Public Member Functions | |
JunctionVcfRecordSource (const std::vector< boost::shared_ptr< cgatools::cgdata::GenomeMetadata > > &genomes, const std::vector< std::string > &junctionFileNames, const std::vector< std::string > fieldNames, const cgatools::reference::CrrFile &crr, size_t scoreThreshold=10, size_t sideLengthThreshold_=70, size_t distanceTolerance=200, size_t junctionLengthThreshold=500, bool normalPriorityOutput=false, bool useHighConfidenceJunctionsForTumor=true) | |
std::vector < cgatools::conv::VcfSubFieldHeaderRecord > | getSubFieldHeaderRecords () const |
Returns the VcfSubFieldHeaderRecords for all genomes. | |
std::string | getSource (size_t idxGenome) const |
Returns the #source=VALUE header value for the given genome, which is the same as the input file's getMetadata().getSoftwareVersionString(). | |
std::vector < cgatools::conv::VcfKvHeaderRecord > | getKeyValueHeaderRecords (size_t idxGenome) const |
Returns #KEY=VALUE records for the given genome. | |
std::string | getAssemblyId (size_t idxGenome) const |
Returns the input file's getMetadata().get("ASSEMBLY_ID"). | |
bool | eof () const |
Record iteration. | |
cgatools::conv::VcfRecordSource & | operator++ () |
const cgatools::conv::VcfRecordWriter & | operator* () const |
const cgatools::conv::VcfRecordWriter * | operator-> () const |
void | writeAllFields (bool v) |
tells the writer whether all eligible fields should be written even if they are not in the list of field names | |
int | run () |
Protected Member Functions | |
int | run1Genome () |
int | run2Genomes () |
bool | add (std::vector< cgatools::conv::VcfSubFieldHeaderRecord > &result, cgatools::conv::VcfSubFieldHeaderRecord::Key key, const std::string &id, const std::string &number, const std::string &type, const std::string &description) const |
JunctionVcfRecordWriter | createRecord (const JunctionRef &jref, size_t side, const JunctionCompatMapPerFile &compat) const |
std::string | getAltField (const JunctionRef &jref, size_t side, bool suppressChrom=false) const |
std::string | getPosition (reference::Location pos, const std::string &sep) const |
std::string | getInfo (const JunctionRef &jref, size_t side) const |
std::string | getMEI (const std::string &med) const |
std::string | getId (const JunctionRef &jref, size_t side) const |
std::string | getFormat (const JunctionRef &jref, size_t side) const |
std::string | getSample (const JunctionRef &jref, size_t side, size_t idx, const JunctionCompatMapPerFile &compat) const |
std::string | getSample (const JunctionRef &jref, size_t side) const |
std::string | getSampleFilter (const JunctionRef &jref) const |
std::string | addFilterFlag (const std::string &flag, bool &filtered) const |
bool | need (const std::string &fieldName) const |
void | copyJunctionListForVcf (const junctions::JunctionRefs &jrl, std::vector< JunctionRefSide > &out, JunctionCompatMapPerFile &compat) const |
void | pickNormalPriorityMatch (const JunctionRef &jr, JunctionRefSet &junctionsToSuppress) const |
void | pickDefaultMatch (const JunctionRef &jr, JunctionRefSet &junctionsToSuppress) const |
Protected Attributes | |
const cgatools::reference::CrrFile & | crr_ |
reference genome | |
std::vector< std::string > | sampleIds_ |
Input genomes' sample IDs. | |
std::vector< std::string > | junctionFileNames_ |
Junction file mames. | |
std::vector< std::string > | fieldNames_ |
Field names. | |
std::set< std::string > | fieldNameSet_ |
bool | writeAllFields_ |
Flag that enables writing of all eligible fields even if they are not in the list of field names. | |
size_t | scoreThreshold_ |
PASS thresholds for discordant DNBs count. | |
size_t | sideLengthThreshold_ |
PASS threshold for minimum junction side length, in base pairs. | |
size_t | junctionLengthThreshold_ |
Length threshold for junction compatibility. | |
size_t | distanceTolerance_ |
Distance tolerance for junction compatibility. | |
bool | normalPriorityOutput_ |
Normal (non-tumor) junction priority for the output. | |
bool | useHighConfidenceJunctionsForTumor_ |
JunctionFiles | junctionFiles_ |
Loaded junction files. | |
std::vector < JunctionVcfRecordWriter > | records_ |
VCF records. | |
size_t | currentRecord_ |
Current VCF record. | |
Static Protected Attributes | |
static const char * | sampleFieldIDs_ [] |
std::vector<cgatools::conv::VcfKvHeaderRecord> cgatools::junctions::JunctionVcfRecordSource::getKeyValueHeaderRecords | ( | size_t | idxGenome | ) | const [virtual] |
Returns #KEY=VALUE records for the given genome.
Must include at least the source_GENOME_REFERENCE key.
Implements cgatools::conv::VcfRecordSource.
std::string cgatools::junctions::JunctionVcfRecordSource::getSource | ( | size_t | idxGenome | ) | const [virtual] |
Returns the #source=VALUE header value for the given genome, which is the same as the input file's getMetadata().getSoftwareVersionString().
Implements cgatools::conv::VcfRecordSource.
std::vector<cgatools::conv::VcfSubFieldHeaderRecord> cgatools::junctions::JunctionVcfRecordSource::getSubFieldHeaderRecords | ( | ) | const [virtual] |
Returns the VcfSubFieldHeaderRecords for all genomes.
Includes, INFO, FORMAT, FILTER, and ALT records.
Implements cgatools::conv::VcfRecordSource.