nvbio::io Namespace Reference

Classes
struct	Cigar
struct	Alignment
struct	AlignmentCompare
struct	BestAlignments
struct	PairedAlignments
struct	BestPairedAlignments
struct	has_second
struct	has_second_paired
struct	has_second_unpaired
struct	is_paired
struct	is_unpaired
struct	is_concordant
struct	is_discordant
struct	is_not_concordant
struct	is_aligned
struct	BAM_header
struct	BAM_reference
struct	BAM_alignment
struct	BAM_alignment_data_block
class	BufferedTextFile
struct	FMIndexDataCore
struct	FMIndexData
struct	FMIndexDataHost
struct	FMIndexDataMMAPInfo
struct	FMIndexDataMMAPServer
struct	FMIndexDataMMAP
struct	FMIndexDataDevice
struct	BamOutput
struct	DeviceOutputBatchSE
struct	HostOutputBatchSE
struct	HostOutputBatchPE
struct	DataBuffer
struct	DebugOutput
struct	OutputFile
struct	GzipCompressor
struct	BGZFCompressor
struct	AlignmentData
struct	SamOutput
struct	IOStats
struct	BNT
struct	DeviceCigarArray
struct	HostCigarArray
struct	ReadDataFile_BAM
struct	read_string
struct	ReadDataView
struct	ReadData
struct	ReadDataRAM
struct	ReadDataDevice
struct	ReadDataStream
struct	ReadDataFile_FASTQ_parser
struct	ReadDataFile_FASTQ_gz
struct	ReadDataFile
struct	ReadDataFile_TXT
struct	ReadDataFile_TXT_gz
struct	ReadDataFile_SAM
struct	SequenceDataInfo
struct	SequenceDataViewCore
struct	SequenceData
struct	SequenceDataStorage
struct	SequenceDataInputStream
struct	SequenceDataOutputStream
struct	SequenceDataAccess
struct	SequenceDataEdit
struct	SequenceDataFile_BAM
struct	sequence_string
struct	SequenceDataEncoderImpl
struct	SequenceDataEncoder
struct	SequenceDataFile_FASTA_gz
struct	SequenceDataOutputFile_FASTA
struct	SequenceDataFile_FASTQ_parser
struct	SequenceDataFile_FASTQ_gz
struct	SequenceDataOutputFile_FASTQ
struct	SequenceDataMMAPServer
struct	SequenceDataMMAP
struct	SequenceDataFile
struct	SequenceDataFile_SAM
struct	SequenceDataTraits
struct	SequenceDataFile_TXT
struct	SequenceDataFile_TXT_gz
struct	SequenceDataOutputFile_TXT
struct	SNP_sequence_index
struct	SNPDatabase

Typedefs
typedef nvbio::HostVectorArray < uint8 >	HostMdsArray
typedef ReadDataView< uint32 *, uint32 *, char *, char * >	ReadDataCore
typedef ReadDataRAM	ReadDataHost
typedef ReadDataDevice	ReadDataCUDA
typedef SequenceDataViewCore < uint32 *, uint32 *, char *, char * >	SequenceDataView
	A non-const SequenceData view More...
typedef SequenceDataViewCore < const uint32 *, const uint32 *, const char *, const char * >	ConstSequenceDataView
	A const SequenceData view More...
typedef SequenceDataViewCore < cuda::ldg_pointer< uint32 > , cuda::ldg_pointer< uint32 > , const char *, const char * >	LdgSequenceDataView
	An LDG-based SequenceData view More...
typedef SequenceDataStorage < host_tag >	SequenceDataHost
	a SequenceData object stored in host memory More...
typedef SequenceDataStorage < device_tag >	SequenceDataDevice
	a SequenceData object stored in device memory More...
typedef SequenceDataInputStream	SequenceDataStream

