Represent a Compacted de Bruijn graph. More...

Public Types
typedef unitigIterator< U, G, false >	iterator
	An iterator for the unitigs of the graph. More...

typedef unitigIterator< U, G, true >	const_iterator
	A constant iterator for the unitigs of the graph. More...

Public Member Functions
	CompactedDBG (const int kmer_length=31, const int minimizer_length=-1)
	Constructor (set up an empty compacted dBG). More...

	CompactedDBG (const CompactedDBG< U, G > &o)
	Copy constructor (copy a compacted de Bruijn graph). More...

	CompactedDBG (CompactedDBG< U, G > &&o)
	Move constructor (move a compacted de Bruijn graph). More...

virtual	~CompactedDBG ()
	Destructor.

CompactedDBG< U, G > &	operator= (const CompactedDBG< U, G > &o)
	Copy assignment operator (copy a compacted de Bruijn graph). More...

CompactedDBG< U, G > &	operator= (CompactedDBG< U, G > &&o)
	Move assignment operator (move a compacted de Bruijn graph). More...

CompactedDBG< U, G > &	operator+= (const CompactedDBG< U, G > &o)
	Addition assignment operator (merge a compacted de Bruijn graph). More...

bool	operator== (const CompactedDBG< U, G > &o) const
	Equality operator. More...

bool	operator!= (const CompactedDBG< U, G > &o) const
	Inequality operator. More...

void	clear ()
	Clear the graph: empty the graph and reset its parameters.

bool	build (CDBG_Build_opt &opt)
	Build the Compacted de Bruijn graph. More...

bool	simplify (const bool delete_short_isolated_unitigs=true, const bool clip_short_tips=true, const bool verbose=false)
	Simplify the Compacted de Bruijn graph: clip short (< 2k length) tips and/or delete short (< 2k length) isolated unitigs. More...

bool	write (const string &output_fn, const size_t nb_threads=1, const bool GFA_output=true, const bool FASTA_output=false, const bool BFG_output=false, const bool write_index_file=true, const bool compressed_output=false, const bool verbose=false) const
	Write the Compacted de Bruijn graph to disk (GFA1 format). More...

bool	read (const string &input_graph_fn, const size_t nb_threads=1, const bool verbose=false)
	Load a Compacted de Bruijn graph from disk (GFA1 or FASTA format). More...

bool	read (const string &input_graph_fn, const string &input_index_fn, const size_t nb_threads=1, const bool verbose=false)
	Read a Compacted de Bruijn graph from disk (GFA1, FASTA or BFG format) using an index file (BFI format). More...

UnitigMap< U, G >	find (const Kmer &km, const bool extremities_only=false)
	Find the unitig containing the queried k-mer in the Compacted de Bruijn graph. More...

const_UnitigMap< U, G >	find (const Kmer &km, const bool extremities_only=false) const
	Find the unitig containing the queried k-mer in the Compacted de Bruijn graph. More...

UnitigMap< U, G >	findUnitig (const char *s, const size_t pos, const size_t len)
	Find the unitig containing the k-mer starting at a given position in a query sequence and extends the mapping (if the k-mer is found, the function extends the mapping from the k-mer as long as the query sequence and the unitig matches). More...

const_UnitigMap< U, G >	findUnitig (const char *s, const size_t pos, const size_t len) const
	Find the unitig containing the k-mer starting at a given position in a query sequence and extends the mapping (if the k-mer is found, the function extends the mapping from the k-mer as long as the query sequence and the unitig matches). More...

vector< pair< size_t, UnitigMap< U, G > > >	searchSequence (const string &s, const bool exact, const bool insertion, const bool deletion, const bool substitution, const bool or_exclusive_match=false)
	Performs exact and/or inexact search of the k-mers of a sequence query in the Compacted de Bruijn graph. More...

vector< pair< size_t, const_UnitigMap< U, G > > >	searchSequence (const string &s, const bool exact, const bool insertion, const bool deletion, const bool substitution, const bool or_exclusive_match=false) const
	Performs exact and/or inexact search of the k-mers of a sequence query in the Compacted de Bruijn graph. More...

