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
|
// Author: Mark Chaisson
#include "iblasr/BlasrMiscs.hpp"
#include "iblasr/BlasrUtils.hpp"
#include "iblasr/BlasrAlign.hpp"
#include "iblasr/RegisterBlasrOptions.h"
//#define USE_GOOGLE_PROFILER
#ifdef USE_GOOGLE_PROFILER
#include "gperftools/profiler.h"
#endif
using namespace std;
// Declare global structures that are shared between threads.
MappingSemaphores semaphores;
ostream *outFilePtr = NULL;
#ifdef USE_PBBAM
PacBio::BAM::IRecordWriter * bamWriterPtr = NULL; // use IRecordWriter for both SAM ands BAM
#endif
HDFRegionTableReader *regionTableReader = NULL;
ReaderAgglomerate *reader = NULL;
// Add comment to version history for each version change !
//
// Version history
//
// 5.0 - a new major version number
// 5.1 - transiotion to POSIX notation - double sashes before multi-character flags
// 5.2 - --sam no longer supported
// 5.3 - --sam supported via pbbam/IRecordWriter
//
const string GetMajorVersion() {
return "5.3";
}
// version format is 3 numbers sparated by dots : Version.Subversion.SHA1
const string GetVersion(void) {
string gitVersionString(SHA1_7); // gitVersionString is first 7 characters of SHA1
string version = GetMajorVersion();
// if (gitVersionString.size() == 7) {
version.append(".");
version.append(gitVersionString);
// }
return version;
}
/// Checks whether a smrtRead meets the following criteria
/// (1) is within the search holeNumber range specified by params.holeNumberRanges.
/// (2) its length greater than params.maxReadlength
/// (3) its read score (rq) is greater than params.minRawSubreadScore
/// (4) its qual is greater than params.minAvgQual.
/// Change stop to false if
/// HoleNumber of the smrtRead is greater than the search holeNumber range.
bool IsGoodRead(const SMRTSequence & smrtRead,
MappingParameters & params,
bool & stop)
{
if (params.holeNumberRangesStr.size() > 0 and
not params.holeNumberRanges.contains(smrtRead.HoleNumber())) {
// Stop processing once the specified zmw hole number is reached.
// Eventually this will change to just seek to hole number, and
// just align one read anyway.
if (smrtRead.HoleNumber() > params.holeNumberRanges.max()){
stop = true;
return false;
}
return false;
}
//
// Discard reads that are too small, or not labeled as having any
// useable/good sequence.
//
if (smrtRead.highQualityRegionScore < params.minRawSubreadScore or
(params.maxReadLength != 0 and smrtRead.length > UInt(params.maxReadLength)) or
(int(smrtRead.length) < params.minReadLength)) {
return false;
}
if (smrtRead.qual.Empty() != false and smrtRead.GetAverageQuality() < params.minAvgQual) {
return false;
}
return true;
}
// Make primary intervals (which are intervals of subreads to align
// in the first round) from none BAM file using region table.
void MakePrimaryIntervals(RegionTable * regionTablePtr,
SMRTSequence & smrtRead,
vector<ReadInterval> & subreadIntervals,
vector<int> & subreadDirections,
int & bestSubreadIndex,
MappingParameters & params)
{
vector<ReadInterval> adapterIntervals;
//
// Determine endpoints of this subread in the main read.
//
if (params.useRegionTable == false) {
//
// When there is no region table, the subread is the entire
// read.
//
ReadInterval wholeRead(0, smrtRead.length);
// The set of subread intervals is just the entire read.
subreadIntervals.push_back(wholeRead);
}
else {
//
// Grab the subread & adapter intervals from the entire region table to
// iterate over.
//
assert(regionTablePtr->HasHoleNumber(smrtRead.HoleNumber()));
subreadIntervals = (*regionTablePtr)[smrtRead.HoleNumber()].SubreadIntervals(smrtRead.length, params.byAdapter);
adapterIntervals = (*regionTablePtr)[smrtRead.HoleNumber()].AdapterIntervals();
}
// The assumption is that neighboring subreads must have the opposite
// directions. So create directions for subread intervals with
// interleaved 0s and 1s.
CreateDirections(subreadDirections, subreadIntervals.size());
//
// Trim the boundaries of subread intervals so that only high quality
// regions are included in the intervals, not N's. Remove intervals
// and their corresponding dirctions, if they are shorter than the
// user specified minimum read length or do not intersect with hq
// region at all. Finally, return index of the (left-most) longest
// subread in the updated vector.
//
int longestSubreadIndex = GetHighQualitySubreadsIntervals(
subreadIntervals, // a vector of subread intervals.
subreadDirections, // a vector of subread directions.
smrtRead.lowQualityPrefix, // hq region start pos.
smrtRead.length - smrtRead.lowQualitySuffix, // hq end pos.
params.minSubreadLength); // minimum read length.
bestSubreadIndex = longestSubreadIndex;
if (params.concordantTemplate == "longestsubread") {
// Use the (left-most) longest full-pass subread as
// template for concordant mapping
int longestFullSubreadIndex = GetLongestFullSubreadIndex(
subreadIntervals, adapterIntervals);
if (longestFullSubreadIndex >= 0) {
bestSubreadIndex = longestFullSubreadIndex;
}
} else if (params.concordantTemplate == "typicalsubread") {
// Use the 'typical' full-pass subread as template for
// concordant mapping.
int typicalFullSubreadIndex = GetTypicalFullSubreadIndex(
subreadIntervals, adapterIntervals);
if (typicalFullSubreadIndex >= 0) {
bestSubreadIndex = typicalFullSubreadIndex;
}
} else if (params.concordantTemplate == "mediansubread") {
// Use the 'median-length' full-pass subread as template for
// concordant mapping.
int medianFullSubreadIndex = GetMedianLengthFullSubreadIndex(
subreadIntervals, adapterIntervals);
if (medianFullSubreadIndex >= 0) {
bestSubreadIndex = medianFullSubreadIndex;
}
} else {
assert(false);
}
}
// Make primary intervals (which are intervals of subreads to align
// in the first round) for BAM file, -concordant,
void MakePrimaryIntervals(vector<SMRTSequence> & subreads,
vector<ReadInterval> & subreadIntervals,
vector<int> & subreadDirections,
int & bestSubreadIndex)
{
MakeSubreadIntervals(subreads, subreadIntervals);
CreateDirections(subreadDirections, subreadIntervals.size());
bestSubreadIndex = GetIndexOfConcordantTemplate(subreadIntervals);
}
/// Scan the next read from input. This may either be a CCS read, unrolled (Polymerase) read,
/// or regular read (though this may be aligned in whole, or by
/// subread).
