int searchTandemDuplications(ControlState& currentState, unsigned NumBoxes, const SearchWindow& window)
{
static int Count_TD = 0;
static int Count_TD_Plus = 0;
static int Count_TD_Minus = 0;
std::vector<unsigned> TD[NumBoxes];
//UserDefinedSettings* userSettings = UserDefinedSettings::Instance();
unsigned TempBoxIndex;
LOG_INFO(*logStream << "Searching tandem duplication events ... " << std::endl);
//std::cout << "std1" << std::endl;
for (unsigned ReadIndex = 0; ReadIndex < currentState.Reads_SR.size(); ReadIndex++) {
SPLIT_READ& currentRead = currentState.Reads_SR[ReadIndex];
//std::cout << "std1a" << std::endl;
if (currentRead.Used || currentRead.UP_Far.empty() || currentRead.FragName != currentRead.FarFragName) {
continue;
}
//std::cout << "std1b" << std::endl;
if (currentRead.MatchedD == Plus) {
//std::cout << "in TD plus" << std::endl;
for (short MAX_SNP_ERROR_index = 0; MAX_SNP_ERROR_index <= currentRead.getMAX_SNP_ERROR(); MAX_SNP_ERROR_index++) {
//std::cout << "std1c" << std::endl;
for (unsigned int CloseIndex = 0; CloseIndex < currentRead.UP_Close.size(); CloseIndex++) {
//std::cout << "std1d" << std::endl;
if (currentRead.Used /* || currentRead. BPLeft == 0*/) {
break;
}
if (currentRead.UP_Close[CloseIndex].Mismatches > MAX_SNP_ERROR_index) {
continue;
}
//std::cout << "std1e " << currentRead.UP_Far.size() << std::endl;
for (int FarIndex = currentRead.UP_Far.size() - 1; FarIndex >= 0; FarIndex--) {
//std::cout << "std1f" << std::endl;
if (currentRead.Used) {
break;
}
if (currentRead.UP_Far[FarIndex].Mismatches > MAX_SNP_ERROR_index) {
continue;
}
if (currentRead.UP_Far[FarIndex].Mismatches + currentRead.UP_Close[CloseIndex].Mismatches > MAX_SNP_ERROR_index) {
continue;
}
//std::cout << "std1g" << std::endl;
if (currentRead.UP_Far[FarIndex].Direction == Minus) {
if (currentRead.UP_Far[FarIndex].LengthStr + currentRead.UP_Close[CloseIndex].LengthStr == currentRead.getReadLength() &&
currentRead.UP_Far[FarIndex].AbsLoc + currentRead.UP_Far[FarIndex].LengthStr < currentRead.UP_Close[CloseIndex].AbsLoc &&
currentRead.UP_Far[FarIndex].AbsLoc + currentRead.UP_Close[CloseIndex].LengthStr < currentRead.UP_Close[CloseIndex].AbsLoc) {
currentRead.Right = currentRead.UP_Close[CloseIndex].AbsLoc - currentRead.UP_Close[CloseIndex].LengthStr + 1;
currentRead.Left = currentRead. UP_Far[FarIndex].AbsLoc + currentRead. UP_Far[FarIndex].LengthStr - 1;
currentRead.BP = currentRead.UP_Close[CloseIndex].LengthStr - 1;
currentRead.IndelSize = currentRead.UP_Close[CloseIndex].AbsLoc - currentRead. UP_Far[FarIndex].AbsLoc + 1;
currentRead.BPRight = currentRead.UP_Close[CloseIndex].AbsLoc - g_SpacerBeforeAfter;
currentRead.BPLeft = currentRead.UP_Far[FarIndex].AbsLoc - g_SpacerBeforeAfter;
if (currentRead. BPLeft == 0) {
continue;
}
LeftMostTD(currentState, currentRead, window);
if (readTransgressesBinBoundaries( currentRead, window.getEnd())) {
saveReadForNextCycle( currentRead, currentState.FutureReads_SR);
} else {