Enumerations
enum	MDS_OP {   MDS_MATCH = 0, MDS_MISMATCH = 1, MDS_INSERTION = 2, MDS_DELETION = 3,   MDS_INVALID = 4 }
enum	AlignmentType { SINGLE_END, PAIRED_END }
enum	AlignmentMate { MATE_1 = 0, MATE_2 = 1 }
enum	AlignmentScore { BEST_SCORE, SECOND_BEST_SCORE }
enum	QualityEncoding {   Phred = 0, Phred33 = 1, Phred64 = 2, Solexa = 3,   Phred = 0, Phred33 = 1, Phred64 = 2, Solexa = 3 }
enum	ReadEncoding { FORWARD = 0x0001, REVERSE = 0x0002, FORWARD_COMPLEMENT = 0x0004, REVERSE_COMPLEMENT = 0x0008 }
enum	PairedEndPolicy {   PE_POLICY_FF = 0, PE_POLICY_FR = 1, PE_POLICY_RF = 2, PE_POLICY_RR = 3,   PE_POLICY_FF = 0, PE_POLICY_FR = 1, PE_POLICY_RF = 2, PE_POLICY_RR = 3 }
enum	AlignmentFlags {   SAMFlag_MultipleSegments = 0x1, SAMFlag_AllSegmentsAligned = 0x2, SAMFlag_SegmentUnmapped = 0x4, SAMFlag_NextSegmentUnmapped = 0x8,   SAMFlag_ReverseComplemented = 0x10, SAMFlag_NextSegmentReverseComplemented = 0x20, SAMFlag_FirstSegment = 0x40, SAMFlag_LastSegment = 0x80,   SAMFlag_SecondaryAlignment = 0x100, SAMFlag_FailedQC = 0x200, SAMFlag_Duplicate = 0x400, SAMFlag_MultipleSegments = 0x1,   SAMFlag_AllSegmentsAligned = 0x2, SAMFlag_SegmentUnmapped = 0x4, SAMFlag_NextSegmentUnmapped = 0x8, SAMFlag_ReverseComplemented = 0x10,   SAMFlag_NextSegmentReverseComplemented = 0x20, SAMFlag_FirstSegment = 0x40, SAMFlag_LastSegment = 0x80, SAMFlag_SecondaryAlignment = 0x100,   SAMFlag_FailedQC = 0x200, SAMFlag_Duplicate = 0x400 }
enum	QualityEncoding {   Phred = 0, Phred33 = 1, Phred64 = 2, Solexa = 3,   Phred = 0, Phred33 = 1, Phred64 = 2, Solexa = 3 }
enum	SequenceEncoding { FORWARD = 0x0001, REVERSE = 0x0002, FORWARD_COMPLEMENT = 0x0004, REVERSE_COMPLEMENT = 0x0008 }
enum	SequenceFlags { SEQUENCE_DATA = 0x0001, SEQUENCE_QUALS = 0x0002, SEQUENCE_NAMES = 0x0004 }
enum	PairedEndPolicy {   PE_POLICY_FF = 0, PE_POLICY_FR = 1, PE_POLICY_RF = 2, PE_POLICY_RR = 3,   PE_POLICY_FF = 0, PE_POLICY_FR = 1, PE_POLICY_RF = 2, PE_POLICY_RR = 3 }
enum	AlignmentFlags {   SAMFlag_MultipleSegments = 0x1, SAMFlag_AllSegmentsAligned = 0x2, SAMFlag_SegmentUnmapped = 0x4, SAMFlag_NextSegmentUnmapped = 0x8,   SAMFlag_ReverseComplemented = 0x10, SAMFlag_NextSegmentReverseComplemented = 0x20, SAMFlag_FirstSegment = 0x40, SAMFlag_LastSegment = 0x80,   SAMFlag_SecondaryAlignment = 0x100, SAMFlag_FailedQC = 0x200, SAMFlag_Duplicate = 0x400, SAMFlag_MultipleSegments = 0x1,   SAMFlag_AllSegmentsAligned = 0x2, SAMFlag_SegmentUnmapped = 0x4, SAMFlag_NextSegmentUnmapped = 0x8, SAMFlag_ReverseComplemented = 0x10,   SAMFlag_NextSegmentReverseComplemented = 0x20, SAMFlag_FirstSegment = 0x40, SAMFlag_LastSegment = 0x80, SAMFlag_SecondaryAlignment = 0x100,   SAMFlag_FailedQC = 0x200, SAMFlag_Duplicate = 0x400 }