/// \params[in] reader: FASTA/FASTQ/BAX.H5/CCS.H5/BAM file reader
/// \params[in] regionTablePtr: RGN.H5 region table pointer.
/// \params[in] params: mapping parameters.
/// \params[out] smrtRead: to save smrt sequence.
/// \params[out] ccsRead: to save ccs sequence.
/// \params[out] readIsCCS: read is CCSSequence.
/// \params[out] readGroupId: associated read group id
/// \params[out] associatedRandInt: random int associated with this zmw,
/// required to for generating deterministic random
/// alignments regardless of nproc.
/// \params[out] stop: whether or not stop mapping remaining reads.
/// \returns whether or not to skip mapping reads of this zmw.
bool FetchReads(ReaderAgglomerate * reader,
RegionTable * regionTablePtr,
SMRTSequence & smrtRead,
CCSSequence & ccsRead,
vector<SMRTSequence> & subreads,
MappingParameters & params,
bool & readIsCCS,
std::string & readGroupId,
int & associatedRandInt,
bool & stop)
{
if ((reader->GetFileType() != FileType::PBBAM and reader->GetFileType() != FileType::PBDATASET) or not params.concordant) {
if (reader->GetFileType() == FileType::HDFCCS ||
reader->GetFileType() == FileType::HDFCCSONLY) {
if (GetNextReadThroughSemaphore(*reader, params, ccsRead, readGroupId, associatedRandInt, semaphores) == false) {
stop = true;
return false;
}
else {
readIsCCS = true;
smrtRead.Copy(ccsRead);
ccsRead.SetQVScale(params.qvScaleType);
smrtRead.SetQVScale(params.qvScaleType);
}
assert(ccsRead.zmwData.holeNumber == smrtRead.zmwData.holeNumber and
ccsRead.zmwData.holeNumber == ccsRead.unrolledRead.zmwData.holeNumber);
} else {
if (GetNextReadThroughSemaphore(*reader, params, smrtRead, readGroupId, associatedRandInt, semaphores) == false) {
stop = true;
return false;
}
else {
smrtRead.SetQVScale(params.qvScaleType);
}
}
//
// Only normal (non-CCS) reads should be masked. Since CCS reads store the raw read, that is masked.
//
bool readHasGoodRegion = true;
if (params.useRegionTable and params.useHQRegionTable) {
if (readIsCCS) {
readHasGoodRegion = MaskRead(ccsRead.unrolledRead, ccsRead.unrolledRead.zmwData, *regionTablePtr);
}
else {
readHasGoodRegion = MaskRead(smrtRead, smrtRead.zmwData, *regionTablePtr);
}
//
// Store the high quality start and end of this read for masking purposes when printing.
//
int hqStart, hqEnd;
int score;
LookupHQRegion(smrtRead.zmwData.holeNumber, *regionTablePtr, hqStart, hqEnd, score);
smrtRead.lowQualityPrefix = hqStart;
smrtRead.lowQualitySuffix = smrtRead.length - hqEnd;
smrtRead.highQualityRegionScore = score;
}
else {
smrtRead.lowQualityPrefix = 0;
smrtRead.lowQualitySuffix = 0;
}
if (not IsGoodRead(smrtRead, params, stop) or stop) return false;
return readHasGoodRegion;
} else {
subreads.clear();
vector<SMRTSequence> reads;
if (GetNextReadThroughSemaphore(*reader, params, reads, readGroupId, associatedRandInt, semaphores) == false) {
stop = true;
return false;
}
for (const SMRTSequence & smrtRead: reads) {
if (IsGoodRead(smrtRead, params, stop)) {
subreads.push_back(smrtRead);
}
}
if (subreads.size() != 0) {
smrtRead.MadeFromSubreadsAsPolymerase(subreads);
return true;
}
else {
return false;
}
}
}
void MapReadsNonCCS(MappingData<T_SuffixArray, T_GenomeSequence, T_Tuple> *mapData,
MappingBuffers & mappingBuffers,
SMRTSequence & smrtRead,
SMRTSequence & smrtReadRC,
vector<SMRTSequence> & subreads,
MappingParameters & params,
const int & associatedRandInt,
ReadAlignments & allReadAlignments,
ofstream & threadOut)
{
DNASuffixArray sarray;
TupleCountTable<T_GenomeSequence, DNATuple> ct;
SequenceIndexDatabase<FASTQSequence> seqdb;
T_GenomeSequence genome;
BWT *bwtPtr;
mapData->ShallowCopySuffixArray(sarray);
mapData->ShallowCopyReferenceSequence(genome);
mapData->ShallowCopySequenceIndexDatabase(seqdb);
mapData->ShallowCopyTupleCountTable(ct);
bwtPtr = mapData->bwtPtr;
SeqBoundaryFtr<FASTQSequence> seqBoundary(&seqdb);
vector<ReadInterval> subreadIntervals;
vector<int> subreadDirections;
int bestSubreadIndex;
if ((mapData->reader->GetFileType() != FileType::PBBAM and mapData->reader->GetFileType() != FileType::PBDATASET) or not params.concordant) {
MakePrimaryIntervals(mapData->regionTablePtr, smrtRead,
subreadIntervals, subreadDirections,
bestSubreadIndex, params);
} else {
MakePrimaryIntervals(subreads,
subreadIntervals, subreadDirections,
bestSubreadIndex);
}
// Flop all directions if direction of the longest subread is 1.
if (bestSubreadIndex >= 0 and
bestSubreadIndex < int(subreadDirections.size()) and
subreadDirections[bestSubreadIndex] == 1) {
UpdateDirections(subreadDirections, true);
}
int startIndex = 0;
int endIndex = subreadIntervals.size();
if (params.concordant) {
// Only the longest subread will be aligned in the first round.
// VR , change the comment
startIndex = max(startIndex, bestSubreadIndex);
endIndex = min(endIndex, bestSubreadIndex + 1);
if (params.verbosity >= 1) {
cout << "Concordant template subread index: " << bestSubreadIndex << ", "
<< smrtRead.HoleNumber() << "/" << subreadIntervals[bestSubreadIndex] << endl;
}
}
//
// Make room for alignments.
//
allReadAlignments.Resize(subreadIntervals.size());
allReadAlignments.alignMode = Subread;
for (int intvIndex = startIndex; intvIndex < endIndex; intvIndex++) {
SMRTSequence subreadSequence, subreadSequenceRC;
MakeSubreadOfInterval(subreadSequence, smrtRead,
subreadIntervals[intvIndex], params);
MakeSubreadRC(subreadSequenceRC, subreadSequence, smrtRead);
//
// Store the sequence that is being mapped in case no hits are
// found, and missing sequences are printed.
