SHOGUN
4.2.0
|
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 91 of file Alphabet.h.
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 More... | |
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 More... | |
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) |
virtual CSGObject * | shallow_copy () const |
virtual CSGObject * | deep_copy () const |
virtual bool | is_generic (EPrimitiveType *generic) const |
template<class T > | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
void | set_generic () |
template<> | |
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 () |
SGStringList< char > | get_modelsel_names () |
void | print_modsel_params () |
char * | get_modsel_param_descr (const char *param_name) |
index_t | get_modsel_param_index (const char *param_name) |
void | build_gradient_parameter_dictionary (CMap< TParameter *, CSGObject * > *dict) |
bool | has (const std::string &name) const |
template<typename T > | |
bool | has (const Tag< T > &tag) const |
template<typename T , typename U = void> | |
bool | has (const std::string &name) const |
template<typename T > | |
void | set (const Tag< T > &_tag, const T &value) |
template<typename T , typename U = void> | |
void | set (const std::string &name, const T &value) |
template<typename T > | |
T | get (const Tag< T > &_tag) const |
template<typename T , typename U = void> | |
T | get (const std::string &name) const |
virtual void | update_parameter_hash () |
virtual bool | parameter_hash_changed () |
virtual bool | equals (CSGObject *other, float64_t accuracy=0.0, bool tolerant=false) |
virtual CSGObject * | clone () |
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) |
Public Attributes | |
SGIO * | io |
Parallel * | parallel |
Version * | version |
Parameter * | m_parameters |
Parameter * | m_model_selection_parameters |
Parameter * | m_gradient_parameters |
uint32_t | m_hash |
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) |
virtual void | load_serializable_pre () throw (ShogunException) |
virtual void | save_serializable_pre () throw (ShogunException) |
virtual void | save_serializable_post () throw (ShogunException) |
template<typename T > | |
void | register_param (Tag< T > &_tag, const T &value) |
template<typename T > | |
void | register_param (const std::string &name, const T &value) |
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)] |
CAlphabet | ( | ) |
default constructor
Definition at line 35 of file Alphabet.cpp.
CAlphabet | ( | char * | alpha, |
int32_t | len | ||
) |
|
virtual |
Definition at line 104 of file Alphabet.cpp.
void add_byte_to_histogram | ( | uint8_t | p | ) |
void add_string_to_histogram | ( | T * | p, |
int64_t | len | ||
) |
make histogram for whole string
p | string |
len | length of string |
Definition at line 183 of file Alphabet.h.
|
inherited |
Builds a dictionary of all parameters in SGObject as well of those of SGObjects that are parameters of this object. Dictionary maps parameters to the objects that own them.
dict | dictionary of parameters to be built. |
Definition at line 630 of file SGObject.cpp.
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
print_error | if errors shall be printed |
Definition at line 617 of file Alphabet.cpp.
bool check_alphabet_size | ( | bool | print_error = true | ) |
check whether symbols in histogram ALL fit in alphabet
print_error | if errors shall be printed |
Definition at line 639 of file Alphabet.cpp.
void clear_histogram | ( | ) |
clear histogram
Definition at line 544 of file Alphabet.cpp.
|
virtualinherited |
Creates a clone of the current object. This is done via recursively traversing all parameters, which corresponds to a deep copy. Calling equals on the cloned object always returns true although none of the memory of both objects overlaps.
Definition at line 747 of file SGObject.cpp.
|
protected |
copy histogram
src | alphabet to copy histogram from |
Definition at line 656 of file Alphabet.cpp.
|
virtualinherited |
A deep copy. All the instance variables will also be copied.
Definition at line 231 of file SGObject.cpp.
Recursively compares the current SGObject to another one. Compares all registered numerical parameters, recursion upon complex (SGObject) parameters. Does not compare pointers!
May be overwritten but please do with care! Should not be necessary in most cases.
other | object to compare with |
accuracy | accuracy to use for comparison (optional) |
tolerant | allows linient check on float equality (within accuracy) |
Definition at line 651 of file SGObject.cpp.
|
inherited |
Getter for a class parameter, identified by a Tag. Throws an exception if the class does not have such a parameter.
_tag | name and type information of parameter |
Definition at line 367 of file SGObject.h.
|
inherited |
Getter for a class parameter, identified by a name. Throws an exception if the class does not have such a parameter.
name | name of the parameter |
Definition at line 388 of file SGObject.h.
