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
|
/*
* chimeraslayercommand.cpp
* Mothur
*
* Created by westcott on 3/31/10.
* Copyright 2010 Schloss Lab. All rights reserved.
*
*/
#include "chimeraslayercommand.h"
#include "deconvolutecommand.h"
#include "referencedb.h"
#include "sequenceparser.h"
#include "counttable.h"
//**********************************************************************************************************************
vector<string> ChimeraSlayerCommand::setParameters(){
try {
CommandParameter ptemplate("reference", "InputTypes", "", "", "none", "none", "none","",false,true,true); parameters.push_back(ptemplate);
CommandParameter pfasta("fasta", "InputTypes", "", "", "none", "none", "none","chimera-accnos",false,true,true); parameters.push_back(pfasta);
CommandParameter pname("name", "InputTypes", "", "", "NameCount", "none", "none","",false,false,true); parameters.push_back(pname);
CommandParameter pcount("count", "InputTypes", "", "", "NameCount-CountGroup", "none", "none","",false,false,true); parameters.push_back(pcount);
CommandParameter pgroup("group", "InputTypes", "", "", "CountGroup", "none", "none","",false,false,true); parameters.push_back(pgroup);
CommandParameter pwindow("window", "Number", "", "50", "", "", "","",false,false); parameters.push_back(pwindow);
CommandParameter pksize("ksize", "Number", "", "7", "", "", "","",false,false); parameters.push_back(pksize);
CommandParameter pmatch("match", "Number", "", "5.0", "", "", "","",false,false); parameters.push_back(pmatch);
CommandParameter pmismatch("mismatch", "Number", "", "-4.0", "", "", "","",false,false); parameters.push_back(pmismatch);
CommandParameter pminsim("minsim", "Number", "", "90", "", "", "","",false,false); parameters.push_back(pminsim);
CommandParameter pmincov("mincov", "Number", "", "70", "", "", "","",false,false); parameters.push_back(pmincov);
CommandParameter pminsnp("minsnp", "Number", "", "10", "", "", "","",false,false); parameters.push_back(pminsnp);
CommandParameter pminbs("minbs", "Number", "", "90", "", "", "","",false,false); parameters.push_back(pminbs);
CommandParameter psearch("search", "Multiple", "kmer-blast", "blast", "", "", "","",false,false); parameters.push_back(psearch);
CommandParameter pprocessors("processors", "Number", "", "1", "", "", "","",false,false,true); parameters.push_back(pprocessors);
CommandParameter prealign("realign", "Boolean", "", "T", "", "", "","",false,false); parameters.push_back(prealign);
CommandParameter ptrim("trim", "Boolean", "", "F", "", "", "","fasta",false,false); parameters.push_back(ptrim);
CommandParameter psplit("split", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(psplit);
CommandParameter pnumwanted("numwanted", "Number", "", "15", "", "", "","",false,false); parameters.push_back(pnumwanted);
CommandParameter piters("iters", "Number", "", "1000", "", "", "","",false,false); parameters.push_back(piters);
CommandParameter pdivergence("divergence", "Number", "", "1.007", "", "", "","",false,false); parameters.push_back(pdivergence);
CommandParameter pdups("dereplicate", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(pdups);
CommandParameter pparents("parents", "Number", "", "3", "", "", "","",false,false); parameters.push_back(pparents);
CommandParameter pincrement("increment", "Number", "", "5", "", "", "","",false,false); parameters.push_back(pincrement);
CommandParameter pblastlocation("blastlocation", "String", "", "", "", "", "","",false,false); parameters.push_back(pblastlocation);
CommandParameter pinputdir("inputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(pinputdir);
CommandParameter poutputdir("outputdir", "String", "", "", "", "", "","",false,false); parameters.push_back(poutputdir);
CommandParameter psave("save", "Boolean", "", "F", "", "", "","",false,false); parameters.push_back(psave);
vector<string> myArray;
for (int i = 0; i < parameters.size(); i++) { myArray.push_back(parameters[i].name); }
return myArray;
}
catch(exception& e) {
m->errorOut(e, "ChimeraSlayerCommand", "setParameters");
exit(1);
}
}
//**********************************************************************************************************************
string ChimeraSlayerCommand::getHelpString(){
try {
string helpString = "";
helpString += "The chimera.slayer command reads a fastafile and referencefile and outputs potentially chimeric sequences.\n";
helpString += "This command was modeled after the chimeraSlayer written by the Broad Institute.\n";
helpString += "The chimera.slayer command parameters are fasta, name, group, template, processors, dereplicate, trim, ksize, window, match, mismatch, divergence. minsim, mincov, minbs, minsnp, parents, search, iters, increment, numwanted, blastlocation and realign.\n";
helpString += "The fasta parameter allows you to enter the fasta file containing your potentially chimeric sequences, and is required, unless you have a valid current fasta file. \n";
helpString += "The name parameter allows you to provide a name file, if you are using reference=self. \n";
helpString += "The group parameter allows you to provide a group file. The group file can be used with a namesfile and reference=self. When checking sequences, only sequences from the same group as the query sequence will be used as the reference. \n";
helpString += "The count parameter allows you to provide a count file. The count file reference=self. If your count file contains group information, when checking sequences, only sequences from the same group as the query sequence will be used as the reference. When you use a count file with group info and dereplicate=T, mothur will create a *.pick.count_table file containing seqeunces after chimeras are removed. \n";
helpString += "You may enter multiple fasta files by separating their names with dashes. ie. fasta=abrecovery.fasta-amazon.fasta \n";
helpString += "The reference parameter allows you to enter a reference file containing known non-chimeric sequences, and is required. You may also set template=self, in this case the abundant sequences will be used as potential parents. \n";
helpString += "The processors parameter allows you to specify how many processors you would like to use. The default is 1. \n";
#ifdef USE_MPI
helpString += "When using MPI, the processors parameter is set to the number of MPI processes running. \n";
#endif
helpString += "If the dereplicate parameter is false, then if one group finds the seqeunce to be chimeric, then all groups find it to be chimeric, default=f.\n";
helpString += "The trim parameter allows you to output a new fasta file containing your sequences with the chimeric ones trimmed to include only their longest piece, default=F. \n";
helpString += "The split parameter allows you to check both pieces of non-chimeric sequence for chimeras, thus looking for trimeras and quadmeras. default=F. \n";
helpString += "The window parameter allows you to specify the window size for searching for chimeras, default=50. \n";
helpString += "The increment parameter allows you to specify how far you move each window while finding chimeric sequences, default=5.\n";
helpString += "The numwanted parameter allows you to specify how many sequences you would each query sequence compared with, default=15.\n";
helpString += "The ksize parameter allows you to input kmersize, default is 7, used if search is kmer. \n";
helpString += "The match parameter allows you to reward matched bases in blast search, default is 5. \n";
helpString += "The parents parameter allows you to select the number of potential parents to investigate from the numwanted best matches after rating them, default is 3. \n";
helpString += "The mismatch parameter allows you to penalize mismatched bases in blast search, default is -4. \n";
helpString += "The divergence parameter allows you to set a cutoff for chimera determination, default is 1.007. \n";
helpString += "The iters parameter allows you to specify the number of bootstrap iters to do with the chimeraslayer method, default=1000.\n";
helpString += "The minsim parameter allows you to specify a minimum similarity with the parent fragments, default=90. \n";
helpString += "The mincov parameter allows you to specify minimum coverage by closest matches found in template. Default is 70, meaning 70%. \n";
helpString += "The minbs parameter allows you to specify minimum bootstrap support for calling a sequence chimeric. Default is 90, meaning 90%. \n";
helpString += "The minsnp parameter allows you to specify percent of SNPs to sample on each side of breakpoint for computing bootstrap support (default: 10) \n";
helpString += "The search parameter allows you to specify search method for finding the closest parent. Choices are blast, and kmer, default blast. \n";
helpString += "The realign parameter allows you to realign the query to the potential parents. Choices are true or false, default true. \n";
helpString += "The blastlocation parameter allows you to specify the location of your blast executable. By default mothur will look in ./blast/bin relative to mothur's executable. \n";
helpString += "If the save parameter is set to true the reference sequences will be saved in memory, to clear them later you can use the clear.memory command. Default=f.";
helpString += "The chimera.slayer command should be in the following format: \n";
helpString += "chimera.slayer(fasta=yourFastaFile, reference=yourTemplate, search=yourSearch) \n";
helpString += "Example: chimera.slayer(fasta=AD.align, reference=core_set_aligned.imputed.fasta, search=kmer) \n";
helpString += "Note: No spaces between parameter labels (i.e. fasta), '=' and parameters (i.e.yourFastaFile).\n";
return helpString;
}
catch(exception& e) {
m->errorOut(e, "ChimeraSlayerCommand", "getHelpString");
exit(1);
}
}
//**********************************************************************************************************************
string ChimeraSlayerCommand::getOutputPattern(string type) {
try {
string pattern = "";
if (type == "chimera") { pattern = "[filename],slayer.chimeras"; }
else if (type == "accnos") { pattern = "[filename],slayer.accnos"; }
else if (type == "fasta") { pattern = "[filename],slayer.fasta"; }
else if (type == "count") { pattern = "[filename],slayer.pick.count_table"; }
else { m->mothurOut("[ERROR]: No definition for type " + type + " output pattern.\n"); m->control_pressed = true; }
return pattern;
}
catch(exception& e) {
m->errorOut(e, "ChimeraSlayerCommand", "getOutputPattern");
exit(1);
}
}
//**********************************************************************************************************************
ChimeraSlayerCommand::ChimeraSlayerCommand(){
try {
abort = true; calledHelp = true;
setParameters();
vector<string> tempOutNames;
outputTypes["chimera"] = tempOutNames;
outputTypes["accnos"] = tempOutNames;
outputTypes["fasta"] = tempOutNames;
outputTypes["count"] = tempOutNames;
}
catch(exception& e) {
m->errorOut(e, "ChimeraSlayerCommand", "ChimeraSlayerCommand");
exit(1);
}
}
//***************************************************************************************************************
ChimeraSlayerCommand::ChimeraSlayerCommand(string option) {
try {
abort = false; calledHelp = false;
ReferenceDB* rdb = ReferenceDB::getInstance();
hasCount = false;
hasName = false;
//allow user to run help
if(option == "help") { help(); abort = true; calledHelp = true; }
else if(option == "citation") { citation(); abort = true; calledHelp = true;}
else {
vector<string> myArray = setParameters();
OptionParser parser(option);
map<string,string> parameters = parser.getParameters();
ValidParameters validParameter("chimera.slayer");
map<string,string>::iterator it;
//check to make sure all parameters are valid for command
for (it = parameters.begin(); it != parameters.end(); it++) {
if (validParameter.isValidParameter(it->first, myArray, it->second) != true) { abort = true; }
}
vector<string> tempOutNames;
outputTypes["chimera"] = tempOutNames;
outputTypes["accnos"] = tempOutNames;
outputTypes["fasta"] = tempOutNames;
outputTypes["count"] = tempOutNames;
//if the user changes the input directory command factory will send this info to us in the output parameter
string inputDir = validParameter.validFile(parameters, "inputdir", false);
if (inputDir == "not found"){ inputDir = ""; }
//check for required parameters
fastafile = validParameter.validFile(parameters, "fasta", false);
if (fastafile == "not found") {
//if there is a current fasta file, use it
string filename = m->getFastaFile();
if (filename != "") { fastaFileNames.push_back(filename); m->mothurOut("Using " + filename + " as input file for the fasta parameter."); m->mothurOutEndLine(); }
else { m->mothurOut("You have no current fastafile and the fasta parameter is required."); m->mothurOutEndLine(); abort = true; }
}else {
m->splitAtDash(fastafile, fastaFileNames);
//go through files and make sure they are good, if not, then disregard them
for (int i = 0; i < fastaFileNames.size(); i++) {
bool ignore = false;
if (fastaFileNames[i] == "current") {
fastaFileNames[i] = m->getFastaFile();
if (fastaFileNames[i] != "") { m->mothurOut("Using " + fastaFileNames[i] + " as input file for the fasta parameter where you had given current."); m->mothurOutEndLine(); }
else {
m->mothurOut("You have no current fastafile, ignoring current."); m->mothurOutEndLine(); ignore=true;
//erase from file list
fastaFileNames.erase(fastaFileNames.begin()+i);
i--;
}
}
if (!ignore) {
if (inputDir != "") {
string path = m->hasPath(fastaFileNames[i]);
//if the user has not given a path then, add inputdir. else leave path alone.
