/usr/include/pbseq/alignment/datastructures/alignment/AlignmentCandidate.hpp is in libblasr-dev 0~20161219-2.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 | #ifndef _ALIGNMENT_ALIGNMENT_CANDIDATE_HPP_
#define _ALIGNMENT_ALIGNMENT_CANDIDATE_HPP_
#include "Alignment.hpp"
// pbdata
#include "../../../pbdata/DNASequence.hpp"
#include "../../../pbdata/FASTQSequence.hpp"
template<typename T_TSequence=FASTASequence, typename T_QSequence=FASTASequence>
class AlignmentCandidate : public blasr::Alignment {
private:
void ReassignSequence(DNASequence &curSeq, bool curIsSubstring, DNASequence &newSeq) {
//
// If this sequence is in control of itself (it is not a substring
// of anoter sequence), it should be freed here to avoid memory
// leaks.
//
if (curIsSubstring == false) {
curSeq.Free();
}
curSeq.seq = newSeq.seq;
curSeq.length = newSeq.length;
}
void ReassignSequence(FASTQSequence &curSeq, bool curIsSubstring, FASTQSequence &newSeq) {
//
// Free the current sequence with the same rules as above.
//
if (curIsSubstring == false) {
curSeq.Free();
}
curSeq.ReferenceSubstring(newSeq, 0, newSeq.length);
}
// TryReadingQVs is a helper function for ReadOptionalQVs. It checks if the
// qvs that are supposed to be copied to a member of AlignmentCandidate are
// in fact empty. If so, then don't substr or copy anything
void TryReadingQVs(const std::string qvs, DNALength start, DNALength length,
std::string *memberQVs) {
if (qvs.size() == 0) {
memberQVs->clear();
} else {
*memberQVs = qvs.substr(start, length);
}
}
public:
T_TSequence tAlignedSeq;
T_QSequence qAlignedSeq;
std::string insertionQV, deletionQV, mergeQV, substitutionQV, deletionTag, substitutionTag;
std::vector<std::string> optionalQVNames;
DNALength tAlignedSeqPos, qAlignedSeqPos;
DNALength tAlignedSeqLength, qAlignedSeqLength;
float pvalVariance, weightVariance, pvalNStdDev, weightNStdDev;
int numSignificantClusters;
int readIndex;
//
// [q/t]IsSubstring refers to whether or not the text or query
// sequences are pointers into longer sequences. If they are,
// then reassigning the target/query sequences just means
// reassigning the seq and length values. If not, they occupy their
// own space, and should have the same lifetime as the alignment
// candidate object.
//
bool tIsSubstring, qIsSubstring;
std::string tTitle, qTitle;
float clusterScore, clusterWeight;
//
// For indexing into sequence index databases, tIndex stores which
// target this match is from.
//
int tIndex;
AlignmentCandidate&operator=(const AlignmentCandidate &rhs) {
tAlignedSeq = rhs.tAlignedSeq;
qAlignedSeq = rhs.qAlignedSeq;
tAlignedSeqPos = rhs.tAlignedSeqPos;
qAlignedSeqPos = rhs.qAlignedSeqPos;
tAlignedSeqLength = rhs.tAlignedSeqLength;
qAlignedSeqLength = rhs.qAlignedSeqLength;
readIndex = rhs.readIndex;
tIndex = rhs.tIndex;
mapQV = rhs.mapQV;
clusterScore = rhs.clusterScore;
clusterWeight = rhs.clusterWeight;
*((Alignment*)this) = ((Alignment&)rhs);
pvalVariance = rhs.pvalVariance;
pvalNStdDev = rhs.pvalNStdDev;
weightVariance=rhs.weightVariance;
weightNStdDev= rhs.weightNStdDev;
insertionQV = rhs.insertionQV;
deletionQV = rhs.deletionQV;
substitutionQV = rhs.substitutionQV;
mergeQV = rhs.mergeQV;
substitutionTag = rhs.substitutionTag;
deletionTag = rhs.deletionTag;
return *this;
}
AlignmentCandidate() {
/*
* The default configuration of an alignment candidate is to have
* the t and q sequences be substrings. This means that the
* position of the substrings starts at 0 (no offset into a longer
* string).