if (readInSpecifiedRegion( currentRead, userSettings->getRegion())) {
TempBoxIndex = (int) (currentRead. BPLeft) / BoxSize;
if (TempBoxIndex < NumBoxes) {
//std::cout << currentRead << std::endl;
TD[TempBoxIndex]. push_back(ReadIndex);
currentRead.Used = true;
Count_TD++;
Count_TD_Plus++;
}
}
}
}
}
}
}
}
} else if (currentRead.MatchedD == Minus) {
//std::cout << "in Minus" << std::endl;
for (short MAX_SNP_ERROR_index = 0; MAX_SNP_ERROR_index <= currentRead.getMAX_SNP_ERROR(); MAX_SNP_ERROR_index++) {
//std::cout << "in Minus 1" << std::endl;
for (int CloseIndex = currentRead.UP_Close.size() - 1; CloseIndex >= 0; CloseIndex--) {
//std::cout << "in Minus 2" << std::endl;
if (currentRead.Used /*|| currentRead. BPLeft == 0*/) {
break;
}
if (currentRead.UP_Close[CloseIndex].Mismatches > MAX_SNP_ERROR_index) {
continue;
}
//std::cout << "in Minus 3" << std::endl;
for (int FarIndex = 0; FarIndex < (int) currentRead.UP_Far.size(); FarIndex++) {
if (currentRead.Used) {
break;
}
if (currentRead.UP_Far[FarIndex].Mismatches > MAX_SNP_ERROR_index) {
continue;
}
if (currentRead.UP_Far[FarIndex].Mismatches + currentRead.UP_Close[CloseIndex].Mismatches > MAX_SNP_ERROR_index) {
continue;
}
if (currentRead.UP_Far[FarIndex]. Direction == Plus) {
//std::cout << "BPLeft" << currentRead. BPLeft << std::endl;
if (currentRead.UP_Close[CloseIndex].LengthStr + currentRead.UP_Far[FarIndex].LengthStr == currentRead.getReadLength() &&
currentRead.UP_Close[CloseIndex].AbsLoc + currentRead.UP_Close[CloseIndex].LengthStr < currentRead.UP_Far[FarIndex]. AbsLoc &&
currentRead.UP_Close[CloseIndex].AbsLoc + currentRead.UP_Far[FarIndex].LengthStr < currentRead.UP_Far[FarIndex]. AbsLoc) {
currentRead.Right = currentRead. UP_Far[FarIndex].AbsLoc - currentRead. UP_Far[FarIndex].LengthStr + 1;
currentRead.Left = currentRead.UP_Close[CloseIndex].AbsLoc + currentRead.UP_Close[CloseIndex].LengthStr - 1;
currentRead.BP = currentRead. UP_Far[FarIndex].LengthStr - 1;
currentRead.IndelSize = currentRead. UP_Far[FarIndex].AbsLoc - currentRead.UP_Close[CloseIndex].AbsLoc + 1;
currentRead.BPRight = currentRead.UP_Far[FarIndex].AbsLoc - g_SpacerBeforeAfter;
currentRead.BPLeft = currentRead.UP_Close[CloseIndex].AbsLoc - g_SpacerBeforeAfter;
//std::cout << "in Minus 4a" << std::endl;
if (currentRead. BPLeft == 0) {
continue;
}
LeftMostTD(currentState, currentRead, window);
//std::cout << "in Minus 4b" << std::endl;
if (readTransgressesBinBoundaries( currentRead, window.getEnd())) {
saveReadForNextCycle( currentRead, currentState.FutureReads_SR);
} else {
if (readInSpecifiedRegion( currentRead, userSettings->getRegion())) {
TempBoxIndex = (int) (currentRead. BPLeft) / BoxSize;
if (TempBoxIndex < NumBoxes) {
//std::cout << currentRead << std::endl;
TD[TempBoxIndex]. push_back(ReadIndex);
currentRead.Used = true;
Count_TD++;
Count_TD_Minus++;
}
}
}
}
}
}
//std::cout << "in Minus 4" << std::endl;
}
}
}
}
//std::cout << "std2" << std::endl;
LOG_INFO(*logStream << "Total: " << Count_TD << "\t+" << Count_TD_Plus << "\t-" << Count_TD_Minus << std::endl);