if (path == "") { fastaFileNames[i] = inputDir + fastaFileNames[i]; }
}
int ableToOpen;
ifstream in;
ableToOpen = m->openInputFile(fastaFileNames[i], in, "noerror");
//if you can't open it, try default location
if (ableToOpen == 1) {
if (m->getDefaultPath() != "") { //default path is set
string tryPath = m->getDefaultPath() + m->getSimpleName(fastaFileNames[i]);
m->mothurOut("Unable to open " + fastaFileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine();
ifstream in2;
ableToOpen = m->openInputFile(tryPath, in2, "noerror");
in2.close();
fastaFileNames[i] = tryPath;
}
}
if (ableToOpen == 1) {
if (m->getOutputDir() != "") { //default path is set
string tryPath = m->getOutputDir() + m->getSimpleName(fastaFileNames[i]);
m->mothurOut("Unable to open " + fastaFileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine();
ifstream in2;
ableToOpen = m->openInputFile(tryPath, in2, "noerror");
in2.close();
fastaFileNames[i] = tryPath;
}
}
in.close();
if (ableToOpen == 1) {
m->mothurOut("Unable to open " + fastaFileNames[i] + ". It will be disregarded."); m->mothurOutEndLine();
//erase from file list
fastaFileNames.erase(fastaFileNames.begin()+i);
i--;
}else {
m->setFastaFile(fastaFileNames[i]);
}
}
}
//make sure there is at least one valid file left
if (fastaFileNames.size() == 0) { m->mothurOut("[ERROR]: no valid files."); m->mothurOutEndLine(); abort = true; }
}
//check for required parameters
namefile = validParameter.validFile(parameters, "name", false);
if (namefile == "not found") { namefile = ""; }
else {
m->splitAtDash(namefile, nameFileNames);
//go through files and make sure they are good, if not, then disregard them
for (int i = 0; i < nameFileNames.size(); i++) {
bool ignore = false;
if (nameFileNames[i] == "current") {
nameFileNames[i] = m->getNameFile();
if (nameFileNames[i] != "") { m->mothurOut("Using " + nameFileNames[i] + " as input file for the name parameter where you had given current."); m->mothurOutEndLine(); }
else {
m->mothurOut("You have no current namefile, ignoring current."); m->mothurOutEndLine(); ignore=true;
//erase from file list
nameFileNames.erase(nameFileNames.begin()+i);
i--;
}
}
if (!ignore) {
if (inputDir != "") {
string path = m->hasPath(nameFileNames[i]);
//if the user has not given a path then, add inputdir. else leave path alone.
if (path == "") { nameFileNames[i] = inputDir + nameFileNames[i]; }
}
int ableToOpen;
ifstream in;
ableToOpen = m->openInputFile(nameFileNames[i], in, "noerror");
//if you can't open it, try default location
if (ableToOpen == 1) {
if (m->getDefaultPath() != "") { //default path is set
string tryPath = m->getDefaultPath() + m->getSimpleName(nameFileNames[i]);
m->mothurOut("Unable to open " + nameFileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine();
ifstream in2;
ableToOpen = m->openInputFile(tryPath, in2, "noerror");
in2.close();
nameFileNames[i] = tryPath;
}
}
if (ableToOpen == 1) {
if (m->getOutputDir() != "") { //default path is set
string tryPath = m->getOutputDir() + m->getSimpleName(nameFileNames[i]);
m->mothurOut("Unable to open " + nameFileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine();
ifstream in2;
ableToOpen = m->openInputFile(tryPath, in2, "noerror");
in2.close();
nameFileNames[i] = tryPath;
}
}
in.close();
if (ableToOpen == 1) {
m->mothurOut("Unable to open " + nameFileNames[i] + ". It will be disregarded."); m->mothurOutEndLine();
//erase from file list
nameFileNames.erase(nameFileNames.begin()+i);
i--;
}else {
m->setNameFile(nameFileNames[i]);
}
}
}
}
if (nameFileNames.size() != 0) { hasName = true; }
//check for required parameters
vector<string> countfileNames;
countfile = validParameter.validFile(parameters, "count", false);
if (countfile == "not found") {
countfile = "";
}else {
m->splitAtDash(countfile, countfileNames);
//go through files and make sure they are good, if not, then disregard them
for (int i = 0; i < countfileNames.size(); i++) {
bool ignore = false;
if (countfileNames[i] == "current") {
countfileNames[i] = m->getCountTableFile();
if (nameFileNames[i] != "") { m->mothurOut("Using " + countfileNames[i] + " as input file for the count parameter where you had given current."); m->mothurOutEndLine(); }
else {
m->mothurOut("You have no current count file, ignoring current."); m->mothurOutEndLine(); ignore=true;
//erase from file list
countfileNames.erase(countfileNames.begin()+i);
i--;
}
}
if (!ignore) {
if (inputDir != "") {
string path = m->hasPath(countfileNames[i]);
//if the user has not given a path then, add inputdir. else leave path alone.
if (path == "") { countfileNames[i] = inputDir + countfileNames[i]; }
}
int ableToOpen;
ifstream in;
ableToOpen = m->openInputFile(countfileNames[i], in, "noerror");
//if you can't open it, try default location
if (ableToOpen == 1) {
if (m->getDefaultPath() != "") { //default path is set
string tryPath = m->getDefaultPath() + m->getSimpleName(countfileNames[i]);
m->mothurOut("Unable to open " + countfileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine();
ifstream in2;
ableToOpen = m->openInputFile(tryPath, in2, "noerror");
in2.close();
countfileNames[i] = tryPath;
}
}
if (ableToOpen == 1) {
if (m->getOutputDir() != "") { //default path is set
string tryPath = m->getOutputDir() + m->getSimpleName(countfileNames[i]);
m->mothurOut("Unable to open " + countfileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine();
ifstream in2;
ableToOpen = m->openInputFile(tryPath, in2, "noerror");
in2.close();
countfileNames[i] = tryPath;
}
}
in.close();
if (ableToOpen == 1) {
m->mothurOut("Unable to open " + countfileNames[i] + ". It will be disregarded."); m->mothurOutEndLine();
//erase from file list
countfileNames.erase(countfileNames.begin()+i);
i--;
}else {
m->setCountTableFile(countfileNames[i]);
}
}
}
}
if (countfileNames.size() != 0) { hasCount = true; }
//make sure there is at least one valid file left
if (hasName && hasCount) { m->mothurOut("[ERROR]: You must enter ONLY ONE of the following: count or name."); m->mothurOutEndLine(); abort = true; }
if (!hasName && hasCount) { nameFileNames = countfileNames; }
if ((hasCount || hasName) && (nameFileNames.size() != fastaFileNames.size())) { m->mothurOut("[ERROR]: The number of name or count files does not match the number of fastafiles, please correct."); m->mothurOutEndLine(); abort=true; }
bool hasGroup = true;
groupfile = validParameter.validFile(parameters, "group", false);
if (groupfile == "not found") { groupfile = ""; hasGroup = false; }
else {
m->splitAtDash(groupfile, groupFileNames);
//go through files and make sure they are good, if not, then disregard them
for (int i = 0; i < groupFileNames.size(); i++) {
bool ignore = false;
if (groupFileNames[i] == "current") {
groupFileNames[i] = m->getGroupFile();
if (groupFileNames[i] != "") { m->mothurOut("Using " + groupFileNames[i] + " as input file for the group parameter where you had given current."); m->mothurOutEndLine(); }
else {
m->mothurOut("You have no current namefile, ignoring current."); m->mothurOutEndLine(); ignore=true;
//erase from file list
groupFileNames.erase(groupFileNames.begin()+i);
i--;
}
}
if (!ignore) {
if (inputDir != "") {
string path = m->hasPath(groupFileNames[i]);
//if the user has not given a path then, add inputdir. else leave path alone.
if (path == "") { groupFileNames[i] = inputDir + groupFileNames[i]; }
}
int ableToOpen;
ifstream in;
ableToOpen = m->openInputFile(groupFileNames[i], in, "noerror");
//if you can't open it, try default location
if (ableToOpen == 1) {
if (m->getDefaultPath() != "") { //default path is set
string tryPath = m->getDefaultPath() + m->getSimpleName(groupFileNames[i]);
m->mothurOut("Unable to open " + groupFileNames[i] + ". Trying default " + tryPath); m->mothurOutEndLine();
ifstream in2;
ableToOpen = m->openInputFile(tryPath, in2, "noerror");
in2.close();
groupFileNames[i] = tryPath;
}
}
if (ableToOpen == 1) {
if (m->getOutputDir() != "") { //default path is set
string tryPath = m->getOutputDir() + m->getSimpleName(groupFileNames[i]);
m->mothurOut("Unable to open " + groupFileNames[i] + ". Trying output directory " + tryPath); m->mothurOutEndLine();
ifstream in2;
ableToOpen = m->openInputFile(tryPath, in2, "noerror");
in2.close();
groupFileNames[i] = tryPath;
}
}
in.close();
if (ableToOpen == 1) {
m->mothurOut("Unable to open " + groupFileNames[i] + ". It will be disregarded."); m->mothurOutEndLine();
//erase from file list
groupFileNames.erase(groupFileNames.begin()+i);
i--;
}else {
m->setGroupFile(groupFileNames[i]);
}
}
}
//make sure there is at least one valid file left
if (groupFileNames.size() == 0) { m->mothurOut("[ERROR]: no valid group files."); m->mothurOutEndLine(); abort = true; }
}
if (hasGroup && (groupFileNames.size() != fastaFileNames.size())) { m->mothurOut("[ERROR]: The number of groupfiles does not match the number of fastafiles, please correct."); m->mothurOutEndLine(); abort=true; }
if (hasGroup && hasCount) { m->mothurOut("[ERROR]: You must enter ONLY ONE of the following: count or group."); m->mothurOutEndLine(); abort = true; }
//if the user changes the output directory command factory will send this info to us in the output parameter
outputDir = validParameter.validFile(parameters, "outputdir", false); if (outputDir == "not found"){ outputDir = ""; }
string temp = validParameter.validFile(parameters, "processors", false); if (temp == "not found"){ temp = m->getProcessors(); }
m->setProcessors(temp);
m->mothurConvert(temp, processors);
temp = validParameter.validFile(parameters, "save", false); if (temp == "not found"){ temp = "f"; }
save = m->isTrue(temp);
rdb->save = save;
if (save) { //clear out old references
rdb->clearMemory();
}
string path;
it = parameters.find("reference");
//user has given a template file
if(it != parameters.end()){
if (it->second == "self") {
templatefile = "self";
if (save) {
m->mothurOut("[WARNING]: You can't save reference=self, ignoring save.");
m->mothurOutEndLine();
save = false;
}
}
else {
path = m->hasPath(it->second);
//if the user has not given a path then, add inputdir. else leave path alone.
