std::string getQuickStats(const std::string &bamFile, std::map< std::string, int > &keyLen, unsigned int &nFlowFZ, unsigned int &nFlowZM) {
std::string errMsg = "";
BamTools::BamReader bamReader;
if(!bamReader.Open(bamFile)) {
errMsg += "Failed to open bam " + bamFile + "\n";
return(errMsg);
}
BamTools::SamHeader samHeader = bamReader.GetHeader();
for (BamTools::SamReadGroupIterator itr = samHeader.ReadGroups.Begin(); itr != samHeader.ReadGroups.End(); ++itr ) {
if(itr->HasID())
keyLen[itr->ID] = itr->HasKeySequence() ? itr->KeySequence.length() : 0;
if(itr->HasFlowOrder())
nFlowZM = std::max(nFlowZM,(unsigned int) itr->FlowOrder.length());
}
BamTools::BamAlignment alignment;
std::vector<uint16_t> flowIntFZ;
while(bamReader.GetNextAlignment(alignment)) {
if(alignment.GetTag("FZ", flowIntFZ))
nFlowFZ = flowIntFZ.size();
break;
}
bamReader.Close();
if(nFlowFZ==0)
std::cout << "NOTE: bam file has no flow signals in FZ tag: " + bamFile + "\n";
if(nFlowZM==0)
std::cout << "NOTE: bam file has no flow signals in ZM tag: " + bamFile + "\n";
return(errMsg);
}
void BamHeaderHelper::GetRefID(BamTools::BamReader &bamReader)
{
BamTools::SamHeader samHeader = bamReader.GetHeader();
for (BamTools::SamSequenceIterator itr = samHeader.Sequences.Begin(); itr != samHeader.Sequences.End(); ++itr) {
string bamseq = itr->Name;
bam_sequence_names.push_back(bamseq);
}
}
void BamHeaderHelper::GetFlowOrder(BamTools::BamReader &bamReader){
BamTools::SamHeader samHeader = bamReader.GetHeader();
if (!samHeader.HasReadGroups()) {
//bamReader.Close();
cerr << "ERROR: there is no read group in " << "this file" << endl;
//exit(1);
}
for (BamTools::SamReadGroupIterator itr = samHeader.ReadGroups.Begin(); itr != samHeader.ReadGroups.End(); ++itr) {
if (itr->HasFlowOrder()) {
flow_order_set.push_back(itr->FlowOrder);
//flowKey = itr->KeySequence;
}
}
}
std::vector< Sample::SharedPtr > BamAlignmentReader::GetBamReaderSamples(const std::string& bamPath)
{
std::vector< Sample::SharedPtr > samplePtrs;
BamTools::BamReader bamReader;
if (!bamReader.Open(bamPath))
{
throw "Unable to open bam file";
}
auto readGroups = bamReader.GetHeader().ReadGroups;
auto iter = readGroups.Begin();
for (; iter != readGroups.End(); ++iter)
{
auto samplePtr = std::make_shared< Sample >((*iter).Sample, (*iter).ID, bamPath);
samplePtrs.emplace_back(samplePtr);
}
bamReader.Close();
return samplePtrs;
}
void Config::InitializationClustering() {
struct stat st;
if(stat(Workspace.c_str(),&st) == 0 and st.st_mode and S_IFDIR != 0) Log("[Warning] Workspace directory already present");
else if (mkdir(Workspace.c_str(), 0755) != 0) {
Log("[Error] Could not create workspace directory: " + Workspace);
exit(1);
}
RunningTasksFile = Workspace + "/" + FilePrefix + "running.tasks";
StatsFile = Workspace + "/" + FilePrefix + "stats";
BinClusterFile = Workspace + "/" + FilePrefix + "bpc";
clusterFile = new ClusterFile(BinClusterFile);
clusterDir = Workspace + "/clusters/";
if(stat(clusterDir.c_str(),&st) == 0 and st.st_mode and S_IFDIR != 0) Log("[Warning] Cluster directory already present");
else if (mkdir(clusterDir.c_str(), 0755) != 0) {
