Sequence utility functions. More...

#include "rwgencode.h"
#include "seq_analysis.h"
#include "seq_util.h"
#include "linked_list.h"
#include "utilities.h"
#include <map>

Functions
int	seq_from_residues (Bmolgroup *molgroup)
	Obtain sequences from residues. More...

int	seq_show (Bmolgroup *molgroup)
	Shows all molecular sequences. More...

int	seq_mass (Bmolgroup *molgroup)
	Shows the masses of all molecular sequences. More...

vector< double >	seq_elements (Bmolgroup *molgroup, Bstring &paramfile)
	Shows the elemental composition of all molecular sequences. More...

int	seq_complement_all (Bmolgroup *molgroup)
	Complements all nucleotide sequences. More...

int	seq_translate_all (Bmolgroup *molgroup, int frame, Bstring &gcfile)
	Translates all nucleotide sequences to protein sequences. More...

long	seq_find_dna (Bmolgroup *molgroup, Bstring &seq)
	Finds a nucleotide sequence. More...

long	seq_find_protein (Bmolgroup *molgroup, Bstring &seq)
	Finds an amino acid sequence. More...

Bstring	seq_find_protein_in_dna (Bmolgroup *molgroup, Bstring &seq, int seqlenmin, int seqlenmax, int side1, int side2, double threshold, Bstring &gcfile)
	Finds the coding region for an amino acid sequence. More...

int	getcode3 (char c, char *cod)
	Converts a one-letter amino acid designation to the three-letter equivalent. More...

char	getcode1 (char *acode)
	Converts a three-letter amino acid designation to the one-letter equivalent. More...

int	complement_sequence (Bstring &nucseq)
	Complements a nucleotide sequence in place. More...

char	get_complement (char nuc)
	Get the Watson-Crick complement of a nucleotide base. More...

Bstring	sequence_translate (Bstring &nucseq, long frame, Bstring &gencode)
	Translates a nucleotide sequence to a protein sequence. More...

Variables
int	verbose

const map< char, string >	res_code

Detailed Description

Sequence utility functions.

Author: Bernard Heymann

Date: Created: 20001029; Modified: 20220713

Function Documentation

◆ complement_sequence()

int complement_sequence ( Bstring & nucseq )

Complements a nucleotide sequence in place.

Parameters

&nucseq nucleotide sequence to be translated.

Returns: int 0.

◆ get_complement()

char get_complement ( char nuc )

Get the Watson-Crick complement of a nucleotide base.

Parameters

nuc	nucleotide.

Returns: char complementing nucleotide.

◆ getcode1()

char getcode1 ( char * acode )

Converts a three-letter amino acid designation to the one-letter equivalent.

Parameters

*acode the desired amino acid three-letter code

Returns

char the corresponding one-letter code

Search through a list of 3-1 mappings for the desired three-letter code.

◆ getcode3()

int getcode3	(	char	c,
		char *	cod
	)

Converts a one-letter amino acid designation to the three-letter equivalent.

Parameters

c	the desired amino acid code letter
*cod	the corresponding three-letter code

Returns

int 0.

Search through a list of 1-3 mappings for the desired letter.

◆ seq_complement_all()

int seq_complement_all ( Bmolgroup * molgroup )

Complements all nucleotide sequences.

Parameters

*molgroup the molecule group.

Returns

int 0.

Search through a list of 1-3 mappings for the desired letter.

◆ seq_elements()

vector< double > seq_elements	(	Bmolgroup *	molgroup,
		Bstring &	paramfile
	)

Shows the elemental composition of all molecular sequences.

Parameters

*molgroup	set of sequences.
&paramfile	file of residue parameters.

Returns: vector<double> array of element numbers: HCNOS

◆ seq_find_dna()

long seq_find_dna	(	Bmolgroup *	molgroup,
		Bstring &	seq
	)

Finds a nucleotide sequence.

