seq) {
$seq->isa("Bio::SeqI") || $self->throw("$seq NOT A SeqI");
@sfs = $seq->get_all_SeqFeatures;
}
$type_map = $type_map || $self->typemap; # dgg: was type_map;
foreach my $feat (@sfs) {
$feat->isa("Bio::SeqFeatureI") || $self->throw("$feat NOT A SeqFeatureI");
$feat->isa("Bio::FeatureHolderI") || $self->throw("$feat NOT A FeatureHolderI");
my $primary_tag = $feat->primary_tag;
#if ($primary_tag =~ /^pseudo(.*)$/) {
# $primary_tag = $1;
# $feat->primary_tag($primary_tag);
#}
my $mtype = $type_map->{$primary_tag};
if ($mtype) {
if (ref($mtype)) {
if (ref($mtype) eq 'ARRAY') {
my $soID;
($mtype, $soID) = @$mtype;
if ($soID && ref($ONTOLOGY)) {
my ($term) = $ONTOLOGY->find_terms(-identifier => $soID);
$mtype = $term->name if $term;
}
# if SO ID is undefined AND we have an ontology to search, we want to delete
# the feature type hash entry in order to force a fuzzy search
elsif (! defined $soID && ref($ONTOLOGY)) {
undef $mtype;
delete $type_map->{$primary_tag};
}
elsif ($undefmap && $mtype eq 'undefined') { # dgg
$mtype= $undefmap;
}
$type_map->{$primary_tag} = $mtype if $mtype;
}
elsif (ref($mtype) eq 'CODE') {
$mtype = $mtype->($feat);
}
else {
$self->throw('must be scalar or CODE ref');
}
}
elsif ($undefmap && $mtype eq 'undefined') { # dgg
$mtype= $undefmap;
}
$feat->primary_tag($mtype);
}
if ($CONF) {
conf_read();
my %perfect_matches;
while (my ($p_tag,$rules) = each %$YAML) {
RULE:
for my $rule (@$rules) {
for my $tags (@$rule) {
while (my ($tag,$values) = each %$tags) {
for my $value (@$values) {
if ($feat->has_tag($tag)) {
for ($feat->get_tag_values($tag)) {
next RULE unless $_ =~ /\Q$value\E/;
}
} elsif ($tag eq 'primary_tag') {
next RULE unless $value eq
$feat->primary_tag;
} elsif ($tag eq 'location') {
next RULE unless $value eq
$feat->start.'..'.$feat->end;
} else { next RULE }
}
}
}
$perfect_matches{$p_tag}++;
}
}
if (scalar(keys %perfect_matches) == 1) {
$mtype = $_ for keys %perfect_matches;
} elsif (scalar(keys %perfect_matches) > 1) {
warn "There are conflicting rules in the config file for the" .
" following types: ";
warn "\t$_\n" for keys %perfect_matches;
warn "Until conflict resolution is built into the converter," .
" you will have to manually edit the config file to remove the" .
" conflict. Sorry :(. Skipping user preference for this entry";
sleep(2);
}
}
if ( ! $mtype && $syn_map) {
if ($feat->has_tag('note')) {
my @all_matches;
my @note = $feat->each_tag_value('note');
for my $k (keys %$syn_map) {
if ($k =~ /"(.+)"/) {
my $syn = $1;
for my $note (@note) {
# look through the notes to see if the description
# is an exact match for synonyms
if ( $syn eq $note ) {
my @map = @{$syn_map->{$k}};
my $best_guess = $map[0];
unshift @{$all_matches[-1]}, [$best_guess];
$mtype = $MANUAL
? manual_curation($feat, $best_guess, \@all_matches)
: $best_guess;
print '#' x 78 . "\nGuessing the proper SO term for GenBank"
. " entry:\n\n" . GenBank_entry($feat) . "\nis:\t$mtype\n"
. '#' x 78 . "\n\n";
} else {
# check both primary tag and and note against
# SO synonyms for best matching description
SO_fuzzy_match( $k, $primary_tag, $note, $syn, \@all_matches);
}
}
}
}
#unless ($mtype) {
for my $note (@note) {