Log("[Error] Could not create cluster directory: " + clusterDir);
exit(1);
}
insertsizeDir = Workspace + "/insertsize/";
if(stat(insertsizeDir.c_str(),&st) == 0 and st.st_mode and S_IFDIR != 0) Log("[Warning] Insertsize directory already present");
else if (mkdir(insertsizeDir.c_str(), 0755) != 0) {
Log("[Error] Could not create insertsize directory: " + insertsizeDir);
exit(1);
}
coverageDir = Workspace + "/coverage/";
if(stat(coverageDir.c_str(),&st) == 0 and st.st_mode and S_IFDIR != 0) Log("[Warning] Coverage directory already present");
else if (mkdir(coverageDir.c_str(), 0755) != 0) {
Log("[Error] Could not create coverage directory: " + coverageDir);
exit(1);
}
if (!ForwardBam.empty() && !ReverseBam.empty() && PairedBam.empty()) {
UsePairedBam = false;
} else if (ForwardBam.empty() && ReverseBam.empty() && !PairedBam.empty()) {
UsePairedBam = true;
} else {
Log("[Error] No correct bam file(s)");
exit(1);
}
BamTools::BamAlignment alignment;
BamTools::BamReader BamReader;
if (UsePairedBam) {
BamReader.Open(PairedBam);
if (not BamReader.IsOpen()) {
Log("[Error] Could not open paired bam");
exit(1);
}
if (PairedIndex.empty()) {
if (not BamReader.LocateIndex(BamTools::BamIndex::STANDARD)) {
PairedIndex = PairedBam.substr(0,PairedBam.find_last_of(".bam")-3) + ".bai";
BamReader.OpenIndex(PairedIndex);
}
if (not BamReader.HasIndex()) {
Log("[Error] No index for bamfile");
exit(1);
}
}
BamTools::SamHeader header = BamReader.GetHeader();
for (BamTools::SamReadGroupIterator it = header.ReadGroups.Begin(); it != header.ReadGroups.End(); it++) {
BamTools::SamReadGroup* readgroup = &*it;
readNameConverter.TrimName(readgroup->ID);
readNameConverter.AddReadGroup(readgroup->ID);
}
long int count = 0;
while (BamReader.GetNextAlignment(alignment)) {
string RG;
if (alignment.GetTag("RG", RG)) {
if (not NameTrim.empty()) readNameConverter.TrimName(RG);
if (readNameConverter.AddReadGroup(RG)) {
Log("[Warning] Readgroup '" + RG + "' found in reads but not in header");
count = 0;
}
}
count++;
if (count > 10000) break;
}
BamReader.Close();
} else {
BamReader.Open(ForwardBam);
if (not BamReader.IsOpen()) {
Log("[Error] Could not open first/forward bam");
exit(1);
}
if (ForwardIndex.empty()) {
if (not BamReader.LocateIndex(BamTools::BamIndex::STANDARD)) {
ForwardIndex = ForwardBam.substr(0,ForwardBam.find_last_of(".bam")-3) + ".bai";
BamReader.OpenIndex(ForwardIndex);
}
if (not BamReader.HasIndex()) {
Log("[Error] No index for forward bamfile");
exit(1);
}
}
BamTools::SamHeader forwardheader = BamReader.GetHeader();
for (BamTools::SamReadGroupIterator it = forwardheader.ReadGroups.Begin(); it != forwardheader.ReadGroups.End(); it++) {
BamTools::SamReadGroup* readgroup = &*it;
readNameConverter.TrimName(readgroup->ID);
readNameConverter.AddReadGroup(readgroup->ID);
}
long int count = 0;
while (BamReader.GetNextAlignment(alignment)) {
string RG;
if (alignment.GetTag("RG", RG)) {
if (!NameTrim.empty()) readNameConverter.TrimName(RG);
if (readNameConverter.AddReadGroup(RG)) {
Log("[Warning] Readgroup '" + RG + "' found in forward reads but not in header");
count = 0;
}
}
count++;
if (count > 10000) break;
}
BamReader.Close();