bool	add (const string &seq, const bool verbose=false)
	Add a sequence to the Compacted de Bruijn graph. More...

bool	remove (const const_UnitigMap< U, G > &um, const bool verbose=false)
	Remove a unitig from the Compacted de Bruijn graph. More...

bool	merge (const CompactedDBG &o, const size_t nb_threads=1, const bool verbose=false)
	Merge a compacted de Bruijn graph. More...

bool	merge (const vector< CompactedDBG > &v, const size_t nb_threads=1, const bool verbose=false)
	Merge multiple compacted de Bruijn graphs. More...

iterator	begin ()
	Create an iterator to the first unitig of the Compacted de Bruijn graph (unitigs are NOT sorted lexicographically). More...

const_iterator	begin () const
	Create an constant iterator to the first unitig of the Compacted de Bruijn graph (unitigs are NOT sorted lexicographically). More...

iterator	end ()
	Create an iterator to the "past-the-last" unitig of the Compacted de Bruijn graph (unitigs are NOT sorted lexicographically). More...

const_iterator	end () const
	Create a constant iterator to the "past-the-last" unitig of the Compacted de Bruijn graph (unitigs are NOT sorted lexicographically). More...

size_t	length () const
	Return the sum of the unitigs length. More...

size_t	nbKmers () const
	Return the number of k-mers in the graph. More...

bool	isInvalid () const
	Return a boolean indicating if the graph is invalid (wrong input parameters/files, error occurring during a method, etc.). More...

int	getK () const
	Return the length of k-mers of the graph. More...

int	getG () const
	Return the length of minimizers of the graph. More...

size_t	size () const
	Return the number of unitigs in the graph. More...

G *	getData ()
	Return a pointer to the graph data. More...

const G *	getData () const
	Return a constant pointer to the graph data. More...

Detailed Description

template<typename Unitig_data_t = void, typename Graph_data_t = void>
class CompactedDBG< Unitig_data_t, Graph_data_t >

Represent a Compacted de Bruijn graph.

The two template parameters of this class corresponds to the type of data to associate with the unitigs of the graph (unitig data) and the type of data to associate with the graph (graph data). If no template parameters are specified or if the types are void, no data are associated with the unitigs nor the graph and no memory will be allocated for such data.

CompactedDBG<> cdbg_1; // No unitig data, no graph data
CompactedDBG<void> cdbg_2; // Equivalent to previous notation
CompactedDBG<void, void> cdbg_3; // Equivalent to previous notation
CompactedDBG<MyUnitigData> cdbg_4; // An object of type MyUnitigData will be associated with each unitig, no graph data
CompactedDBG<MyUnitigData, void> cdbg_5; // Equivalent to previous notation
CompactedDBG<void, MyGraphData> cdbg_6; // No unitig data, an object of type MyGraphData will be associated with the graph
CompactedDBG<MyUnitigData, MyGraphData> cdbg_7; // Unitig data of type MyUnitigData for each unitig, graph data of type MyGraphData

If data are to be associated with the unitigs, these data must be wrapped into a class that inherits from the abstract class CDBG_Data_t, such as in:

class MyUnitigData : public CDBG_Data_t<MyUnitigData> { ... };

CompactedDBG<MyUnitigData> cdbg;

Because CDBG_Data_t is an abstract class, all the methods from the base class (CDBG_Data_t) must be implemented in your wrapper (the derived class, aka MyUnitigData in this example). IMPORTANT: If you do not implement those methods in your class, default ones that have no effect will be applied.

Member Typedef Documentation

◆ const_iterator

template<typename Unitig_data_t = void, typename Graph_data_t = void>

typedef unitigIterator<U, G, true> CompactedDBG< Unitig_data_t, Graph_data_t >::const_iterator

A constant iterator for the unitigs of the graph.

No specific order is assumed.

◆ iterator

template<typename Unitig_data_t = void, typename Graph_data_t = void>

typedef unitigIterator<U, G, false> CompactedDBG< Unitig_data_t, Graph_data_t >::iterator

An iterator for the unitigs of the graph.