*/
tIsSubstring = true;
qIsSubstring = true;
tTitle = "";
qTitle = "";
tAlignedSeqPos = 0;
qAlignedSeqPos = 0;
tAlignedSeqLength = 0;
qAlignedSeqLength = 0;
tIndex = 0;
readIndex = 0;
mapQV = 50;
clusterScore = 0;
clusterWeight = 0;
numSignificantClusters = 0;
pvalVariance = pvalNStdDev = 0;
weightVariance = weightNStdDev = 0;
}
void Print(std::ostream & out = std::cout) {
out << "An AlignmentCandidate object (mapQV "
<< mapQV << ", clusterscore " << clusterScore
<< ", tTitle: " << tTitle << ", qTitle: " << qTitle
<< ")." << std::endl;
out << " query: " << qTitle << ", "
<< "qName: " << qName << ","
<< "qStrand: " << qStrand << ", "
<< "qPos: " << qPos << ", "
<< "qLen: " << qLength << ", "
<< "qAlignLength: " << qAlignLength << ", "
<< "qAlignedSeqPos:" << qAlignedSeqPos << ", "
<< "qAlignedSeqLen:" << qAlignedSeqLength << std::endl
<< " target: " << tTitle << ", "
<< "tName: " << tName << ","
<< "tStrand: " << tStrand << ", "
<< "tPos: " << tPos << ", "
<< "tLen: " << tLength << ", "
<< "tAlignLength: " << tAlignLength << ", "
<< "tAlignedSeqPos:" << tAlignedSeqPos << ", "
<< "tAlignedSeqLen:" << tAlignedSeqLength << std::endl;
tAlignedSeq.Print(out);
}
AlignmentCandidate(const AlignmentCandidate &rhs) {
*this = rhs;
}
DNALength GenomicTBegin() {
return tAlignedSeqPos + tPos;
}
DNALength GenomicTEnd() {
return tAlignedSeqPos + tPos + TEnd();
}
void GetQIntervalOnForwardStrand(int &qStart, int &qEnd) {
GetQInterval(qStart, qEnd, true);
}
void GetQInterval(int &qStart, int &qEnd, bool useForwardStrand=false) {
qStart = qEnd = 0;
if (blocks.size() == 0) { return; }
qStart = blocks[0].qPos + qAlignedSeqPos;
qEnd = QEnd() + qAlignedSeqPos;
if (useForwardStrand and qStrand == 1) {
int forQEnd, forQStart;
forQStart = qLength - qEnd;
forQEnd = qLength - qStart;
qStart = forQStart;
qEnd = forQEnd;
}
}
DNALength QAlignEnd() {
return QEnd() + qPos + qAlignedSeqPos;
}
DNALength QAlignStart() {
return qPos + qAlignedSeqPos;
}
DNALength TAlignStart() {
return tPos + tAlignedSeqPos;
}
// Synonyms for T/QStart
DNALength GetQBasesToStart() {
return qPos + qAlignedSeqPos;
}
DNALength GetTBasesToStart() {
return tPos + tAlignedSeqPos;
}
// ReadOptionalQVs populates the optional QV attributes of
// AlignmentCandidate with values read from a vector.
void ReadOptionalQVs(const std::vector<std::string>& optionalQVs,
DNALength start, DNALength length) {
TryReadingQVs(optionalQVs[0], start, length, &insertionQV);
TryReadingQVs(optionalQVs[1], start, length, &deletionQV);
TryReadingQVs(optionalQVs[2], start, length, &substitutionQV);
TryReadingQVs(optionalQVs[3], start, length, &mergeQV);
TryReadingQVs(optionalQVs[4], start, length, &substitutionTag);
TryReadingQVs(optionalQVs[5], start, length, &deletionTag);
}
// CopyQVs fills a vector with optional QV attributes.
void CopyQVs(std::vector<std::string> *optionalQVs) {
optionalQVNames.clear();
optionalQVs->clear();
optionalQVs->push_back(insertionQV);
optionalQVNames.push_back("InsertionQV");
optionalQVs->push_back(deletionQV);
optionalQVNames.push_back("DeletionQV");
optionalQVs->push_back(substitutionQV);
optionalQVNames.push_back("SubstitutionQV");
optionalQVs->push_back(mergeQV);
optionalQVNames.push_back("MergeQV");
optionalQVs->push_back(substitutionTag);
optionalQVNames.push_back("SubstitutionTag");
optionalQVs->push_back(deletionTag);
optionalQVNames.push_back("DeletionTag");
}
void AppendAlignment(AlignmentCandidate &next) {
//
// If the next alignment is empty, just return now.
