#include <Multilign_object.h>

Inheritance diagram for Multilign_object:

Public Member Functions
	Multilign_object ()
	Default constructor: More...

	Multilign_object (const vector< vector< string > > &inputlist, const bool isrna=true, ProgressHandler *progress=NULL)

	Multilign_object (const bool Multifind, const string &outputmultifind, const vector< string > &ctfiles, ProgressHandler *progress=NULL, const bool isrna=true)

	~Multilign_object ()

int	CountBP (const int i=0, const int j=0, const double percent=0.8) const
	count the number of basepairs with the lowest free energies below the percent of the miminal free energy. Dsv file is used for the counting. By default, the first dsv file in the progressive dynalign calculations is used, i.e. i = 0 and j = 0. More...

int	ProgressiveMultilign (const short int numProcessors=1, const bool Dsv=1, const bool Ali=1, const short int maxtrace=750, const short int bpwin=2, const short int awin=1, const short int percent=20, const short int imaxseparation=-99, const float gap=0.4, const bool singleinsert=true, const short int singlefold_subopt_percent=30, const bool local=false)

int	MultiTempMultilign ()

int	WriteAlignment (const string allali="all.ali") const
	calculate and output multiple alignment More...

int	GetErrorCode () const
	Return an error code, where a return of zero is no error. More...

string	GetErrorMessage (const int error) const

const string	GetErrorDetails ()

void	ResetError ()
	Reset the underlying RNA objects internal error code, after an error is handled. More...

int	SetMaxPairs (const int maxpairs=-1)

int	GetMaxPairs () const
	get the value of MaxPairs More...

int	AverageLength () const
	get the average length of the input sequences More...

int	SetIterations (const int it=2)
	set the value of iterations More...

int	GetIterations () const
	get the value of iterations More...

int	SetMaxDsv (const float maxdsvchange=1)
	set the value of MaxDsv/maxdsvchange More...

float	GetMaxDsv () const
	get the value of MaxDsv/maxdsvchange More...

int	GetSequenceNumber () const
	get the sequence number More...

int	SetIndexSeq (size_t indexSeq=1)
	set the Index Sequence for Multilign calculation. More...

int	SetIndexSeq (const string seqname)
	an overloaded function accepting a string as its parameter. More...

string	GetIndexSeq () const
	return the filename of the index seq. More...

void	Randomize ()
	randomize the order of inputList. More...

int	AddOneInput (const string seq, const string ct, const string constraint="", const string shape="")
	add one entry into inputList. More...

int	RemoveOneInput (const string seq)
	remove one entry from inputList. More...

void	SetSHAPESlope (const double slope=1.8)
	set the slope parameter for SHAPE More...

double	GetSHAPESlope () const
	get the SHAPESlope More...

void	SetSHAPEIntercept (const double intercept=-0.6)
	set the intercept parameter for SHAPE. More...

double	GetSHAPEIntercept () const
	get the SHAPEIntercept. More...

void	SetTemperature (const double temp=310.15)
	set the temperature to fold the sequences. More...

double	GetTemperature () const
	get the temperature to fold the sequences More...

void	SetNucType (const bool isrna=true)
	set the flag isRNA to be true or false. By default it is true. When it is true, RNA nearest neighbor parameters are used. More...

bool	GetNucType () const
	get the type fo nucleic acid More...

int	CleanupIntermediateFiles () const
	delete intermediate pairwise dsv and aout files More...

void	SetProgress (ProgressHandler *Progress=NULL)
	Provide a TProgressDialog for following calculation progress. More...

void	StopProgress ()
	Provide a means to stop using a TProgressDialog by assigning NULL to progress pointer. More...

ProgressHandler *	GetProgress () const
	get the progress More...

void	GetInputFilenames ()
	For diagnostic purpose only. Output the input sequence, ct, constraints, and SHAPE filenames to stdout. More...

void	GetPairs ()
	For diagnostic purpose only. Output the paired sequence filenames to stdout. More...

vector< float >	get_energies ()

vector< float >	get_dGIndex ()

vector< vector< string > >	get_pair_alignments ()

Protected Attributes
int	ErrorCode

vector< string >	input_alignment

vector< string >	input_sequences

vector< string >	ct_files

string	output_multifind

vector< float >	energies

vector< float >	dGIndex

vector< vector< string > >	pair_alignments

Private Types
typedef vector< string >::size_type	vs_index

typedef vector< vector< string > >::iterator	vvs_it

typedef vector< vector< string > >::const_iterator	vvs_cit

Private Member Functions
int	PairSeq1 ()

int	PairMultifindSeq1 ()

int	PrepInput ()
	This function check the legality of the input filenames and prepare the parameters for the multilign calculations. It should be called before multilign calcultions at least once and whenever something related to seq/ct changes, e.g. SetIndexSeq, AddOneInput, RemoveOneInput, Randomize, etc. More...