No specific order is assumed.

Constructor & Destructor Documentation

◆ CompactedDBG() [1/3]

template<typename Unitig_data_t = void, typename Graph_data_t = void>

CompactedDBG< Unitig_data_t, Graph_data_t >::CompactedDBG	(	const int	kmer_length = `31`,
		const int	minimizer_length = `-1`
	)

Constructor (set up an empty compacted dBG).

Parameters

kmer_length	is the length k of k-mers used in the graph (each unitig is of length at least k).
minimizer_length	is the length g of minimizers (g < k) used in the graph.

◆ CompactedDBG() [2/3]

template<typename Unitig_data_t = void, typename Graph_data_t = void>

CompactedDBG< Unitig_data_t, Graph_data_t >::CompactedDBG ( const CompactedDBG< U, G > & o )

Copy constructor (copy a compacted de Bruijn graph).

This function is expensive in terms of time and memory as the content of a compacted de Bruijn graph is copied. After the call to this function, the same graph exists twice in memory.

Parameters

o	is a constant reference to the compacted de Bruijn graph to copy.

◆ CompactedDBG() [3/3]

template<typename Unitig_data_t = void, typename Graph_data_t = void>

CompactedDBG< Unitig_data_t, Graph_data_t >::CompactedDBG ( CompactedDBG< U, G > && o )

Move constructor (move a compacted de Bruijn graph).

The content of o is moved ("transfered") to a new compacted de Bruijn graph. The compacted de Bruijn graph referenced by o will be empty after the call to this constructor.

Parameters

o	is a reference on a reference to the compacted de Bruijn graph to move.

Member Function Documentation

◆ add()

template<typename Unitig_data_t = void, typename Graph_data_t = void>

bool CompactedDBG< Unitig_data_t, Graph_data_t >::add	(	const string &	seq,
		const bool	verbose = `false`
	)

Add a sequence to the Compacted de Bruijn graph.

Non-{A,C,G,T} characters such as Ns are discarded. The function automatically breaks the sequence into unitig(s). Those unitigs can be stored as the reverse-complement of the input sequence.

Parameters

seq	is a string containing the sequence to insert.
verbose	is a boolean indicating if information messages must be printed during the function execution.

Returns: a boolean indicating if the sequence was successfully inserted in the graph.

◆ begin() [1/2]

template<typename Unitig_data_t = void, typename Graph_data_t = void>

iterator CompactedDBG< Unitig_data_t, Graph_data_t >::begin ( )

Create an iterator to the first unitig of the Compacted de Bruijn graph (unitigs are NOT sorted lexicographically).

Returns: an iterator to the first unitig of the graph.

◆ begin() [2/2]

template<typename Unitig_data_t = void, typename Graph_data_t = void>

const_iterator CompactedDBG< Unitig_data_t, Graph_data_t >::begin ( ) const

Create an constant iterator to the first unitig of the Compacted de Bruijn graph (unitigs are NOT sorted lexicographically).

Returns: a constant iterator to the first unitig of the graph.

◆ build()

template<typename Unitig_data_t = void, typename Graph_data_t = void>

bool CompactedDBG< Unitig_data_t, Graph_data_t >::build ( CDBG_Build_opt & opt )

Build the Compacted de Bruijn graph.

Parameters

opt	is a structure from which the members are parameters of this function. See CDBG_Build_opt.

Returns: boolean indicating if the graph has been built successfully.

◆ end() [1/2]

template<typename Unitig_data_t = void, typename Graph_data_t = void>

iterator CompactedDBG< Unitig_data_t, Graph_data_t >::end ( )

Create an iterator to the "past-the-last" unitig of the Compacted de Bruijn graph (unitigs are NOT sorted lexicographically).

Returns: an iterator to the "past-the-last" unitig of the graph.

◆ end() [2/2]

template<typename Unitig_data_t = void, typename Graph_data_t = void>

const_iterator CompactedDBG< Unitig_data_t, Graph_data_t >::end ( ) const

Create a constant iterator to the "past-the-last" unitig of the Compacted de Bruijn graph (unitigs are NOT sorted lexicographically).

