On disk DNA suffix array and hash. More...

Classes
class	incremental_hash
	Update the hash value of a sequence incrementally. More...

class	incremental_query
	Incrementally elongate a query while keeping track of the suffix array range. More...

class	incremental_reverse_query
	Incrementally elongate a query while keeping track of the suffix array range (queries the reverse index). More...

class	iterator
	Iterator that decodes raw suffix array coordinates into chromosome-position pairs. More...

Public Types
enum	SeqEnc { ENC_DNA =0, ENC_CHAR =1, ENC_UNKNOWN }
	Enum of possible encodings of the DNA sequence.

typedef intpack::const_iterator	raw_iterator

typedef std::pair < raw_iterator, raw_iterator >	rawrange

typedef std::pair< iterator, iterator >	range

Public Member Functions
	suffix_index (const std::string &indexfile, const bool map_lcp=false, const bool map_rev=false)
	Constructor: mmap the index file.

void	decode_position (shore::refseq_coor &res, const size_t raw, const int reverse_offset)
	Decode a raw suffix array coordinate to a chromosome-position pair. More...

raw_iterator	array_begin () const
	Direct access to the start of the suffix array data.

raw_iterator	array_end () const
	Direct access to the end of the suffix array data.

raw_iterator	lcp_begin () const
	Direct access to the start of the LCP array data.

raw_iterator	lcp_end () const
	Direct access to the end of the LCP array data.

packeddna_iterator	sequence_begin () const
	Direct access to the start of the sequence data.

packeddna_iterator	sequence_end () const
	Direct access to the end of the sequence data.

iterator	coor_begin () const

iterator	coor_end () const

template<typename Iter >
rawrange	match_raw (Iter f, Iter t, typename boost::enable_if< boost::is_same< typename std::iterator_traits< Iter >::value_type, nuc::packed_base > >::type *dummy=0) const
	Find all perfect matches for the given sequence (version for nuc::packed_base iterators).

template<typename Iter >
rawrange	match_raw (Iter f, Iter t, typename boost::enable_if< boost::is_same< typename std::iterator_traits< Iter >::value_type, nuc::base > >::type *dummy=0) const
	Find all perfect matches for the given sequence (version for nuc::base iterators).

template<typename Iter >
rawrange	match_raw (Iter f, Iter t, typename boost::enable_if< boost::is_same< typename std::iterator_traits< Iter >::value_type, char > >::type *dummy=0) const
	Find all perfect matches for the given sequence (version for char iterators).

template<typename Iter >
range	match (Iter f, Iter t) const
	Find all perfect matches for the given sequence.

range	match (const std::string &str) const
	Find all perfect matches for the given sequence.

template<typename Iter >
std::pair< rawrange, Iter >	match5_raw (Iter f, Iter t, typename boost::enable_if< boost::is_same< typename std::iterator_traits< Iter >::value_type, nuc::packed_base > >::type *dummy=0) const
	Find the longest perfect match for the 5'end of the given sequence.

template<typename Iter >
std::pair< rawrange, Iter >	match5_reverse_raw (Iter f, Iter t, typename boost::enable_if< boost::is_same< typename std::iterator_traits< Iter >::value_type, nuc::packed_base > >::type *dummy=0) const
	Find the longest perfect match for the 5'end of the given sequence.

template<typename Iter >
std::pair< range, Iter >	match5 (Iter f, Iter t) const
	Find the longest perfect match for the 5'end of the given sequence.

std::pair< range, std::string::const_iterator >	match5 (const std::string &query) const
	Find the longest perfect match for the 5'end of the given sequence.

template<typename Iter >
std::pair< range, Iter >	match5_reverse (Iter f, Iter t) const
	Find the longest perfect match for the 5'end of the given sequence.

std::pair< range, std::string::const_iterator >	match5_reverse (const std::string &query) const
	Find the longest perfect match for the 5'end of the given sequence.

template<typename Iter >
size_t	count (Iter f, Iter t) const
	Count the number of occurences of a kmer.

size_t	count (const std::string &str) const
	Count the number of occurences of a kmer.

template<typename Iter >
double	calc_freq (Iter f, Iter t) const
	Calculate the frequency of a kmer.

double	calc_freq (const std::string &str) const
	Calculate the frequency of a kmer.

const idxinfo	get_header () const
	Get the index header.