int	PrepMultifindInput ()

void	ToHead (vvs_it first, vvs_it middle)
	move the element pointed by middle before the first-pointed element. More...

int	NameDsvFiles ()
	name all the dsv files More...

int	NameMultifindDsvFiles ()

int	NameAliFiles ()
	name all the ali files More...

int	NameMultifindAliFiles ()

Private Attributes
ProgressHandler *	progress

vector< vector< string > >	inputList

vector< pair< vs_index, vs_index > >	seqPair

string **	dsvFiles

string **	aliFiles

int	maxPairs
	The following are the parameters for Multilign calculations. More...

float	maxDsv

int	iterations

double	SHAPESlope

double	SHAPEIntercept

Dynalign_object *	instance

Thermodynamics	thermo

Detailed Description

Multilign_object Class.

The Multilign_object class provides an entry point for the Multilign algorithm.

Member Typedef Documentation

typedef vector<string>::size_type Multilign_object::vs_index

private

typedef vector<vector<string> >::const_iterator Multilign_object::vvs_cit

private

typedef vector<vector<string> >::iterator Multilign_object::vvs_it

private

Constructor & Destructor Documentation

Multilign_object::Multilign_object ( )

Default constructor:

Multilign_object::Multilign_object	(	const vector< vector< string > > &	inputlist,
		const bool	isrna = `true`,
		ProgressHandler *	progress = `NULL`
	)

Constructor:

Parameters

inputlist	is a vector of vectors of strings storing the name of the filenames. Currently, inputList is an matrix of 4 columns: col 1 is the input seq filename; col 2 is the output ct filename; col 3 is the input constraint filename; col 4 is the input SHAPE filename. Empty string is not allowed for Col 1 and Col 2; If no SHAPE or folding constraints are given, Col 3 and Col 4 for the correponding sequence are empty strings.
isrna	is a bool indicating the sequences are RNA or DNA. The default of true indicates RNA.
progress	is a TProgressDialog for reporting progress of the calculation to the user. The default value of NULL means that no communication is provided.

Multilign_object::Multilign_object	(	const bool	Multifind,
		const string &	outputmultifind,
		const vector< string > &	ctfiles,
		ProgressHandler *	progress = `NULL`,
		const bool	isrna = `true`
	)

Multilign_object::~Multilign_object ( )

Member Function Documentation

int Multilign_object::AddOneInput	(	const string	seq,
		const string	ct,
		const string	constraint = `""`,
		const string	shape = `""`
	)

add one entry into inputList.

Parameters

seq	is a string value of sequence filename to be appended1
ct	is a string value of corresponding ct filename
constraint	is a string value of corresponding constraint filename. By default, it is empty, meaning no folding constraint exists
shape	is string value of corresponding SHAPE filename. By default, it is empty, meaning no SHAPE exists.

Returns: a is int value of ErrorCode

int Multilign_object::AverageLength ( ) const

get the average length of the input sequences

Returns: the average length of the input sequences.

int Multilign_object::CleanupIntermediateFiles ( ) const

delete intermediate pairwise dsv and aout files

Returns: an int value of error code.

int Multilign_object::CountBP	(	const int	i = `0`,
		const int	j = `0`,
		const double	percent = `0.8`
	)		const

count the number of basepairs with the lowest free energies below the percent of the miminal free energy. Dsv file is used for the counting. By default, the first dsv file in the progressive dynalign calculations is used, i.e. i = 0 and j = 0.

Parameters

i	is an int value indicating which one in the iteration.
j	is an int value indicating which iteration.
percent	is threshold of double value in percentage.

Returns: an int of the number of basepairs counted.

vector<float> Multilign_object::get_dGIndex ( )

inline

vector<float> Multilign_object::get_energies ( )

inline

vector<vector<string> > Multilign_object::get_pair_alignments ( )

inline

int Multilign_object::GetErrorCode ( ) const

inline

Return an error code, where a return of zero is no error.

This function returns and error flag that is generated during construction by RNA(const char &filename, const int type, const bool IsRNA=true) or from CalculateFreeEnergy(). An error of zero is always no error. Other codes are errors and a c-string can be fetched for the error with GetErrorMessage().

Returns: An integer that provides the error code.

const string Multilign_object::GetErrorDetails ( )

inline

string Multilign_object::GetErrorMessage ( const int error ) const

Return error messages based on code from GetErrorCode and other error codes. 0 = no error 1000 = Error associated with sequence 1 or with a procedure, function will get message from sequence 1 (the inherited RNA class). 2000 = Error associated with sequence 2, function will get message from sequence 2 (the RNA2 class). 3000 = Errors with each sequence, function will get messages from each.