if (path == "") { parameters["reference"] = inputDir + it->second; }
templatefile = validParameter.validFile(parameters, "reference", true);
if (templatefile == "not open") { abort = true; }
else if (templatefile == "not found") { //check for saved reference sequences
if (rdb->referenceSeqs.size() != 0) {
templatefile = "saved";
}else {
m->mothurOut("[ERROR]: You don't have any saved reference sequences and the reference parameter is a required.");
m->mothurOutEndLine();
abort = true;
}
}else { if (save) { rdb->setSavedReference(templatefile); } }
}
}else if (hasName) { templatefile = "self";
if (save) {
m->mothurOut("[WARNING]: You can't save reference=self, ignoring save.");
m->mothurOutEndLine();
save = false;
}
}else if (hasCount) { templatefile = "self";
if (save) {
m->mothurOut("[WARNING]: You can't save reference=self, ignoring save.");
m->mothurOutEndLine();
save = false;
}
}
else {
if (rdb->referenceSeqs.size() != 0) {
templatefile = "saved";
}else {
m->mothurOut("[ERROR]: You don't have any saved reference sequences and the reference parameter is a required.");
m->mothurOutEndLine();
templatefile = ""; abort = true;
}
}
temp = validParameter.validFile(parameters, "ksize", false); if (temp == "not found") { temp = "7"; }
m->mothurConvert(temp, ksize);
temp = validParameter.validFile(parameters, "window", false); if (temp == "not found") { temp = "50"; }
m->mothurConvert(temp, window);
temp = validParameter.validFile(parameters, "match", false); if (temp == "not found") { temp = "5"; }
m->mothurConvert(temp, match);
temp = validParameter.validFile(parameters, "mismatch", false); if (temp == "not found") { temp = "-4"; }
m->mothurConvert(temp, mismatch);
temp = validParameter.validFile(parameters, "divergence", false); if (temp == "not found") { temp = "1.007"; }
m->mothurConvert(temp, divR);
temp = validParameter.validFile(parameters, "minsim", false); if (temp == "not found") { temp = "90"; }
m->mothurConvert(temp, minSimilarity);
temp = validParameter.validFile(parameters, "mincov", false); if (temp == "not found") { temp = "70"; }
m->mothurConvert(temp, minCoverage);
temp = validParameter.validFile(parameters, "minbs", false); if (temp == "not found") { temp = "90"; }
m->mothurConvert(temp, minBS);
temp = validParameter.validFile(parameters, "minsnp", false); if (temp == "not found") { temp = "10"; }
m->mothurConvert(temp, minSNP);
temp = validParameter.validFile(parameters, "parents", false); if (temp == "not found") { temp = "3"; }
m->mothurConvert(temp, parents);
temp = validParameter.validFile(parameters, "realign", false); if (temp == "not found") { temp = "t"; }
realign = m->isTrue(temp);
temp = validParameter.validFile(parameters, "trim", false); if (temp == "not found") { temp = "f"; }
trim = m->isTrue(temp);
temp = validParameter.validFile(parameters, "split", false); if (temp == "not found") { temp = "f"; }
trimera = m->isTrue(temp);
search = validParameter.validFile(parameters, "search", false); if (search == "not found") { search = "blast"; }
temp = validParameter.validFile(parameters, "iters", false); if (temp == "not found") { temp = "1000"; }
m->mothurConvert(temp, iters);
temp = validParameter.validFile(parameters, "increment", false); if (temp == "not found") { temp = "5"; }
m->mothurConvert(temp, increment);
temp = validParameter.validFile(parameters, "numwanted", false); if (temp == "not found") { temp = "15"; }
m->mothurConvert(temp, numwanted);
temp = validParameter.validFile(parameters, "dereplicate", false);
if (temp == "not found") { temp = "false"; }
dups = m->isTrue(temp);
blastlocation = validParameter.validFile(parameters, "blastlocation", false);
if (blastlocation == "not found") { blastlocation = ""; }
else {
//add / to name if needed
string lastChar = blastlocation.substr(blastlocation.length()-1);
#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix)
if (lastChar != "/") { blastlocation += "/"; }
#else
if (lastChar != "\\") { blastlocation += "\\"; }
#endif
blastlocation = m->getFullPathName(blastlocation);
string formatdbCommand = "";
#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix)
formatdbCommand = blastlocation + "formatdb";
#else
formatdbCommand = blastlocation + "formatdb.exe";
#endif
//test to make sure formatdb exists
ifstream in;
formatdbCommand = m->getFullPathName(formatdbCommand);
int ableToOpen = m->openInputFile(formatdbCommand, in, "no error"); in.close();
if(ableToOpen == 1) { m->mothurOut("[ERROR]: " + formatdbCommand + " file does not exist. mothur requires formatdb.exe to run chimera.slayer."); m->mothurOutEndLine(); abort = true; }
string blastCommand = "";
#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix)
blastCommand = blastlocation + "megablast";
#else
blastCommand = blastlocation + "megablast.exe";
#endif
//test to make sure formatdb exists
ifstream in2;
blastCommand = m->getFullPathName(blastCommand);
ableToOpen = m->openInputFile(blastCommand, in2, "no error"); in2.close();
if(ableToOpen == 1) { m->mothurOut("[ERROR]: " + blastCommand + " file does not exist. mothur requires blastall.exe to run chimera.slayer."); m->mothurOutEndLine(); abort = true; }
}
if ((search != "blast") && (search != "kmer")) { m->mothurOut(search + " is not a valid search."); m->mothurOutEndLine(); abort = true; }
if ((hasName || hasCount) && (templatefile != "self")) { m->mothurOut("You have provided a namefile or countfile and the reference parameter is not set to self. I am not sure what reference you are trying to use, aborting."); m->mothurOutEndLine(); abort=true; }
if (hasGroup && (templatefile != "self")) { m->mothurOut("You have provided a group file and the reference parameter is not set to self. I am not sure what reference you are trying to use, aborting."); m->mothurOutEndLine(); abort=true; }
//until we resolve the issue 10-18-11
#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix)
#else
//processors=1;
#endif
}
}
catch(exception& e) {
m->errorOut(e, "ChimeraSlayerCommand", "ChimeraSlayerCommand");
exit(1);
}
}
//***************************************************************************************************************
int ChimeraSlayerCommand::execute(){
try{
if (abort == true) { if (calledHelp) { return 0; } return 2; }
for (int s = 0; s < fastaFileNames.size(); s++) {
m->mothurOut("Checking sequences from " + fastaFileNames[s] + " ..." ); m->mothurOutEndLine();
int start = time(NULL);
if (outputDir == "") { outputDir = m->hasPath(fastaFileNames[s]); }//if user entered a file with a path then preserve it
map<string, string> variables;
variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[s]));
string outputFileName = getOutputFileName("chimera", variables);
string accnosFileName = getOutputFileName("accnos", variables);
string trimFastaFileName = getOutputFileName("fasta", variables);
string newCountFile = "";
//clears files
ofstream out, out1, out2;
m->openOutputFile(outputFileName, out); out.close();
m->openOutputFile(accnosFileName, out1); out1.close();
if (trim) { m->openOutputFile(trimFastaFileName, out2); out2.close(); }
outputNames.push_back(outputFileName); outputTypes["chimera"].push_back(outputFileName);
outputNames.push_back(accnosFileName); outputTypes["accnos"].push_back(accnosFileName);
if (trim) { outputNames.push_back(trimFastaFileName); outputTypes["fasta"].push_back(trimFastaFileName); }
//maps a filename to priority map.
//if no groupfile this is fastafileNames[s] -> prioirity
//if groupfile then this is each groups seqs -> priority
map<string, map<string, int> > fileToPriority;
map<string, map<string, int> >::iterator itFile;
map<string, string> fileGroup;
fileToPriority[fastaFileNames[s]] = priority; //default
fileGroup[fastaFileNames[s]] = "noGroup";
map<string, string> uniqueNames;
int totalChimeras = 0;
lines.clear();
if (templatefile == "self") {
if (hasCount) {
SequenceCountParser* parser = NULL;
setUpForSelfReference(parser, fileGroup, fileToPriority, s);
if (parser != NULL) { uniqueNames = parser->getAllSeqsMap(); delete parser; }
}else {
SequenceParser* parser = NULL;
setUpForSelfReference(parser, fileGroup, fileToPriority, s);
if (parser != NULL) { uniqueNames = parser->getAllSeqsMap(); delete parser; }
}
}
if (m->control_pressed) { for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } return 0; }
if (fileToPriority.size() == 1) { //you running without a groupfile
itFile = fileToPriority.begin();
string thisFastaName = itFile->first;
map<string, int> thisPriority = itFile->second;
#ifdef USE_MPI
MPIExecute(thisFastaName, outputFileName, accnosFileName, trimFastaFileName, thisPriority);
#else
//break up file
vector<unsigned long long> positions;
#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix)
positions = m->divideFile(thisFastaName, processors);
for (int i = 0; i < (positions.size()-1); i++) { lines.push_back(linePair(positions[i], positions[(i+1)])); }
#else
if (processors == 1) { lines.push_back(linePair(0, 1000)); }
else {
positions = m->setFilePosFasta(thisFastaName, numSeqs);
if (positions.size() < processors) { processors = positions.size(); }
//figure out how many sequences you have to process
int numSeqsPerProcessor = numSeqs / processors;
for (int i = 0; i < processors; i++) {
int startIndex = i * numSeqsPerProcessor;
if(i == (processors - 1)){ numSeqsPerProcessor = numSeqs - i * numSeqsPerProcessor; }
lines.push_back(linePair(positions[startIndex], numSeqsPerProcessor));
}
}
#endif
if(processors == 1){ numSeqs = driver(lines[0], outputFileName, thisFastaName, accnosFileName, trimFastaFileName, thisPriority); }
else{ numSeqs = createProcesses(outputFileName, thisFastaName, accnosFileName, trimFastaFileName, thisPriority); }
if (m->control_pressed) { outputTypes.clear(); if (trim) { m->mothurRemove(trimFastaFileName); } m->mothurRemove(outputFileName); m->mothurRemove(accnosFileName); for (int j = 0; j < outputNames.size(); j++) { m->mothurRemove(outputNames[j]); } return 0; }
#endif
}else { //you have provided a groupfile
string countFile = "";
if (hasCount) {
countFile = nameFileNames[s];
variables["[filename]"] = outputDir + m->getRootName(m->getSimpleName(nameFileNames[s]));
newCountFile = getOutputFileName("count", variables);
}
#ifdef USE_MPI
MPIExecuteGroups(outputFileName, accnosFileName, trimFastaFileName, fileToPriority, fileGroup, newCountFile, countFile);
#else
if (processors == 1) {
numSeqs = driverGroups(outputFileName, accnosFileName, trimFastaFileName, fileToPriority, fileGroup, newCountFile);
if (hasCount && dups) {
CountTable c; c.readTable(nameFileNames[s], true, false);
if (!m->isBlank(newCountFile)) {
ifstream in2;
m->openInputFile(newCountFile, in2);
string name, group;
while (!in2.eof()) {
in2 >> name >> group; m->gobble(in2);
c.setAbund(name, group, 0);
}
in2.close();
}
m->mothurRemove(newCountFile);
c.printTable(newCountFile);
}
}
else { numSeqs = createProcessesGroups(outputFileName, accnosFileName, trimFastaFileName, fileToPriority, fileGroup, newCountFile, countFile); } //destroys fileToPriority
#endif
#ifdef USE_MPI
int pid;
MPI_Comm_rank(MPI_COMM_WORLD, &pid); //find out who we are
if (pid == 0) {
#endif
if (!dups) {
totalChimeras = deconvoluteResults(uniqueNames, outputFileName, accnosFileName, trimFastaFileName);
m->mothurOutEndLine(); m->mothurOut(toString(totalChimeras) + " chimera found."); m->mothurOutEndLine();
}else {
if (hasCount) {
set<string> doNotRemove;
CountTable c; c.readTable(newCountFile, true, true);
vector<string> namesInTable = c.getNamesOfSeqs();
for (int i = 0; i < namesInTable.size(); i++) {
int temp = c.getNumSeqs(namesInTable[i]);
if (temp == 0) { c.remove(namesInTable[i]); }
else { doNotRemove.insert((namesInTable[i])); }
}
//remove names we want to keep from accnos file.