for my $name (values %$type_map) {
# check primary tag against SO names for best matching
# descriptions //NML also need to check against
# definition && camel case split terms
SO_fuzzy_match($name, $primary_tag, $note, $name, \@all_matches);
}
}
#}
if (scalar(@all_matches) && !$mtype) {
my $top_matches = first { defined $_ } @{$all_matches[-1]};
my $best_guess = $top_matches->[0];
# if guess has quotes, it is a synonym term. we need to
# look up the corresponding name term
# otherwise, guess is a name, so we can use it directly
if ($best_guess =~ /"(.+)"/) {
$best_guess = $syn_map->{$best_guess}->[0];
}
@RETURN = @all_matches;
$mtype = $MANUAL
? manual_curation($feat, $best_guess, \@all_matches)
: $best_guess;
print '#' x 78 . "\nGuessing the proper SO term for GenBank"
. " entry:\n\n" . GenBank_entry($feat) . "\nis:\t$mtype\n"
. '#' x 78 . "\n\n";
}
}
$mtype ||= $undefmap;
$feat->primary_tag($mtype);
}
}
}
sub SO_fuzzy_match {
my $candidate = shift;
my $primary_tag = shift;
my $note = shift;
my $SO_terms = shift;
my $best_matches_ref = shift;
my $modifier = shift;
$modifier ||= '';
my @feat_terms;
for ( split(" |_", $primary_tag) ) {
#my @camelCase = /(?:[A-Z]|[a-z])(?:[A-Z]+|[a-z]*)(?=$|[A-Z])/g;
my @camelCase = /(?:[A-Z]|[a-z])(?:[A-Z]+|[a-z]*)(?=$|[A-Z]|[;:.,])/g;
push @feat_terms, @camelCase;
}
for ( split(" |_", $note) ) {
#my @camelCase = /(?:[A-Z]|[a-z])(?:[A-Z]+|[a-z]*)(?=$|[A-Z])/g;
#my @camelCase = /(?:[A-Z]|[a-z])(?:[A-Z]+|[a-z]*)(?=$|[A-Z]|[;:.,])/g;
(my $word = $_) =~ s/[;:.,]//g;
push @feat_terms, $word;
}
my @SO_terms = split(" |_", $SO_terms);
# fuzzy match works on a simple point system. When 2 words match,
# the $plus counter adds one. When they don't, the $minus counter adds
# one. This is used to sort similar matches together. Better matches
# are found at the end of the array, near the top.
# NML: can we improve best match by using synonym tags
# EXACT,RELATED,NARROW,BROAD?
my ($plus, $minus) = (0, 0);
my %feat_terms;
my %SO_terms;
#unique terms
map {$feat_terms{$_} = 1} @feat_terms;
map {$SO_terms{$_} = 1} @SO_terms;
for my $st (keys %SO_terms) {
for my $ft (keys %feat_terms) {
($st =~ m/$modifier\Q$ft\E/) ? $plus++ : $minus++;
}
}
push @{$$best_matches_ref[$plus][$minus]}, $candidate if $plus;
}
sub manual_curation {
my ($feat, $default_opt, $all_matches) = @_;
my @all_matches = @$all_matches;
# convert all SO synonyms into names and filter
# all matches into unique term list because
# synonyms can map to multiple duplicate names
my (@unique_SO_terms, %seen);
for (reverse @all_matches) {
for (@$_) {
for (@$_) {
#my @names;
if ($_ =~ /"(.+)"/) {
for (@{$SYN_MAP->{$_}}) {
push @unique_SO_terms, $_ unless $seen{$_};
$seen{$_}++;
}
} else {
push @unique_SO_terms, $_ unless $seen{$_};
$seen{$_}++;
}
}
}
}
my $s = scalar(@unique_SO_terms);
my $choice = 0;
my $more =
"[a]uto : automatic input (selects best guess for remaining entries)\r" .
"[f]ind : search for other SO terms matching your query (e.g. f gene)\r" .
"[i]nput : add a specific term\r" .
"[r]eset : reset to the beginning of matches\r" .
"[s]kip : skip this entry (selects best guess for this entry)\r"
;
$more .=
"[n]ext : view the next ".OPTION_CYCLE." terms\r" .