Functions
NVBIO_FORCEINLINE NVBIO_HOST_DEVICE bool	distinct_alignments (const uint32 pos1, const bool rc1, const uint32 pos2, const bool rc2, const uint32 dist)
NVBIO_FORCEINLINE NVBIO_HOST_DEVICE bool	distinct_alignments (const uint32 apos1, const uint32 opos1, const bool arc1, const bool orc1, const uint32 apos2, const uint32 opos2, const bool arc2, const bool orc2, const uint32 dist)
NVBIO_FORCEINLINE NVBIO_HOST_DEVICE bool	distinct_alignments (const Alignment &p1, const Alignment &p2, const uint32 dist=1)
NVBIO_FORCEINLINE NVBIO_HOST_DEVICE bool	distinct_alignments (const PairedAlignments &p1, const PairedAlignments &p2)
NVBIO_FORCEINLINE NVBIO_HOST_DEVICE bool	distinct_alignments (const PairedAlignments &p1, const PairedAlignments &p2, const uint32 dist)
NVBIO_FORCEINLINE NVBIO_HOST_DEVICE bool	distinct_alignments (const uint32 apos1, const uint32 opos1, const bool arc1, const bool orc1, const uint32 apos2, const uint32 opos2, const bool arc2, const bool orc2)
void	init_ssa (const FMIndexData &driver_data, FMIndexData::ssa_storage_type &ssa, FMIndexData::ssa_storage_type &rssa)
void	init_ssa (const FMIndexDataDevice &driver_data, FMIndexDataDevice::ssa_storage_type &ssa, FMIndexDataDevice::ssa_storage_type &rssa)
AlignmentData	get (HostOutputBatchSE &batch, const uint32 aln_id)
AlignmentData	get_mate (HostOutputBatchPE &batch, const uint32 aln_id, const AlignmentMate mate)
AlignmentData	get_anchor_mate (HostOutputBatchPE &batch, const uint32 aln_id)
AlignmentData	get_opposite_mate (HostOutputBatchPE &batch, const uint32 aln_id)
uint32	compute_cigar_pos (const uint32 sink, const uint32 alignment)
template<typename vector_type >
uint32	reference_cigar_length (const vector_type cigar, const uint32 cigar_len)
template<typename vector_type >
uint32	count_symbols (const Cigar::Operation type, const vector_type cigar, const uint32 cigar_len)
template<typename vector_type >
void	analyze_md_string (const vector_type mds, uint32 &n_mm, uint32 &n_gapo, uint32 &n_gape)
ReadDataStream *	open_read_file (const char *read_file_name, const QualityEncoding qualities, const uint32 max_reads, const uint32 truncate_read_len, const ReadEncoding flags)
template<QualityEncoding quality_encoding, typename read_type >
void	encode (const read_type read, ReadData::read_stream_type::iterator stream, char *qual_stream)
template<typename read_type >
void	encode (const QualityEncoding quality_encoding, const read_type read, ReadData::read_stream_type::iterator stream, char *qual_stream)
void	encode (const ReadDataRAM::StrandOp conversion_flags, const QualityEncoding quality_encoding, const uint32 read_len, const uint8 *read, const uint8 *quality, ReadData::read_stream_type::iterator stream, char *qual_stream)
