CAlphabet Class Reference

Detailed Description

The class Alphabet implements an alphabet and alphabet utility functions.

These utility functions can be used to remap characters to more (bit-)efficient representations, check if a string is valid, compute histograms etc.

Currently supported alphabets are DNA, RAWDNA, RNA, PROTEIN, BINARY, ALPHANUM, CUBE, RAW, IUPAC_NUCLEIC_ACID and IUPAC_AMINO_ACID.

Definition at line 88 of file Alphabet.h.

Inheritance diagram for CAlphabet:

Public Member Functions
	CAlphabet ()
	CAlphabet (char *alpha, int32_t len)
	CAlphabet (EAlphabet alpha)
	CAlphabet (CAlphabet *alpha)
virtual	~CAlphabet ()
bool	set_alphabet (EAlphabet alpha)
EAlphabet	get_alphabet () const
int32_t	get_num_symbols () const
int32_t	get_num_bits () const
uint8_t	remap_to_bin (uint8_t c)
uint8_t	remap_to_char (uint8_t c)
void	clear_histogram ()
	clear histogram
template<class T >
void	add_string_to_histogram (T *p, int64_t len)
void	add_byte_to_histogram (uint8_t p)
void	print_histogram ()
	print histogram
SGVector< int64_t >	get_histogram ()
bool	check_alphabet (bool print_error=true)
bool	is_valid (uint8_t c)
bool	check_alphabet_size (bool print_error=true)
int32_t	get_num_symbols_in_histogram ()
int32_t	get_max_value_in_histogram ()
int32_t	get_num_bits_in_histogram ()
virtual const char *	get_name () const
template<>
void	translate_from_single_order (float32_t *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val, int32_t gap)
template<>
void	translate_from_single_order (float64_t *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val, int32_t gap)
template<>
void	translate_from_single_order (floatmax_t *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val, int32_t gap)
template<>
void	translate_from_single_order_reversed (float32_t *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val, int32_t gap)
template<>
void	translate_from_single_order_reversed (float64_t *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val, int32_t gap)
template<>
void	translate_from_single_order_reversed (floatmax_t *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val, int32_t gap)
Public Member Functions inherited from CSGObject
	CSGObject ()
	CSGObject (const CSGObject &orig)
virtual	~CSGObject ()
virtual bool	is_generic (EPrimitiveType *generic) const
template<class T >
void	set_generic ()
void	unset_generic ()
virtual void	print_serializable (const char *prefix="")
virtual bool	save_serializable (CSerializableFile *file, const char *prefix="")
virtual bool	load_serializable (CSerializableFile *file, const char *prefix="")
void	set_global_io (SGIO *io)
SGIO *	get_global_io ()
void	set_global_parallel (Parallel *parallel)
Parallel *	get_global_parallel ()
void	set_global_version (Version *version)
Version *	get_global_version ()
SGVector< char * >	get_modelsel_names ()
char *	get_modsel_param_descr (const char *param_name)
index_t	get_modsel_param_index (const char *param_name)

Static Public Member Functions
static const char *	get_alphabet_name (EAlphabet alphabet)
template<class ST >
static void	translate_from_single_order (ST *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val)
template<class ST >
static void	translate_from_single_order_reversed (ST *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val)
template<class ST >
static void	translate_from_single_order (ST *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val, int32_t gap)
template<class ST >
static void	translate_from_single_order_reversed (ST *obs, int32_t sequence_length, int32_t start, int32_t p_order, int32_t max_val, int32_t gap)

Static Public Attributes
static const uint8_t	B_A = 0
static const uint8_t	B_C = 1
static const uint8_t	B_G = 2
static const uint8_t	B_T = 3
static const uint8_t	B_0 = 4
static const uint8_t	MAPTABLE_UNDEF = 0xff
static const char *	alphabet_names [18]

Protected Member Functions
void	init_map_table ()
void	copy_histogram (CAlphabet *src)
virtual void	load_serializable_post () throw (ShogunException)
Protected Member Functions inherited from CSGObject
virtual void	load_serializable_pre () throw (ShogunException)
virtual void	save_serializable_pre () throw (ShogunException)
virtual void	save_serializable_post () throw (ShogunException)

Protected Attributes
EAlphabet	alphabet
int32_t	num_symbols
int32_t	num_bits
bool	valid_chars [1<< (sizeof(uint8_t)*8)]
uint8_t	maptable_to_bin [1<< (sizeof(uint8_t)*8)]
uint8_t	maptable_to_char [1<< (sizeof(uint8_t)*8)]
int64_t	histogram [1<< (sizeof(uint8_t)*8)]

Additional Inherited Members
Public Attributes inherited from CSGObject
SGIO *	io
Parallel *	parallel
Version *	version
Parameter *	m_parameters
Parameter *	m_model_selection_parameters

Constructor & Destructor Documentation

CAlphabet

(

)

default constructor

Definition at line 34 of file Alphabet.cpp.