"[p]rev : view the previous ".OPTION_CYCLE." terms" if ($s > OPTION_CYCLE);
my $msg = #"\n\n" . '-' x 156 . "\n"
"The converter found $s possible matches for the following GenBank entry: ";
my $directions =
"Type a number to select the SO term that best matches"
. " the genbank entry, or use any of the following options:\r" . '_' x 76 . "\r$more";
# lookup filtered list to pull out definitions
my @options = map {
my $term = $_;
my %term;
for (['name', 'name'], ['def', 'definition'], ['synonym',
'each_synonym']) {
my ($label, $method) = @$_;
$term{$label} = \@{[$term->$method]};
}
[++$choice, $_->name, ($_->definition || 'none'), \%term, $_->each_synonym ];
} map { $ONTOLOGY->find_terms(-name => $_) } @unique_SO_terms;
my $option = options_cycle(0, OPTION_CYCLE, $msg, $feat, $directions,
$default_opt, @options);
if ($option eq 'skip') { return $default_opt
} elsif ($option eq 'auto') {
$MANUAL = 0;
return $default_opt;
} else { return $option }
}
sub options_cycle {
my ($start, $stop, $msg, $feat, $directions, $best_guess, @opt) = @_;
#NML: really should only call GenBank_entry once. Will need to change
#method to return array & shift off header
my $entry = GenBank_entry($feat, "\r");
my $total = scalar(@opt);
($start,$stop) = (0, OPTION_CYCLE)
if ( ($start < 0) && ($stop > 0) );
($start,$stop) = (0, OPTION_CYCLE)
if ( ( ($stop - $start) < OPTION_CYCLE ) && $stop < $total);
($start,$stop) = ($total - OPTION_CYCLE, $total) if $start < 0;
($start,$stop) = (0, OPTION_CYCLE) if $start >= $total;
$stop = $total if $stop > $total;
my $dir_copy = $directions;
my $msg_copy = $msg;
my $format = "format STDOUT = \n" .
'-' x 156 . "\n" .
'^' . '<' x 77 . '| Available Commands:' . "\n" .
'$msg_copy' . "\n" .
'-' x 156 . "\n" .
' ' x 78 . "|\n" .
'^' . '<' x 77 . '| ^' . '<' x 75 . '~' . "\n" .
'$entry' . ' ' x 74 . '$dir_copy,' . "\n" .
(' ' x 20 . '^' . '<' x 57 . '| ^' . '<' x 75 . '~' . "\n" .
' ' x 20 . '$entry,' . ' ' x 53 . '$dir_copy,' . "\n") x 1000 . ".\n";
{
# eval throws redefined warning that breaks formatting.
# Turning off warnings just for the eval to fix this.
no warnings 'redefine';
eval $format;
}
write;
print '-' x 156 . "\n" .
'Showing results ' . ( $stop ? ( $start + 1 ) : $start ) .
" - $stop of possible SO term matches: (best guess is \"$best_guess\")" .
"\n" . '-' x 156 . "\n";
for (my $i = $start; $i < $stop; $i+=2) {
my ($left, $right) = @opt[$i,$i+1];
my ($nL, $nmL, $descL, $termL, @synL) = @$left;
#odd numbered lists can cause fatal undefined errors, so check
#to make sure we have data
my ($nR, $nmR, $descR, $termR, @synR) = ref($right) ? @$right : (undef, undef, undef);
my $format = "format STDOUT = \n";
$format .=
' ' x 78 . "|\n" .
'@>>: name: ^' . '<' x 64 . '~' . ' |' .
( ref($right) ? ('@>>: name: ^' . '<' x 64 . '~' ) : '' ) . "\n" .
'$nL,' . ' ' x 7 . '$nmL,' .
( ref($right) ? (' ' x 63 . '$nR,' . ' ' x 7 . "\$nmR,") : '' ) . "\n" .
' ' x 11 . '^' . '<' x 61 . '...~' . ' |' .
(ref($right) ? (' ^' . '<' x 61 . '...~') : '') . "\n" .
' ' x 11 . '$nmL,' .
(ref($right) ? (' ' x 74 . '$nmR,') : '') . "\n" .
#' ' x 78 . '|' . "\n" .
' def: ^' . '<' x 65 . ' |' .
(ref($right) ? (' def: ^' . '<' x 64 . '~') : '') . "\n" .
' ' x 11 . '$descL,' .
(ref($right) ? (' ' x 72 . '$descR,') : '') . "\n" .
(' ^' . '<' x 65 . ' |' .