NVBIO_FORCEINLINE NVBIO_HOST_DEVICE bool	operator== (const SequenceDataInfo &op1, const SequenceDataInfo &op2)
NVBIO_FORCEINLINE NVBIO_HOST_DEVICE bool	operator!= (const SequenceDataInfo &op1, const SequenceDataInfo &op2)
template<Alphabet ALPHABET, typename SequenceDataT >
SequenceDataAccess< ALPHABET, SequenceDataT >	make_access (const SequenceDataT &data)
template<Alphabet ALPHABET, QualityEncoding quality_encoding, typename sequence_type >
void	encode (const sequence_type sequence, typename SequenceDataEdit< ALPHABET, SequenceDataView >::sequence_stream_type stream, char *qual_stream)
template<Alphabet ALPHABET, typename sequence_type >
void	encode (const QualityEncoding quality_encoding, const sequence_type sequence, typename SequenceDataEdit< ALPHABET, SequenceDataView >::sequence_stream_type stream, char *qual_stream)
template<Alphabet ALPHABET>
void	encode (const SequenceDataEncoder::StrandOp conversion_flags, const QualityEncoding quality_encoding, const uint32 sequence_len, const uint8 *sequence, const uint8 *quality, typename SequenceDataEdit< ALPHABET, SequenceDataView >::sequence_stream_type stream, char *qual_stream)
SequenceDataEncoder *	create_encoder (const Alphabet alphabet, SequenceDataHost *data)
int	next (const Alphabet alphabet, SequenceDataHost *data, SequenceDataStream *stream, const uint32 batch_size, const uint32 batch_bps)
int	append (const Alphabet alphabet, SequenceDataHost *data, SequenceDataStream *stream, const uint32 batch_size, const uint32 batch_bps)
int	skip (SequenceDataStream *stream, const uint32 batch_size, const uint32 batch_bps)
SequenceDataMMAP *	map_sequence_file (const char *sequence_file_name)
bool	is_pac_archive (const char *sequence_file_name)
bool	load_pac (const Alphabet alphabet, SequenceDataHost *sequence_data, const char *prefix, const SequenceFlags load_flags, const QualityEncoding qualities)
bool	load_pac (const Alphabet alphabet, SequenceDataMMAPServer *sequence_data, const char *prefix, const char *mapped_name, const SequenceFlags load_flags, const QualityEncoding qualities)
SequenceDataStream *	open_sequence_file (const char *sequence_file_name, const QualityEncoding qualities, const uint32 max_seqs, const uint32 max_sequence_len, const SequenceEncoding flags, const uint32 trim3, const uint32 trim5)
bool	load_sequence_file (const Alphabet alphabet, SequenceDataHost *sequence_data, const char *sequence_file_name, const SequenceFlags load_flags, const QualityEncoding qualities)
SequenceDataHost *	load_sequence_file (const Alphabet alphabet, const char *sequence_file_name, const SequenceFlags load_flags, const QualityEncoding qualities)
SequenceDataOutputStream *	open_output_sequence_file (const char *sequence_file_name, const char *options)
bool	loadVCF (SNPDatabase &output, const char *file_name)