//std::cout << "TD 1" << std::endl;
std::ofstream TDOutf(userSettings->getTDOutputFilename().c_str(), std::ios::app);
SortAndOutputTandemDuplications(currentState, NumBoxes, window.getChromosome()->getSeq(), currentState.Reads_SR, TD, TDOutf, false);
//std::cout << "TD 2" << std::endl;
//std::cout << "std3" << std::endl;
for (unsigned int i = 0; i < NumBoxes; i++) {
TD[i].clear();
}
// std::cout << "std4" << std::endl;
return EXIT_SUCCESS;
}
int searchTandemDuplicationsNT(ControlState& currentState, unsigned NumBoxes, const SearchWindow& window)
{
static int Count_TD_NT = 0;
static int Count_TD_NT_Plus = 0;
static int Count_TD_NT_Minus = 0;
std::vector<unsigned> TD_NT[NumBoxes];
int CloseIndex = 0;
int FarIndex = 0;
//UserDefinedSettings* userSettings = UserDefinedSettings::Instance();
LOG_INFO(*logStream << "Searching tandem duplication events with non-template sequence ... " << std::endl);
for (unsigned ReadIndex = 0; ReadIndex < currentState.Reads_SR.size(); ReadIndex++) {
SPLIT_READ& currentRead = currentState.Reads_SR[ReadIndex];
if (currentRead.Used || currentRead.UP_Far.empty() || currentRead.FragName != currentRead.FarFragName) {
continue;
}
CloseIndex = currentRead.UP_Close.size() - 1;
FarIndex = currentRead.UP_Far.size() - 1;
if (currentRead.UP_Far[FarIndex].LengthStr + currentRead.UP_Close[CloseIndex].LengthStr >= currentRead.getReadLength()) {
continue;
}
if (currentRead.UP_Far[FarIndex].Mismatches + currentRead.UP_Close[CloseIndex].Mismatches >
(short) (1 + userSettings->Seq_Error_Rate * (currentRead.UP_Far[FarIndex].LengthStr + currentRead.UP_Close[CloseIndex].LengthStr))) {
continue;
}
if (currentRead.MatchedD == Plus) {
if (currentRead.UP_Far[FarIndex].Direction == Minus) {
if (currentRead.UP_Far[FarIndex].AbsLoc + currentRead.UP_Far[FarIndex].LengthStr < currentRead.UP_Close[CloseIndex].AbsLoc &&
currentRead.UP_Far[FarIndex].AbsLoc + currentRead.UP_Close[CloseIndex].LengthStr < currentRead.UP_Close[CloseIndex].AbsLoc &&
currentRead.UP_Far[FarIndex].LengthStr + currentRead.UP_Close[CloseIndex].LengthStr > userSettings->Min_Num_Matched_Bases) {
currentRead.Right = currentRead.UP_Close[CloseIndex].AbsLoc - currentRead.UP_Close[CloseIndex].LengthStr + 1;
currentRead.Left = currentRead.UP_Far[FarIndex].AbsLoc + currentRead.UP_Far[FarIndex].LengthStr - 1;
currentRead.BP = currentRead.UP_Close[CloseIndex].LengthStr - 1;
currentRead.IndelSize = currentRead.UP_Close[CloseIndex].AbsLoc - currentRead.UP_Far[FarIndex].AbsLoc + 1;
currentRead.NT_size = currentRead.getReadLength() - currentRead.UP_Close[CloseIndex].LengthStr - currentRead.UP_Far[FarIndex].LengthStr;
currentRead.NT_str = currentRead.getUnmatchedSeqRev().substr( currentRead.BP + 1, currentRead.NT_size);
currentRead.BPRight = currentRead.UP_Close[CloseIndex].AbsLoc - g_SpacerBeforeAfter;
currentRead.BPLeft = currentRead.UP_Far[FarIndex].AbsLoc - g_SpacerBeforeAfter;
if (readTransgressesBinBoundaries( currentRead, window.getEnd())) {