Parameters

error is the integer error code provided by GetErrorCode().

Returns: A string that provides an error message or from other functions that return integer error codes.

string Multilign_object::GetIndexSeq ( ) const

return the filename of the index seq.

Returns: a string of index seq filename.

void Multilign_object::GetInputFilenames ( )

For diagnostic purpose only. Output the input sequence, ct, constraints, and SHAPE filenames to stdout.

The following functions are used for Diagnostic purpose only ////////////Generally not needed, but for debugging input.

int Multilign_object::GetIterations ( ) const

get the value of iterations

Returns: the value of iterations.

float Multilign_object::GetMaxDsv ( ) const

get the value of MaxDsv/maxdsvchange

Returns: the value of MaxDsv/maxdsvchange.

int Multilign_object::GetMaxPairs ( ) const

get the value of MaxPairs

Returns: the value of MaxPairs

bool Multilign_object::GetNucType ( ) const

get the type fo nucleic acid

Returns: return true when it is of RNA prediction; otherwise, false.

void Multilign_object::GetPairs ( )

For diagnostic purpose only. Output the paired sequence filenames to stdout.

ProgressHandler * Multilign_object::GetProgress ( ) const

get the progress

Returns: the pointer to TProgressDialog

int Multilign_object::GetSequenceNumber ( ) const

get the sequence number

Returns: the number of input sequences

double Multilign_object::GetSHAPEIntercept ( ) const

get the SHAPEIntercept.

Returns: SHAPEIntercept of double value.

double Multilign_object::GetSHAPESlope ( ) const

get the SHAPESlope

Returns: a SHAPESlope of double value.

double Multilign_object::GetTemperature ( ) const

get the temperature to fold the sequences

Returns: a double value of the set temperature.

int Multilign_object::MultiTempMultilign ( )

int Multilign_object::NameAliFiles ( )

private

name all the ali files

Returns: an int value of errorcode

int Multilign_object::NameDsvFiles ( )

private

name all the dsv files

Returns: an int value of errorcode

int Multilign_object::NameMultifindAliFiles ( )

private

int Multilign_object::NameMultifindDsvFiles ( )

private

int Multilign_object::PairMultifindSeq1 ( )

private

int Multilign_object::PairSeq1 ( )

private

private functions /////////////////////////////// Pair sequences for dynalign calculation

Returns: the value of ErrorCode

int Multilign_object::PrepInput ( )

private

This function check the legality of the input filenames and prepare the parameters for the multilign calculations. It should be called before multilign calcultions at least once and whenever something related to seq/ct changes, e.g. SetIndexSeq, AddOneInput, RemoveOneInput, Randomize, etc.

Returns: the int value of ErrorCode.

int Multilign_object::PrepMultifindInput ( )

private

int Multilign_object::ProgressiveMultilign	(	const short int	numProcessors = `1`,
		const bool	Dsv = `1`,
		const bool	Ali = `1`,
		const short int	maxtrace = `750`,
		const short int	bpwin = `2`,
		const short int	awin = `1`,
		const short int	percent = `20`,
		const short int	imaxseparation = `-99`,
		const float	gap = `0.4`,
		const bool	singleinsert = `true`,
		const short int	singlefold_subopt_percent = `30`,
		const bool	local = `false`
	)

The core function doing dynalign calculation and templating In case of error, the function returns a non-zero that can be parsed by GetErrorMessage() or GetErrorMessageString().

Parameters

Dsv	is a boolean value indicating to output pairwise dsv files or not. It has to be set to true currently.
Ali	is a boolean value indicating to output pairwise ali files or not. It has to be set to true currently.
maxtrace	is the maximum number of common structures to be determined.
bpwin	the the base pair window parameter, where 0 allows the structures to have similar pairs and larger windows make the structures more diverse.
awin	is the alignment window parameter, where 0 allows the alignments to be similar and larger values make the alignments more diverse.
percent	is the maximum percent difference in total folding free energy change above the lowest for suboptimal common structures.
imaxseparation	is the maximum separation between aligned nucleotides. Values >= 0 are the traditional parameter, those below zero trigger the HMM alignment method, which is now prefered.
gap	is the cost of adding gap nucleotides in the alignment in kcal/mol.
singleinsert	is whether single basepair inserts are allowed in one sequence vs the other.
singlefold_subopt_percent	is the maximum % difference of folding energy above the lowest free energy structure for pairs in single sequence folding that will be allowed in the dynalign calculation.
local	is whether Dynalign is being run in local (true) or global mode (false).
numProcessors	is the number of processors to use for the calculation. This requires a compilation for SMP.