(ref($right) ? (' ^' . '<' x 64 . '~') : '') . "\n" .
' ' x 11 . '$descL,' .
(ref($right) ? (' ' x 72 . '$descR,') : '') . "\n") x 5 .
' ^' . '<' x 61 . '...~ |' .
(ref($right) ? (' ^' . '<' x 61 . '...~') : '') . "\n" .
' ' x 11 . '$descL,' .
(ref($right) ? (' ' x 72 . '$descR,') : '') . "\n" .
".\n";
{
# eval throws redefined warning that breaks formatting.
# Turning off warnings just for the eval to fix this.
no warnings 'redefine';
eval $format;
}
write;
}
print '-' x 156 . "\nenter a command:";
while (<STDIN>) {
(my $input = $_) =~ s/\s+$//;
if ($input =~ /^\d+$/) {
if ( $input && defined $opt[$input-1] ) {
return $opt[$input-1]->[1]
} else {
print "\nThat number is not an option. Please enter a valid number.\n:";
}
} elsif ($input =~ /^n/i | $input =~ /next/i ) {
return options_cycle($start + OPTION_CYCLE, $stop + OPTION_CYCLE, $msg,
$feat, $directions, $best_guess, @opt)
} elsif ($input =~ /^p/i | $input =~ /prev/i ) {
return options_cycle($start - OPTION_CYCLE, $stop - OPTION_CYCLE, $msg,
$feat, $directions, $best_guess, @opt)
} elsif ( $input =~ /^s/i || $input =~ /skip/i ) { return 'skip'
} elsif ( $input =~ /^a/i || $input =~ /auto/i ) { return 'auto'
} elsif ( $input =~ /^r/i || $input =~ /reset/i ) {
return manual_curation($feat, $best_guess, \@RETURN );
} elsif ( $input =~ /^f/i || $input =~ /find/i ) {
my ($query, @query_results);
if ($input =~ /(?:^f|find)\s+?(.*?)$/) { $query = $1;
} else {
#do a SO search
print "Type your search query\n:";
while (<STDIN>) { chomp($query = $_); last }
}
for (keys(%$TYPE_MAP), keys(%$SYN_MAP)) {
SO_fuzzy_match($_, $query, '', $_, \@query_results, '(?i)');
}
return manual_curation($feat, $best_guess, \@query_results);
} elsif ( $input =~ /^i/i || $input =~ /input/i ) {
#NML fast input for later
#my $query;
#if ($input =~ /(?:^i|input)\s+?(.*?)$/) { $query = $1 };
#manual input
print "Type the term you want to use\n:";
while (<STDIN>) {
chomp(my $input = $_);
if (! $TYPE_MAP->{$input}) {
print "\"$input\" doesn't appear to be a valid SO term. Are ".
"you sure you want to use it? (y or n)\n:";
while (<STDIN>) {
chomp(my $choice = $_);
if ($choice eq 'y') {
print
"\nWould you like to save your preference for " .
"future use (so you don't have to redo manual " .
"curation for this feature everytime you run " .
"the converter)? (y or n)\n";
#NML: all these while loops are a mess. Really should condense it.
while (<STDIN>) {
chomp(my $choice = $_);
if ($choice eq 'y') {
curation_save($feat, $input);
return $input;
} elsif ($choice eq 'n') {
return $input
} else {
print "\nDidn't recognize that command. Please " .
"type y or n.\n:"
}
}
} elsif ($choice eq 'n') {
return options_cycle($start, $stop, $msg, $feat,
$directions, $best_guess, @opt)
} else {
print "\nDidn't recognize that command. Please " .
"type y or n.\n:"
}
}
} else {
print
"\nWould you like to save your preference for " .
"future use (so you don't have to redo manual " .
"curation for this feature everytime you run " .
"the converter)? (y or n)\n";
#NML: all these while loops are a mess. Really should condense it.
while (<STDIN>) {
chomp(my $choice = $_);
if ($choice eq 'y') {
curation_save($feat, $input);
return $input;
} elsif ($choice eq 'n') {
return $input
} else {
print "\nDidn't recognize that command. Please " .