EAlphabet get_alphabet | ( | ) | const |
|
static |
return alphabet name
alphabet | alphabet type to get name from |
Definition at line 669 of file Alphabet.cpp.
|
inherited |
|
inherited |
|
inherited |
SGVector< int64_t > get_histogram | ( | ) |
int32_t get_max_value_in_histogram | ( | ) |
return maximum value in histogram
Definition at line 550 of file Alphabet.cpp.
|
inherited |
Definition at line 531 of file SGObject.cpp.
|
inherited |
Returns description of a given parameter string, if it exists. SG_ERROR otherwise
param_name | name of the parameter |
Definition at line 555 of file SGObject.cpp.
|
inherited |
Returns index of model selection parameter with provided index
param_name | name of model selection parameter |
Definition at line 568 of file SGObject.cpp.
|
virtual |
int32_t get_num_bits | ( | ) | const |
get number of bits necessary to store all symbols in alphabet
Definition at line 149 of file Alphabet.h.
int32_t get_num_bits_in_histogram | ( | ) |
return number of bits required to store all symbols in histogram
Definition at line 577 of file Alphabet.cpp.
int32_t get_num_symbols | ( | ) | const |
get number of symbols in alphabet
Definition at line 139 of file Alphabet.h.
int32_t get_num_symbols_in_histogram | ( | ) |
return number of symbols in histogram
Definition at line 565 of file Alphabet.cpp.
|
inherited |
Checks if object has a class parameter identified by a name.
name | name of the parameter |
Definition at line 289 of file SGObject.h.
|
inherited |
Checks if object has a class parameter identified by a Tag.
tag | tag of the parameter containing name and type information |
Definition at line 301 of file SGObject.h.
|
inherited |
Checks if a type exists for a class parameter identified by a name.
name | name of the parameter |
Definition at line 312 of file SGObject.h.
|
protected |
init map table
Definition at line 179 of file Alphabet.cpp.
|
virtualinherited |
If the SGSerializable is a class template then TRUE will be returned and GENERIC is set to the type of the generic.
generic | set to the type of the generic if returning TRUE |
Definition at line 329 of file SGObject.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
c | symbol |
Definition at line 221 of file Alphabet.h.
|
virtualinherited |
Load this object from file. If it will fail (returning FALSE) then this object will contain inconsistent data and should not be used!
file | where to load from |
prefix | prefix for members |
Definition at line 402 of file SGObject.cpp.
|
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.
ShogunException | Will be thrown if an error occurres. |
Reimplemented from CSGObject.
Definition at line 749 of file Alphabet.cpp.
|
protectedvirtualinherited |
Can (optionally) be overridden to pre-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::LOAD_SERIALIZABLE_PRE is called.
ShogunException | will be thrown if an error occurs. |
Reimplemented in CDynamicArray< T >, CDynamicArray< float64_t >, CDynamicArray< float32_t >, CDynamicArray< int32_t >, CDynamicArray< char >, CDynamicArray< bool >, and CDynamicObjectArray.
Definition at line 454 of file SGObject.cpp.
|
virtualinherited |
Definition at line 295 of file SGObject.cpp.
void print_histogram | ( | ) |
print histogram
Definition at line 587 of file Alphabet.cpp.
|
inherited |
prints all parameter registered for model selection and their type
Definition at line 507 of file SGObject.cpp.
|
virtualinherited |
prints registered parameters out
prefix | prefix for members |
Definition at line 341 of file SGObject.cpp.
|
protectedinherited |
Registers a class parameter which is identified by a tag. This enables the parameter to be modified by set() and retrieved by get(). Parameters can be registered in the constructor of the class.
_tag | name and type information of parameter |
value | value of the parameter |
Definition at line 439 of file SGObject.h.
|
protectedinherited |
Registers a class parameter which is identified by a name. This enables the parameter to be modified by set() and retrieved by get(). Parameters can be registered in the constructor of the class.
name | name of the parameter |
value | value of the parameter along with type information |
Definition at line 452 of file SGObject.h.
uint8_t remap_to_bin | ( | uint8_t | c | ) |
remap element e.g translate ACGT to 0123
c | element to remap |
Definition at line 159 of file Alphabet.h.
uint8_t remap_to_char | ( | uint8_t | c | ) |
remap element e.g translate 0123 to ACGT
c | element to remap |
Definition at line 169 of file Alphabet.h.
|
virtualinherited |
Save this object to file.
file | where to save the object; will be closed during returning if PREFIX is an empty string. |
prefix | prefix for members |
Definition at line 347 of file SGObject.cpp.
|
protectedvirtualinherited |
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::SAVE_SERIALIZABLE_POST is called.
ShogunException | will be thrown if an error occurs. |
Reimplemented in CKernel.
Definition at line 469 of file SGObject.cpp.
|
protectedvirtualinherited |
Can (optionally) be overridden to pre-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::SAVE_SERIALIZABLE_PRE is called.
ShogunException | will be thrown if an error occurs. |
Reimplemented in CKernel, CDynamicArray< T >, CDynamicArray< float64_t >, CDynamicArray< float32_t >, CDynamicArray< int32_t >, CDynamicArray< char >, CDynamicArray< bool >, and CDynamicObjectArray.
Definition at line 464 of file SGObject.cpp.
|
inherited |
Setter for a class parameter, identified by a Tag. Throws an exception if the class does not have such a parameter.