//
allReadAlignments.SetSequence(intvIndex, subreadSequence);
vector<T_AlignmentCandidate*> alignmentPtrs;
mapData->metrics.numReads++;
assert(subreadSequence.zmwData.holeNumber == smrtRead.zmwData.holeNumber);
//
// Try default and fast parameters to map the read.
//
MapRead(subreadSequence, subreadSequenceRC,
genome, // possibly multi fasta file read into one sequence
sarray, *bwtPtr, // The suffix array, and the bwt-fm index structures
seqBoundary, // Boundaries of contigs in the
// genome, alignments do not span
// the ends of boundaries.
ct, // Count table to use word frequencies in the genome to weight matches.
seqdb, // Information about the names of
// chromosomes in the genome, and
// where their sequences are in the genome.
params, // A huge list of parameters for
// mapping, only compile/command
// line values set.
mapData->metrics, // Keep track of time/ hit counts,
// etc.. Not fully developed, but
// should be.
alignmentPtrs, // Where the results are stored.
mappingBuffers, // A class of buffers for structurs
// like dyanmic programming
// matrices, match lists, etc., that are not
// reallocated between calls to
// MapRead. They are cleared though.
mapData, // Some values that are shared
// across threads.
semaphores);
//
// No alignments were found, sometimes parameters are
// specified to try really hard again to find an alignment.
// This sets some parameters that use a more sensitive search
// at the cost of time.
//
if ((alignmentPtrs.size() == 0 or alignmentPtrs[0]->pctSimilarity < 80) and params.doSensitiveSearch) {
MappingParameters sensitiveParams = params;
sensitiveParams.SetForSensitivity();
MapRead(subreadSequence, subreadSequenceRC, genome,
sarray, *bwtPtr,
seqBoundary, ct, seqdb,
sensitiveParams, mapData->metrics,
alignmentPtrs, mappingBuffers,
mapData,
semaphores);
}
//
// Store the mapping quality values.
//
if (alignmentPtrs.size() > 0 and
alignmentPtrs[0]->score < params.maxScore and
params.storeMapQV) {
StoreMapQVs(subreadSequence, alignmentPtrs, params);
}
//
// Select alignments for this subread.
//
vector<T_AlignmentCandidate*> selectedAlignmentPtrs =
SelectAlignmentsToPrint(alignmentPtrs, params, associatedRandInt);
allReadAlignments.AddAlignmentsForSeq(intvIndex, selectedAlignmentPtrs);
//
// Move reference from subreadSequence, which will be freed at
// the end of this loop to the smrtRead, which exists for the
// duration of aligning all subread of the smrtRead.
//
for (size_t a = 0; a < alignmentPtrs.size(); a++) {
if (alignmentPtrs[a]->qStrand == 0) {
alignmentPtrs[a]->qAlignedSeq.ReferenceSubstring(smrtRead,
alignmentPtrs[a]->qAlignedSeq.seq - subreadSequence.seq,
alignmentPtrs[a]->qAlignedSeqLength);
}
else {
alignmentPtrs[a]->qAlignedSeq.ReferenceSubstring(smrtReadRC,
alignmentPtrs[a]->qAlignedSeq.seq - subreadSequenceRC.seq,
alignmentPtrs[a]->qAlignedSeqLength);
}
}
// Fix for memory leakage bug due to undeleted Alignment Candidate objectts which wasn't selected
// for printing
// delete all AC which are in complement of SelectedAlignmemntPtrs vector
// namely (SelectedAlignmentPtrs/alignmentPtrs)
for (size_t ii = 0; ii < alignmentPtrs.size(); ii++)
{
int found =0;
for (size_t jj = 0; jj < selectedAlignmentPtrs.size(); jj++)
{
if (alignmentPtrs[ii] == selectedAlignmentPtrs[jj] )
{
found = 1;
break;
}
}
if (found == 0) delete alignmentPtrs[ii];
}
subreadSequence.Free();
subreadSequenceRC.Free();
} // End of looping over subread intervals within [startIndex, endIndex).
if (params.verbosity >= 3)
allReadAlignments.Print(threadOut);
// If not concordant , all done
if (params.concordant) {
allReadAlignments.read = smrtRead;
allReadAlignments.alignMode = ZmwSubreads;
if (startIndex >= 0 && startIndex < int(allReadAlignments.subreadAlignments.size())) {
vector<T_AlignmentCandidate*> selectedAlignmentPtrs =
allReadAlignments.CopySubreadAlignments(startIndex);
for(int alignmentIndex = 0; alignmentIndex < int(selectedAlignmentPtrs.size());
alignmentIndex++) {
FlankTAlignedSeq(selectedAlignmentPtrs[alignmentIndex],
seqdb, genome, params.flankSize);
}
for (int intvIndex = 0; intvIndex < int(subreadIntervals.size()); intvIndex++) {
if (intvIndex == startIndex) continue;
int passDirection = subreadDirections[intvIndex];
int passStartBase = subreadIntervals[intvIndex].start;
int passNumBases = subreadIntervals[intvIndex].end - passStartBase;
if (passNumBases <= params.minReadLength) {continue;}
mapData->metrics.numReads++;
SMRTSequence subread;
subread.ReferenceSubstring(smrtRead, passStartBase, passNumBases);
subread.CopyTitle(smrtRead.title);
// The unrolled alignment should be relative to the entire read.
if (params.clipping == SAMOutput::subread) {
SMRTSequence maskedSubread;
MakeSubreadOfInterval(maskedSubread, smrtRead,
subreadIntervals[intvIndex], params);
allReadAlignments.SetSequence(intvIndex, maskedSubread);
maskedSubread.Free();
} else {
allReadAlignments.SetSequence(intvIndex, smrtRead);
}
for (size_t alnIndex = 0; alnIndex < selectedAlignmentPtrs.size(); alnIndex++) {
T_AlignmentCandidate * alignment = selectedAlignmentPtrs[alnIndex];
if (alignment->score > params.maxScore) break;
AlignSubreadToAlignmentTarget(allReadAlignments,
subread,
smrtRead,
alignment,
passDirection,
subreadIntervals[intvIndex],
intvIndex,
params, mappingBuffers, threadOut);
if (params.concordantAlignBothDirections) {
AlignSubreadToAlignmentTarget(allReadAlignments,
subread,
smrtRead,
alignment,
((passDirection==0)?1:0),
subreadIntervals[intvIndex],
intvIndex,
params, mappingBuffers, threadOut);
}
} // End of aligning this subread to each selected alignment.
subread.Free();
} // End of aligning each subread to where the template subread aligned to.
