Neff Computation. More...

#include "flagHandler.h"
#include "msaReader.h"
#include "msaWriter.h"
#include "multimerHandler.h"
#include <iostream>
#include <vector>
#include <string>
#include <unordered_map>
#include <cmath>
#include <sstream>
#include <climits>
#include "common.h"
#include <fstream>
#include <algorithm>
#include <tuple>
#include <random>
#include <set>
#include <thread>
#include <future>
#include <mutex>
#include <chrono>

Functions
int	char2num (char c, const string &standardLetters, const string &nonStandardLetters, NonStandardHandler nonStandardOption)
	Map char residues to digit based on given 'nonStandardOption'.

void	removeGappyPositions (vector< vector< int > > &sequences, float gapCutoff)
	Remove gappy positions from sequences based on given 'gapCutoff'.

vector< vector< int > >	processSequences (vector< Sequence > sequences, string standardLetters, string nonStandardLetters, NonStandardHandler nonStandardOption, float gapCutoff)
	Map chars to digits based on provided 'nonStandardOption' and also remove gappy positions based on given 'gapCutoff'.

vector< int >	computeWeights (vector< vector< int > > sequences, float threshold, bool isSymmetric, string standardLetters, NonStandardHandler nonStandardOption)
	Compute sequence weights based on given options.

float	computeNeff (vector< int > sequenceWeights, Normalization norm, int length)
	Cumpote NEFF values based on sequence weights and given normalization.

Alphabet	getAlphabet (FlagHandler &flagHandler)
	Get given alphabet by user.

Normalization	getNormalization (FlagHandler &flagHandler)
	Get given normalization option by user.

NonStandardHandler	getNonStandardOption (FlagHandler &flagHandler)
	Get given non_standard_option option by user.

void	checkFlags (FlagHandler &flagHandler)
	Check flags

void	setDepth (vector< Sequence > &sequences, int depth)
	Set MSA depth based on 'depth' flag.

int	getNonGapStartPosition (string firstAlignement, int startPos)
	Get the index of the given startPos in the original first sequence of MSA despite of gaps in the MSA.

int	getNonGapEndPosition (string firstAlignement, int startPos, int length)
	Get the end index in the original sequence after a 'length' number of non-gap positions.

void	getPositions (vector< Sequence > &sequences, FlagHandler flagHandler)
	Set desired positiones to compute NEFF for based on given 'pos_start' and 'pos_end' flags.

void	integrateUniqueSequences (vector< Sequence > &integratedSequences, const vector< Sequence > &sequences)
	to merge sequences and remove redundant sequences

vector< float >	computeResidueNEFF (const vector< vector< int > > &sequences, const vector< int > &sequenceWeights, Normalization norm)
	Compute per-residue (column-wise) NEFF.

int	main (int argc, char **argv)

Variables
const char *	docstr

unordered_map< string, FlagInfo >	Flags

Detailed Description

Neff Computation.

This program computes Number of EFFective sequences (NEFF) for a multiple sequence alignment (MSA) file. NEFF is a measure of effective sequence number that takes into account the redundancy and similarity of sequences in the MSA. It is commonly used in bioinformatics to assess the diversity of a set of sequences.

Usage: ./neff –file=<input_file> [options]

Options: –file=<input_file> Input files (comma-separated, no spaces) containing multiple sequence alignments (required)
" --format=<input_format> Input file formats (comma-separated, no spaces) containing formats of multiple sequence alignments (optional)\n" –alphabet=

Valid alphabet of MSA; alphabet option (0: Protein, 1: RNA, 2: DNA) (default: 0)
" --check_validation=<true/false> Perform validation on sequences (default: false)\n" –threshold=

Threshold value of considering two sequences similar (default: 0.8)
" --norm=<value> NEFF normalization option (0: sqrt(Length of alignment), 1: Length of alignment, 2: No normalization) (default: 0)\n" –omit_query_gaps=<true/false> Omit gap positions of query sequence from all sequences for NEFF computation (default: true)
" --is_symmetric=<true/false> Consider gaps in similarity cutoff computation (asymmetric) or not (symmetric) (default: true)\n" –non_standard_option=

Handling non-standard letters in the given alphabet (0: AsStandard, 1: ConsiderGapInCutoff, 2: ConsiderGap)
" --depth=<value> Depth of MSA to be cosidered in computation (default: depth of given MSA)\n" –gap_cutoff=

Cutoff value for removing gappy positions, when #gaps in position >= gap_cutoff (default=1 : does not remove anything)
" --pos_start=<value> Start position of each sequence to be considered in neff (inclusive (default: 1))\n" –pos_end=

Last position of each sequence to be considered in neff (inclusive (default: length of MSA sequence))
" --only_weights=<true/false> Return only sequence weights, as # similar sequence, rather than the final NEFF (default: false)\n" –multimer_MSA=<true/false> Compute NEFF for a multimer MSA (default: false)
" –stoichiom=<value> Multimer stoichiometry (default: empty) –chain_length=<list of values> Length of the chains in heteromer multimer (default: 0)\n" –residue_neff=<true/false> Compute per-resiue (column-wise) NEFF (default: false)

For more comprehensive instructions, please refer to the documentation at https://maryam-haghani.github.io/NEFFy.

Function Documentation

◆ char2num()

int char2num	(	char	c,
		const string &	standardLetters,
		const string &	nonStandardLetters,
		NonStandardHandler	nonStandardOption )

Map char residues to digit based on given 'nonStandardOption'.