CAlphabet	(	char *	alpha,
		int32_t	len
	)

constructor

Parameters

alpha	alphabet to use
len	len

Definition at line 40 of file Alphabet.cpp.

CAlphabet

(

EAlphabet

alpha

)

constructor

Parameters

alpha

alphabet (type) to use

Definition at line 87 of file Alphabet.cpp.

CAlphabet

(

CAlphabet *

alpha

)

constructor

Parameters

alpha

alphabet to use

Definition at line 94 of file Alphabet.cpp.

~CAlphabet ( )

virtual

Definition at line 103 of file Alphabet.cpp.

Member Function Documentation

void add_byte_to_histogram

(

uint8_t

p

)

add element to histogram

Parameters

p

element

Definition at line 190 of file Alphabet.h.

void add_string_to_histogram	(	T *	p,
		int64_t	len
	)

make histogram for whole string

Parameters

p	string
len	length of string

Definition at line 180 of file Alphabet.h.

bool check_alphabet

(

bool

print_error = true

)

check whether symbols in histogram are valid in alphabet e.g. for DNA if only letters ACGT appear

Parameters

print_error

if errors shall be printed

Returns

if symbols in histogram are valid in alphabet

Definition at line 600 of file Alphabet.cpp.

bool check_alphabet_size

(

bool

print_error = true

)

check whether symbols in histogram ALL fit in alphabet

Parameters

print_error

if errors shall be printed

Returns

if symbols in histogram ALL fit in alphabet

Definition at line 622 of file Alphabet.cpp.

void clear_histogram

(

)

clear histogram

Definition at line 543 of file Alphabet.cpp.

void copy_histogram ( CAlphabet *  src )

protected

copy histogram

Parameters

src	alphabet to copy histogram from

Definition at line 639 of file Alphabet.cpp.

EAlphabet get_alphabet

(

)

const

get alphabet

Returns

alphabet

Definition at line 127 of file Alphabet.h.

const char * get_alphabet_name ( EAlphabet  alphabet )

static

return alphabet name

Parameters

alphabet

alphabet type to get name from

Definition at line 652 of file Alphabet.cpp.

SGVector< int64_t > get_histogram

(

)

get histogram

Returns

histogram

Definition at line 595 of file Alphabet.cpp.

int32_t get_max_value_in_histogram

(

)

return maximum value in histogram

Returns

maximum value in histogram

Definition at line 549 of file Alphabet.cpp.

virtual const char* get_name ( ) const

virtual

Returns

object name

Implements CSGObject.

Definition at line 258 of file Alphabet.h.

int32_t get_num_bits

(

)

const

get number of bits necessary to store all symbols in alphabet

Returns

number of necessary storage bits

Definition at line 146 of file Alphabet.h.

int32_t get_num_bits_in_histogram

(

)

return number of bits required to store all symbols in histogram

Returns

number of bits required to store all symbols in histogram

Definition at line 576 of file Alphabet.cpp.

int32_t get_num_symbols

(

)

const

get number of symbols in alphabet

Returns

number of symbols

Definition at line 136 of file Alphabet.h.

int32_t get_num_symbols_in_histogram

(

)

return number of symbols in histogram

Returns

number of symbols in histogram

Definition at line 564 of file Alphabet.cpp.

void init_map_table ( )

protected

init map table

Definition at line 178 of file Alphabet.cpp.

bool is_valid

(

uint8_t

c

)

check whether symbols are valid in alphabet e.g. for DNA if symbol is one of the A,C,G or T

Parameters

c

symbol

Returns

if symbol is a valid character in alphabet

Definition at line 218 of file Alphabet.h.

void load_serializable_post ( ) throw (ShogunException)

protectedvirtual

Can (optionally) be overridden to post-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::LOAD_SERIALIZABLE_POST is called.

Exceptions

ShogunException

Will be thrown if an error occurres.

Reimplemented from CSGObject.

Definition at line 732 of file Alphabet.cpp.

void print_histogram

(

)

print histogram

Definition at line 586 of file Alphabet.cpp.

uint8_t remap_to_bin

(

uint8_t

c

)

remap element e.g translate ACGT to 0123

Parameters

c	element to remap

Returns

remapped element

Definition at line 156 of file Alphabet.h.

uint8_t remap_to_char

(

uint8_t

c

)

remap element e.g translate 0123 to ACGT

Parameters

c	element to remap

Returns

remapped element

Definition at line 166 of file Alphabet.h.

bool set_alphabet

(

EAlphabet

alpha

)

set alphabet and initialize mapping table (for remap)

Parameters

alpha

new alphabet

Definition at line 107 of file Alphabet.cpp.

void translate_from_single_order ( ST *  obs, int32_t  sequence_length, int32_t  start, int32_t  p_order, int32_t  max_val  )

static

translate from single order

Parameters

obs	observation
sequence_length	length of sequence
start	start
p_order	order
max_val	maximum value