Enumeration Type Documentation

enum nvbio::io::AlignmentFlags

Enumerator
SAMFlag_MultipleSegments
SAMFlag_AllSegmentsAligned
SAMFlag_SegmentUnmapped
SAMFlag_NextSegmentUnmapped
SAMFlag_ReverseComplemented
SAMFlag_NextSegmentReverseComplemented
SAMFlag_FirstSegment
SAMFlag_LastSegment
SAMFlag_SecondaryAlignment
SAMFlag_FailedQC
SAMFlag_Duplicate
SAMFlag_MultipleSegments
SAMFlag_AllSegmentsAligned
SAMFlag_SegmentUnmapped
SAMFlag_NextSegmentUnmapped
SAMFlag_ReverseComplemented
SAMFlag_NextSegmentReverseComplemented
SAMFlag_FirstSegment
SAMFlag_LastSegment
SAMFlag_SecondaryAlignment
SAMFlag_FailedQC
SAMFlag_Duplicate

Definition at line 44 of file sam.h.

Function Documentation

template<typename vector_type >

void nvbio::io::analyze_md_string	(	const vector_type	mds,
		uint32 &	n_mm,
		uint32 &	n_gapo,
		uint32 &	n_gape
	)

Definition at line 77 of file output_utils.h.

int nvbio::io::append ( const Alphabet  alphabet, SequenceDataHost *  data, SequenceDataStream *  stream, const uint32  batch_size, const uint32  batch_bps  )

related

Definition at line 504 of file sequence_encoder.cpp.

uint32 nvbio::io::compute_cigar_pos ( const uint32  sink, const uint32  alignment  )

inline

Definition at line 37 of file output_utils.h.

template<typename vector_type >

uint32 nvbio::io::count_symbols	(	const Cigar::Operation	type,
		const vector_type	cigar,
		const uint32	cigar_len
	)

Definition at line 60 of file output_utils.h.

SequenceDataEncoder * nvbio::io::create_encoder	(	const Alphabet	alphabet,
		SequenceDataHost *	data
	)

create a sequence encoder

Definition at line 424 of file sequence_encoder.cpp.

NVBIO_FORCEINLINE NVBIO_HOST_DEVICE bool nvbio::io::distinct_alignments	(	const uint32	apos1,
		const uint32	opos1,
		const bool	arc1,
		const bool	orc1,
		const uint32	apos2,
		const uint32	opos2,
		const bool	arc2,
		const bool	orc2
	)

Definition at line 51 of file alignments_inl.h.

template<Alphabet ALPHABET, QualityEncoding quality_encoding, typename sequence_type >

void nvbio::io::encode	(	const sequence_type	sequence,
		typename SequenceDataEdit< ALPHABET, SequenceDataView >::sequence_stream_type	stream,
		char *	qual_stream
	)

Definition at line 180 of file sequence_encoder.cpp.

template<Alphabet ALPHABET, typename sequence_type >

void nvbio::io::encode	(	const QualityEncoding	quality_encoding,
		const sequence_type	sequence,
		typename SequenceDataEdit< ALPHABET, SequenceDataView >::sequence_stream_type	stream,
		char *	qual_stream
	)

Definition at line 207 of file sequence_encoder.cpp.

template<Alphabet ALPHABET>

void nvbio::io::encode	(	const SequenceDataEncoder::StrandOp	conversion_flags,
		const QualityEncoding	quality_encoding,
		const uint32	sequence_len,
		const uint8 *	sequence,
		const uint8 *	quality,
		typename SequenceDataEdit< ALPHABET, SequenceDataView >::sequence_stream_type	stream,
		char *	qual_stream
	)

Definition at line 236 of file sequence_encoder.cpp.

template<QualityEncoding quality_encoding, typename read_type >

void nvbio::io::encode	(	const read_type	read,
		ReadData::read_stream_type::iterator	stream,
		char *	qual_stream
	)

Definition at line 382 of file reads.cpp.

template<typename read_type >

void nvbio::io::encode	(	const QualityEncoding	quality_encoding,
		const read_type	read,
		ReadData::read_stream_type::iterator	stream,
		char *	qual_stream
	)

Definition at line 409 of file reads.cpp.

void nvbio::io::encode	(	const ReadDataRAM::StrandOp	conversion_flags,
		const QualityEncoding	quality_encoding,
		const uint32	read_len,
		const uint8 *	read,
		const uint8 *	quality,
		ReadData::read_stream_type::iterator	stream,
		char *	qual_stream
	)

Definition at line 434 of file reads.cpp.

AlignmentData nvbio::io::get	(	HostOutputBatchSE &	batch,
		const uint32	aln_id
	)

Definition at line 41 of file output_priv.cpp.

AlignmentData nvbio::io::get_anchor_mate	(	HostOutputBatchPE &	batch,
		const uint32	aln_id
	)

Definition at line 85 of file output_priv.cpp.

