#include <bloom_filter.hpp>

Public Member Functions
	SeedBloomFilter ()

	SeedBloomFilter (size_t bytes, unsigned k, const std::vector< std::string > &seeds, unsigned hash_num_per_seed)

	SeedBloomFilter (const std::string &path)

	SeedBloomFilter (const SeedBloomFilter &)=delete

	SeedBloomFilter (SeedBloomFilter &&)=delete

SeedBloomFilter &	operator= (const SeedBloomFilter &)=delete

SeedBloomFilter &	operator= (SeedBloomFilter &&)=delete

void	insert (const char *seq, size_t seq_len)

void	insert (const std::string &seq)

void	insert (const uint64_t *hashes)

void	insert (const std::vector< uint64_t > &hashes)

std::vector< std::vector< unsigned > >	contains (const char *seq, size_t seq_len) const

std::vector< std::vector< unsigned > >	contains (const std::string &seq) const

bool	contains (const uint64_t *hashes) const

bool	contains (const std::vector< uint64_t > &hashes) const

std::vector< std::vector< unsigned > >	contains_insert (const char *seq, size_t seq_len)

std::vector< std::vector< unsigned > >	contains_insert (const std::string &seq)

bool	contains_insert (const uint64_t *hashes)

bool	contains_insert (const std::vector< uint64_t > &hashes)

size_t	get_bytes () const

uint64_t	get_pop_cnt () const

double	get_occupancy () const

unsigned	get_total_hash_num () const

double	get_fpr () const

unsigned	get_k () const

const std::vector< std::string > &	get_seeds () const

const std::vector< btllib::hashing_internals::SpacedSeed > &	get_parsed_seeds () const

unsigned	get_hash_num_per_seed () const

unsigned	get_hash_num () const

const std::string &	get_hash_fn () const

KmerBloomFilter &	get_kmer_bloom_filter ()

void	save (const std::string &path)

Static Public Member Functions
static bool	is_bloom_file (const std::string &path)

Detailed Description

Bloom filter data structure that stores spaced seed k-mers.

Constructor & Destructor Documentation

◆ SeedBloomFilter() [1/3]

btllib::SeedBloomFilter::SeedBloomFilter ( )

inline

Construct a dummy Seed Bloom filter (e.g. as a default argument).

◆ SeedBloomFilter() [2/3]

btllib::SeedBloomFilter::SeedBloomFilter	(	size_t	bytes,
		unsigned	k,
		const std::vector< std::string > &	seeds,
		unsigned	hash_num_per_seed )

Construct an empty Seed Bloom filter of given size.

Parameters

bytes	Filter size in bytes.
k	K-mer size.
seeds	A vector of spaced seeds in string format. 0s indicate ignored and 1s indicate relevant bases.

◆ SeedBloomFilter() [3/3]

btllib::SeedBloomFilter::SeedBloomFilter ( const std::string & path )

explicit

Load a Seed Bloom filter from a file.

Parameters

path	Filepath to load from.

Member Function Documentation

◆ contains() [1/4]

std::vector< std::vector< unsigned > > btllib::SeedBloomFilter::contains	(	const char *	seq,
		size_t	seq_len ) const

Query the presence of spaced seed k-mers of a sequence.

Parameters

seq	Sequence to k-merize.
seq_len	Length of seq.

Returns: A vector indicating which seeds had a hit for every k-mer. The indices of the outer vector are indices of seq k-mers. The indices of inner vector are indices of spaced seeds hit for that k-mer.

◆ contains() [2/4]

std::vector< std::vector< unsigned > > btllib::SeedBloomFilter::contains ( const std::string & seq ) const

inline

Query the presence of spaced seed k-mers of a sequence.

Parameters

seq	Sequence to k-merize.

Returns: A vector indicating which seeds had a hit for every k-mer. The indices of the outer vector are indices of seq k-mers. The indices of inner vector are indices of spaced seeds hit for that k-mer.

◆ contains() [3/4]

bool btllib::SeedBloomFilter::contains ( const std::vector< uint64_t > & hashes ) const

inline

Check for the presence of an element's hash values. A single spaced seed is an element here.

Parameters

hashes Integer vector of hash values.

◆ contains() [4/4]

bool btllib::SeedBloomFilter::contains ( const uint64_t * hashes ) const

inline

Check for the presence of an element's hash values. A single spaced seed is an element here.

Parameters

hashes Integer array of hash values. Array size should equal the hash_num_per_seed argument used when the Bloom filter was constructed.

◆ contains_insert() [1/4]

std::vector< std::vector< unsigned > > btllib::SeedBloomFilter::contains_insert	(	const char *	seq,
		size_t	seq_len )

Query the presence of spaced seed k-mers of a sequence and insert if missing.

Parameters

seq	Sequence to k-merize.
seq_len	Length of seq.

Returns: A vector indicating which seeds had a hit for every k-mer before insertion. The indices of the outer vector are indices of seq k-mers. The indices of inner vector are indices of spaced seeds hit for that k-mer.

◆ contains_insert() [2/4]

std::vector< std::vector< unsigned > > btllib::SeedBloomFilter::contains_insert ( const std::string & seq )

inline

Query the presence of spaced seed k-mers of a sequence and insert if missing.

Parameters

seq	Sequence to k-merize.