Definition at line 743 of file Alphabet.cpp.

void translate_from_single_order ( ST *  obs, int32_t  sequence_length, int32_t  start, int32_t  p_order, int32_t  max_val, int32_t  gap  )

static

translate from single order

Parameters

obs	observation
sequence_length	length of sequence
start	start
p_order	order
max_val	maximum value
gap	gap

Definition at line 819 of file Alphabet.cpp.

void translate_from_single_order	(	float32_t *	obs,
		int32_t	sequence_length,
		int32_t	start,
		int32_t	p_order,
		int32_t	max_val,
		int32_t	gap
	)

Definition at line 938 of file Alphabet.cpp.

void translate_from_single_order	(	float64_t *	obs,
		int32_t	sequence_length,
		int32_t	start,
		int32_t	p_order,
		int32_t	max_val,
		int32_t	gap
	)

Definition at line 942 of file Alphabet.cpp.

void translate_from_single_order	(	floatmax_t *	obs,
		int32_t	sequence_length,
		int32_t	start,
		int32_t	p_order,
		int32_t	max_val,
		int32_t	gap
	)

Definition at line 946 of file Alphabet.cpp.

void translate_from_single_order_reversed ( ST *  obs, int32_t  sequence_length, int32_t  start, int32_t  p_order, int32_t  max_val  )

static

translate from single order reversed

Parameters

obs	observation
sequence_length	length of sequence
start	start
p_order	order
max_val	maximum value

Definition at line 781 of file Alphabet.cpp.

void translate_from_single_order_reversed ( ST *  obs, int32_t  sequence_length, int32_t  start, int32_t  p_order, int32_t  max_val, int32_t  gap  )

static

translate from single order reversed

Parameters

obs	observation
sequence_length	length of sequence
start	start
p_order	order
max_val	maximum value
gap	gap

Definition at line 881 of file Alphabet.cpp.

template void translate_from_single_order_reversed< float32_t >	(	float32_t *	obs,
		int32_t	sequence_length,
		int32_t	start,
		int32_t	p_order,
		int32_t	max_val,
		int32_t	gap
	)

Definition at line 950 of file Alphabet.cpp.

template void translate_from_single_order_reversed< float64_t >	(	float64_t *	obs,
		int32_t	sequence_length,
		int32_t	start,
		int32_t	p_order,
		int32_t	max_val,
		int32_t	gap
	)

Definition at line 954 of file Alphabet.cpp.

template void translate_from_single_order_reversed< floatmax_t >	(	floatmax_t *	obs,
		int32_t	sequence_length,
		int32_t	start,
		int32_t	p_order,
		int32_t	max_val,
		int32_t	gap
	)

Definition at line 958 of file Alphabet.cpp.

Member Data Documentation

EAlphabet alphabet

protected

alphabet

Definition at line 350 of file Alphabet.h.

const char * alphabet_names

static

Initial value:

{
    "DNA","RAWDNA", "RNA", "PROTEIN", "BINARY", "ALPHANUM",
    "CUBE", "RAW", "IUPAC_NUCLEIC_ACID", "IUPAC_AMINO_ACID",
    "NONE", "DIGIT", "DIGIT2", "RAWDIGIT", "RAWDIGIT2", "UNKNOWN",
    "SNP", "RAWSNP"}

alphabet names

Definition at line 335 of file Alphabet.h.

const uint8_t B_0 = 4

static

B_0

Definition at line 331 of file Alphabet.h.

const uint8_t B_A = 0

static

B_A

Definition at line 323 of file Alphabet.h.

const uint8_t B_C = 1

static

B_C

Definition at line 325 of file Alphabet.h.

const uint8_t B_G = 2

static

B_G

Definition at line 327 of file Alphabet.h.

const uint8_t B_T = 3

static

B_T

Definition at line 329 of file Alphabet.h.

int64_t histogram[1<< (sizeof(uint8_t)*8)]

protected

histogram

Definition at line 362 of file Alphabet.h.

uint8_t maptable_to_bin[1<< (sizeof(uint8_t)*8)]

protected

maptable to bin

Definition at line 358 of file Alphabet.h.

uint8_t maptable_to_char[1<< (sizeof(uint8_t)*8)]

protected

maptable to char

Definition at line 360 of file Alphabet.h.

const uint8_t MAPTABLE_UNDEF = 0xff

static

MAPTABLE UNDEF

Definition at line 333 of file Alphabet.h.

int32_t num_bits

protected

number of bits

Definition at line 354 of file Alphabet.h.

int32_t num_symbols

protected

number of symbols

Definition at line 352 of file Alphabet.h.

bool valid_chars[1<< (sizeof(uint8_t)*8)]

protected

valid chars

Definition at line 356 of file Alphabet.h.

---

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

• Alphabet.h
• Alphabet.cpp