set<string> accnosNames = m->readAccnos(accnosFileName);
ofstream out2;
m->openOutputFile(accnosFileName, out2);
for (set<string>::iterator it = accnosNames.begin(); it != accnosNames.end(); it++) {
if (doNotRemove.count(*it) == 0) { out2 << (*it) << endl; }
}
out2.close();
c.printTable(newCountFile);
outputNames.push_back(newCountFile); outputTypes["count"].push_back(newCountFile);
}
}
#ifdef USE_MPI
}
MPI_Barrier(MPI_COMM_WORLD); //make everyone wait
#endif
}
m->mothurOut("It took " + toString(time(NULL) - start) + " secs to check " + toString(numSeqs) + " sequences."); m->mothurOutEndLine();
}
//set accnos file as new current accnosfile
string current = "";
itTypes = outputTypes.find("accnos");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setAccnosFile(current); }
}
if (trim) {
itTypes = outputTypes.find("fasta");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setFastaFile(current); }
}
}
itTypes = outputTypes.find("count");
if (itTypes != outputTypes.end()) {
if ((itTypes->second).size() != 0) { current = (itTypes->second)[0]; m->setCountTableFile(current); }
}
m->mothurOutEndLine();
m->mothurOut("Output File Names: "); m->mothurOutEndLine();
for (int i = 0; i < outputNames.size(); i++) { m->mothurOut(outputNames[i]); m->mothurOutEndLine(); }
m->mothurOutEndLine();
return 0;
}
catch(exception& e) {
m->errorOut(e, "ChimeraSlayerCommand", "execute");
exit(1);
}
}
//**********************************************************************************************************************
int ChimeraSlayerCommand::MPIExecuteGroups(string outputFileName, string accnosFileName, string trimFastaFileName, map<string, map<string, int> >& fileToPriority, map<string, string>& fileGroup, string countlist, string countfile){
try {
#ifdef USE_MPI
int pid;
int tag = 2001;
MPI_Status status;
MPI_Comm_rank(MPI_COMM_WORLD, &pid); //find out who we are
MPI_Comm_size(MPI_COMM_WORLD, &processors);
//put filenames in a vector, then pass each process a starting and ending point in the vector
//all processes already have the fileToPriority and fileGroup, they just need to know which files to process
map<string, map<string, int> >::iterator itFile;
vector<string> filenames;
for(itFile = fileToPriority.begin(); itFile != fileToPriority.end(); itFile++) { filenames.push_back(itFile->first); }
int numGroupsPerProcessor = ceil(filenames.size() / (double) processors);
int startIndex = pid * numGroupsPerProcessor;
int endIndex = (pid+1) * numGroupsPerProcessor;
if(pid == (processors - 1)){ endIndex = filenames.size(); }
vector<unsigned long long> MPIPos;
MPI_File outMPI;
MPI_File outMPIAccnos;
MPI_File outMPIFasta;
MPI_File outMPICount;
int outMode=MPI_MODE_CREATE|MPI_MODE_WRONLY;
int inMode=MPI_MODE_RDONLY;
char outFilename[1024];
strcpy(outFilename, outputFileName.c_str());
char outAccnosFilename[1024];
strcpy(outAccnosFilename, accnosFileName.c_str());
char outFastaFilename[1024];
strcpy(outFastaFilename, trimFastaFileName.c_str());
char outCountFilename[1024];
strcpy(outCountFilename, countlist.c_str());
MPI_File_open(MPI_COMM_WORLD, outFilename, outMode, MPI_INFO_NULL, &outMPI);
MPI_File_open(MPI_COMM_WORLD, outAccnosFilename, outMode, MPI_INFO_NULL, &outMPIAccnos);
if (trim) { MPI_File_open(MPI_COMM_WORLD, outFastaFilename, outMode, MPI_INFO_NULL, &outMPIFasta); }
if (hasCount && dups) { MPI_File_open(MPI_COMM_WORLD, outCountFilename, outMode, MPI_INFO_NULL, &outMPICount); }
if (m->control_pressed) { MPI_File_close(&outMPI); if (trim) { MPI_File_close(&outMPIFasta); } MPI_File_close(&outMPIAccnos); if (hasCount && dups) { MPI_File_close(&outMPICount); } return 0; }
//print headers
if (pid == 0) { //you are the root process
m->mothurOutEndLine();
m->mothurOut("Only reporting sequence supported by " + toString(minBS) + "% of bootstrapped results.");
m->mothurOutEndLine();
string outTemp = "Name\tLeftParent\tRightParent\tDivQLAQRB\tPerIDQLAQRB\tBootStrapA\tDivQLBQRA\tPerIDQLBQRA\tBootStrapB\tFlag\tLeftWindow\tRightWindow\n";
//print header
int length = outTemp.length();
char* buf2 = new char[length];
memcpy(buf2, outTemp.c_str(), length);
MPI_File_write_shared(outMPI, buf2, length, MPI_CHAR, &status);
delete buf2;
}
MPI_Barrier(MPI_COMM_WORLD); //make everyone wait
for (int i = startIndex; i < endIndex; i++) {
int start = time(NULL);
int num = 0;
string thisFastaName = filenames[i];
map<string, int> thisPriority = fileToPriority[thisFastaName];
char inFileName[1024];
strcpy(inFileName, thisFastaName.c_str());
MPI_File inMPI;
MPI_File_open(MPI_COMM_SELF, inFileName, inMode, MPI_INFO_NULL, &inMPI); //comm, filename, mode, info, filepointer
MPIPos = m->setFilePosFasta(thisFastaName, num); //fills MPIPos, returns numSeqs
cout << endl << "Checking sequences from group: " << fileGroup[thisFastaName] << "." << endl;
set<string> cnames;
driverMPI(0, num, inMPI, outMPI, outMPIAccnos, outMPIFasta, cnames, MPIPos, thisFastaName, thisPriority, true);
numSeqs += num;
MPI_File_close(&inMPI);
m->mothurRemove(thisFastaName);
if (dups) {
if (cnames.size() != 0) {
if (hasCount) {
for (set<string>::iterator it = cnames.begin(); it != cnames.end(); it++) {
string outputString = (*it) + "\t" + fileGroup[thisFastaName] + "\n";
int length = outputString.length();
char* buf2 = new char[length];
memcpy(buf2, outputString.c_str(), length);
MPI_File_write_shared(outMPICount, buf2, length, MPI_CHAR, &status);
delete buf2;
}
}else {
map<string, map<string, string> >::iterator itGroupNameMap = group2NameMap.find(fileGroup[thisFastaName]);
if (itGroupNameMap != group2NameMap.end()) {
map<string, string> thisnamemap = itGroupNameMap->second;
map<string, string>::iterator itN;
for (set<string>::iterator it = cnames.begin(); it != cnames.end(); it++) {
itN = thisnamemap.find(*it);
if (itN != thisnamemap.end()) {
vector<string> tempNames; m->splitAtComma(itN->second, tempNames);
for (int j = 0; j < tempNames.size(); j++) { //write to accnos file
string outputString = tempNames[j] + "\n";
int length = outputString.length();
char* buf2 = new char[length];
memcpy(buf2, outputString.c_str(), length);
MPI_File_write_shared(outMPIAccnos, buf2, length, MPI_CHAR, &status);
delete buf2;
}
}else { m->mothurOut("[ERROR]: parsing cannot find " + *it + ".\n"); m->control_pressed = true; }
}
}else { m->mothurOut("[ERROR]: parsing cannot find " + fileGroup[thisFastaName] + ".\n"); m->control_pressed = true; }
}
}
}
cout << endl << "It took " << toString(time(NULL) - start) << " secs to check " + toString(num) + " sequences from group " << fileGroup[thisFastaName] << "." << endl;
}
if (pid == 0) {
for(int i = 1; i < processors; i++) {
int temp = 0;
MPI_Recv(&temp, 1, MPI_INT, i, 2001, MPI_COMM_WORLD, &status);
numSeqs += temp;
}
}else{ MPI_Send(&numSeqs, 1, MPI_INT, 0, 2001, MPI_COMM_WORLD); }
MPI_File_close(&outMPI);
MPI_File_close(&outMPIAccnos);
if (trim) { MPI_File_close(&outMPIFasta); }
if (hasCount && dups) { MPI_File_close(&outMPICount); }
MPI_Barrier(MPI_COMM_WORLD); //make everyone wait
#endif
return 0;
}catch(exception& e) {
m->errorOut(e, "ChimeraSlayerCommand", "MPIExecuteGroups");
exit(1);
}
}
//**********************************************************************************************************************
int ChimeraSlayerCommand::MPIExecute(string inputFile, string outputFileName, string accnosFileName, string trimFastaFileName, map<string, int>& priority){
try {
#ifdef USE_MPI
int pid, numSeqsPerProcessor;
int tag = 2001;
vector<unsigned long long> MPIPos;
MPI_Status status;
MPI_Comm_rank(MPI_COMM_WORLD, &pid); //find out who we are
MPI_Comm_size(MPI_COMM_WORLD, &processors);
MPI_File inMPI;
MPI_File outMPI;
MPI_File outMPIAccnos;
MPI_File outMPIFasta;
int outMode=MPI_MODE_CREATE|MPI_MODE_WRONLY;
int inMode=MPI_MODE_RDONLY;
char outFilename[1024];
strcpy(outFilename, outputFileName.c_str());
char outAccnosFilename[1024];
strcpy(outAccnosFilename, accnosFileName.c_str());
char outFastaFilename[1024];
strcpy(outFastaFilename, trimFastaFileName.c_str());
char inFileName[1024];
strcpy(inFileName, inputFile.c_str());
MPI_File_open(MPI_COMM_WORLD, inFileName, inMode, MPI_INFO_NULL, &inMPI); //comm, filename, mode, info, filepointer
MPI_File_open(MPI_COMM_WORLD, outFilename, outMode, MPI_INFO_NULL, &outMPI);
MPI_File_open(MPI_COMM_WORLD, outAccnosFilename, outMode, MPI_INFO_NULL, &outMPIAccnos);
if (trim) { MPI_File_open(MPI_COMM_WORLD, outFastaFilename, outMode, MPI_INFO_NULL, &outMPIFasta); }
if (m->control_pressed) { MPI_File_close(&inMPI); MPI_File_close(&outMPI); if (trim) { MPI_File_close(&outMPIFasta); } MPI_File_close(&outMPIAccnos); return 0; }
if (pid == 0) { //you are the root process
m->mothurOutEndLine();
m->mothurOut("Only reporting sequence supported by " + toString(minBS) + "% of bootstrapped results.");
m->mothurOutEndLine();
string outTemp = "Name\tLeftParent\tRightParent\tDivQLAQRB\tPerIDQLAQRB\tBootStrapA\tDivQLBQRA\tPerIDQLBQRA\tBootStrapB\tFlag\tLeftWindow\tRightWindow\n";
//print header
int length = outTemp.length();
char* buf2 = new char[length];
memcpy(buf2, outTemp.c_str(), length);
MPI_File_write_shared(outMPI, buf2, length, MPI_CHAR, &status);
delete buf2;
MPIPos = m->setFilePosFasta(inputFile, numSeqs); //fills MPIPos, returns numSeqs
if (templatefile != "self") { //if template=self we can only use 1 processor
//send file positions to all processes
for(int i = 1; i < processors; i++) {
MPI_Send(&numSeqs, 1, MPI_INT, i, tag, MPI_COMM_WORLD);
MPI_Send(&MPIPos[0], (numSeqs+1), MPI_LONG, i, tag, MPI_COMM_WORLD);
}
}
//figure out how many sequences you have to align
numSeqsPerProcessor = numSeqs / processors;
int startIndex = pid * numSeqsPerProcessor;
if(pid == (processors - 1)){ numSeqsPerProcessor = numSeqs - pid * numSeqsPerProcessor; }
if (templatefile == "self") { //if template=self we can only use 1 processor
startIndex = 0;
numSeqsPerProcessor = numSeqs;
}
//do your part
set<string> cnames;
driverMPI(startIndex, numSeqsPerProcessor, inMPI, outMPI, outMPIAccnos, outMPIFasta, cnames, MPIPos, inputFile, priority, false);
if (m->control_pressed) { MPI_File_close(&inMPI); MPI_File_close(&outMPI); if (trim) { MPI_File_close(&outMPIFasta); } MPI_File_close(&outMPIAccnos); return 0; }
}else{ //you are a child process