template<typename Iter >
suffix_index::rawrange	match_raw (Iter f, Iter t, typename boost::enable_if< boost::is_same< typename std::iterator_traits< Iter >::value_type, nuc::packed_base > >::type *dummy) const

template<typename Iter >
suffix_index::rawrange	match_raw (Iter f, Iter t, typename boost::enable_if< boost::is_same< typename std::iterator_traits< Iter >::value_type, nuc::base > >::type *dummy) const

template<typename Iter >
suffix_index::rawrange	match_raw (Iter f, Iter t, typename boost::enable_if< boost::is_same< typename std::iterator_traits< Iter >::value_type, char > >::type *dummy) const

template<typename Iter >
suffix_index::range	match (Iter f, Iter t) const

template<typename Iter >
std::pair < suffix_index::rawrange, Iter >	match5_raw (Iter f, Iter t, typename boost::enable_if< boost::is_same< typename std::iterator_traits< Iter >::value_type, nuc::packed_base > >::type *dummy) const

template<typename Iter >
std::pair< suffix_index::range, Iter >	match5 (Iter f, Iter t) const

template<typename Iter >
std::pair < suffix_index::rawrange, Iter >	match5_reverse_raw (Iter f, Iter t, typename boost::enable_if< boost::is_same< typename std::iterator_traits< Iter >::value_type, nuc::packed_base > >::type *dummy) const

template<typename Iter >
std::pair< suffix_index::range, Iter >	match5_reverse (Iter f, Iter t) const

Static Public Member Functions
static void	build (const std::string &fasta_fn, const std::string &out_fn, std::ostream *const log=0, const int kmersize=10, const bool with_lcp=false, const bool with_rev=false)
	Create index file from fasta input.

static void	build (const std::vector< std::string > &fasta_fn, const std::string &out_fn, std::ostream *const log=0, const int kmersize=10, const bool with_lcp=false, const bool with_rev=false)
	Create index file from fasta input.

static void	build (const std::vector< std::string > &fasta_fn, std::ostream &out, std::ostream *const log=0, const int kmersize=10, const bool with_lcp=false, const bool with_rev=false)
	Create index file from fasta input.

template<typename Iter >
static size_t	lhash (Iter f, Iter t, const size_t n, typename boost::enable_if< boost::is_same< typename std::iterator_traits< Iter >::value_type, nuc::packed_base > >::type *dummy=0)
	Calculate the hash index for a DNA sequence. More...

template<typename Iter >
static size_t	rhash (Iter f, Iter t, const size_t n, typename boost::enable_if< boost::is_same< typename std::iterator_traits< Iter >::value_type, nuc::packed_base > >::type *dummy=0)
	Calculate the hash index for a DNA sequence. More...

template<typename Iter >
static size_t	lhash (Iter f, Iter t, const size_t n, typename boost::enable_if< boost::is_same< typename std::iterator_traits< Iter >::value_type, nuc::base > >::type *dummy=0)

template<typename Iter >
static size_t	lhash (Iter f, Iter t, const size_t n, typename boost::enable_if< boost::is_same< typename std::iterator_traits< Iter >::value_type, char > >::type *dummy=0)

template<typename Iter >
static size_t	rhash (Iter f, Iter t, const size_t n, typename boost::enable_if< boost::is_same< typename std::iterator_traits< Iter >::value_type, nuc::base > >::type *dummy=0)

template<typename Iter >
static size_t	rhash (Iter f, Iter t, const size_t n, typename boost::enable_if< boost::is_same< typename std::iterator_traits< Iter >::value_type, char > >::type *dummy=0)

static const std::string	unhash (const size_t hash, const size_t len)
	Reconstructs the DNA sequence from a hash (inverse of lhash()).

Detailed Description

On disk DNA suffix array and hash.

Member Function Documentation

void shore::suffix_index::decode_position	(	shore::refseq_coor &	res,
		const size_t	raw,
		const int	reverse_offset
	)

Decode a raw suffix array coordinate to a chromosome-position pair.

Parameters

reverse_offset Length of the match for reverse index matches, zero for forward index matches.

template<typename Iter >

static size_t shore::suffix_index::lhash	(	Iter	f,
		Iter	t,
		const size_t	n,
		typename boost::enable_if< boost::is_same< typename std::iterator_traits< Iter >::value_type, nuc::packed_base > >::type *	dummy = `0`
	)

inlinestatic

Calculate the hash index for a DNA sequence.

Parameters

f	Start of the DNA.
t	End of the DNA.
n	Length of the sequence to be hashed, may not be equal to t-f.

The hash returned will point to the first suffix array entry that matches the DNA.

template<typename Iter >

static size_t shore::suffix_index::rhash	(	Iter	f,
		Iter	t,
		const size_t	n,
		typename boost::enable_if< boost::is_same< typename std::iterator_traits< Iter >::value_type, nuc::packed_base > >::type *	dummy = `0`
	)

inlinestatic

Calculate the hash index for a DNA sequence.

Parameters

f	Start of the DNA.
t	End of the DNA.
n	Length of the sequence to be hashed, may not be equal to t-f.

The hash returned will point to the end of the suffix array entries that match the DNA.

The documentation for this class was generated from the following file:

shore/algo/suffix_index.hpp

Classes

Public Types

Public Member Functions

Static Public Member Functions

Detailed Description

Member Function Documentation