_tag | name and type information of parameter |
value | value of the parameter |
Definition at line 328 of file SGObject.h.
|
inherited |
Setter for a class parameter, identified by a name. Throws an exception if the class does not have such a parameter.
name | name of the parameter |
value | value of the parameter along with type information |
Definition at line 354 of file SGObject.h.
bool set_alphabet | ( | EAlphabet | alpha | ) |
set alphabet and initialize mapping table (for remap)
alpha | new alphabet |
Definition at line 108 of file Alphabet.cpp.
|
inherited |
Definition at line 74 of file SGObject.cpp.
|
inherited |
Definition at line 79 of file SGObject.cpp.
|
inherited |
Definition at line 84 of file SGObject.cpp.
|
inherited |
Definition at line 89 of file SGObject.cpp.
|
inherited |
Definition at line 94 of file SGObject.cpp.
|
inherited |
Definition at line 99 of file SGObject.cpp.
|
inherited |
Definition at line 104 of file SGObject.cpp.
|
inherited |
Definition at line 109 of file SGObject.cpp.
|
inherited |
Definition at line 114 of file SGObject.cpp.
|
inherited |
Definition at line 119 of file SGObject.cpp.
|
inherited |
Definition at line 124 of file SGObject.cpp.
|
inherited |
Definition at line 129 of file SGObject.cpp.
|
inherited |
Definition at line 134 of file SGObject.cpp.
|
inherited |
Definition at line 139 of file SGObject.cpp.
|
inherited |
Definition at line 144 of file SGObject.cpp.
|
inherited |
set generic type to T
|
inherited |
|
inherited |
set the parallel object
parallel | parallel object to use |
Definition at line 274 of file SGObject.cpp.
|
inherited |
set the version object
version | version object to use |
Definition at line 316 of file SGObject.cpp.
|
virtualinherited |
A shallow copy. All the SGObject instance variables will be simply assigned and SG_REF-ed.
Reimplemented in CGaussianKernel.
Definition at line 225 of file SGObject.cpp.
|
static |
translate from single order
obs | observation |
sequence_length | length of sequence |
start | start |
p_order | order |
max_val | maximum value |
Definition at line 760 of file Alphabet.cpp.
|
static |
translate from single order
obs | observation |
sequence_length | length of sequence |
start | start |
p_order | order |
max_val | maximum value |
gap | gap |
Definition at line 836 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 955 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 959 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 963 of file Alphabet.cpp.
|
static |
translate from single order reversed
obs | observation |
sequence_length | length of sequence |
start | start |
p_order | order |
max_val | maximum value |
Definition at line 798 of file Alphabet.cpp.
|
static |
translate from single order reversed
obs | observation |
sequence_length | length of sequence |
start | start |
p_order | order |
max_val | maximum value |
gap | gap |
Definition at line 898 of file Alphabet.cpp.
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 | ||
) |
Definition at line 967 of file Alphabet.cpp.
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 | ||
) |
Definition at line 971 of file Alphabet.cpp.
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 | ||
) |
Definition at line 975 of file Alphabet.cpp.
|
inherited |
unset generic type
this has to be called in classes specializing a template class
Definition at line 336 of file SGObject.cpp.
|
virtualinherited |
Updates the hash of current parameter combination
Definition at line 281 of file SGObject.cpp.
|
protected |
alphabet
Definition at line 353 of file Alphabet.h.
|
static |
alphabet names
Definition at line 338 of file Alphabet.h.
|
static |
B_0
Definition at line 334 of file Alphabet.h.
|
static |
B_A
Definition at line 326 of file Alphabet.h.
|
static |
B_C
Definition at line 328 of file Alphabet.h.
|
static |
B_G
Definition at line 330 of file Alphabet.h.
|
static |
B_T
Definition at line 332 of file Alphabet.h.
|
protected |
histogram
Definition at line 365 of file Alphabet.h.
|
inherited |
io
Definition at line 537 of file SGObject.h.
|
inherited |
parameters wrt which we can compute gradients
Definition at line 552 of file SGObject.h.
|
inherited |
Hash of parameter values
Definition at line 555 of file SGObject.h.
|
inherited |
model selection parameters
Definition at line 549 of file SGObject.h.
|
inherited |
parameters
Definition at line 546 of file SGObject.h.
|
protected |
maptable to bin
Definition at line 361 of file Alphabet.h.
|
protected |
maptable to char
Definition at line 363 of file Alphabet.h.
|
static |
MAPTABLE UNDEF
Definition at line 336 of file Alphabet.h.
|
protected |
number of bits
Definition at line 357 of file Alphabet.h.
|
protected |
number of symbols
Definition at line 355 of file Alphabet.h.
|
inherited |
parallel
Definition at line 540 of file SGObject.h.
|
protected |
valid chars
Definition at line 359 of file Alphabet.h.
|
inherited |
version
Definition at line 543 of file SGObject.h.