saveReadForNextCycle(currentRead, currentState.FutureReads_SR);
}
else {
if ( readInSpecifiedRegion( currentRead, userSettings->getRegion())) {
TD_NT[(int) currentRead. BPLeft / BoxSize]. push_back(ReadIndex);
currentRead.Used = true;
Count_TD_NT++;
Count_TD_NT_Plus++;
}
}
}
}
}
else if (currentRead.MatchedD == Minus) {
if (currentRead.UP_Far[FarIndex].Direction == Plus) {
if (currentRead.UP_Close[CloseIndex].AbsLoc + currentRead.UP_Close[CloseIndex].LengthStr < currentRead.UP_Far[FarIndex].AbsLoc &&
currentRead.UP_Close[CloseIndex].AbsLoc + currentRead.UP_Far[FarIndex].LengthStr < currentRead.UP_Far[FarIndex].AbsLoc &&
currentRead.UP_Far[FarIndex].LengthStr + currentRead.UP_Close[CloseIndex].LengthStr > userSettings->Min_Num_Matched_Bases) {
currentRead.Right = currentRead.UP_Far[FarIndex].AbsLoc - currentRead.UP_Far[FarIndex].LengthStr + 1;
currentRead.Left = currentRead.UP_Close[CloseIndex].AbsLoc + currentRead.UP_Close[CloseIndex].LengthStr - 1;
currentRead.BP = currentRead.UP_Far[FarIndex].LengthStr - 1;
currentRead.IndelSize = currentRead.UP_Far[FarIndex].AbsLoc - currentRead.UP_Close[CloseIndex].AbsLoc + 1;
currentRead.NT_size = currentRead.getReadLength() - currentRead.UP_Close[CloseIndex].LengthStr - currentRead.UP_Far[FarIndex].LengthStr;
currentRead.NT_str = currentRead.getUnmatchedSeq(). substr( currentRead.BP + 1, currentRead.NT_size);
currentRead.BPRight = currentRead.UP_Far[FarIndex].AbsLoc - g_SpacerBeforeAfter;
currentRead.BPLeft = currentRead.UP_Close[CloseIndex].AbsLoc - g_SpacerBeforeAfter;
if (readTransgressesBinBoundaries( currentRead, window.getEnd())) {
saveReadForNextCycle(currentRead, currentState.FutureReads_SR);
}
else {
if ( readInSpecifiedRegion( currentRead, userSettings->getRegion())) {
TD_NT[(int) currentRead. BPLeft / BoxSize]. push_back(ReadIndex);
currentRead.Used = true;
Count_TD_NT++;
Count_TD_NT_Minus++;
}
}
}
}
}
}
LOG_INFO(*logStream << "Total: " << Count_TD_NT << "\t+" << Count_TD_NT_Plus << "\t-" << Count_TD_NT_Minus << std::endl);
std::ofstream TDOutf(userSettings->getTDOutputFilename().c_str(), std::ios::app);
SortAndOutputTandemDuplications(currentState, NumBoxes, window.getChromosome()->getSeq(), currentState.Reads_SR, TD_NT, TDOutf, true);
TDOutf.close();
for (unsigned int i = 0; i < NumBoxes; i++) {
TD_NT[i].clear();
}
return EXIT_SUCCESS;
}
int searchTandemDuplications(ControlState& currentState, unsigned NumBoxes)
{
static int Count_TD = 0;
static int Count_TD_Plus = 0;
static int Count_TD_Minus = 0;
std::vector<unsigned> TD[NumBoxes];
LOG_INFO(std::cout << "Searching tandem duplication events ... " << std::endl);
for (unsigned ReadIndex = 0; ReadIndex < currentState.Reads.size(); ReadIndex++) {
if (currentState.Reads[ReadIndex].Used
|| currentState.Reads[ReadIndex].UP_Far.empty()) {
continue;
}
if (currentState.Reads[ReadIndex].MatchedD == Plus) {
for (short MAX_SNP_ERROR_index = 0; MAX_SNP_ERROR_index
<= currentState.Reads[ReadIndex].MAX_SNP_ERROR; MAX_SNP_ERROR_index++) {
