NucleotideContigFragmentRDDFunctions

Instance Constructors

new NucleotideContigFragmentRDDFunctions(rdd: RDD[NucleotideContigFragment])

Value Members

final def !=(arg0: Any): Boolean

Definition Classes
AnyRef → Any
final def ##(): Int

Definition Classes
AnyRef → Any
final def ==(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def adamGetReferenceString(region: ReferenceRegion): String

From a set of contigs, returns the base sequence that corresponds to a region of the reference.
From a set of contigs, returns the base sequence that corresponds to a region of the reference.
region
Reference region over which to get sequence.
returns
String of bases corresponding to reference sequence.

Exceptions thrown
UnsupportedOperationException
Throws exception if query region is not found.
def adamGetSequenceDictionary(performLexSort: Boolean = false): SequenceDictionary

Aggregates together a sequence dictionary from the different individual reference sequences used in this dataset.
Aggregates together a sequence dictionary from the different individual reference sequences used in this dataset.
returns
A sequence dictionary describing the reference contigs in this dataset.

Definition Classes
ADAMSequenceDictionaryRDDAggregator
final def asInstanceOf[T0]: T0

Definition Classes
Any
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
def countKmers(kmerLength: Int, optSd: Option[SequenceDictionary] = None): RDD[(String, Long)]

Counts the k-mers contained in a FASTA contig.
Counts the k-mers contained in a FASTA contig.
kmerLength
The length of k-mers to count.
optSd
An optional sequence dictionary. If none is provided, we recompute the sequence dictionary on the fly. Default is None.
returns
Returns an RDD containing k-mer/count pairs.
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def equals(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
def flankAdjacentFragments(flankLength: Int, optSd: Option[SequenceDictionary] = None): RDD[NucleotideContigFragment]

For all adjacent records in the RDD, we extend the records so that the adjacent records now overlap by _n_ bases, where _n_ is the flank length.
For all adjacent records in the RDD, we extend the records so that the adjacent records now overlap by _n_ bases, where _n_ is the flank length.
flankLength
The length to extend adjacent records by.
optSd
An optional sequence dictionary. If none is provided, we recompute the sequence dictionary on the fly. Default is None.
returns
Returns the RDD, with all adjacent fragments extended with flanking sequence.
final def getClass(): Class[_]

Definition Classes
AnyRef → Any
def getSequenceRecordsFromElement(elem: NucleotideContigFragment): Set[SequenceRecord]

For a single RDD element, returns 0+ sequence record elements.
For a single RDD element, returns 0+ sequence record elements.
elem
Element from which to extract sequence records.
returns
A seq of sequence records.

Definition Classes
NucleotideContigFragmentRDDFunctions → ADAMSequenceDictionaryRDDAggregator
def hashCode(): Int

Definition Classes
AnyRef → Any
final def isInstanceOf[T0]: Boolean

Definition Classes
Any
def isTraceEnabled(): Boolean

Attributes
protected
Definition Classes
Logging
def log: Logger

Attributes
protected
Definition Classes
Logging
def logDebug(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logDebug(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logError(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logError(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logInfo(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logInfo(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logName: String

Attributes
protected
Definition Classes
Logging
def logTrace(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logTrace(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def logWarning(msg: ⇒ String, throwable: Throwable): Unit

Attributes
protected
Definition Classes
Logging
def logWarning(msg: ⇒ String): Unit

Attributes
protected
Definition Classes
Logging
def mergeFragments(): RDD[NucleotideContigFragment]

Merge fragments by contig name.
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

Definition Classes
AnyRef
def saveAsFasta(fileName: String, lineWidth: Int = 60): Unit

Save nucleotide contig fragments in FASTA format.
Save nucleotide contig fragments in FASTA format.
fileName
file name
lineWidth
hard wrap FASTA formatted sequence at line width, default 60
lazy val sc: SparkContext

Definition Classes
ADAMSequenceDictionaryRDDAggregator
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def toReads(): RDD[AlignmentRecord]

Converts an RDD of nucleotide contig fragments into reads.
Converts an RDD of nucleotide contig fragments into reads. Adjacent contig fragments are combined.
returns
Returns an RDD of reads.
def toString(): String

Definition Classes
AnyRef → Any
final def wait(): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long, arg1: Int): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )

class NucleotideContigFragmentRDDFunctions extends ADAMSequenceDictionaryRDDAggregator[NucleotideContigFragment]

Instance Constructors

new NucleotideContigFragmentRDDFunctions(rdd: RDD[NucleotideContigFragment])

Value Members

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: Any): Boolean

def adamGetReferenceString(region: ReferenceRegion): String

def adamGetSequenceDictionary(performLexSort: Boolean = false): SequenceDictionary

final def asInstanceOf[T0]: T0

def clone(): AnyRef

def countKmers(kmerLength: Int, optSd: Option[SequenceDictionary] = None): RDD[(String, Long)]

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def finalize(): Unit

def flankAdjacentFragments(flankLength: Int, optSd: Option[SequenceDictionary] = None): RDD[NucleotideContigFragment]

final def getClass(): Class[_]

def getSequenceRecordsFromElement(elem: NucleotideContigFragment): Set[SequenceRecord]

def hashCode(): Int

final def isInstanceOf[T0]: Boolean

def isTraceEnabled(): Boolean

def log: Logger

def logDebug(msg: ⇒ String, throwable: Throwable): Unit

def logDebug(msg: ⇒ String): Unit

def logError(msg: ⇒ String, throwable: Throwable): Unit

def logError(msg: ⇒ String): Unit

def logInfo(msg: ⇒ String, throwable: Throwable): Unit

def logInfo(msg: ⇒ String): Unit

def logName: String

def logTrace(msg: ⇒ String, throwable: Throwable): Unit

def logTrace(msg: ⇒ String): Unit

def logWarning(msg: ⇒ String, throwable: Throwable): Unit

def logWarning(msg: ⇒ String): Unit

def mergeFragments(): RDD[NucleotideContigFragment]

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

def saveAsFasta(fileName: String, lineWidth: Int = 60): Unit

lazy val sc: SparkContext

final def synchronized[T0](arg0: ⇒ T0): T0

def toReads(): RDD[AlignmentRecord]

def toString(): String

final def wait(): Unit

final def wait(arg0: Long, arg1: Int): Unit

final def wait(arg0: Long): Unit

Inherited from ADAMSequenceDictionaryRDDAggregator[NucleotideContigFragment]

Inherited from Logging

Inherited from Serializable

Inherited from Serializable

Inherited from AnyRef

Inherited from Any

Ungrouped