Returns: a constant iterator to the "past-the-last" unitig of the graph.

◆ find() [1/2]

template<typename Unitig_data_t = void, typename Graph_data_t = void>

UnitigMap<U, G> CompactedDBG< Unitig_data_t, Graph_data_t >::find	(	const Kmer &	km,
		const bool	extremities_only = `false`
	)

Find the unitig containing the queried k-mer in the Compacted de Bruijn graph.

Parameters

km	is the queried k-mer (see Kmer class). It does not need to be a canonical k-mer.
extremities_only	is a boolean indicating if the k-mer must be searched only in the unitig heads and tails (extremities_only = true). By default, the k-mer is searched everywhere (extremities_only = false) but is is slightly slower than looking only in the unitig heads and tails.

Returns: UnitigMap<U, G> object containing the k-mer mapping information to the unitig containing the queried k-mer (if present). If the queried k-mer is not found, UnitigMap::isEmpty = true (see UnitigMap class).

◆ find() [2/2]

template<typename Unitig_data_t = void, typename Graph_data_t = void>

const_UnitigMap<U, G> CompactedDBG< Unitig_data_t, Graph_data_t >::find	(	const Kmer &	km,
		const bool	extremities_only = `false`
	)		const

Find the unitig containing the queried k-mer in the Compacted de Bruijn graph.

Parameters

km	is the queried k-mer (see Kmer class). It does not need to be a canonical k-mer.
extremities_only	is a boolean indicating if the k-mer must be searched only in the unitig heads and tails (extremities_only = true). By default, the k-mer is searched everywhere (extremities_only = false) but is is slightly slower than looking only in the unitig heads and tails.

Returns: const_UnitigMap<U, G> object containing the k-mer mapping information to the unitig having the queried k-mer (if present). If the k-mer is not found, const_UnitigMap::isEmpty = true (see UnitigMap class).

◆ findUnitig() [1/2]

template<typename Unitig_data_t = void, typename Graph_data_t = void>

UnitigMap<U, G> CompactedDBG< Unitig_data_t, Graph_data_t >::findUnitig	(	const char *	s,
		const size_t	pos,
		const size_t	len
	)

Find the unitig containing the k-mer starting at a given position in a query sequence and extends the mapping (if the k-mer is found, the function extends the mapping from the k-mer as long as the query sequence and the unitig matches).

Parameters

s	is a pointer to an array of character containing the sequence to query.
pos	is the position of the first k-mer to find in the sequence to query.
len	is the length of s.

Returns: UnitigMap<U, G> object containing the mapping information to the unitig having the queried k-mer (if present). If the k-mer is found, the function extends the mapping from the k-mer as long as the query sequence and the unitig matches (um.len >= 1).

◆ findUnitig() [2/2]

template<typename Unitig_data_t = void, typename Graph_data_t = void>

const_UnitigMap<U, G> CompactedDBG< Unitig_data_t, Graph_data_t >::findUnitig	(	const char *	s,
		const size_t	pos,
		const size_t	len
	)		const

Find the unitig containing the k-mer starting at a given position in a query sequence and extends the mapping (if the k-mer is found, the function extends the mapping from the k-mer as long as the query sequence and the unitig matches).

Parameters

s	is a pointer to an array of character containing the sequence to query.
pos	is the position of the first k-mer to find in the sequence to query.
len	is the length of s.

Returns: const_UnitigMap<U, G> object containing the mapping information to the unitig having the queried k-mer (if present). If the k-mer is found, the function extends the mapping from the k-mer as long as the query sequence and the unitig matches (um.len >= 1).

◆ getData() [1/2]

template<typename Unitig_data_t = void, typename Graph_data_t = void>

G* CompactedDBG< Unitig_data_t, Graph_data_t >::getData ( )

inline

Return a pointer to the graph data.

Pointer is nullptr if type of graph data is void.