if (templatefile != "self") { //if template=self we can only use 1 processor
MPI_Recv(&numSeqs, 1, MPI_INT, 0, tag, MPI_COMM_WORLD, &status);
MPIPos.resize(numSeqs+1);
MPI_Recv(&MPIPos[0], (numSeqs+1), MPI_LONG, 0, tag, MPI_COMM_WORLD, &status);
//figure out how many sequences you have to align
numSeqsPerProcessor = numSeqs / processors;
int startIndex = pid * numSeqsPerProcessor;
if(pid == (processors - 1)){ numSeqsPerProcessor = numSeqs - pid * numSeqsPerProcessor; }
//do your part
set<string> cnames;
driverMPI(startIndex, numSeqsPerProcessor, inMPI, outMPI, outMPIAccnos, outMPIFasta, cnames, MPIPos, inputFile, priority, false);
if (m->control_pressed) { MPI_File_close(&inMPI); MPI_File_close(&outMPI); if (trim) { MPI_File_close(&outMPIFasta); } MPI_File_close(&outMPIAccnos); return 0; }
}
}
//close files
MPI_File_close(&inMPI);
MPI_File_close(&outMPI);
MPI_File_close(&outMPIAccnos);
if (trim) { MPI_File_close(&outMPIFasta); }
MPI_Barrier(MPI_COMM_WORLD); //make everyone wait - just in case
#endif
return numSeqs;
}
catch(exception& e) {
m->errorOut(e, "ChimeraSlayerCommand", "MPIExecute");
exit(1);
}
}
//**********************************************************************************************************************
int ChimeraSlayerCommand::deconvoluteResults(map<string, string>& uniqueNames, string outputFileName, string accnosFileName, string trimFileName){
try {
map<string, string>::iterator itUnique;
int total = 0;
if (trimera) { //add in more potential uniqueNames
map<string, string> newUniqueNames = uniqueNames;
for (map<string, string>::iterator it = uniqueNames.begin(); it != uniqueNames.end(); it++) {
newUniqueNames[(it->first)+"_LEFT"] = (it->first)+"_LEFT";
newUniqueNames[(it->first)+"_RIGHT"] = (it->first)+"_RIGHT";
}
uniqueNames = newUniqueNames;
newUniqueNames.clear();
}
//edit accnos file
ifstream in2;
m->openInputFile(accnosFileName, in2, "no error");
ofstream out2;
m->openOutputFile(accnosFileName+".temp", out2);
string name; name = "";
set<string> chimerasInFile;
set<string>::iterator itChimeras;
while (!in2.eof()) {
if (m->control_pressed) { in2.close(); out2.close(); m->mothurRemove(outputFileName); m->mothurRemove((accnosFileName+".temp")); return 0; }
in2 >> name; m->gobble(in2);
//find unique name
itUnique = uniqueNames.find(name);
if (itUnique == uniqueNames.end()) { m->mothurOut("[ERROR]: trouble parsing accnos results. Cannot find "+ name + "."); m->mothurOutEndLine(); m->control_pressed = true; }
else {
itChimeras = chimerasInFile.find((itUnique->second));
if (itChimeras == chimerasInFile.end()) {
out2 << itUnique->second << endl;
chimerasInFile.insert((itUnique->second));
total++;
}
}
}
in2.close();
out2.close();
m->mothurRemove(accnosFileName);
rename((accnosFileName+".temp").c_str(), accnosFileName.c_str());
//edit chimera file
ifstream in;
m->openInputFile(outputFileName, in);
ofstream out;
m->openOutputFile(outputFileName+".temp", out); out.setf(ios::fixed, ios::floatfield); out.setf(ios::showpoint);
string rest, parent1, parent2, line;
set<string> namesInFile; //this is so if a sequence is found to be chimera in several samples we dont write it to the results file more than once
set<string>::iterator itNames;
//assumptions - in file each read will always look like...
/*
F11Fcsw_92754 no
F11Fcsw_63104 F11Fcsw_33372 F11Fcsw_37007 0.89441 80.4469 0.2 1.03727 93.2961 52.2 no 0-241 243-369
*/
//get header line
if (!in.eof()) {
line = m->getline(in); m->gobble(in);
out << line << endl;
}
//for the chimera file, we want to make sure if any group finds a sequence to be chimeric then all groups do,
//so if this is a report that did not find it to be chimeric, but it appears in the accnos file,
//then ignore this report and continue until we find the report that found it to be chimeric
while (!in.eof()) {
if (m->control_pressed) { in.close(); out.close(); m->mothurRemove((outputFileName+".temp")); return 0; }
in >> name; m->gobble(in);
in >> parent1; m->gobble(in);
if (name == "Name") { //name = "Name" because we append the header line each time we add results from the groups
line = m->getline(in); m->gobble(in);
}else {
if (parent1 == "no") {
//find unique name
itUnique = uniqueNames.find(name);
if (itUnique == uniqueNames.end()) { m->mothurOut("[ERROR]: trouble parsing chimera results. Cannot find "+ name + "."); m->mothurOutEndLine(); m->control_pressed = true; }
else {
//is this sequence really not chimeric??
itChimeras = chimerasInFile.find(itUnique->second);
if (itChimeras == chimerasInFile.end()) {
//is this sequence not already in the file
itNames = namesInFile.find((itUnique->second));
if (itNames == namesInFile.end()) { out << itUnique->second << '\t' << "no" << endl; namesInFile.insert(itUnique->second); }
}
}
}else { //read the rest of the line
double DivQLAQRB,PerIDQLAQRB,BootStrapA,DivQLBQRA,PerIDQLBQRA,BootStrapB;
string flag, range1, range2;
bool print = false;
in >> parent2 >> DivQLAQRB >> PerIDQLAQRB >> BootStrapA >> DivQLBQRA >> PerIDQLBQRA >> BootStrapB >> flag >> range1 >> range2; m->gobble(in);
//find unique name
itUnique = uniqueNames.find(name);
if (itUnique == uniqueNames.end()) { m->mothurOut("[ERROR]: trouble parsing chimera results. Cannot find "+ name + "."); m->mothurOutEndLine(); m->control_pressed = true; }
else {
name = itUnique->second;
//is this name already in the file
itNames = namesInFile.find((name));
if (itNames == namesInFile.end()) { //no not in file
if (flag == "no") { //are you really a no??
//is this sequence really not chimeric??
itChimeras = chimerasInFile.find(name);
//then you really are a no so print, otherwise skip
if (itChimeras == chimerasInFile.end()) { print = true; }
}else{ print = true; }
}
}
if (print) {
out << name << '\t';
namesInFile.insert(name);
//output parent1's name
itUnique = uniqueNames.find(parent1);
if (itUnique == uniqueNames.end()) { m->mothurOut("[ERROR]: trouble parsing chimera results. Cannot find parentA "+ parent1 + "."); m->mothurOutEndLine(); m->control_pressed = true; }
else { out << itUnique->second << '\t'; }
//output parent2's name
itUnique = uniqueNames.find(parent2);
if (itUnique == uniqueNames.end()) { m->mothurOut("[ERROR]: trouble parsing chimera results. Cannot find parentA "+ parent2 + "."); m->mothurOutEndLine(); m->control_pressed = true; }
else { out << itUnique->second << '\t'; }
out << DivQLAQRB << '\t' << PerIDQLAQRB << '\t' << BootStrapA << '\t' << DivQLBQRA << '\t' << PerIDQLBQRA << '\t' << BootStrapB << '\t' << flag << '\t' << range1 << '\t' << range2 << endl;
}
}
}
}
in.close();
out.close();
m->mothurRemove(outputFileName);
rename((outputFileName+".temp").c_str(), outputFileName.c_str());
//edit fasta file
if (trim) {
ifstream in3;
m->openInputFile(trimFileName, in3);
ofstream out3;
m->openOutputFile(trimFileName+".temp", out3);
namesInFile.clear();
while (!in3.eof()) {
if (m->control_pressed) { in3.close(); out3.close(); m->mothurRemove(outputFileName); m->mothurRemove(accnosFileName); m->mothurRemove((trimFileName+".temp")); return 0; }
Sequence seq(in3); m->gobble(in3);
if (seq.getName() != "") {
//find unique name
itUnique = uniqueNames.find(seq.getName());
if (itUnique == uniqueNames.end()) { m->mothurOut("[ERROR]: trouble parsing accnos results. Cannot find "+ seq.getName() + "."); m->mothurOutEndLine(); m->control_pressed = true; }
else {
itNames = namesInFile.find((itUnique->second));
if (itNames == namesInFile.end()) {
seq.printSequence(out3);
}
}
}
}
in3.close();
out3.close();
m->mothurRemove(trimFileName);
rename((trimFileName+".temp").c_str(), trimFileName.c_str());
}
return total;
}
catch(exception& e) {
m->errorOut(e, "ChimeraSlayerCommand", "deconvoluteResults");
exit(1);
}
}
//**********************************************************************************************************************
int ChimeraSlayerCommand::setUpForSelfReference(SequenceParser*& parser, map<string, string>& fileGroup, map<string, map<string, int> >& fileToPriority, int s){
try {
fileGroup.clear();
fileToPriority.clear();
string nameFile = "";
if (nameFileNames.size() != 0) { //you provided a namefile and we don't need to create one
nameFile = nameFileNames[s];
}else { nameFile = getNamesFile(fastaFileNames[s]); }
//you provided a groupfile
string groupFile = "";
if (groupFileNames.size() != 0) { groupFile = groupFileNames[s]; }
if (groupFile == "") {
if (processors != 1) { m->mothurOut("When using template=self, mothur can only use 1 processor, continuing."); m->mothurOutEndLine(); processors = 1; }
//sort fastafile by abundance, returns new sorted fastafile name
m->mothurOut("Sorting fastafile according to abundance..."); cout.flush();
priority = sortFastaFile(fastaFileNames[s], nameFile);
m->mothurOut("Done."); m->mothurOutEndLine();
fileToPriority[fastaFileNames[s]] = priority;
fileGroup[fastaFileNames[s]] = "noGroup";
}else {
//Parse sequences by group
parser = new SequenceParser(groupFile, fastaFileNames[s], nameFile);
vector<string> groups = parser->getNamesOfGroups();
for (int i = 0; i < groups.size(); i++) {
vector<Sequence> thisGroupsSeqs = parser->getSeqs(groups[i]);
map<string, string> thisGroupsMap = parser->getNameMap(groups[i]);
group2NameMap[groups[i]] = thisGroupsMap;
string newFastaFile = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[s])) + groups[i] + "-sortedTemp.fasta";
priority = sortFastaFile(thisGroupsSeqs, thisGroupsMap, newFastaFile);
fileToPriority[newFastaFile] = priority;
fileGroup[newFastaFile] = groups[i];
}
}
return 0;
}
catch(exception& e) {
m->errorOut(e, "ChimeraSlayerCommand", "setUpForSelfReference");
exit(1);
}
}
//**********************************************************************************************************************
int ChimeraSlayerCommand::setUpForSelfReference(SequenceCountParser*& parser, map<string, string>& fileGroup, map<string, map<string, int> >& fileToPriority, int s){
try {
fileGroup.clear();
fileToPriority.clear();
string nameFile = "";
if (nameFileNames.size() != 0) { //you provided a namefile and we don't need to create one
nameFile = nameFileNames[s];
}else { m->control_pressed = true; return 0; }
CountTable ct;
if (!ct.testGroups(nameFile)) {