for(size_t alignmentIndex = 0; alignmentIndex < selectedAlignmentPtrs.size();
alignmentIndex++) {
if (selectedAlignmentPtrs[alignmentIndex])
delete selectedAlignmentPtrs[alignmentIndex];
}
} // End of if startIndex >= 0 and < subreadAlignments.size()
} // End of if params.concordant
}
//
// invoked for mapping entire ZMW as a single entity
// either for CCS reads : all subreads of a ZMW collapsed/merged into a single read
// or Polymerase reads : all subreads of a ZMW stitched into a single read
//
void MapReadsCCS(MappingData<T_SuffixArray, T_GenomeSequence, T_Tuple> *mapData,
MappingBuffers & mappingBuffers,
SMRTSequence & smrtRead,
SMRTSequence & smrtReadRC,
CCSSequence & ccsRead,
const bool readIsCCS,
MappingParameters & params,
const int & associatedRandInt,
ReadAlignments & allReadAlignments,
ofstream & threadOut)
{
DNASuffixArray sarray;
TupleCountTable<T_GenomeSequence, DNATuple> ct;
SequenceIndexDatabase<FASTQSequence> seqdb;
T_GenomeSequence genome;
BWT *bwtPtr;
mapData->ShallowCopySuffixArray(sarray);
mapData->ShallowCopyReferenceSequence(genome);
mapData->ShallowCopySequenceIndexDatabase(seqdb);
mapData->ShallowCopyTupleCountTable(ct);
bwtPtr = mapData->bwtPtr;
SeqBoundaryFtr<FASTQSequence> seqBoundary(&seqdb);
//
// The read must be mapped as a whole, even if it contains subreads.
//
vector<T_AlignmentCandidate*> alignmentPtrs;
mapData->metrics.numReads++;
smrtRead.SubreadStart(0).SubreadEnd(smrtRead.length);
smrtReadRC.SubreadStart(0).SubreadEnd(smrtRead.length);
MapRead(smrtRead, smrtReadRC,
genome, sarray, *bwtPtr, seqBoundary, ct, seqdb, params, mapData->metrics,
alignmentPtrs, mappingBuffers, mapData, semaphores);
//
// Store the mapping quality values.
//
if (alignmentPtrs.size() > 0 and
alignmentPtrs[0]->score < params.maxScore and
params.storeMapQV) {
StoreMapQVs(smrtRead, alignmentPtrs, params);
}
//
// Select de novo ccs-reference alignments for subreads to align to.
//
vector<T_AlignmentCandidate*> selectedAlignmentPtrs =
SelectAlignmentsToPrint(alignmentPtrs, params, associatedRandInt);
//
// Just one sequence is aligned. There is one primary hit, and
// all other are secondary.
//
//
// Here unrolled reads are aligned
//
if (readIsCCS == false or params.useCcsOnly) {
// if -noSplitSubreads or -useccsdenovo.
//
// Record some information for proper SAM Annotation.
//
allReadAlignments.Resize(1);
allReadAlignments.AddAlignmentsForSeq(0, selectedAlignmentPtrs);
if (params.useCcsOnly) {
allReadAlignments.alignMode = CCSDeNovo;
}
else {
allReadAlignments.alignMode = Fullread;
}
allReadAlignments.SetSequence(0, smrtRead);
}
//
// Here CCS reads are aligned
//
else if (readIsCCS) { // if -useccsall or -useccs
// Flank alignment candidates to both ends.
for(size_t alignmentIndex = 0; alignmentIndex < selectedAlignmentPtrs.size();
alignmentIndex++) {
FlankTAlignedSeq(selectedAlignmentPtrs[alignmentIndex],
seqdb, genome, params.flankSize);
}
//
// Align the ccs subread to where the denovo sequence mapped (explode).
//
CCSIterator ccsIterator;
FragmentCCSIterator fragmentCCSIterator;
CCSIterator *subreadIterator;
//
// Choose a different iterator over subreads depending on the
// alignment mode. When the mode is allpass, include the
// framgents that are not necessarily full pass.
//
if (params.useAllSubreadsInCcs) {
//
// Use all subreads even if they are not full pass
fragmentCCSIterator.Initialize(&ccsRead, mapData->regionTablePtr);
subreadIterator = &fragmentCCSIterator;
allReadAlignments.alignMode = CCSAllPass;
}
else {
// Use only full pass reads.
ccsIterator.Initialize(&ccsRead);
subreadIterator = &ccsIterator;
allReadAlignments.alignMode = CCSFullPass;
}
allReadAlignments.Resize(subreadIterator->GetNumPasses());
int passDirection, passStartBase, passNumBases;
SMRTSequence subread;
//
// The read was previously set to the smrtRead, which was the
// de novo ccs sequence. Since the alignments of exploded
// reads are reported, the unrolled read should be used as the
// reference when printing.
//
allReadAlignments.read = ccsRead.unrolledRead;
subreadIterator->Reset();
int subreadIndex;
//
// Realign all subreads to selected reference locations.
//
for (subreadIndex = 0; subreadIndex < subreadIterator->GetNumPasses(); subreadIndex++) {
int retval = subreadIterator->GetNext(passDirection, passStartBase, passNumBases);
assert(retval == 1);
if (passNumBases <= params.minReadLength) { continue; }
ReadInterval subreadInterval(passStartBase, passStartBase + passNumBases);
subread.ReferenceSubstring(ccsRead.unrolledRead, passStartBase, passNumBases-1);
subread.CopyTitle(ccsRead.title);
// The unrolled alignment should be relative to the entire read.
allReadAlignments.SetSequence(subreadIndex, ccsRead.unrolledRead);
//
// Align this subread to all the positions that the de novo
// sequence has aligned to.
//
for (size_t alignmentIndex = 0; alignmentIndex < selectedAlignmentPtrs.size(); alignmentIndex++) {
T_AlignmentCandidate *alignment = selectedAlignmentPtrs[alignmentIndex];
if (alignment->score > params.maxScore) break;
AlignSubreadToAlignmentTarget(allReadAlignments,
subread, ccsRead.unrolledRead,
alignment,
passDirection,
subreadInterval,
subreadIndex,
params, mappingBuffers, threadOut);
} // End of aligning this subread to where the de novo ccs has aligned to.
subread.Free();
} // End of alignining all subreads to where the de novo ccs has aligned to.