//
if (next.blocks.size() == 0) {
return;
}
//
// It is necessary to determine how much after the first alignment
// the second alignment starts, in order to
assert(GetTBasesToStart() <= next.GetTBasesToStart());
assert(GetQBasesToStart() <= next.GetQBasesToStart());
assert(GetTBasesToStart() + TEnd() <= next.GetTBasesToStart());
assert(GetQBasesToStart() + QEnd() <= next.GetQBasesToStart());
//
// qOffset is the offset of the frame of reference for the 'next'
// alignment relative to this one. If the frame of reference is
// the same (qOffset == 0 and tOffset == 0), then the alignment
// blocks may simply be appended. If it is non zero, then the
// location in the query or target where the alignment has started
// is different, and the values of qPos or tPos need to be
// adjusted accordingly.
DNALength qOffset = next.qPos + next.qAlignedSeqPos - qPos - qAlignedSeqPos;
DNALength tOffset = next.tPos + next.tAlignedSeqPos - tPos - tAlignedSeqPos;
DNALength origQEnd = QEnd();
DNALength origTEnd = TEnd();
/* DNALength tGap = next.GetTBasesToStart() + next.blocks[0].tPos - (GetTBasesToStart() + TEnd());
DNALength qGap = next.GetQBasesToStart() + next.blocks[0].qPos - (GetQBasesToStart() + QEnd());
*/
DNALength tGap = next.GetTBasesToStart() - (GetTBasesToStart() + TEnd());
DNALength qGap = next.GetQBasesToStart() - (GetQBasesToStart() + QEnd());
//
if ( gaps.size() > 0 and next.gaps.size() > 0 ) {
//
// Determine the gap between the two alignments in order to assign
// the gap between them.
DNALength commonGap = 0;
DNALength gapDiff = 0;
if (tGap >= qGap) {
gapDiff = tGap - qGap;
commonGap = tGap - gapDiff;
tGap = gapDiff;
qGap = 0;
}
else {
gapDiff = qGap - tGap;
commonGap = qGap - gapDiff;
qGap = gapDiff;
tGap = 0;
}
if (commonGap > 0) {
// There is some portion of sequence between the two alignments
// that is a common gap. Add a block representing this.
blasr::Block block;
block.qPos = origQEnd;
block.tPos = origTEnd;
block.length = commonGap;
blocks.push_back(block);
blasr::GapList emptyGap;
gaps.push_back(emptyGap);
}
blasr::GapList endGapList;
//
// When gapDiff == 0, an empty list is appended.
//
if (next.gaps.size() > 0) {
//
// The first gap in the next alignment is already handled by
// the gap created with the endGap. So get rid of the first
// gaps.
// next.gaps[0].resize(0);
AppendAlignmentGaps(next);
}
}
//
// Finally append all the blocks.
//
AppendAlignmentBlocks(next, qOffset, tOffset);
}
void FreeSubsequences() {
if (tIsSubstring == false) {
tAlignedSeq.Free();
}
if (qIsSubstring == false) {
qAlignedSeq.Free();
}
}
void ReassignTSequence(DNASequence &newSeq) {
ReassignSequence(tAlignedSeq, tIsSubstring, newSeq);
}
template<typename T_Sequence>
void ReassignQSequence(T_Sequence &newSeq) {
ReassignSequence(qAlignedSeq, qIsSubstring, newSeq);
}
~AlignmentCandidate() {
qAlignedSeq.Free();
tAlignedSeq.Free();
}
};
//
// Define a default alignment candidate for aligning quality-sequence
// to a reference without quality.
//
typedef AlignmentCandidate<DNASequence,FASTQSequence> T_AlignmentCandidate;
class SortAlignmentPointersByScore {
public:
/// Sort AlignmentCandidate pointer by score, then by target position.
int operator()(T_AlignmentCandidate *lhs, T_AlignmentCandidate* rhs);
};
class SortAlignmentPointersByMapQV {
public:
/// Sort AlignmentCandidate pointer by mapQV, then by target position.
int operator()(T_AlignmentCandidate *lhs, T_AlignmentCandidate* rhs);
};
#endif // _ALIGNMENT_ALIGNMENT_CANDIDATE_HPP_
|