Returns: an int that indicates an error code (0 = no error, non-zero = error occurred).

void Multilign_object::Randomize ( )

randomize the order of inputList.

int Multilign_object::RemoveOneInput ( const string seq )

remove one entry from inputList.

Parameters

seq	is a string value of sequence filename of which the entry in inputList will be removed

Returns: a int value of ErrorCode

void Multilign_object::ResetError ( )

Reset the underlying RNA objects internal error code, after an error is handled.

int Multilign_object::SetIndexSeq ( size_t indexSeq = 1 )

set the Index Sequence for Multilign calculation.

Parameters

indexSeq is a size_t value indicating which sequence is the index sequence; by default it is the 1st one.

Returns: a int value of ErrorCode

int Multilign_object::SetIndexSeq ( const string seqname )

an overloaded function accepting a string as its parameter.

Parameters

seqname is the seq filename that will be set as the index sequence.

Returns: an int value of ErrorCode

int Multilign_object::SetIterations ( const int it = 2 )

set the value of iterations

Parameters

it	is an value of int assigned to iterations. By default it is set to 2.

Returns: an errorcode

int Multilign_object::SetMaxDsv ( const float maxdsvchange = 1 )

set the value of MaxDsv/maxdsvchange

Parameters

maxdsvchange is a value of float assigned to MaxDsv. By default it is set to 1.

Returns: an errorcode

int Multilign_object::SetMaxPairs ( const int maxpairs = -1 )

Parameters

maxpairs is int value defining how the MaxPairs will be set. By default it is set to be -1, meaning the average length of all the sequences.

Returns: an errorcode.

void Multilign_object::SetNucType ( const bool isrna = true )

set the flag isRNA to be true or false. By default it is true. When it is true, RNA nearest neighbor parameters are used.

Parameters

isrna

void Multilign_object::SetProgress ( ProgressHandler * Progress = NULL )

Provide a TProgressDialog for following calculation progress.

Parameters

Progress is a pointer to TProgressDialog

void Multilign_object::SetSHAPEIntercept ( const double intercept = -0.6 )

set the intercept parameter for SHAPE.

Parameters

intercept is a double value assigned to SHAPEIntercept. By default, it is set to -0.6.

void Multilign_object::SetSHAPESlope ( const double slope = 1.8 )

set the slope parameter for SHAPE

Parameters

slope is a double value assigned to SHAPESlope. By default, it is set to 1.8.

void Multilign_object::SetTemperature ( const double temp = 310.15 )

set the temperature to fold the sequences.

Parameters

temp	is a double value of temperature; by default it is set to 310.15K

void Multilign_object::StopProgress ( )

Provide a means to stop using a TProgressDialog by assigning NULL to progress pointer.

void Multilign_object::ToHead	(	vvs_it	first,
		vvs_it	middle
	)

private

move the element pointed by middle before the first-pointed element.

Parameters

first	is an vector<vector<string> >::iterator
middle	is the same type.

int Multilign_object::WriteAlignment ( const string allali = "all.ali" ) const

calculate and output multiple alignment

Parameters

allali is the output filename of multiple alignment

Returns: an int of error code.

Member Data Documentation

string** Multilign_object::aliFiles

private

vector<string> Multilign_object::ct_files

protected

vector<float> Multilign_object::dGIndex

protected

string** Multilign_object::dsvFiles

private

vector<float> Multilign_object::energies

protected

int Multilign_object::ErrorCode

protected

vector<string> Multilign_object::input_alignment

protected

vector<string> Multilign_object::input_sequences

protected

vector<vector<string> > Multilign_object::inputList

private

Dynalign_object* Multilign_object::instance

private

int Multilign_object::iterations

private

float Multilign_object::maxDsv

private

int Multilign_object::maxPairs

private

The following are the parameters for Multilign calculations.

string Multilign_object::output_multifind

protected

vector<vector<string> > Multilign_object::pair_alignments

mutableprotected

ProgressHandler* Multilign_object::progress

private

vector<pair<vs_index, vs_index> > Multilign_object::seqPair

private

double Multilign_object::SHAPEIntercept

private

double Multilign_object::SHAPESlope

private

Thermodynamics Multilign_object::thermo

private

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

RNA_class/Multilign_object.h
RNA_class/Multilign_object.cpp

Public Member Functions

Protected Attributes

Private Types

Private Member Functions

Private Attributes

Detailed Description

Member Typedef Documentation

Constructor & Destructor Documentation

Member Function Documentation

Member Data Documentation