for (unsigned int CloseIndex = 0; CloseIndex
< currentState.Reads[ReadIndex].UP_Close.size(); CloseIndex++) {
if (currentState.Reads[ReadIndex].Used) {
break;
}
if (currentState.Reads[ReadIndex].UP_Close[CloseIndex]. Mismatches
> MAX_SNP_ERROR_index) {
continue;
}
for (int FarIndex =
currentState.Reads[ReadIndex].UP_Far.size() - 1; FarIndex
>= 0; FarIndex--) {
if (currentState.Reads[ReadIndex].Used) {
break;
}
if (currentState.Reads[ReadIndex].UP_Far[FarIndex]. Mismatches
> MAX_SNP_ERROR_index) {
continue;
}
if (currentState.Reads[ReadIndex].UP_Far[FarIndex]. Mismatches
+ currentState.Reads[ReadIndex].UP_Close[CloseIndex]. Mismatches
> MAX_SNP_ERROR_index) {
continue;
}
if (currentState.Reads[ReadIndex].UP_Far[FarIndex]. Direction
== Minus) {
if (currentState.Reads[ReadIndex].UP_Far[FarIndex].LengthStr
+ currentState.Reads[ReadIndex].UP_Close[CloseIndex].LengthStr
== currentState.Reads[ReadIndex].ReadLength
&& currentState.Reads[ReadIndex].UP_Far[FarIndex].AbsLoc
+ currentState.Reads[ReadIndex].UP_Far[FarIndex].LengthStr
< currentState.Reads[ReadIndex].UP_Close[CloseIndex].AbsLoc
&& currentState.Reads[ReadIndex].UP_Far[FarIndex].AbsLoc
+ currentState.Reads[ReadIndex].UP_Close[CloseIndex].LengthStr
< currentState.Reads[ReadIndex].UP_Close[CloseIndex].AbsLoc) {
currentState.Reads[ReadIndex].Right
= currentState.Reads[ReadIndex]. UP_Close[CloseIndex].AbsLoc
- currentState.Reads[ReadIndex]. UP_Close[CloseIndex].LengthStr
+ 1;
currentState.Reads[ReadIndex].Left
= currentState.Reads[ReadIndex]. UP_Far[FarIndex].AbsLoc
+ currentState.Reads[ReadIndex]. UP_Far[FarIndex].LengthStr
- 1;
currentState.Reads[ReadIndex].BP
= currentState.Reads[ReadIndex]. UP_Close[CloseIndex].LengthStr
- 1;
currentState.Reads[ReadIndex].IndelSize
= currentState.Reads[ReadIndex]. UP_Close[CloseIndex].AbsLoc
- currentState.Reads[ReadIndex]. UP_Far[FarIndex].AbsLoc
+ 1;
//currentState.Reads[ReadIndex].InsertedStr = "";
currentState.Reads[ReadIndex].BPRight
= currentState.Reads[ReadIndex].UP_Close[CloseIndex].AbsLoc
- g_SpacerBeforeAfter;
currentState.Reads[ReadIndex].BPLeft
= currentState.Reads[ReadIndex].UP_Far[FarIndex].AbsLoc
- g_SpacerBeforeAfter;
if (readTransgressesBinBoundaries(
currentState.Reads[ReadIndex],
currentState.upperBinBorder)) {
saveReadForNextCycle(
currentState.Reads[ReadIndex],
currentState.FutureReads);
}
else {
if (readInSpecifiedRegion(
currentState.Reads[ReadIndex],
currentState.regionStartDefined,
currentState.regionEndDefined,
currentState.startOfRegion,
currentState.endOfRegion)) {
TD[(int) currentState.Reads[ReadIndex]. BPLeft
/ BoxSize]. push_back(ReadIndex);
currentState.Reads[ReadIndex].Used
= true;
Count_TD++;
Count_TD_Plus++;
}
}
}
}
}
}
}
}
else if (currentState.Reads[ReadIndex].MatchedD == Minus) {
for (short MAX_SNP_ERROR_index = 0; MAX_SNP_ERROR_index
<= currentState.Reads[ReadIndex].MAX_SNP_ERROR; MAX_SNP_ERROR_index++) {
for (int CloseIndex =
currentState.Reads[ReadIndex].UP_Close.size() - 1; CloseIndex