BamReader.Open(ReverseBam);
if (not BamReader.IsOpen()) {
Log("[Error] Could not open second/reverse bam");
exit(1);
}
if (ReverseIndex.empty()) {
if (not BamReader.LocateIndex(BamTools::BamIndex::STANDARD)) {
ReverseIndex = ReverseBam.substr(0,ReverseBam.find_last_of(".bam")-3) + ".bai";
BamReader.OpenIndex(ReverseIndex);
}
if (not BamReader.HasIndex()) {
Log("[Error] No index for reverse bamfile");
exit(1);
}
}
BamTools::SamHeader reverseheader = BamReader.GetHeader();
for (BamTools::SamReadGroupIterator it = reverseheader.ReadGroups.Begin(); it != reverseheader.ReadGroups.End(); it++) {
BamTools::SamReadGroup* readgroup = &*it;
readNameConverter.TrimName(readgroup->ID);
if (readNameConverter.AddReadGroup(readgroup->ID)) {
Log("[Warning] Readgroup '" + readgroup->ID + "' found in reverse but not in forward");
}
}
count = 0;
while (BamReader.GetNextAlignment(alignment)) {
string RG;
if (alignment.GetTag("RG", RG)) {
if (!NameTrim.empty()) readNameConverter.TrimName(RG);
if (readNameConverter.AddReadGroup(RG)) {
Log("[Warning] Readgroup '" + RG + "' found in reverse reads but not in header");
count = 0;
}
}
count++;
if (count > 10000) break;
}
BamReader.Close();
}
for(map<string, int>::iterator it = readNameConverter.ReadGroups.begin(); it!=readNameConverter.ReadGroups.end(); ++it) {
ostringstream logBuffer;
logBuffer << "Readgroup found: " << it->second << " - " << it->first;
Log(logBuffer.str());
}
writeConfigFile(Workspace + FilePrefix + "config");
}
void MyBamGroup::ReadGroup(char *bamFile){
BamTools::BamReader bamReader;
if(!bamReader.Open(std::string(bamFile))) {
errMsg = "Failed to open bam " + std::string(bamFile) + "\n";
} else {
BamTools::SamHeader samHeader = bamReader.GetHeader();
for (BamTools::SamReadGroupIterator itr = samHeader.ReadGroups.Begin(); itr != samHeader.ReadGroups.End(); ++itr ) {
if(itr->HasID()) {
ID.push_back(itr->ID);
} else {
ID.push_back("");
}
if(itr->HasFlowOrder()) {
FlowOrder.push_back(itr->FlowOrder);
} else {
FlowOrder.push_back("");
}
if(itr->HasKeySequence()) {
KeySequence.push_back(itr->KeySequence);
} else {
KeySequence.push_back("");
}
if(itr->HasDescription()) {
Description.push_back(itr->Description);
} else {
Description.push_back("");
}
if(itr->HasLibrary()) {
Library.push_back(itr->Library);
} else {
Library.push_back("");
}
if(itr->HasPlatformUnit()) {
PlatformUnit.push_back(itr->PlatformUnit);
} else {
PlatformUnit.push_back("");
}
if(itr->HasPredictedInsertSize()) {
PredictedInsertSize.push_back(itr->PredictedInsertSize);
} else {
PredictedInsertSize.push_back("");
}
if(itr->HasProductionDate()) {
ProductionDate.push_back(itr->ProductionDate);
} else {
ProductionDate.push_back("");
}
if(itr->HasProgram()) {
Program.push_back(itr->Program);
} else {
Program.push_back("");
}
if(itr->HasSample()) {
Sample.push_back(itr->Sample);
} else {
Sample.push_back("");
}
if(itr->HasSequencingCenter()) {
SequencingCenter.push_back(itr->SequencingCenter);
} else {
SequencingCenter.push_back("");
}
if(itr->HasSequencingTechnology()) {
SequencingTechnology.push_back(itr->SequencingTechnology);
} else {
SequencingTechnology.push_back("");
}
}
bamReader.Close();
}
}