if (processors != 1) { m->mothurOut("When using template=self, mothur can only use 1 processor, continuing."); m->mothurOutEndLine(); processors = 1; }
//sort fastafile by abundance, returns new sorted fastafile name
m->mothurOut("Sorting fastafile according to abundance..."); cout.flush();
priority = sortFastaFile(fastaFileNames[s], nameFile);
m->mothurOut("Done."); m->mothurOutEndLine();
fileToPriority[fastaFileNames[s]] = priority;
fileGroup[fastaFileNames[s]] = "noGroup";
}else {
//Parse sequences by group
parser = new SequenceCountParser(nameFile, fastaFileNames[s]);
vector<string> groups = parser->getNamesOfGroups();
for (int i = 0; i < groups.size(); i++) {
vector<Sequence> thisGroupsSeqs = parser->getSeqs(groups[i]);
map<string, int> thisGroupsMap = parser->getCountTable(groups[i]);
string newFastaFile = outputDir + m->getRootName(m->getSimpleName(fastaFileNames[s])) + groups[i] + "-sortedTemp.fasta";
sortFastaFile(thisGroupsSeqs, thisGroupsMap, newFastaFile);
fileToPriority[newFastaFile] = thisGroupsMap;
fileGroup[newFastaFile] = groups[i];
}
}
return 0;
}
catch(exception& e) {
m->errorOut(e, "ChimeraSlayerCommand", "setUpForSelfReference");
exit(1);
}
}
//**********************************************************************************************************************
string ChimeraSlayerCommand::getNamesFile(string& inputFile){
try {
string nameFile = "";
m->mothurOutEndLine(); m->mothurOut("No namesfile given, running unique.seqs command to generate one."); m->mothurOutEndLine(); m->mothurOutEndLine();
//use unique.seqs to create new name and fastafile
string inputString = "fasta=" + inputFile;
m->mothurOut("/******************************************/"); m->mothurOutEndLine();
m->mothurOut("Running command: unique.seqs(" + inputString + ")"); m->mothurOutEndLine();
m->mothurCalling = true;
Command* uniqueCommand = new DeconvoluteCommand(inputString);
uniqueCommand->execute();
map<string, vector<string> > filenames = uniqueCommand->getOutputFiles();
delete uniqueCommand;
m->mothurCalling = false;
m->mothurOut("/******************************************/"); m->mothurOutEndLine();
nameFile = filenames["name"][0];
inputFile = filenames["fasta"][0];
return nameFile;
}
catch(exception& e) {
m->errorOut(e, "ChimeraSlayerCommand", "getNamesFile");
exit(1);
}
}
//**********************************************************************************************************************
int ChimeraSlayerCommand::driverGroups(string outputFName, string accnos, string fasta, map<string, map<string, int> >& fileToPriority, map<string, string>& fileGroup, string countlist){
try {
int totalSeqs = 0;
ofstream outCountList;
if (hasCount && dups) { m->openOutputFile(countlist, outCountList); }
for (map<string, map<string, int> >::iterator itFile = fileToPriority.begin(); itFile != fileToPriority.end(); itFile++) {
if (m->control_pressed) { return 0; }
int start = time(NULL);
string thisFastaName = itFile->first;
map<string, int> thisPriority = itFile->second;
string thisoutputFileName = outputDir + m->getRootName(m->getSimpleName(thisFastaName)) + fileGroup[thisFastaName] + "slayer.chimera";
string thisaccnosFileName = outputDir + m->getRootName(m->getSimpleName(thisFastaName)) + fileGroup[thisFastaName] + "slayer.accnos";
string thistrimFastaFileName = outputDir + m->getRootName(m->getSimpleName(thisFastaName)) + fileGroup[thisFastaName] + "slayer.fasta";
m->mothurOutEndLine(); m->mothurOut("Checking sequences from group: " + fileGroup[thisFastaName] + "."); m->mothurOutEndLine();
lines.clear();
#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix)
int proc = 1;
vector<unsigned long long> positions = m->divideFile(thisFastaName, proc);
lines.push_back(linePair(positions[0], positions[1]));
#else
lines.push_back(linePair(0, 1000));
#endif
int numSeqs = driver(lines[0], thisoutputFileName, thisFastaName, thisaccnosFileName, thistrimFastaFileName, thisPriority);
//if we provided a count file with group info and set dereplicate=t, then we want to create a *.pick.count_table
//This table will zero out group counts for seqs determined to be chimeric by that group.
if (dups) {
if (!m->isBlank(thisaccnosFileName)) {
ifstream in;
m->openInputFile(thisaccnosFileName, in);
string name;
if (hasCount) {
while (!in.eof()) {
in >> name; m->gobble(in);
outCountList << name << '\t' << fileGroup[thisFastaName] << endl;
}
in.close();
}else {
map<string, map<string, string> >::iterator itGroupNameMap = group2NameMap.find(fileGroup[thisFastaName]);
if (itGroupNameMap != group2NameMap.end()) {
map<string, string> thisnamemap = itGroupNameMap->second;
map<string, string>::iterator itN;
ofstream out;
m->openOutputFile(thisaccnosFileName+".temp", out);
while (!in.eof()) {
in >> name; m->gobble(in);
itN = thisnamemap.find(name);
if (itN != thisnamemap.end()) {
vector<string> tempNames; m->splitAtComma(itN->second, tempNames);
for (int j = 0; j < tempNames.size(); j++) { out << tempNames[j] << endl; }
}else { m->mothurOut("[ERROR]: parsing cannot find " + name + ".\n"); m->control_pressed = true; }
}
out.close();
in.close();
m->renameFile(thisaccnosFileName+".temp", thisaccnosFileName);
}else { m->mothurOut("[ERROR]: parsing cannot find " + fileGroup[thisFastaName] + ".\n"); m->control_pressed = true; }
}
}
}
//append files
m->appendFiles(thisoutputFileName, outputFName); m->mothurRemove(thisoutputFileName);
m->appendFiles(thisaccnosFileName, accnos); m->mothurRemove(thisaccnosFileName);
if (trim) { m->appendFiles(thistrimFastaFileName, fasta); m->mothurRemove(thistrimFastaFileName); }
m->mothurRemove(thisFastaName);
totalSeqs += numSeqs;
m->mothurOutEndLine(); m->mothurOut("It took " + toString(time(NULL) - start) + " secs to check " + toString(numSeqs) + " sequences from group " + fileGroup[thisFastaName] + "."); m->mothurOutEndLine();
}
if (hasCount && dups) { outCountList.close(); }
return totalSeqs;
}
catch(exception& e) {
m->errorOut(e, "ChimeraSlayerCommand", "driverGroups");
exit(1);
}
}
/**************************************************************************************************/
int ChimeraSlayerCommand::createProcessesGroups(string outputFName, string accnos, string fasta, map<string, map<string, int> >& fileToPriority, map<string, string>& fileGroup, string countlist, string countFile) {
try {
int process = 1;
int num = 0;
processIDS.clear();
if (fileToPriority.size() < processors) { processors = fileToPriority.size(); }
CountTable newCount;
if (hasCount && dups) { newCount.readTable(countFile, true, false); }
int groupsPerProcessor = fileToPriority.size() / processors;
int remainder = fileToPriority.size() % processors;
vector< map<string, map<string, int> > > breakUp;
for (int i = 0; i < processors; i++) {
map<string, map<string, int> > thisFileToPriority;
map<string, map<string, int> >::iterator itFile;
int count = 0;
int enough = groupsPerProcessor;
if (i == 0) { enough = groupsPerProcessor + remainder; }
for (itFile = fileToPriority.begin(); itFile != fileToPriority.end();) {
thisFileToPriority[itFile->first] = itFile->second;
fileToPriority.erase(itFile++);
count++;
if (count == enough) { break; }
}
breakUp.push_back(thisFileToPriority);
}
#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix)
//loop through and create all the processes you want
while (process != processors) {
int pid = fork();
if (pid > 0) {
processIDS.push_back(pid); //create map from line number to pid so you can append files in correct order later
process++;
}else if (pid == 0){
num = driverGroups(outputFName + toString(m->mothurGetpid(process)) + ".temp", accnos + m->mothurGetpid(process) + ".temp", fasta + toString(m->mothurGetpid(process)) + ".temp", breakUp[process], fileGroup, accnos + toString(m->mothurGetpid(process)) + ".byCount");
//pass numSeqs to parent
ofstream out;
string tempFile = outputFName + toString(m->mothurGetpid(process)) + ".num.temp";
m->openOutputFile(tempFile, out);
out << num << endl;
out.close();
exit(0);
}else {
m->mothurOut("[ERROR]: unable to spawn the necessary processes."); m->mothurOutEndLine();
for (int i = 0; i < processIDS.size(); i++) { kill (processIDS[i], SIGINT); }
exit(0);
}
}
num = driverGroups(outputFName, accnos, fasta, breakUp[0], fileGroup, accnos + ".byCount");
//force parent to wait until all the processes are done
for (int i=0;i<processors;i++) {
int temp = processIDS[i];
wait(&temp);
}
for (int i = 0; i < processIDS.size(); i++) {
ifstream in;
string tempFile = outputFName + toString(processIDS[i]) + ".num.temp";
m->openInputFile(tempFile, in);
if (!in.eof()) { int tempNum = 0; in >> tempNum; num += tempNum; }
in.close(); m->mothurRemove(tempFile);
}
#else
//////////////////////////////////////////////////////////////////////////////////////////////////////
//Windows version shared memory, so be careful when passing variables through the slayerData struct.
//Above fork() will clone, so memory is separate, but that's not the case with windows,
//////////////////////////////////////////////////////////////////////////////////////////////////////
vector<slayerData*> pDataArray;
DWORD dwThreadIdArray[processors-1];
HANDLE hThreadArray[processors-1];
//Create processor worker threads.
for(int i=1; i<processors; i++ ){
string extension = toString(i) + ".temp";
slayerData* tempslayer = new slayerData(group2NameMap, hasCount, dups, (accnos + toString(i) +".byCount"), (outputFName + extension), (fasta + extension), (accnos + extension), templatefile, search, blastlocation, trimera, trim, realign, m, breakUp[i], fileGroup, ksize, match, mismatch, window, minSimilarity, minCoverage, minBS, minSNP, parents, iters, increment, numwanted, divR, priority, i);
pDataArray.push_back(tempslayer);
processIDS.push_back(i);
//MySlayerThreadFunction is in header. It must be global or static to work with the threads.
//default security attributes, thread function name, argument to thread function, use default creation flags, returns the thread identifier
hThreadArray[i-1] = CreateThread(NULL, 0, MySlayerGroupThreadFunction, pDataArray[i-1], 0, &dwThreadIdArray[i-1]);
}
num = driverGroups(outputFName, accnos, fasta, breakUp[0], fileGroup, accnos + ".byCount");
//Wait until all threads have terminated.