Returns: A pointer to the graph data. Pointer is nullptr if type of graph data is void.

◆ getData() [2/2]

template<typename Unitig_data_t = void, typename Graph_data_t = void>

const G* CompactedDBG< Unitig_data_t, Graph_data_t >::getData ( ) const

inline

Return a constant pointer to the graph data.

Pointer is nullptr if type of graph data is void.

Returns: A constant pointer to the graph data. Pointer is nullptr if type of graph data is void.

◆ getG()

template<typename Unitig_data_t = void, typename Graph_data_t = void>

int CompactedDBG< Unitig_data_t, Graph_data_t >::getG ( ) const

inline

Return the length of minimizers of the graph.

Returns: Length of minimizers of the graph.

◆ getK()

template<typename Unitig_data_t = void, typename Graph_data_t = void>

int CompactedDBG< Unitig_data_t, Graph_data_t >::getK ( ) const

inline

Return the length of k-mers of the graph.

Returns: Length of k-mers of the graph.

◆ isInvalid()

template<typename Unitig_data_t = void, typename Graph_data_t = void>

bool CompactedDBG< Unitig_data_t, Graph_data_t >::isInvalid ( ) const

inline

Return a boolean indicating if the graph is invalid (wrong input parameters/files, error occurring during a method, etc.).

Returns: A boolean indicating if the graph is invalid.

◆ length()

template<typename Unitig_data_t = void, typename Graph_data_t = void>

size_t CompactedDBG< Unitig_data_t, Graph_data_t >::length ( ) const

Return the sum of the unitigs length.

Returns: An integer which corresponds to the sum of the unitigs length.

◆ merge() [1/2]

template<typename Unitig_data_t = void, typename Graph_data_t = void>

bool CompactedDBG< Unitig_data_t, Graph_data_t >::merge	(	const CompactedDBG< Unitig_data_t, Graph_data_t > &	o,
		const size_t	nb_threads = `1`,
		const bool	verbose = `false`
	)

Merge a compacted de Bruijn graph.

After merging, all unitigs of o have been added to and compacted with the current compacted de Bruijn graph (this). If the unitigs of o had data of type "MyUnitigData" associated, they have been added to the current compacted de Bruijn graph using the functions of the class MyUnitigData which are also present in its base class CDBG_Data_t<MyUnitigData>. Note that if multiple compacted de Bruijn graphs have to be merged, it is more efficient to call CompactedDBG::merge with a vector of CompactedDBG as input.

Parameters

o	is a constant reference to the compacted de Bruijn graph to merge.
nb_threads	is an integer indicating how many threads can be used during the merging.
verbose	is a boolean indicating if information messages must be printed during the execution of the function.

Returns: a boolean indicating if the graph has been successfully merged.

◆ merge() [2/2]

template<typename Unitig_data_t = void, typename Graph_data_t = void>

bool CompactedDBG< Unitig_data_t, Graph_data_t >::merge	(	const vector< CompactedDBG< Unitig_data_t, Graph_data_t > > &	v,
		const size_t	nb_threads = `1`,
		const bool	verbose = `false`
	)

Merge multiple compacted de Bruijn graphs.

After merging, all unitigs of the compacted de Bruijn graphs have been added to and compacted with the current compacted de Bruijn graph (this). If the unitigs had data of type "MyUnitigData" associated, they have been added to the current compacted de Bruijn graph using the functions of the class MyUnitigData which are also present in its base class CCDBG_Data_t<MyUnitigData>.

Parameters

v	is a constant reference to a vector of colored and compacted de Bruijn graphs to merge.
nb_threads	is an integer indicating how many threads can be used during the merging.
verbose	is a boolean indicating if information messages must be printed during the execution of the function.

Returns: a boolean indicating if the graphs have been successfully merged.

◆ nbKmers()

template<typename Unitig_data_t = void, typename Graph_data_t = void>

size_t CompactedDBG< Unitig_data_t, Graph_data_t >::nbKmers ( ) const

Return the number of k-mers in the graph.

Returns: An integer which corresponds to the number of k-mers in the graph.