} // End of if readIsCCS and !params.useCcsOnly
// Fix for memory leakage due to undeleted Alignment Candidate objectts not selected
// for printing
// delete all AC which are in complement of SelectedAlignmemntPtrs vector
// namely (SelectedAlignmentPtrs/alignmentPtrs)
for (size_t ii = 0; ii < alignmentPtrs.size(); ii++)
{
int found =0;
for (size_t jj = 0; jj < selectedAlignmentPtrs.size(); jj++)
{
if (alignmentPtrs[ii] == selectedAlignmentPtrs[jj] )
{
found = 1;
break;
}
}
if (found == 0) delete alignmentPtrs[ii];
}
}
void MapReads(MappingData<T_SuffixArray, T_GenomeSequence, T_Tuple> *mapData)
{
//
// Step 1, initialize local pointers to map data
// for programming shorthand.
//
MappingParameters params = mapData->params;
DNASuffixArray sarray;
TupleCountTable<T_GenomeSequence, DNATuple> ct;
SequenceIndexDatabase<FASTQSequence> seqdb;
T_GenomeSequence genome;
mapData->ShallowCopySuffixArray(sarray);
mapData->ShallowCopyReferenceSequence(genome);
mapData->ShallowCopySequenceIndexDatabase(seqdb);
mapData->ShallowCopyTupleCountTable(ct);
SeqBoundaryFtr<FASTQSequence> seqBoundary(&seqdb);
int numAligned = 0;
SMRTSequence smrtRead, smrtReadRC;
SMRTSequence unrolledReadRC;
CCSSequence ccsRead;
// Print verbose logging to pid.threadid.log for each thread.
ofstream threadOut;
if (params.verbosity >= 3) {
stringstream ss;
ss << getpid() << "." << pthread_self();
string threadLogFileName = ss.str() + ".log";
threadOut.open(threadLogFileName.c_str(), ios::out|ios::app);
}
//
// Reuse the following buffers during alignment. Since these keep
// storage contiguous, hopefully this will decrease memory
// fragmentation.
//
MappingBuffers mappingBuffers;
while (true) {
// Fetch reads from a zmw
bool readIsCCS = false;
AlignmentContext alignmentContext;
// Associate each sequence to read in with a determined random int.
int associatedRandInt = 0;
bool stop = false;
vector<SMRTSequence> subreads;
bool readsOK = FetchReads(mapData->reader, mapData->regionTablePtr,
smrtRead, ccsRead, subreads,
params, readIsCCS,
alignmentContext.readGroupId,
associatedRandInt, stop);
if (stop) break;
if (not readsOK) continue;
if (params.verbosity > 1) {
cout << "aligning read: " << endl;
smrtRead.PrintSeq(cout);
}
smrtRead.MakeRC(smrtReadRC);
// important
// 1. CCS and unrolled mode are mutually exclusive
// 2. Reverse Complement Read is generated fort CCS only
//
if (readIsCCS) {
ccsRead.unrolledRead.MakeRC(unrolledReadRC);
}
//
// When aligning subreads separately, iterate over each subread, and
// print the alignments for these.
//
ReadAlignments allReadAlignments;
allReadAlignments.read = smrtRead;
// currently 3 ways of mapping
// regular, CCS , and Polymerase (unrolled)
//
// for regular subreads MapReadsNonCCS
// for mapping ZMW as a whole (CCS or Polymerase) MapReadsCCS
// For the future , change the name of functions to be more desriptive
// noSplitSubreads is in essense unrolled - Polymerase read mode
//
if (readIsCCS == false and params.mapSubreadsSeparately) {
// (not readIsCCS and not -noSplitSubreads)
MapReadsNonCCS(mapData, mappingBuffers,
smrtRead, smrtReadRC, subreads,
params, associatedRandInt,
allReadAlignments, threadOut);
} // End of if (readIsCCS == false and params.mapSubreadsSeparately).
else { // if (readIsCCS or (not readIsCCS and -noSplitSubreads) )
MapReadsCCS(mapData, mappingBuffers,
smrtRead, smrtReadRC, ccsRead,
readIsCCS, params, associatedRandInt,
allReadAlignments, threadOut);
} // End of if not (readIsCCS == false and params.mapSubreadsSeparately)
PrintAllReadAlignments(allReadAlignments, alignmentContext,
*mapData->outFilePtr,
*mapData->unalignedFilePtr,
params,
subreads,
#ifdef USE_PBBAM
bamWriterPtr,
#endif
semaphores);
allReadAlignments.Clear();
smrtReadRC.Free();
smrtRead.Free();
if (readIsCCS) {
ccsRead.Free();
unrolledReadRC.Free();
}
numAligned++;
if(numAligned % 100 == 0) {
mappingBuffers.Reset();
}
} // End of while (true).
smrtRead.Free();
smrtReadRC.Free();
unrolledReadRC.Free();
ccsRead.Free();
if (params.nProc > 1) {
#ifdef __APPLE__
sem_wait(semaphores.reader);
sem_post(semaphores.reader);
#else
sem_wait(&semaphores.reader);
sem_post(&semaphores.reader);
#endif
}
if (params.nProc > 1) {
pthread_exit(NULL);
}
threadOut.close();
}
int main(int argc, char* argv[]) {
//
// Configure parameters for refining alignments.
//
MappingParameters params;
CommandLineParser clp;
clp.SetHelp(BlasrHelp(params));
clp.SetConciseHelp(BlasrConciseHelp());
clp.SetProgramSummary(BlasrSummaryHelp());
clp.SetProgramName("blasr");
clp.SetVersion(GetVersion());
// Register Blasr options.
RegisterBlasrOptions(clp, params);
// Parse command line args.
clp.ParseCommandLine(argc, argv, params.readsFileNames);
string commandLine;
clp.CommandLineToString(argc, argv, commandLine);
if (params.printVerboseHelp) {
cout << BlasrHelp(params) << endl;
exit(0); // Not a failure.
}
if (params.printDiscussion) {
cout << BlasrDiscussion();
exit(0); // Not a failure.
}
if (argc < 3) {
cout << BlasrConciseHelp();
exit(1); // A failure.
}
int a, b;
for (a = 0; a < 5; a++ ) {
for (b = 0; b < 5; b++ ){
if (a != b) {
SMRTDistanceMatrix[a][b] += params.mismatch;
}
else {
SMRTDistanceMatrix[a][b] += params.match;
}
}
}
if (params.scoreMatrixString != "") {
if (StringToScoreMatrix(params.scoreMatrixString, SMRTDistanceMatrix) == false) {
cout << "ERROR. The string " << endl
<< params.scoreMatrixString << endl
<< "is not a valid format. It should be a quoted, space separated string of " << endl
<< "integer values. The matrix: " << endl
<< " A C G T N" << endl
<< " A 1 2 3 4 5" << endl
<< " C 6 7 8 9 10" << endl
<< " G 11 12 13 14 15" << endl
<< " T 16 17 18 19 20" << endl
<< " N 21 22 23 24 25" << endl
<< " should be specified as \"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\"" << endl;
exit(1);
}
}
cerr << "[INFO] " << GetTimestamp() << " [blasr] started." << endl;
params.MakeSane();
//
// The random number generator is used for subsampling for debugging
// and testing consensus and selecting hits when hit policy is random
// or randombest.