AlignmentData nvbio::io::get_mate	(	HostOutputBatchPE &	batch,
		const uint32	aln_id,
		const AlignmentMate	mate
	)

Definition at line 57 of file output_priv.cpp.

AlignmentData nvbio::io::get_opposite_mate	(	HostOutputBatchPE &	batch,
		const uint32	aln_id
	)

Definition at line 101 of file output_priv.cpp.

bool nvbio::io::is_pac_archive

(

const char *

sequence_file_name)

check whether the file name points to a pac archive

Definition at line 244 of file sequence_pac.cpp.

bool nvbio::io::load_pac	(	const Alphabet	alphabet,
		SequenceDataHost *	sequence_data,
		const char *	prefix,
		const SequenceFlags	load_flags,
		const QualityEncoding	qualities
	)

load a sequence file

Parameters

sequence_file_name	the file to open
qualities	the encoding of the qualities
max_seqs	maximum number of reads to input
max_sequence_len	maximum read length - reads will be truncated
flags	a set of flags indicating which strands to encode in the batch for each read. For example, passing FORWARD | REVERSE_COMPLEMENT will result in a stream containing BOTH the forward and reverse-complemented strands.

Definition at line 275 of file sequence_pac.cpp.

bool nvbio::io::load_pac	(	const Alphabet	alphabet,
		struct SequenceDataMMAPServer *	sequence_data,
		const char *	prefix,
		const char *	mapped_name,
		const SequenceFlags	load_flags,
		const QualityEncoding	qualities
	)

load a sequence file

Parameters

sequence_file_name	the file to open
qualities	the encoding of the qualities
max_seqs	maximum number of reads to input
max_sequence_len	maximum read length - reads will be truncated
flags	a set of flags indicating which strands to encode in the batch for each read. For example, passing FORWARD | REVERSE_COMPLEMENT will result in a stream containing BOTH the forward and reverse-complemented strands.

Definition at line 359 of file sequence_pac.cpp.

bool nvbio::io::load_sequence_file	(	const Alphabet	alphabet,
		SequenceDataHost *	sequence_data,
		const char *	sequence_file_name,
		const SequenceFlags	load_flags,
		const QualityEncoding	qualities
	)

Definition at line 227 of file sequence_priv.cpp.

SequenceDataHost* nvbio::io::load_sequence_file	(	const Alphabet	alphabet,
		const char *	sequence_file_name,
		const SequenceFlags	load_flags,
		const QualityEncoding	qualities
	)

load a sequence file

Parameters

alphabet	the alphabet used to encode the sequence data
sequence_file_name	the file to open
load_flags	a set of flags indicating what to load
qualities	the encoding of the qualities

Definition at line 255 of file sequence_priv.cpp.

bool nvbio::io::loadVCF	(	SNPDatabase &	output,
		const char *	file_name
	)

Definition at line 95 of file vcf.cpp.

int nvbio::io::next ( const Alphabet  alphabet, SequenceDataHost *  data, SequenceDataStream *  stream, const uint32  batch_size, const uint32  batch_bps  )

related

Definition at line 455 of file sequence_encoder.cpp.

SequenceDataOutputStream* nvbio::io::open_output_sequence_file ( const char *  sequence_file_name, const char *  options  )

related

Definition at line 276 of file sequence_priv.cpp.

SequenceDataStream* nvbio::io::open_sequence_file ( const char *  sequence_file_name, const QualityEncoding  qualities, const uint32  max_seqs, const uint32  max_sequence_len, const SequenceEncoding  flags, const uint32  trim3, const uint32  trim5  )

related

Definition at line 85 of file sequence_priv.cpp.

template<typename vector_type >

uint32 nvbio::io::reference_cigar_length	(	const vector_type	cigar,
		const uint32	cigar_len
	)

Definition at line 44 of file output_utils.h.

int nvbio::io::skip	(	SequenceDataStream *	stream,
		const uint32	batch_size,
		const uint32	batch_bps
	)

Definition at line 553 of file sequence_encoder.cpp.