◆ operator!=()

template<typename Unitig_data_t = void, typename Graph_data_t = void>

bool CompactedDBG< Unitig_data_t, Graph_data_t >::operator!= ( const CompactedDBG< U, G > & o ) const

inline

Inequality operator.

Returns: a boolean indicating if two compacted de Bruijn graphs have different unitigs (does not compare the data associated with the unitigs).

◆ operator+=()

template<typename Unitig_data_t = void, typename Graph_data_t = void>

CompactedDBG<U, G>& CompactedDBG< Unitig_data_t, Graph_data_t >::operator+= ( const CompactedDBG< U, G > & o )

Addition assignment operator (merge a compacted de Bruijn graph).

After merging, all unitigs of o have been added to and compacted with the current compacted de Bruijn graph (this). If the unitigs of o had data of type "MyUnitigData" associated, they have been added to the current compacted de Bruijn graph using the functions of the class MyUnitigData which are in base class CDBG_Data_t<MyUnitigData>. This function is similar to CompactedDBG::merge except that it uses only one thread while CompactedDBG::merge can work with multiple threads (number of threads provided as a parameter). Note that if multiple compacted de Bruijn graphs have to be merged, it is more efficient to call CompactedDBG::merge with a vector of CompactedDBG as input.

Parameters

o	is a constant reference to the compacted de Bruijn graph to merge.

Returns: a reference to the current compacted de Bruijn after merging.

◆ operator=() [1/2]

template<typename Unitig_data_t = void, typename Graph_data_t = void>

CompactedDBG<U, G>& CompactedDBG< Unitig_data_t, Graph_data_t >::operator= ( CompactedDBG< U, G > && o )

Move assignment operator (move a compacted de Bruijn graph).

The content of o is moved ("transfered") to a new compacted de Bruijn graph. The compacted de Bruijn graph referenced by o will be empty after the call to this operator.

Parameters

o	is a reference on a reference to the compacted de Bruijn graph to move.

Returns: a reference to the compacted de Bruijn which has (and owns) the content of o.

◆ operator=() [2/2]

template<typename Unitig_data_t = void, typename Graph_data_t = void>

CompactedDBG<U, G>& CompactedDBG< Unitig_data_t, Graph_data_t >::operator= ( const CompactedDBG< U, G > & o )

Copy assignment operator (copy a compacted de Bruijn graph).

This function is expensive in terms of time and memory as the content of a compacted de Bruijn graph is copied. After the call to this function, the same graph exists twice in memory.

Parameters

o	is a constant reference to the compacted de Bruijn graph to copy.

Returns: a reference to the compacted de Bruijn which is the copy.

◆ operator==()

template<typename Unitig_data_t = void, typename Graph_data_t = void>

bool CompactedDBG< Unitig_data_t, Graph_data_t >::operator== ( const CompactedDBG< U, G > & o ) const

Equality operator.

Returns: a boolean indicating if two compacted de Bruijn graphs have the same unitigs (does not compare the data associated with the unitigs).

◆ read() [1/2]

template<typename Unitig_data_t = void, typename Graph_data_t = void>

bool CompactedDBG< Unitig_data_t, Graph_data_t >::read	(	const string &	input_graph_fn,
		const size_t	nb_threads = `1`,
		const bool	verbose = `false`
	)

Load a Compacted de Bruijn graph from disk (GFA1 or FASTA format).

This function detects if an index file (BFI format) exists (same prefix as graph) for the input graph and will use it to load the graph. Otherwise, loading will be slower than read() with the index graph file. If the input GFA file has not been built by Bifrost or if the input is FASTA format, it is your responsibility to make sure that the graph is correctly compacted and to set correctly the parameters of the graph (such as the k-mer length) before the call to this function.

Parameters

input_graph_fn	is a string containing the name of the graph file to read.
nb_threads	is a number indicating how many threads can be used to read the graph from disk.
verbose	is a boolean indicating if information messages must be printed during the function execution.

Returns: boolean indicating if the graph has been read successfully.