Parameters

*molgroup	the molecule group.
&seq	sequence to find.

Returns: long position.

◆ seq_find_protein()

long seq_find_protein	(	Bmolgroup *	molgroup,
		Bstring &	seq
	)

Finds an amino acid sequence.

Parameters

*molgroup	the molecule group.
&seq	sequence to find.

Returns: long position.

◆ seq_find_protein_in_dna()

Bstring seq_find_protein_in_dna	(	Bmolgroup *	molgroup,
		Bstring &	seq,
		int	seqlenmin,
		int	seqlenmax,
		int	side1,
		int	side2,
		double	threshold,
		Bstring &	gcfile
	)

Finds the coding region for an amino acid sequence.

Parameters

*molgroup	the molecule group.
&seq	sequence to find.
seqlenmin	sequence length minimum.
seqlenmax	sequence length maximum.
side1	preceding sequence length to include.
side2	succeeding sequence length to include.
threshold	threshold for reporting possible hits.
&gcfile	file with genetic code.

Returns

Bstring coding sequence.

All molecules in the group are searched in all 6 possible frames.

◆ seq_from_residues()

int seq_from_residues ( Bmolgroup * molgroup )

Obtain sequences from residues.

Parameters

*molgroup set of molecules.

Returns: int 0

◆ seq_mass()

int seq_mass ( Bmolgroup * molgroup )

Shows the masses of all molecular sequences.

Parameters

*molgroup set of sequences.

Returns: int 0

◆ seq_show()

int seq_show ( Bmolgroup * molgroup )

Shows all molecular sequences.

Parameters

*molgroup set of sequences.

Returns: int 0

◆ seq_translate_all()

int seq_translate_all	(	Bmolgroup *	molgroup,
		int	frame,
		Bstring &	gcfile
	)

Translates all nucleotide sequences to protein sequences.

Parameters

*molgroup	the molecule group.
frame	the frame for translation.
&gcfile	file with genetic code.

Returns

int 0.

Each nucleic acid sequence in the molecule group is translated to the
protein sequence.

◆ sequence_translate()

Bstring sequence_translate	(	Bstring &	nucseq,
		long	frame,
		Bstring &	gencode
	)

Translates a nucleotide sequence to a protein sequence.

Parameters

&nucseq	nucleotide sequence to be translated.
frame	coding frame.
&gencode	genetic code: array of amino acids.

Returns: Bstring translated protein sequence.

Variable Documentation

◆ res_code

const map<char, string> res_code

Initial value:

= {
        {'-', "GAP"}, 
        {'*', "UNK"}, 
        {'A', "ALA"}, 
        {'B', "ASX"}, 
        {'C', "CYS"}, 
        {'D', "ASP"}, 
        {'E', "GLU"}, 
        {'F', "PHE"}, 
        {'G', "GLY"}, 
        {'H', "HIS"}, 
        {'I', "ILE"}, 
        {'K', "LYS"}, 
        {'L', "LEU"}, 
        {'M', "MET"}, 
        {'N', "ASN"}, 
        {'P', "PRO"}, 
        {'Q', "GLN"}, 
        {'R', "ARG"}, 
        {'S', "SER"}, 
        {'T', "THR"}, 
        {'V', "VAL"}, 
        {'W', "TRP"}, 
        {'Y', "TYR"}, 
        {'Z', "GLX"}, 
        {'X', "UNK"}
}

◆ verbose

int verbose

extern

Functions

Variables

Detailed Description

Function Documentation

◆ complement_sequence()

◆ get_complement()

◆ getcode1()

◆ getcode3()

◆ seq_complement_all()

◆ seq_elements()

◆ seq_find_dna()

◆ seq_find_protein()

◆ seq_find_protein_in_dna()

◆ seq_from_residues()

◆ seq_mass()

◆ seq_show()

◆ seq_translate_all()

◆ sequence_translate()

Variable Documentation

◆ res_code

◆ verbose