>= 0; CloseIndex--) {
if (currentState.Reads[ReadIndex].Used) {
break;
}
if (currentState.Reads[ReadIndex].UP_Close[CloseIndex]. Mismatches
> MAX_SNP_ERROR_index) {
continue;
}
for (int FarIndex = 0; FarIndex
< (int) currentState.Reads[ReadIndex].UP_Far.size(); FarIndex++) {
if (currentState.Reads[ReadIndex].Used) {
break;
}
if (currentState.Reads[ReadIndex].UP_Far[FarIndex]. Mismatches
> MAX_SNP_ERROR_index) {
continue;
}
if (currentState.Reads[ReadIndex].UP_Far[FarIndex]. Mismatches
+ currentState.Reads[ReadIndex].UP_Close[CloseIndex]. Mismatches
> MAX_SNP_ERROR_index) {
continue;
}
if (currentState.Reads[ReadIndex].UP_Far[FarIndex]. Direction
== Plus) {
if (currentState.Reads[ReadIndex]. UP_Close[CloseIndex].LengthStr
+ currentState.Reads[ReadIndex].UP_Far[FarIndex]. LengthStr
== currentState.Reads[ReadIndex].ReadLength
&& currentState.Reads[ReadIndex]. UP_Close[CloseIndex].AbsLoc
+ currentState.Reads[ReadIndex].UP_Close[CloseIndex].LengthStr
< currentState.Reads[ReadIndex].UP_Far[FarIndex]. AbsLoc
&& currentState.Reads[ReadIndex]. UP_Close[CloseIndex].AbsLoc
+ currentState.Reads[ReadIndex].UP_Far[FarIndex].LengthStr
< currentState.Reads[ReadIndex].UP_Far[FarIndex]. AbsLoc) {
currentState.Reads[ReadIndex].Right
= currentState.Reads[ReadIndex]. UP_Far[FarIndex].AbsLoc
- currentState.Reads[ReadIndex]. UP_Far[FarIndex].LengthStr
+ 1;
currentState.Reads[ReadIndex].Left
= currentState.Reads[ReadIndex]. UP_Close[CloseIndex].AbsLoc
+ currentState.Reads[ReadIndex]. UP_Close[CloseIndex].LengthStr
- 1;
currentState.Reads[ReadIndex].BP
= currentState.Reads[ReadIndex]. UP_Far[FarIndex].LengthStr
- 1;
currentState.Reads[ReadIndex].IndelSize
= currentState.Reads[ReadIndex]. UP_Far[FarIndex].AbsLoc
- currentState.Reads[ReadIndex]. UP_Close[CloseIndex].AbsLoc
+ 1;
//currentState.Reads[ReadIndex].InsertedStr = "";
currentState.Reads[ReadIndex].BPRight
= currentState.Reads[ReadIndex].UP_Far[FarIndex].AbsLoc
- g_SpacerBeforeAfter;
currentState.Reads[ReadIndex].BPLeft
= currentState.Reads[ReadIndex].UP_Close[CloseIndex].AbsLoc
- g_SpacerBeforeAfter;
if (readTransgressesBinBoundaries(
currentState.Reads[ReadIndex],
currentState.upperBinBorder)) {
saveReadForNextCycle(
currentState.Reads[ReadIndex],
currentState.FutureReads);
}
else {
if (readInSpecifiedRegion(
currentState.Reads[ReadIndex],
currentState.regionStartDefined,
currentState.regionEndDefined,
currentState.startOfRegion,
currentState.endOfRegion)) {
TD[(int) currentState.Reads[ReadIndex]. BPLeft
/ BoxSize]. push_back(ReadIndex);
currentState.Reads[ReadIndex].Used
= true;
Count_TD++;
Count_TD_Minus++;
}
}
}
}
}
}
}
}
}
LOG_INFO(std::cout << "Total: " << Count_TD << "\t+" << Count_TD_Plus << "\t-"
<< Count_TD_Minus << std::endl);
std::ofstream TDOutf(currentState.TDOutputFilename.c_str(), std::ios::app);
SortAndOutputTandemDuplications(NumBoxes, currentState.CurrentChr,
currentState.Reads, TD, TDOutf, false);
for (unsigned int i = 0; i < NumBoxes; i++) {
TD[i].clear();
}
return EXIT_SUCCESS;
}