//
if (params.useRandomSeed == true) {
InitializeRandomGenerator(params.randomSeed);
}
else {
InitializeRandomGeneratorWithTime();
}
//
// Various aspects of timing are stored here. However this isn't
// quite finished.
//
MappingMetrics metrics;
ofstream fullMetricsFile;
if (params.fullMetricsFileName != "") {
CrucialOpen(params.fullMetricsFileName, fullMetricsFile, std::ios::out);
metrics.SetStoreList();
}
//
// If reading a separate region table, there is a 1-1 correspondence
// between region table and bas file.
//
if (params.readSeparateRegionTable) {
if (FileOfFileNames::IsFOFN(params.regionTableFileName)) {
FileOfFileNames::FOFNToList(params.regionTableFileName, params.regionTableFileNames);
}
else {
params.regionTableFileNames.push_back(params.regionTableFileName);
}
}
if (params.regionTableFileNames.size() != 0 and
params.regionTableFileNames.size() != params.queryFileNames.size()) {
cout << "Error, there are not the same number of region table files as input files." << endl;
exit(1);
}
// If reading a separate ccs fofn, there is a 1-1 corresponence
// between ccs fofn and base file.
if (params.readSeparateCcsFofn) {
if (FileOfFileNames::IsFOFN(params.ccsFofnFileName)) {
FileOfFileNames::FOFNToList(params.ccsFofnFileName, params.ccsFofnFileNames);
}
else {
params.ccsFofnFileNames.push_back(params.ccsFofnFileName);
}
}
if (params.ccsFofnFileNames.size() != 0 and
params.ccsFofnFileNames.size() != params.queryFileNames.size()) {
cout << "Error, there are not the same number of ccs files as input files." << endl;
exit(1);
}
SequenceIndexDatabase<FASTASequence> seqdb;
SeqBoundaryFtr<FASTASequence> seqBoundary(&seqdb);
//
// Initialize the sequence index database if it used. If it is not
// specified, it is initialized by default when reading a multiFASTA
// file.
//
if (params.useSeqDB) {
ifstream seqdbin;
CrucialOpen(params.seqDBName, seqdbin);
seqdb.ReadDatabase(seqdbin);
}
//
// Make sure the reads file exists and can be opened before
// trying to read any of the larger data structures.
//
FASTASequence fastaGenome;
T_Sequence genome;
FASTAReader genomeReader;
//
// The genome is in normal FASTA, or condensed (lossy homopolymer->unipolymer)
// format. Both may be read in using a FASTA reader.
//
if (!genomeReader.Init(params.genomeFileName)) {
cout << "Could not open genome file " << params.genomeFileName << endl;
exit(1);
}
if (params.printSAM or params.printBAM) {
genomeReader.computeMD5 = true;
}
//
// If no sequence title database is supplied, initialize one when
// reading in the reference, and consider a seqdb to be present.
//
if (!params.useSeqDB) {
genomeReader.ReadAllSequencesIntoOne(fastaGenome, &seqdb);
params.useSeqDB = true;
}
else {
genomeReader.ReadAllSequencesIntoOne(fastaGenome);
}
genomeReader.Close();
//
// The genome may have extra spaces in the fasta name. Get rid of those.
//
for (int t = 0; t < fastaGenome.titleLength; t++ ){
if (fastaGenome.title[t] == ' ') {
fastaGenome.titleLength = t;
fastaGenome.title[t] = '\0';
break;
}
}
genome.seq = fastaGenome.seq;
genome.length = fastaGenome.length;
genome.title = fastaGenome.title;
genome.deleteOnExit = false;
genome.titleLength = fastaGenome.titleLength;
genome.ToUpper();
DNASuffixArray sarray;
TupleCountTable<T_GenomeSequence, DNATuple> ct;
ofstream outFile;
outFile.exceptions(ostream::failbit);
ofstream unalignedOutFile;
BWT bwt;
if (params.useBwt) {
if (bwt.Read(params.bwtFileName) == 0) {
cout << "ERROR! Could not read the BWT file. " << params.bwtFileName << endl;
exit(1);
}
}
else {
if (!params.useSuffixArray) {
//
// There was no explicit specification of a suffix
// array on the command line, so build it on the fly here.
//
genome.ToThreeBit();
vector<int> alphabet;
sarray.InitThreeBitDNAAlphabet(alphabet);
sarray.LarssonBuildSuffixArray(genome.seq, genome.length, alphabet);
if (params.minMatchLength > 0) {
if (params.anchorParameters.useLookupTable == true) {
if (params.lookupTableLength > params.minMatchLength) {
params.lookupTableLength = params.minMatchLength;
}
sarray.BuildLookupTable(genome.seq, genome.length, params.lookupTableLength);
}
}
genome.ConvertThreeBitToAscii();
params.useSuffixArray = 1;
}
else if (params.useSuffixArray) {
if (sarray.Read(params.suffixArrayFileName)) {
if (params.minMatchLength != 0) {
params.listTupleSize = min(8, params.minMatchLength);
}
else {
params.listTupleSize = sarray.lookupPrefixLength;
}
if (params.minMatchLength < int(sarray.lookupPrefixLength)) {
cerr << "WARNING. The value of -minMatch " << params.minMatchLength << " is less than the smallest searched length of " << sarray.lookupPrefixLength << ". Setting -minMatch to " << sarray.lookupPrefixLength << "." << endl;
params.minMatchLength = sarray.lookupPrefixLength;
}
}
else {
cout << "ERROR. " << params.suffixArrayFileName << " is not a valid suffix array. " << endl
<< " Make sure it is generated with the latest version of sawriter." << endl;
exit(1);
}
}
}
if (params.minMatchLength < int(sarray.lookupPrefixLength)) {
cerr << "WARNING. The value of -minMatch " << params.minMatchLength << " is less than the smallest searched length of " << sarray.lookupPrefixLength << ". Setting -minMatch to " << sarray.lookupPrefixLength << "." << endl;
params.minMatchLength = sarray.lookupPrefixLength;
}
//
// It is required to have a tuple count table
// for estimating the background frequencies
// for word matching.
// If one is specified on the command line, simply read
// it in. If not, this is operating under the mode
// that everything is computed from scratch.