"type y or n.\n:"
}
}
}
}
} else {
print "\nDidn't recognize that command. Please re-enter your choice.\n:"
}
}
}
sub GenBank_entry {
my ($f, $delimiter, $num) = @_;
$delimiter ||= "\n";
my $entry =
($num ? ' [1] ' : ' ' x 5) . $f->primary_tag
. ($num
? ' ' x (12 - length $f->primary_tag ) . ' [2] '
: ' ' x (15 - length $f->primary_tag)
)
. $f->start.'..'.$f->end
. "$delimiter";
if ($num) {
words_tag($f, \$entry);
} else {
for my $tag ($f->all_tags) {
for my $val ( $f->each_tag_value($tag) ) {
$entry .= ' ' x 20;
#$entry .= "/$tag=\"$val\"$delimiter";
$entry .= $val eq '_no_value'
? "/$tag$delimiter"
: "/$tag=\"$val\"$delimiter";
}
}
}
return $entry;
}
sub gff_validate {
warn "Validating GFF file\n" if $DEBUG;
my @feat = @_;
my (%parent2child, %all_ids, %descendants, %reserved);
for my $f (@feat) {
for my $aTags (['Parent', \%parent2child], ['ID', \%all_ids]) {
map { push @{$$aTags[1]->{$_}}, $f } $f->get_tag_values($$aTags[0])
if $f->has_tag($$aTags[0]);
}
}
if ($SO_FILE) {
while (my ($parentID, $aChildren) = each %parent2child) {
parent_validate($parentID, $aChildren, \%all_ids, \%descendants, \%reserved);
}
}
id_validate(\%all_ids, \%reserved);
}
sub parent_validate {
my ($parentID, $aChildren, $hAll, $hDescendants, $hReserved) = @_;
my $aParents = $hAll->{$parentID};
map {
my $child = $_;
$child->add_tag_value( validation_error =>
"feature tried to add Parent tag, but no Parent found with ID $parentID"
);
my %parents;
map { $parents{$_} = 1 } $child->get_tag_values('Parent');
delete $parents{$parentID};
my @parents = keys %parents;
$child->remove_tag('Parent');
unless ($child->has_tag('ID')) {
my $id = gene_name($child);
$child->add_tag_value('ID', $id);
push @{$hAll->{$id}}, $child
}
$child->add_tag_value('Parent', @parents) if @parents;
} @$aChildren and return unless scalar(@$aParents);
my $par = join(',', map { $_->primary_tag } @$aParents);
warn scalar(@$aParents)." POSSIBLE PARENT(S): $par" if $DEBUG;
#NML manual curation needs to happen here
my %parentsToRemove;
CHILD:
for my $child (@$aChildren) {
my $childType = $child->primary_tag;
warn "WORKING ON $childType at ".$child->start.' to '.$child->end
if $DEBUG;
for (my $i = 0; $i < scalar(@$aParents); $i++) {
my $parent = $aParents->[$i];
my $parentType = $parent->primary_tag;
warn "CHECKING $childType against $parentType" if $DEBUG;
#cache descendants so we don't have to do repeat searches
unless ($hDescendants->{$parentType}) {
for my $term ($ONTOLOGY->find_terms(
-name => $parentType
) ) {
map {
$hDescendants->{$parentType}{$_->name}++
} $ONTOLOGY->get_descendant_terms($term);
}
# NML: hopefully temporary fix.
# SO doesn't consider exon/CDS to be a child of mRNA
# even though common knowledge dictates that they are
# This cheat fixes the false positives for now
if ($parentType eq 'mRNA') {
$hDescendants->{$parentType}{'exon'} = 1;
$hDescendants->{$parentType}{'CDS'} = 1;
}
}
warn "\tCAN $childType at " . $child->start . ' to ' . $child->end .
" be a child of $parentType?" if $DEBUG;
if ($hDescendants->{$parentType}{$childType}) {
warn "\tYES, $childType can be a child of $parentType" if $DEBUG;
#NML need to deal with multiple children matched to multiple different
#parents. This model only assumes the first parent id that matches a child will
#be the reserved feature.