WaitForMultipleObjects(processors-1, hThreadArray, TRUE, INFINITE);
//Close all thread handles and free memory allocations.
for(int i=0; i < pDataArray.size(); i++){
if (pDataArray[i]->fileToPriority.size() != pDataArray[i]->end) {
m->mothurOut("[ERROR]: process " + toString(i) + " only processed " + toString(pDataArray[i]->end) + " of " + toString(pDataArray[i]->fileToPriority.size()) + " groups assigned to it, quitting. \n"); m->control_pressed = true;
}
num += pDataArray[i]->count;
CloseHandle(hThreadArray[i]);
delete pDataArray[i];
}
#endif
//read my own
if (hasCount && dups) {
if (!m->isBlank(accnos + ".byCount")) {
ifstream in2;
m->openInputFile(accnos + ".byCount", in2);
string name, group;
while (!in2.eof()) {
in2 >> name >> group; m->gobble(in2);
newCount.setAbund(name, group, 0);
}
in2.close();
}
m->mothurRemove(accnos + ".byCount");
}
//append output files
for(int i=0;i<processIDS.size();i++){
m->appendFiles((outputFName + toString(processIDS[i]) + ".temp"), outputFName);
m->mothurRemove((outputFName + toString(processIDS[i]) + ".temp"));
m->appendFiles((accnos + toString(processIDS[i]) + ".temp"), accnos);
m->mothurRemove((accnos + toString(processIDS[i]) + ".temp"));
if (trim) {
m->appendFiles((fasta + toString(processIDS[i]) + ".temp"), fasta);
m->mothurRemove((fasta + toString(processIDS[i]) + ".temp"));
}
if (hasCount && dups) {
if (!m->isBlank(accnos + toString(processIDS[i]) + ".byCount")) {
ifstream in2;
m->openInputFile(accnos + toString(processIDS[i]) + ".byCount", in2);
string name, group;
while (!in2.eof()) {
in2 >> name >> group; m->gobble(in2);
newCount.setAbund(name, group, 0);
}
in2.close();
}
m->mothurRemove(accnos + toString(processIDS[i]) + ".byCount");
}
}
//print new *.pick.count_table
if (hasCount && dups) { newCount.printTable(countlist); }
return num;
}
catch(exception& e) {
m->errorOut(e, "ChimeraSlayerCommand", "createProcessesGroups");
exit(1);
}
}
//**********************************************************************************************************************
int ChimeraSlayerCommand::driver(linePair filePos, string outputFName, string filename, string accnos, string fasta, map<string, int>& priority){
try {
if (m->debug) { m->mothurOut("[DEBUG]: filename = " + filename + "\n"); }
Chimera* chimera;
if (templatefile != "self") { //you want to run slayer with a reference template
chimera = new ChimeraSlayer(filename, templatefile, trim, search, ksize, match, mismatch, window, divR, minSimilarity, minCoverage, minBS, minSNP, parents, iters, increment, numwanted, realign, blastlocation, rand());
}else {
chimera = new ChimeraSlayer(filename, templatefile, trim, priority, search, ksize, match, mismatch, window, divR, minSimilarity, minCoverage, minBS, minSNP, parents, iters, increment, numwanted, realign, blastlocation, rand());
}
if (m->control_pressed) { delete chimera; return 0; }
if (chimera->getUnaligned()) { delete chimera; m->mothurOut("Your template sequences are different lengths, please correct."); m->mothurOutEndLine(); m->control_pressed = true; return 0; }
templateSeqsLength = chimera->getLength();
ofstream out;
m->openOutputFile(outputFName, out);
ofstream out2;
m->openOutputFile(accnos, out2);
ofstream out3;
if (trim) { m->openOutputFile(fasta, out3); }
ifstream inFASTA;
m->openInputFile(filename, inFASTA);
inFASTA.seekg(filePos.start);
if (filePos.start == 0) { chimera->printHeader(out); }
bool done = false;
int count = 0;
while (!done) {
if (m->control_pressed) { delete chimera; out.close(); out2.close(); if (trim) { out3.close(); } inFASTA.close(); return 1; }
Sequence* candidateSeq = new Sequence(inFASTA); m->gobble(inFASTA);
string candidateAligned = candidateSeq->getAligned();
if (candidateSeq->getName() != "") { //incase there is a commented sequence at the end of a file
if (candidateSeq->getAligned().length() != templateSeqsLength) {
m->mothurOut(candidateSeq->getName() + " is not the same length as the template sequences. Skipping."); m->mothurOutEndLine();
}else{
//find chimeras
chimera->getChimeras(candidateSeq);
if (m->control_pressed) { delete chimera; delete candidateSeq; return 1; }
//if you are not chimeric, then check each half
data_results wholeResults = chimera->getResults();
//determine if we need to split
bool isChimeric = false;
if (wholeResults.flag == "yes") {
string chimeraFlag = "no";
if( (wholeResults.results[0].bsa >= minBS && wholeResults.results[0].divr_qla_qrb >= divR)
||
(wholeResults.results[0].bsb >= minBS && wholeResults.results[0].divr_qlb_qra >= divR) ) { chimeraFlag = "yes"; }
if (chimeraFlag == "yes") {
if ((wholeResults.results[0].bsa >= minBS) || (wholeResults.results[0].bsb >= minBS)) { isChimeric = true; }
}
}
if ((!isChimeric) && trimera) {
//split sequence in half by bases
string leftQuery, rightQuery;
Sequence tempSeq(candidateSeq->getName(), candidateAligned);
divideInHalf(tempSeq, leftQuery, rightQuery);
//run chimeraSlayer on each piece
Sequence* left = new Sequence(candidateSeq->getName(), leftQuery);
Sequence* right = new Sequence(candidateSeq->getName(), rightQuery);
//find chimeras
chimera->getChimeras(left);
data_results leftResults = chimera->getResults();
chimera->getChimeras(right);
data_results rightResults = chimera->getResults();
//if either piece is chimeric then report
Sequence trimmed = chimera->print(out, out2, leftResults, rightResults);
if (trim) { trimmed.printSequence(out3); }
delete left; delete right;
}else { //already chimeric
//print results
Sequence trimmed = chimera->print(out, out2);
if (trim) { trimmed.printSequence(out3); }
}
}
count++;
}
#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix)
unsigned long long pos = inFASTA.tellg();
if ((pos == -1) || (pos >= filePos.end)) { break; }
#else
if (inFASTA.eof()) { break; }
#endif
delete candidateSeq;
//report progress
if((count) % 100 == 0){ m->mothurOutJustToScreen("Processing sequence: " + toString(count) + "\n"); }
}
//report progress
if((count) % 100 != 0){ m->mothurOutJustToScreen("Processing sequence: " + toString(count)+ "\n"); }
int numNoParents = chimera->getNumNoParents();
if (numNoParents == count) { m->mothurOut("[WARNING]: megablast returned 0 potential parents for all your sequences. This could be due to formatdb.exe not being setup properly, please check formatdb.log for errors."); m->mothurOutEndLine(); }
out.close();
out2.close();
if (trim) { out3.close(); }
inFASTA.close();
delete chimera;
return count;
}
catch(exception& e) {
m->errorOut(e, "ChimeraSlayerCommand", "driver");
exit(1);
}
}
//**********************************************************************************************************************
#ifdef USE_MPI
int ChimeraSlayerCommand::driverMPI(int start, int num, MPI_File& inMPI, MPI_File& outMPI, MPI_File& outAccMPI, MPI_File& outFastaMPI, set<string>& cnames, vector<unsigned long long>& MPIPos, string filename, map<string, int>& priority, bool byGroup){
try {
MPI_Status status;
int pid;
MPI_Comm_rank(MPI_COMM_WORLD, &pid); //find out who we are
Chimera* chimera;
if (templatefile != "self") { //you want to run slayer with a reference template
chimera = new ChimeraSlayer(filename, templatefile, trim, search, ksize, match, mismatch, window, divR, minSimilarity, minCoverage, minBS, minSNP, parents, iters, increment, numwanted, realign, blastlocation, rand());
}else {
chimera = new ChimeraSlayer(filename, templatefile, trim, priority, search, ksize, match, mismatch, window, divR, minSimilarity, minCoverage, minBS, minSNP, parents, iters, increment, numwanted, realign, blastlocation, rand(), byGroup);
}
if (m->control_pressed) { delete chimera; return 0; }
if (chimera->getUnaligned()) { delete chimera; m->mothurOut("Your template sequences are different lengths, please correct."); m->mothurOutEndLine(); m->control_pressed = true; return 0; }
templateSeqsLength = chimera->getLength();
for(int i=0;i<num;i++){
if (m->control_pressed) { delete chimera; return 1; }
//read next sequence
int length = MPIPos[start+i+1] - MPIPos[start+i];
char* buf4 = new char[length];
MPI_File_read_at(inMPI, MPIPos[start+i], buf4, length, MPI_CHAR, &status);
string tempBuf = buf4;
if (tempBuf.length() > length) { tempBuf = tempBuf.substr(0, length); }
istringstream iss (tempBuf,istringstream::in);
delete buf4;
Sequence* candidateSeq = new Sequence(iss); m->gobble(iss);
string candidateAligned = candidateSeq->getAligned();
if (candidateSeq->getName() != "") { //incase there is a commented sequence at the end of a file
if (candidateSeq->getAligned().length() != templateSeqsLength) {
m->mothurOut(candidateSeq->getName() + " is not the same length as the template sequences. Skipping."); m->mothurOutEndLine();
}else{
//find chimeras
chimera->getChimeras(candidateSeq);
if (m->control_pressed) { delete chimera; delete candidateSeq; return 1; }
//if you are not chimeric, then check each half
data_results wholeResults = chimera->getResults();
//determine if we need to split
bool isChimeric = false;
if (wholeResults.flag == "yes") {
string chimeraFlag = "no";
if( (wholeResults.results[0].bsa >= minBS && wholeResults.results[0].divr_qla_qrb >= divR)
||
(wholeResults.results[0].bsb >= minBS && wholeResults.results[0].divr_qlb_qra >= divR) ) { chimeraFlag = "yes"; }
if (chimeraFlag == "yes") {
if ((wholeResults.results[0].bsa >= minBS) || (wholeResults.results[0].bsb >= minBS)) { isChimeric = true; }
}
}
if ((!isChimeric) && trimera) {
//split sequence in half by bases
string leftQuery, rightQuery;
Sequence tempSeq(candidateSeq->getName(), candidateAligned);
divideInHalf(tempSeq, leftQuery, rightQuery);
//run chimeraSlayer on each piece
Sequence* left = new Sequence(candidateSeq->getName(), leftQuery);
Sequence* right = new Sequence(candidateSeq->getName(), rightQuery);
//find chimeras
chimera->getChimeras(left);
data_results leftResults = chimera->getResults();
chimera->getChimeras(right);
data_results rightResults = chimera->getResults();
//if either piece is chimeric then report
bool flag = false;
Sequence trimmed = chimera->print(outMPI, outAccMPI, leftResults, rightResults, flag);
if (flag) { cnames.insert(candidateSeq->getName()); }
if (trim) {
string outputString = ">" + trimmed.getName() + "\n" + trimmed.getAligned() + "\n";
//write to accnos file
int length = outputString.length();
char* buf2 = new char[length];
memcpy(buf2, outputString.c_str(), length);
MPI_File_write_shared(outFastaMPI, buf2, length, MPI_CHAR, &status);
delete buf2;
}
delete left; delete right;
}else {
//print results
Sequence trimmed = chimera->print(outMPI, outAccMPI);
cnames.insert(candidateSeq->getName());
if (trim) {
string outputString = ">" + trimmed.getName() + "\n" + trimmed.getAligned() + "\n";
//write to accnos file
int length = outputString.length();
char* buf2 = new char[length];
memcpy(buf2, outputString.c_str(), length);
MPI_File_write_shared(outFastaMPI, buf2, length, MPI_CHAR, &status);
delete buf2;
}
}
}
}
delete candidateSeq;
//report progress
if((i+1) % 100 == 0){ cout << "Processing sequence: " << (i+1) << endl; }
}
//report progress
if(num % 100 != 0){ cout << "Processing sequence: " << num << endl; }
int numNoParents = chimera->getNumNoParents();
if (numNoParents == num) { cout << "[WARNING]: megablast returned 0 potential parents for all your sequences. This could be due to formatdb.exe not being setup properly, please check formatdb.log for errors." << endl; }
delete chimera;
return 0;
}
catch(exception& e) {
m->errorOut(e, "ChimeraSlayerCommand", "driverMPI");
exit(1);
}
}
#endif
/**************************************************************************************************/
int ChimeraSlayerCommand::createProcesses(string outputFileName, string filename, string accnos, string fasta, map<string, int>& thisPriority) {
try {
int process = 0;
int num = 0;
processIDS.clear();
if (m->debug) { m->mothurOut("[DEBUG]: filename = " + filename + "\n"); }
#if defined (__APPLE__) || (__MACH__) || (linux) || (__linux) || (__linux__) || (__unix__) || (__unix)
//loop through and create all the processes you want
while (process != processors) {
int pid = fork();
if (pid > 0) {
processIDS.push_back(pid); //create map from line number to pid so you can append files in correct order later
process++;
}else if (pid == 0){
num = driver(lines[process], outputFileName + toString(m->mothurGetpid(process)) + ".temp", filename, accnos + toString(m->mothurGetpid(process)) + ".temp", fasta + toString(m->mothurGetpid(process)) + ".temp", thisPriority);
//pass numSeqs to parent
ofstream out;
string tempFile = outputFileName + toString(m->mothurGetpid(process)) + ".num.temp";
m->openOutputFile(tempFile, out);
out << num << endl;
out.close();
exit(0);
}else {
m->mothurOut("[ERROR]: unable to spawn the necessary processes."); m->mothurOutEndLine();
for (int i = 0; i < processIDS.size(); i++) { kill (processIDS[i], SIGINT); }
exit(0);
}
}
//force parent to wait until all the processes are done
for (int i=0;i<processors;i++) {
int temp = processIDS[i];
wait(&temp);
}
for (int i = 0; i < processIDS.size(); i++) {
ifstream in;
string tempFile = outputFileName + toString(processIDS[i]) + ".num.temp";
m->openInputFile(tempFile, in);
if (!in.eof()) { int tempNum = 0; in >> tempNum; num += tempNum; }
in.close(); m->mothurRemove(tempFile);
}
#else
//////////////////////////////////////////////////////////////////////////////////////////////////////
//Windows version shared memory, so be careful when passing variables through the slayerData struct.