//
TupleMetrics saLookupTupleMetrics;
if (params.useCountTable) {
ifstream ctIn;
CrucialOpen(params.countTableName, ctIn, std::ios::in | std::ios::binary);
ct.Read(ctIn);
saLookupTupleMetrics = ct.tm;
} else {
saLookupTupleMetrics.Initialize(params.lookupTableLength);
ct.InitCountTable(saLookupTupleMetrics);
ct.AddSequenceTupleCountsLR(genome);
}
TitleTable titleTable;
if (params.useTitleTable) {
ofstream titleTableOut;
CrucialOpen(params.titleTableName, titleTableOut);
//
// When using a sequence index database, the title table is simply copied
// from the sequencedb.
//
if (params.useSeqDB) {
titleTable.Copy(seqdb.names, seqdb.nSeqPos-1);
titleTable.ResetTableToIntegers(seqdb.names, seqdb.nameLengths, seqdb.nSeqPos-1);
}
else {
//
// No seqdb, so there is just one sequence. Still the user specified a title
// table, so just the first sequence in the fasta file should be used.
//
titleTable.Copy(&fastaGenome.title, 1);
titleTable.ResetTableToIntegers(&genome.title, &genome.titleLength, 1);
fastaGenome.titleLength = strlen(genome.title);
}
titleTable.Write(titleTableOut);
}
else {
if (params.useSeqDB) {
//
// When using a sequence index database, but not the titleTable,
// it is necessary to truncate the titles at the first space to
// be compatible with the way other alignment programs interpret
// fasta titles. When printing the title table, there is all
// sorts of extra storage space, so the full line is stored.
//
seqdb.SequenceTitleLinesToNames();
}
}
ostream *outFilePtr = &cout;
ofstream outFileStrm;
ofstream unalignedFile;
ostream *unalignedFilePtr = NULL;
ofstream metricsOut, lcpBoundsOut;
ofstream anchorFileStrm;
ofstream clusterOut, *clusterOutPtr;
if (params.anchorFileName != "") {
CrucialOpen(params.anchorFileName, anchorFileStrm, std::ios::out);
}
if (params.clusterFileName != "") {
CrucialOpen(params.clusterFileName, clusterOut, std::ios::out);
clusterOutPtr = &clusterOut;
clusterOut << "total_size p_value n_anchors read_length align_score read_accuracy anchor_probability min_exp_anchors seq_length" << endl;
}
else {
clusterOutPtr = NULL;
}
if (params.outFileName != "") {
if (not params.printBAM) {
CrucialOpen(params.outFileName, outFileStrm, std::ios::out);
outFilePtr = &outFileStrm;
} // otherwise, use bamWriter and initialize it later
}
if (params.printHeader) {
switch(params.printFormat) {
case(SummaryPrint):
SummaryOutput::PrintHeader(*outFilePtr);
break;
case(Interval):
IntervalOutput::PrintHeader(*outFilePtr);
break;
case(CompareSequencesParsable):
CompareSequencesOutput::PrintHeader(*outFilePtr);
break;
}
}
if (params.printUnaligned == true) {
CrucialOpen(params.unalignedFileName, unalignedFile, std::ios::out);
unalignedFilePtr = &unalignedFile;
}
if (params.metricsFileName != "") {
CrucialOpen(params.metricsFileName, metricsOut);
}
if (params.lcpBoundsFileName != "") {
CrucialOpen(params.lcpBoundsFileName, lcpBoundsOut);
// lcpBoundsOut << "pos depth width lnwidth" << endl;
}
//
// Configure the mapping database.
//
MappingData<T_SuffixArray, T_GenomeSequence, T_Tuple> *mapdb = new MappingData<T_SuffixArray, T_GenomeSequence, T_Tuple>[params.nProc];
int procIndex;
pthread_attr_t *threadAttr = new pthread_attr_t[params.nProc];
// MappingSemaphores semaphores;
//
// When there are multiple processes running along, sometimes there
// are semaphores to worry about.
//
if (params.nProc > 1) {
semaphores.InitializeAll();
}
for (procIndex = 0; procIndex < params.nProc; procIndex++ ){
pthread_attr_init(&threadAttr[procIndex]);
}
//
// Start the mapping jobs.
//
if (params.subsample < 1) {
InitializeRandomGeneratorWithTime();
reader = new ReaderAgglomerate(params.subsample);
}
else {
reader = new ReaderAgglomerate(params.startRead, params.stride);
}
// In case the input is fasta, make all bases in upper case.
reader->SetToUpper();
regionTableReader = new HDFRegionTableReader;
RegionTable regionTable;
//
// Store lists of how long it took to map each read.
//
metrics.clocks.SetStoreList(true);
if (params.useCcs) {
reader->UseCCS();
}
string commandLineString; // Restore command.
clp.CommandLineToString(argc, argv, commandLineString);
if (params.printSAM or params.printBAM) {
string so = "UNKNOWN"; // sorting order;
string version = GetVersion(); //blasr version;
SAMHeaderPrinter shp(so, seqdb,
params.queryFileNames, params.queryReadType,
params.samQVList, "BLASR", version,
commandLineString);
string headerString = shp.ToString();// SAM/BAM header
if (params.printSAM) {
// this is not going to be executed since sam is printed via bam
*outFilePtr << headerString;
} else if (params.printBAM) {
// here both bam and sam are handled
#ifdef USE_PBBAM
PacBio::BAM::BamHeader header = PacBio::BAM::BamHeader(headerString);
// Create bam header
// Both file name and SAMHeader are required in order to create a BamWriter.
// sam_via_bam changes
if (params.sam_via_bam)
{
bamWriterPtr = new PacBio::BAM::SamWriter(params.outFileName, header);
}
else
{
bamWriterPtr = new PacBio::BAM::BamWriter(params.outFileName, header);
}
#else
REQUIRE_PBBAM_ERROR();
#endif
}
}
for (size_t readsFileIndex = 0; readsFileIndex < params.queryFileNames.size(); readsFileIndex++ ){
params.readsFileIndex = readsFileIndex;
//
// Configure the reader to use the correct read and region
// file names.
//
reader->SetReadFileName(params.queryFileNames[params.readsFileIndex]);
// if PBBAM , need to construct scrap file name and check if exist
//
// Initialize using already set file names.