Parameters

c	input letter
standardLetters
nonStandardLetters
nonStandardOption

Returns

◆ checkFlags()

void checkFlags ( FlagHandler & flagHandler )

Check flags

Parameters

flagHandler

◆ computeNeff()

float computeNeff	(	vector< int >	sequenceWeights,
		Normalization	norm,
		int	length )

Cumpote NEFF values based on sequence weights and given normalization.

Parameters

sequenceWeights
norm
sequenceLength

Returns

◆ computeResidueNEFF()

vector< float > computeResidueNEFF	(	const vector< vector< int > > &	sequences,
		const vector< int > &	sequenceWeights,
		Normalization	norm )

Compute per-residue (column-wise) NEFF.

Parameters

sequences
sequenceWeights
norm

Returns

◆ computeWeights()

vector< int > computeWeights	(	vector< vector< int > >	sequences,
		float	threshold,
		bool	isSymmetric,
		string	standardLetters,
		NonStandardHandler	nonStandardOption )

Compute sequence weights based on given options.

Parameters

sequences
threshold
norm
isSymmetric
nonStandardOption

Returns: inverse of sequence weights

◆ getAlphabet()

Alphabet getAlphabet ( FlagHandler & flagHandler )

Get given alphabet by user.

Parameters

flagHandler

Returns

◆ getNonGapEndPosition()

int getNonGapEndPosition	(	string	firstAlignement,
		int	startPos,
		int	length )

Get the end index in the original sequence after a 'length' number of non-gap positions.

Parameters

firstAlignement
startPos
length

Returns: The end index in the MSA sequence including gaps.

◆ getNonGapStartPosition()

int getNonGapStartPosition	(	string	firstAlignement,
		int	startPos )

Get the index of the given startPos in the original first sequence of MSA despite of gaps in the MSA.

Parameters

firstAlignement
startPos

Returns: startPos + number of gaps until that position for the first sequence in the MSA

◆ getNonStandardOption()

NonStandardHandler getNonStandardOption ( FlagHandler & flagHandler )

Get given non_standard_option option by user.

Parameters

flagHandler

Returns

◆ getNormalization()

Normalization getNormalization ( FlagHandler & flagHandler )

Get given normalization option by user.

Parameters

flagHandler

Returns

◆ getPositions()

void getPositions	(	vector< Sequence > &	sequences,
		FlagHandler	flagHandler )

Set desired positiones to compute NEFF for based on given 'pos_start' and 'pos_end' flags.

Parameters

sequences
flagHandler

◆ integrateUniqueSequences()

void integrateUniqueSequences	(	vector< Sequence > &	integratedSequences,
		const vector< Sequence > &	sequences )

to merge sequences and remove redundant sequences

Parameters

integratedSequences
sequences

◆ main()

int main	(	int	argc,
		char **	argv )

omit gap positions of query sequence in all sequences if omitGapsInQuery=true

◆ processSequences()

vector< vector< int > > processSequences	(	vector< Sequence >	sequences,
		string	standardLetters,
		string	nonStandardLetters,
		NonStandardHandler	nonStandardOption,
		float	gapCutoff )

Map chars to digits based on provided 'nonStandardOption' and also remove gappy positions based on given 'gapCutoff'.

Parameters

omitGapsInQuery
alphabet
nonStandardOption
gapCutoff

Returns

◆ removeGappyPositions()

void removeGappyPositions	(	vector< vector< int > > &	sequences,
		float	gapCutoff )

Remove gappy positions from sequences based on given 'gapCutoff'.

Parameters

sequences
gapCutoff

◆ setDepth()

void setDepth	(	vector< Sequence > &	sequences,
		int	depth )

Set MSA depth based on 'depth' flag.

Parameters

sequences
flagHandler

Variable Documentation

◆ docstr

const char* docstr

◆ Flags

unordered_map<string, FlagInfo> Flags

Initial value:

=
{
    {"file", {true, ""}},                   
    {"format", {false, ""}},                
    {"alphabet", {false, "0"}},             
    {"check_validation", {false, "false"}}, 
    {"threshold", {false, "0.8"}},          
    {"norm", {false, "0"}},                 
    {"omit_query_gaps", {false, "true"}},   
    {"is_symmetric", {false, "true"}},      
    {"non_standard_option", {false, "0"}},  
    {"depth", {false, "inf"}},              
    {"gap_cutoff", {false, "1"}},           
    {"pos_start", {false, "1"}},            
    {"pos_end", {false, "inf"}},            
    {"only_weights", {false, "false"}},     
    {"multimer_MSA", {false, "false"}},     
    {"stoichiom", {false, ""}},             
    {"chain_length", {false, "0"}},         
    {"residue_neff", {false, "false"}}      
}

Functions

Variables

Detailed Description

Function Documentation

◆ char2num()

◆ checkFlags()

◆ computeNeff()

◆ computeResidueNEFF()

◆ computeWeights()

◆ getAlphabet()

◆ getNonGapEndPosition()

◆ getNonGapStartPosition()

◆ getNonStandardOption()

◆ getNormalization()

◆ getPositions()

◆ integrateUniqueSequences()

◆ main()

◆ processSequences()

◆ removeGappyPositions()

◆ setDepth()

Variable Documentation

◆ docstr

◆ Flags