◆ read() [2/2]

template<typename Unitig_data_t = void, typename Graph_data_t = void>

bool CompactedDBG< Unitig_data_t, Graph_data_t >::read	(	const string &	input_graph_fn,
		const string &	input_index_fn,
		const size_t	nb_threads = `1`,
		const bool	verbose = `false`
	)

Read a Compacted de Bruijn graph from disk (GFA1, FASTA or BFG format) using an index file (BFI format).

Index files make the loading much faster than the other function read() without meta graph file. If the input GFA file has not been built by Bifrost or if the input is FASTA format, it is your responsibility to make sure that the graph is correctly compacted and to set correctly the parameters of the graph (k-mer length and g-mer) before the call to this function.

Parameters

input_graph_fn	is a string containing the name of the graph file to read.
input_index_fn	is a string containing the name of the index file to read.
nb_threads	is a number indicating how many threads can be used to read the graph from disk.
verbose	is a boolean indicating if information messages must be printed during the function execution.

Returns: boolean indicating if the graph has been read successfully.

◆ remove()

template<typename Unitig_data_t = void, typename Graph_data_t = void>

bool CompactedDBG< Unitig_data_t, Graph_data_t >::remove	(	const const_UnitigMap< U, G > &	um,
		const bool	verbose = `false`
	)

Remove a unitig from the Compacted de Bruijn graph.

Parameters

um	is a UnitigMap object containing the information of the unitig to remove from the graph.
verbose	is a boolean indicating if information messages must be printed during the execution of the function.

Returns: a boolean indicating if the unitig was successfully removed from the graph.

◆ searchSequence() [1/2]

template<typename Unitig_data_t = void, typename Graph_data_t = void>

vector<pair<size_t, UnitigMap<U, G> > > CompactedDBG< Unitig_data_t, Graph_data_t >::searchSequence	(	const string &	s,
		const bool	exact,
		const bool	insertion,
		const bool	deletion,
		const bool	substitution,
		const bool	or_exclusive_match = `false`
	)

Performs exact and/or inexact search of the k-mers of a sequence query in the Compacted de Bruijn graph.

Parameters

s	is a string representing the sequence to be searched (the query).
exact	is a boolean indicating if the exact k-mers of string s must be searched.
insertion	is a boolean indicating if the inexact k-mers of string s, with one insertion, must be searched.
deletion	is a boolean indicating if the inexact k-mers of string s, with one deletion, must be searched.
substitution	is a boolean indicating if the inexact k-mers of string s, with one substitution, must be searched.
or_exclusive_match	is a boolean indicating to NOT search for the inexact k-mers at any given position in s if the exact corresponding k-mer at that position is found in the graph. This option might lead to a substantial running time decrease.

Returns: a vector of pair<size_t, UnitigMap<U, G>> objects. Each such pair has two elements: the position of the k-mer match in sequence s and the corresponding k-mer match in the graph. Note that no information is given on whether the match is exact or inexact, nor on what edit operation makes the match to be inexact or at what position the edit operation takes place.

◆ searchSequence() [2/2]

template<typename Unitig_data_t = void, typename Graph_data_t = void>

vector<pair<size_t, const_UnitigMap<U, G> > > CompactedDBG< Unitig_data_t, Graph_data_t >::searchSequence	(	const string &	s,
		const bool	exact,
		const bool	insertion,
		const bool	deletion,
		const bool	substitution,
		const bool	or_exclusive_match = `false`
	)		const

Performs exact and/or inexact search of the k-mers of a sequence query in the Compacted de Bruijn graph.

Parameters

s	is a string representing the sequence to be searched (the query).
exact	is a boolean indicating if the exact k-mers of string s must be searched.
insertion	is a boolean indicating if the inexact k-mers of string s, with one insertion, must be searched.
deletion	is a boolean indicating if the inexact k-mers of string s, with one deletion, must be searched.
substitution	is a boolean indicating if the inexact k-mers of string s, with one substitution, must be searched.
or_exclusive_match	is a boolean indicating to NOT search for the inexact k-mers at any given position in s if the exact corresponding k-mer at that position is found in the graph. This option might lead to a substantial running time decrease.