Returns: A vector indicating which seeds had a hit for every k-mer before insertion. The indices of the outer vector are indices of seq k-mers. The indices of inner vector are indices of spaced seeds hit for that k-mer.

◆ contains_insert() [3/4]

bool btllib::SeedBloomFilter::contains_insert ( const std::vector< uint64_t > & hashes )

inline

Check for the presence of an element's hash values and insert if missing. A single spaced seed is an element here.

Parameters

hashes Integer vector of hash values.

Returns: True if present before insertion, false otherwise.

◆ contains_insert() [4/4]

bool btllib::SeedBloomFilter::contains_insert ( const uint64_t * hashes )

inline

Check for the presence of an element's hash values and insert if missing. A single spaced seed is an element here.

Parameters

hashes Integer array of hash values. Array size should equal the hash_num_per_seed argument used when the Bloom filter was constructed.

Returns: True if present before insertion, false otherwise.

◆ get_bytes()

size_t btllib::SeedBloomFilter::get_bytes ( ) const

inline

Get filter size in bytes.

◆ get_fpr()

double btllib::SeedBloomFilter::get_fpr ( ) const

Get the false positive rate of at least one seed falsely reporting a hit per k-mer.

◆ get_hash_fn()

const std::string & btllib::SeedBloomFilter::get_hash_fn ( ) const

inline

Get the name of the hash function used.

◆ get_hash_num()

unsigned btllib::SeedBloomFilter::get_hash_num ( ) const

inline

Get the number of hash values per element, i.e. seed.

◆ get_hash_num_per_seed()

unsigned btllib::SeedBloomFilter::get_hash_num_per_seed ( ) const

inline

Get the number of hash values per element, i.e. seed.

◆ get_k()

unsigned btllib::SeedBloomFilter::get_k ( ) const

inline

Get the k-mer size used.

◆ get_kmer_bloom_filter()

KmerBloomFilter & btllib::SeedBloomFilter::get_kmer_bloom_filter ( )

inline

Get a reference to the underlying Kmer Bloom filter.

◆ get_occupancy()

double btllib::SeedBloomFilter::get_occupancy ( ) const

inline

Get the fraction of the filter occupied by 1 bits.

◆ get_parsed_seeds()

const std::vector< btllib::hashing_internals::SpacedSeed > & btllib::SeedBloomFilter::get_parsed_seeds ( ) const

inline

Get the seeds used in parsed format. Parsed format is a vector of indices of 0s in the seed.

◆ get_pop_cnt()

uint64_t btllib::SeedBloomFilter::get_pop_cnt ( ) const

inline

Get population count, i.e. the number of 1 bits in the filter.

◆ get_seeds()

const std::vector< std::string > & btllib::SeedBloomFilter::get_seeds ( ) const

inline

Get the seeds used in string format.

◆ get_total_hash_num()

unsigned btllib::SeedBloomFilter::get_total_hash_num ( ) const

inline

Get the number of hash values per k-mer, i.e. total number of hash values for all seeds.

◆ insert() [1/4]

void btllib::SeedBloomFilter::insert	(	const char *	seq,
		size_t	seq_len )

Insert a sequence's spaced seed k-mers into the filter.

Parameters

seq	Sequence to k-merize.
seq_len	Length of seq.

◆ insert() [2/4]

void btllib::SeedBloomFilter::insert ( const std::string & seq )

inline

Insert a sequence's spaced seed k-mers into the filter.

Parameters

seq	Sequence to k-merize.

◆ insert() [3/4]

void btllib::SeedBloomFilter::insert ( const std::vector< uint64_t > & hashes )

inline

Insert an element's hash values.

Parameters

hashes Integer vector of hash values.

◆ insert() [4/4]

void btllib::SeedBloomFilter::insert ( const uint64_t * hashes )

inline

Insert an element's hash values.

Parameters

hashes Integer array of hash values. Array size should equal the hash_num argument used when the Bloom filter was constructed.

◆ is_bloom_file()

static bool btllib::SeedBloomFilter::is_bloom_file ( const std::string & path )

inlinestatic

Check whether the file at the given path is a saved Seed Bloom filter.

Parameters

path	Filepath to check.

◆ save()

void btllib::SeedBloomFilter::save ( const std::string & path )

Save the Bloom filter to a file that can be loaded in the future.

Parameters

path	Filepath to store filter at.

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

include/btllib/bloom_filter.hpp

Public Member Functions

Static Public Member Functions

Detailed Description

Constructor & Destructor Documentation

◆ SeedBloomFilter() [1/3]

◆ SeedBloomFilter() [2/3]

◆ SeedBloomFilter() [3/3]

Member Function Documentation

◆ contains() [1/4]

◆ contains() [2/4]

◆ contains() [3/4]

◆ contains() [4/4]

◆ contains_insert() [1/4]

◆ contains_insert() [2/4]

◆ contains_insert() [3/4]

◆ contains_insert() [4/4]

◆ get_bytes()

◆ get_fpr()

◆ get_hash_fn()

◆ get_hash_num()

◆ get_hash_num_per_seed()

◆ get_k()

◆ get_kmer_bloom_filter()

◆ get_occupancy()

◆ get_parsed_seeds()

◆ get_pop_cnt()

◆ get_seeds()

◆ get_total_hash_num()

◆ insert() [1/4]

◆ insert() [2/4]

◆ insert() [3/4]

◆ insert() [4/4]

◆ is_bloom_file()

◆ save()