$hReserved->{$parentID}{$parent}{'parent'} = $parent;
push @{$hReserved->{$parentID}{$parent}{'children'}}, $child;
#mark parent for later removal from all IDs
#so we don't accidentally change any parents
$parentsToRemove{$i}++;
next CHILD;
}
}
#NML shouldn't have to check this; somehow child can lose Parent
#it's happening W3110
#need to track this down
if ( $child->has_tag('Parent') ) {
warn "\tNO, @{[$child->primary_tag]} cannot be a child of $parentID"
if $DEBUG;
my %parents;
map { $parents{$_} = 1 } $child->get_tag_values('Parent');
delete $parents{$parentID};
my @parents = keys %parents;
warn 'VALIDATION ERROR '.$child->primary_tag." at ".$child->start .
' to ' . $child->end . " cannot be a child of ID $parentID"
if $DEBUG;
$child->add_tag_value( validation_error =>
"feature cannot be a child of $parentID");
$child->remove_tag('Parent');
unless ($child->has_tag('ID')) {
my $id = gene_name($child);
$child->add_tag_value('ID', $id);
push @{$hAll->{$id}}, $child
}
$child->add_tag_value('Parent', @parents) if @parents;
}
}
#delete $aParents->[$_] for keys %parentsToRemove;
splice(@$aParents, $_, 1) for keys %parentsToRemove;
}
sub id_validate {
my ($hAll, $hReserved) = @_;
for my $id (keys %$hAll) {
#since 1 feature can have this id,
#let's just shift it off and uniquify
#the rest (unless it's reserved)
shift @{$hAll->{$id}} unless $hReserved->{$id};
for my $feat (@{$hAll->{$id}}) {
id_uniquify(0, $id, $feat, $hAll);
}
}
for my $parentID (keys %$hReserved) {
my @keys = keys %{$hReserved->{$parentID}};
shift @keys;
for my $k (@keys) {
my $parent = $hReserved->{$parentID}{$k}{'parent'};
my $aChildren= $hReserved->{$parentID}{$k}{'children'};
my $value = id_uniquify(0, $parentID, $parent, $hAll);
for my $child (@$aChildren) {
my %parents;
map { $parents{$_}++ } $child->get_tag_values('Parent');
$child->remove_tag('Parent');
delete $parents{$parentID};
$parents{$value}++;
my @parents = keys %parents;
$child->add_tag_value('Parent', @parents);
}
}
}
}
sub id_uniquify {
my ($count, $value, $feat, $hAll) = @_;
warn "UNIQUIFYING $value" if $DEBUG;
if (! $count) {
$feat->add_tag_value(Alias => $value);
$value .= ('.' . $feat->primary_tag)
} elsif ($count == 1) {
$value .= ".$count"
} else {
chop $value;
$value .= $count
}
$count++;
warn "ENDED UP WITH $value" if $DEBUG;
if ( $hAll->{$value} ) {
warn "$value IS ALREADY TAKEN" if $DEBUG;
id_uniquify($count, $value, $feat, $hAll);
} else {
#warn "something's breaking ".$feat->primary_tag.' at '.$feat->start.' to '.$feat->end;
$feat->remove_tag('ID');
$feat->add_tag_value('ID', $value);
push @{$hAll->{$value}}, $value;
}
$value;
}
sub conf_read {
print "\nCannot read $CONF. Change file permissions and retry, " .
"or enter another file\n" and conf_locate() unless -r $CONF;
print "\nCannot write $CONF. Change file permissions and retry, " .
"or enter another file\n" and conf_locate() unless -w $CONF;
$YAML = LoadFile($CONF);
}
sub conf_create {
my ($path, $input) = @_;
print "Cannot write to $path. Change directory permissions and retry " .
"or enter another save path\n" and conf_locate() unless -w $path;
$CONF = $input;
open(FH, '>', $CONF);
close(FH);
conf_read();
}
sub conf_write { DumpFile($CONF, $YAML) }
sub conf_locate {
print "\nEnter the location of a previously saved config, or a new " .
"path and file name to create a new config (this step is " .
"necessary to save any preferences)";
print "\n\nenter a command:";
while (<STDIN>) {
chomp(my $input = $_);
my ($fn, $path, $suffix) = fileparse($input, qr/\.[^.]*/);
if (-e $input && (! -d $input)) {
print "\nReading $input...\n";
$CONF = $input;
conf_read();
last;
} elsif (! -d $input && $fn.$suffix) {
print "Creating $input...\n";
conf_create($path, $input);
last;
} elsif (-e $input && -d $input) {
print "You only entered a directory. " .