Returns: a vector of pair<size_t, const_UnitigMap<U, G>> objects. Each such pair has two elements: the position of the k-mer match in sequence s and the corresponding k-mer match in the graph. Note that no information is given on whether the match is exact or inexact, nor on what edit operation makes the match to be inexact or at what position the edit operation takes place.

◆ simplify()

template<typename Unitig_data_t = void, typename Graph_data_t = void>

bool CompactedDBG< Unitig_data_t, Graph_data_t >::simplify	(	const bool	delete_short_isolated_unitigs = `true`,
		const bool	clip_short_tips = `true`,
		const bool	verbose = `false`
	)

Simplify the Compacted de Bruijn graph: clip short (< 2k length) tips and/or delete short (< 2k length) isolated unitigs.

Parameters

delete_short_isolated_unitigs	is a boolean indicating short isolated unitigs must be removed.
clip_short_tips	is a boolean indicating short tips must be clipped.
verbose	is a boolean indicating if information messages must be printed during the function execution.

Returns: boolean indicating if the graph has been simplified successfully.

◆ size()

template<typename Unitig_data_t = void, typename Graph_data_t = void>

size_t CompactedDBG< Unitig_data_t, Graph_data_t >::size ( ) const

inline

Return the number of unitigs in the graph.

Returns: Number of unitigs in the graph.

◆ write()

template<typename Unitig_data_t = void, typename Graph_data_t = void>

bool CompactedDBG< Unitig_data_t, Graph_data_t >::write	(	const string &	output_fn,
		const size_t	nb_threads = `1`,
		const bool	GFA_output = `true`,
		const bool	FASTA_output = `false`,
		const bool	BFG_output = `false`,
		const bool	write_index_file = `true`,
		const bool	compressed_output = `false`,
		const bool	verbose = `false`
	)		const

Write the Compacted de Bruijn graph to disk (GFA1 format).

Parameters

output_fn	is a string containing the name of the file in which the graph will be written.
nb_threads	is a number indicating how many threads can be used to write the graph to disk.
GFA_output	indicates if the graph will be output in GFA format.
FASTA_output	indicates if the graph will be output in FASTA format.
BFG_output	indicates if the graph will be output in BFG/BFI format.
write_index_file	indicates if an index file is written to disk. Index files enable faster graph loading. This parameter is discarded if BFG format output is selected (index output is required then).
compressed_output	indicates if the output file is compressed.
verbose	is a boolean indicating if information messages must be printed during the function execution.

Returns: boolean indicating if the graph has been written successfully.

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

src/CompactedDBG.hpp

Public Types

Public Member Functions

Detailed Description

template<typename Unitig_data_t = void, typename Graph_data_t = void> class CompactedDBG< Unitig_data_t, Graph_data_t >

Member Typedef Documentation

◆ const_iterator

◆ iterator

Constructor & Destructor Documentation

◆ CompactedDBG() [1/3]

◆ CompactedDBG() [2/3]

◆ CompactedDBG() [3/3]

Member Function Documentation

◆ add()

◆ begin() [1/2]

◆ begin() [2/2]

◆ build()

◆ end() [1/2]

◆ end() [2/2]

◆ find() [1/2]

◆ find() [2/2]

◆ findUnitig() [1/2]

◆ findUnitig() [2/2]

◆ getData() [1/2]

◆ getData() [2/2]

◆ getG()

◆ getK()

◆ isInvalid()

◆ length()

◆ merge() [1/2]

◆ merge() [2/2]

◆ nbKmers()

◆ operator!=()

◆ operator+=()

◆ operator=() [1/2]

◆ operator=() [2/2]

◆ operator==()

◆ read() [1/2]

◆ read() [2/2]

◆ remove()

◆ searchSequence() [1/2]

◆ searchSequence() [2/2]

◆ simplify()

◆ size()

◆ write()

template<typename Unitig_data_t = void, typename Graph_data_t = void>
class CompactedDBG< Unitig_data_t, Graph_data_t >