//
// unrolled Need to pass unrolled option
// unrolled If not PBDATASET also need to construct scrap file name and
// test if it exists in the same directory, if not exit with error message
//
int initReturnValue;
if ( ( (reader->GetFileType() == FileType::PBDATASET) || (reader->GetFileType() == FileType::PBBAM)) and not params.mapSubreadsSeparately) {
if ( reader->GetFileType() == FileType::PBBAM ) {
reader->SetScrapsFileName(params.scrapsFileNames[params.readsFileIndex]);
}
initReturnValue = reader->Initialize(true);
}
else {
initReturnValue = reader->Initialize();
}
if (initReturnValue <= 0) {
cerr << "WARNING! Could not open file " << params.queryFileNames[params.readsFileIndex] << endl;
continue;
}
// Check whether use ccs only.
if (reader->GetFileType() == FileType::HDFCCSONLY) {
params.useAllSubreadsInCcs = false;
params.useCcs = params.useCcsOnly = true;
}
string changeListIdString;
reader->hdfBasReader.GetChangeListID(changeListIdString);
ChangeListID changeListId(changeListIdString);
params.qvScaleType = DetermineQVScaleFromChangeListID(changeListId);
if (reader->FileHasZMWInformation() and params.useRegionTable) {
if (params.readSeparateRegionTable) {
if (regionTableReader->Initialize(params.regionTableFileNames[params.readsFileIndex]) == 0) {
cout << "ERROR! Could not read the region table " << params.regionTableFileNames[params.readsFileIndex] <<endl;
exit(1);
}
params.useRegionTable = true;
}
else {
if (reader->HasRegionTable()) {
if (regionTableReader->Initialize(params.queryFileNames[params.readsFileIndex]) == 0) {
cout << "ERROR! Could not read the region table " << params.queryFileNames[params.readsFileIndex] <<endl;
exit(1);
}
params.useRegionTable = true;
}
else {
params.useRegionTable = false;
}
}
}
else {
params.useRegionTable = false;
}
//
// Check to see if there is a region table. If there is a separate
// region table, use that (over the region table in the bas
// file). If there is a region table in the bas file, use that,
// without having to specify a region table on the command line.
//
if (params.useRegionTable) {
regionTable.Reset();
regionTableReader->ReadTable(regionTable);
regionTableReader->Close();
}
//
// Check to see if there is a separate ccs fofn. If there is a separate
// ccs fofn, use that over the one in the bas file.
//
//if (params.readSeparateCcsFofn and params.useCcs) {
// if (reader->SetCCS(params.ccsFofnFileNames[params.readsFileIndex]) == 0) {
// cout << "ERROR! Could not read the ccs file "
// << params.ccsFofnFileNames[params.readsFileIndex] << endl;
// exit(1);
// }
// }
if (reader->GetFileType() != FileType::HDFCCS and
reader->GetFileType() != FileType::HDFBase and
reader->GetFileType() != FileType::HDFPulse and
reader->GetFileType() != FileType::PBBAM and
reader->GetFileType() != FileType::PBDATASET and
params.concordant) {
cerr << "WARNING! Option concordant is only enabled when "
<< "input reads are in PacBio bax/pls.h5, bam or "
<< "dataset xml format." << endl;
params.concordant = false;
}
#ifdef USE_GOOGLE_PROFILER
char *profileFileName = getenv("CPUPROFILE");
if (profileFileName != NULL) {
ProfilerStart(profileFileName);
}
else {
ProfilerStart("google_profile.txt");
}
#endif
assert (initReturnValue > 0);
if (params.nProc == 1) {
mapdb[0].Initialize(&sarray, &genome, &seqdb, &ct, params, reader, ®ionTable,
outFilePtr, unalignedFilePtr, &anchorFileStrm, clusterOutPtr);
mapdb[0].bwtPtr = &bwt;
if (params.fullMetricsFileName != "") {
mapdb[0].metrics.SetStoreList(true);
}
if (params.lcpBoundsFileName != "") {
mapdb[0].lcpBoundsOutPtr = &lcpBoundsOut;
}
else {
mapdb[0].lcpBoundsOutPtr = NULL;
}
MapReads(&mapdb[0]);
metrics.Collect(mapdb[0].metrics);
}
else {
pthread_t *threads = new pthread_t[params.nProc];
for (procIndex = 0; procIndex < params.nProc; procIndex++ ){
//
// Initialize thread-specific parameters.
//
mapdb[procIndex].Initialize(&sarray, &genome, &seqdb, &ct, params, reader, ®ionTable,
outFilePtr, unalignedFilePtr, &anchorFileStrm, clusterOutPtr);
mapdb[procIndex].bwtPtr = &bwt;
if (params.fullMetricsFileName != "") {
mapdb[procIndex].metrics.SetStoreList(true);
}
if (params.lcpBoundsFileName != "") {
mapdb[procIndex].lcpBoundsOutPtr = &lcpBoundsOut;
}
else {
mapdb[procIndex].lcpBoundsOutPtr = NULL;
}
if (params.outputByThread) {
ofstream *outPtr =new ofstream;
mapdb[procIndex].outFilePtr = outPtr;
stringstream outNameStream;
outNameStream << params.outFileName << "." << procIndex;
mapdb[procIndex].params.outFileName = outNameStream.str();
CrucialOpen(mapdb[procIndex].params.outFileName, *outPtr, std::ios::out);
}
pthread_create(&threads[procIndex], &threadAttr[procIndex], (void* (*)(void*))MapReads, &mapdb[procIndex]);
}
for (procIndex = 0; procIndex < params.nProc; procIndex++) {
pthread_join(threads[procIndex], NULL);
}
for (procIndex = 0; procIndex < params.nProc; procIndex++) {
metrics.Collect(mapdb[procIndex].metrics);
if (params.outputByThread) {
delete mapdb[procIndex].outFilePtr;
}
}
if (threads) {
delete threads;
threads = NULL;
}
}
reader->Close();
}
if (!reader) {delete reader; reader = NULL;}
fastaGenome.Free();
#ifdef USE_GOOGLE_PROFILER
ProfilerStop();
#endif
if (mapdb != NULL) {
delete[] mapdb;
}
if (threadAttr != NULL) {
delete[] threadAttr;
}
seqdb.FreeDatabase();
if (regionTableReader) {
delete regionTableReader;
}
if (params.metricsFileName != "") {
metrics.PrintSummary(metricsOut);
}
if (params.fullMetricsFileName != "") {
metrics.PrintFullList(fullMetricsFile);
}
if (params.outFileName != "") {
if (params.printBAM) {
#ifdef USE_PBBAM
assert(bamWriterPtr);
try {
if (!params.sam_via_bam) { // no need to flush for SAM , but need to understand why
bamWriterPtr->TryFlush();
}
delete bamWriterPtr;
bamWriterPtr = NULL;
} catch (std::exception e) {
cout << "Error, could not flush bam records to bam file." << endl;
exit(1);
}
#else
REQUIRE_PBBAM_ERROR();
#endif
} else {
outFileStrm.close();
}
}
cerr << "[INFO] " << GetTimestamp() << " [blasr] ended." << endl;
return 0;
}
|