"Please enter BOTH a directory and filename\n";
} else {
print "$input does not appear to be a valid path. Please enter a " .
"valid directory and filename\n";
}
print "\nenter a command:";
}
}
sub curation_save {
my ($feat, $input) = @_;
#my $error = "Enter the location of a previously saved config, or a new " .
# "path and file name to create a new config (this step is " .
# "necessary to save any preferences)\n";
if (!$CONF) {
print "\n\n";
conf_locate();
} elsif (! -e $CONF) {
print "\n\nThe config file you have chosen doesn't exist.\n";
conf_locate();
} else { conf_read() }
my $entry = GenBank_entry($feat, "\r", 1);
my $msg = "Term entered: $input";
my $directions = "Please select any/all tags that provide evidence for the term you
have entered. You may enter multiple tags by separating them by commas/dashes
(e.g 1,3,5-7). For tags with more than one word value (i.e 'note'), you have
the option of either selecting the entire note as evidence, or specific
keywords. If a tag has multiple keywords, they will be tagged alphabetically
for selection. To select a specific keyword in a tag field, you must enter the
tag number followed by the keyword letter (e.g 3a). Multiple keywords may be
selected by entering each letter separated by commas/dashes (e.g 3b,f,4a-c). The more tags you select, the more specific the GenBank entry will have
to be to match your curation. To match the GenBank entry exactly as it
appears, type every number (start-end), or just type 'all'. Remember, once the converter saves your
preference, you will no longer be prompted to choose a feature type for any
matching entries until you edit the curation.ini file.";
my $msg_copy = $msg;
my $dir_copy = $directions;
my $format = "format STDOUT = \n" .
'-' x 156 . "\n" .
'^' . '<' x 77 . '| Directions:' . "\n" .
'$msg_copy' . "\n" .
'-' x 156 . "\n" .
' ' x 78 . "|\n" .
'^' . '<' x 77 . '| ^' . '<' x 75 . '~' . "\n" .
'$entry' . ' ' x 74 . '$dir_copy,' . "\n" .
(' ' x 15 . '^' . '<' x 62 . '| ^' . '<' x 75 . '~' . "\n" .
' ' x 15 . '$entry,' . ' ' x 58 . '$dir_copy,' . "\n") x 20 . ".\n";
{
# eval throws redefined warning that breaks formatting.
# Turning off warnings just for the eval to fix this.
no warnings 'redefine';
eval $format;
}
write;
print '-' x 156 . "\nenter a command:";
my @tags = words_tag($feat);
my $final = {};
my $choices;
while (<STDIN>) {
chomp(my $choice = $_);
if (scalar(keys %$final) && $choice =~ /^y/i) { last
} elsif (scalar(keys %$final) && $choice =~ /^n/i) { curation_save($feat, $input)
} elsif (scalar(keys %$final)) { print "\nInvalid selection. Please try again\n";
} elsif ($choice eq 'all') {
$choice = '';
for (my $i=1; $i < scalar(@tags); $i++) {
$choice .= "$i,";
}
chop $choice;
}
#print "CHOICE [$choice]";
my @selections;
for (split(/(?<=\w)[^[:alnum:]\-]+(?=\d)/, $choice)) {
if ($_ =~ /(\d+)(?:\D*)-(\d+)(.*)/) {
for ($1..$2) { push @selections, $_ }
my $dangling_alphas = $3;
alpha_expand($dangling_alphas, \@selections);
} else {
alpha_expand($_, \@selections);
}
}
foreach my $numbers (@selections) {
my @c = split(/(?=[\w])/, $numbers);
s/\W+//g foreach @c;
my $num;
{
$^W = 0;
$num = 0 + shift @c;
}
my $tag = $tags[$num];
if (ref $tag && scalar(@c)) {
my $no_value;
foreach (@c) {
if (defined $tag->{$_}) {
$choices .= "${num}[$_] ";
my ($t,$v) = @{$tag->{$_}};
push @{${$final->{$input}}[0]{$t}}, $v;