//Above fork() will clone, so memory is separate, but that's not the case with windows,
//////////////////////////////////////////////////////////////////////////////////////////////////////
vector<slayerData*> pDataArray;
DWORD dwThreadIdArray[processors];
HANDLE hThreadArray[processors];
//Create processor worker threads.
for( int i=0; i<processors; i++ ){
string extension = toString(i) + ".temp";
slayerData* tempslayer = new slayerData((outputFileName + extension), (fasta + extension), (accnos + extension), filename, templatefile, search, blastlocation, trimera, trim, realign, m, lines[i].start, lines[i].end, ksize, match, mismatch, window, minSimilarity, minCoverage, minBS, minSNP, parents, iters, increment, numwanted, divR, priority, i);
pDataArray.push_back(tempslayer);
processIDS.push_back(i);
//MySlayerThreadFunction is in header. It must be global or static to work with the threads.
//default security attributes, thread function name, argument to thread function, use default creation flags, returns the thread identifier
hThreadArray[i] = CreateThread(NULL, 0, MySlayerThreadFunction, pDataArray[i], 0, &dwThreadIdArray[i]);
}
//Wait until all threads have terminated.
WaitForMultipleObjects(processors, hThreadArray, TRUE, INFINITE);
//Close all thread handles and free memory allocations.
for(int i=0; i < pDataArray.size(); i++){
num += pDataArray[i]->count;
CloseHandle(hThreadArray[i]);
delete pDataArray[i];
}
#endif
rename((outputFileName + toString(processIDS[0]) + ".temp").c_str(), outputFileName.c_str());
rename((accnos + toString(processIDS[0]) + ".temp").c_str(), accnos.c_str());
if (trim) { rename((fasta + toString(processIDS[0]) + ".temp").c_str(), fasta.c_str()); }
//append output files
for(int i=1;i<processIDS.size();i++){
m->appendFiles((outputFileName + toString(processIDS[i]) + ".temp"), outputFileName);
m->mothurRemove((outputFileName + toString(processIDS[i]) + ".temp"));
m->appendFiles((accnos + toString(processIDS[i]) + ".temp"), accnos);
m->mothurRemove((accnos + toString(processIDS[i]) + ".temp"));
if (trim) {
m->appendFiles((fasta + toString(processIDS[i]) + ".temp"), fasta);
m->mothurRemove((fasta + toString(processIDS[i]) + ".temp"));
}
}
return num;
}
catch(exception& e) {
m->errorOut(e, "ChimeraSlayerCommand", "createProcesses");
exit(1);
}
}
/**************************************************************************************************/
int ChimeraSlayerCommand::divideInHalf(Sequence querySeq, string& leftQuery, string& rightQuery) {
try {
string queryUnAligned = querySeq.getUnaligned();
int numBases = int(queryUnAligned.length() * 0.5);
string queryAligned = querySeq.getAligned();
leftQuery = querySeq.getAligned();
rightQuery = querySeq.getAligned();
int baseCount = 0;
int leftSpot = 0;
for (int i = 0; i < queryAligned.length(); i++) {
//if you are a base
if (isalpha(queryAligned[i])) {
baseCount++;
}
//if you have half
if (baseCount >= numBases) { leftSpot = i; break; } //first half
}
//blank out right side
for (int i = leftSpot; i < leftQuery.length(); i++) { leftQuery[i] = '.'; }
//blank out left side
for (int i = 0; i < leftSpot; i++) { rightQuery[i] = '.'; }
return 0;
}
catch(exception& e) {
m->errorOut(e, "ChimeraSlayerCommand", "divideInHalf");
exit(1);
}
}
/**************************************************************************************************/
map<string, int> ChimeraSlayerCommand::sortFastaFile(string fastaFile, string nameFile) {
try {
map<string, int> nameAbund;
//read through fastafile and store info
map<string, string> seqs;
ifstream in;
m->openInputFile(fastaFile, in);
while (!in.eof()) {
if (m->control_pressed) { in.close(); return nameAbund; }
Sequence seq(in); m->gobble(in);
seqs[seq.getName()] = seq.getAligned();
}
in.close();
//read namefile or countfile
vector<seqPriorityNode> nameMapCount;
int error;
if (hasCount) {
CountTable ct;
ct.readTable(nameFile, true, false);
for(map<string, string>::iterator it = seqs.begin(); it != seqs.end(); it++) {
int num = ct.getNumSeqs(it->first);
if (num == 0) { error = 1; }
else {
seqPriorityNode temp(num, it->second, it->first);
nameMapCount.push_back(temp);
}
}
}else { error = m->readNames(nameFile, nameMapCount, seqs); }
if (m->control_pressed) { return nameAbund; }
if (error == 1) { m->control_pressed = true; return nameAbund; }
if (seqs.size() != nameMapCount.size()) { m->mothurOut( "The number of sequences in your fastafile does not match the number of sequences in your namefile, aborting."); m->mothurOutEndLine(); m->control_pressed = true; return nameAbund; }
sort(nameMapCount.begin(), nameMapCount.end(), compareSeqPriorityNodes);
string newFasta = fastaFile + ".temp";
ofstream out;
m->openOutputFile(newFasta, out);
//print new file in order of
for (int i = 0; i < nameMapCount.size(); i++) {
out << ">" << nameMapCount[i].name << endl << nameMapCount[i].seq << endl;
nameAbund[nameMapCount[i].name] = nameMapCount[i].numIdentical;
}
out.close();
rename(newFasta.c_str(), fastaFile.c_str());
return nameAbund;
}
catch(exception& e) {
m->errorOut(e, "ChimeraSlayerCommand", "sortFastaFile");
exit(1);
}
}
/**************************************************************************************************/
map<string, int> ChimeraSlayerCommand::sortFastaFile(vector<Sequence>& thisseqs, map<string, string>& nameMap, string newFile) {
try {
map<string, int> nameAbund;
vector<seqPriorityNode> nameVector;
//read through fastafile and store info
map<string, string> seqs;
for (int i = 0; i < thisseqs.size(); i++) {
if (m->control_pressed) { return nameAbund; }
map<string, string>::iterator itNameMap = nameMap.find(thisseqs[i].getName());
if (itNameMap == nameMap.end()){
m->control_pressed = true;
m->mothurOut("[ERROR]: " + thisseqs[i].getName() + " is in your fastafile, but is not in your namesfile, please correct."); m->mothurOutEndLine();
}else {
int num = m->getNumNames(itNameMap->second);
seqPriorityNode temp(num, thisseqs[i].getAligned(), thisseqs[i].getName());
nameVector.push_back(temp);
}
}
//sort by num represented
sort(nameVector.begin(), nameVector.end(), compareSeqPriorityNodes);
if (m->control_pressed) { return nameAbund; }
if (thisseqs.size() != nameVector.size()) { m->mothurOut( "The number of sequences in your fastafile does not match the number of sequences in your namefile, aborting."); m->mothurOutEndLine(); m->control_pressed = true; return nameAbund; }
ofstream out;
m->openOutputFile(newFile, out);
//print new file in order of
for (int i = 0; i < nameVector.size(); i++) {
out << ">" << nameVector[i].name << endl << nameVector[i].seq << endl;
nameAbund[nameVector[i].name] = nameVector[i].numIdentical;
}
out.close();
return nameAbund;
}
catch(exception& e) {
m->errorOut(e, "ChimeraSlayerCommand", "sortFastaFile");
exit(1);
}
}
/**************************************************************************************************/
int ChimeraSlayerCommand::sortFastaFile(vector<Sequence>& thisseqs, map<string, int>& countMap, string newFile) {
try {
vector<seqPriorityNode> nameVector;
//read through fastafile and store info
map<string, string> seqs;
for (int i = 0; i < thisseqs.size(); i++) {
if (m->control_pressed) { return 0; }
map<string, int>::iterator itCountMap = countMap.find(thisseqs[i].getName());
if (itCountMap == countMap.end()){
m->control_pressed = true;
m->mothurOut("[ERROR]: " + thisseqs[i].getName() + " is in your fastafile, but is not in your count file, please correct."); m->mothurOutEndLine();
}else {
seqPriorityNode temp(itCountMap->second, thisseqs[i].getAligned(), thisseqs[i].getName());
nameVector.push_back(temp);
}
}
//sort by num represented
sort(nameVector.begin(), nameVector.end(), compareSeqPriorityNodes);
if (m->control_pressed) { return 0; }
if (thisseqs.size() != nameVector.size()) { m->mothurOut( "The number of sequences in your fastafile does not match the number of sequences in your count file, aborting."); m->mothurOutEndLine(); m->control_pressed = true; return 0; }
ofstream out;
m->openOutputFile(newFile, out);
//print new file in order of
for (int i = 0; i < nameVector.size(); i++) {
out << ">" << nameVector[i].name << endl << nameVector[i].seq << endl;
}
out.close();
return 0;
}
catch(exception& e) {
m->errorOut(e, "ChimeraSlayerCommand", "sortFastaFile");
exit(1);
}
}
/**************************************************************************************************/
|