} else { $no_value++ }
}
if ($no_value) {
_selection_add($tag,$final,$input,\$choices,$num);
#my ($t,$v) = @{$tag->{'all'}};
#unless (defined ${$final->{$input}}[0]{$t}) {
#$choices .= "$num, ";
#push @{${$final->{$input}}[0]{$t}}, $v
#}
}
$choices = substr($choices, 0, -2);
$choices .= ', ';
} elsif (ref $tag) {
_selection_add($tag,$final,$input,\$choices,$num);
#my ($t,$v) = @{$tag->{'all'}};
#unless (defined ${$final->{$input}}[0]{$t}) {
#$choices .= "$num, ";
#push @{${$final->{$input}}[0]{$t}}, $v
#}
}
}
$choices = substr($choices, 0, -2) if $choices;
if ($final) {
print "\nYou have chosen the following tags:\n$choices\n";
print "This will be written to the config file as:\n";
print Dump $final;
print "\nIs this correct? (y or n)\n";
} else { print "\nInvalid selection. Please try again\n" }
}
push @{$YAML->{$input}}, $final->{$input};
conf_write();
}
# words_tag() splits each tag value string into multiple words so that the
# user can select the parts he/she wants to use for curation
# it can tag 702 (a - zz) separate words; this should be enough
sub words_tag {
my ($feat, $entry) = @_;
my @tags;
@tags[1,2] = ({'all' => ['primary_tag', $feat->primary_tag]}, {'all' => ['location', $feat->start.'..'.$feat->end]});
my $i = 3;
foreach my $tag ($feat->all_tags) {
foreach my $value ($feat->each_tag_value($tag)) {
my ($string, $tagged_string);
my @words = split(/(?=\w+?)/, $value);
my $pos = 0;
foreach my $word (@words) {
(my $sanitized_word = $word) =~ s/\W+?//g;
$string .= $word;
my $lead = int($pos/ALPHABET_DIVISOR);
my $lag = $pos % ALPHABET_DIVISOR;
my $a = $lead ? ${(ALPHABET)}[$lead-1] : '';
$a .= $lag ? ${(ALPHABET)}[$lag] : 'a';
$tagged_string .= " ($a) $word";
$tags[$i]{$a} = [$tag, $sanitized_word];
$pos++;
}
$value = $tagged_string if scalar(@words) > 1;
$$entry .= "[$i] /$tag=\"$value\"\r";
$tags[$i]{'all'} = [$tag, $string];
}
$i++;
}
return @tags;
}
sub alpha_expand {
my ($dangling_alphas, $selections) = @_;
if (defined($dangling_alphas) && $dangling_alphas =~ /(\d)*([[:alpha:]]+)-([[:alpha:]]+)/) {
my $digit = $1;
push @$selections, $digit if $digit;
my $start = $2;
my $stop = $3;
my @starts = split('', $start);
my @stops = split('', $stop);
my ($final_start, $final_stop);
for ([\$final_start, \@starts], [\$final_stop, \@stops]) {
my ($final, $splits) = @$_;
my $int = ${(ALPHABET_TO_NUMBER)}{$$splits[0]};
my $rem;
if ($$splits[1]) {
$rem = ${(ALPHABET_TO_NUMBER)}{$$splits[1]};
$int++
} else {
$rem = $int;
$int = 0;
}
$$final = $int * ALPHABET_DIVISOR;
$$final += $rem;
}
my $last_number = pop @$selections;
for my $pos ($final_start..$final_stop) {
my $lead = int($pos/ALPHABET_DIVISOR);
my $lag = $pos % ALPHABET_DIVISOR;
my $alpha = $lead ? ${(ALPHABET)}[$lead-1] : '';
$alpha .= $lag ? ${(ALPHABET)}[$lag] : 'a';
push @$selections, $last_number.$alpha;
}
} elsif (defined($dangling_alphas)) {
if ($dangling_alphas =~ /^\d/) {
push @$selections, $dangling_alphas;
} elsif ($dangling_alphas =~ /^\D/) {
#print "$dangling_alphas ".Dumper @$selections;
my $last_number = pop @$selections;
$last_number ||= '';
push @$selections, $last_number.$dangling_alphas;
#$$selections[-1] .= $dangling_alphas;
}
}
}
sub _selection_add {
my ($tag, $final, $input, $choices, $num) = @_;
my ($t,$v) = @{$tag->{'all'}};
unless (defined ${$final->{$input}}[0]{$t}) {
$$choices .= "$num, ";
push @{${$final->{$input}}[0]{$t}}, $v
}
}
|