Various utility- and helper-functions used throughout the Vienna RNA package. More...

This graph shows which files directly or indirectly include this file:

Macros
#define	VRNA_INPUT_ERROR 1U

#define	VRNA_INPUT_QUIT 2U

#define	VRNA_INPUT_MISC 4U

#define	VRNA_INPUT_FASTA_HEADER 8U

#define	VRNA_INPUT_SEQUENCE 16U

#define	VRNA_INPUT_CONSTRAINT 32U

#define	VRNA_INPUT_NO_TRUNCATION 256U

#define	VRNA_INPUT_NO_REST 512U

#define	VRNA_INPUT_NO_SPAN 1024U

#define	VRNA_INPUT_NOSKIP_BLANK_LINES 2048U

#define	VRNA_INPUT_BLANK_LINE 4096U

#define	VRNA_INPUT_NOSKIP_COMMENTS 128U

#define	VRNA_INPUT_COMMENT 8192U

#define	VRNA_CONSTRAINT_PIPE 1U

#define	VRNA_CONSTRAINT_DOT 2U

#define	VRNA_CONSTRAINT_X 4U

#define	VRNA_CONSTRAINT_ANG_BRACK 8U

#define	VRNA_CONSTRAINT_RND_BRACK 16U

#define	VRNA_CONSTRAINT_MULTILINE 32U

#define	VRNA_CONSTRAINT_NO_HEADER 64U

#define	VRNA_CONSTRAINT_ALL 128U

#define	VRNA_CONSTRAINT_G 256U

#define	VRNA_OPTION_MULTILINE 32U

#define	MIN2(A, B) ((A) < (B) ? (A) : (B))

#define	MAX2(A, B) ((A) > (B) ? (A) : (B))

#define	MIN3(A, B, C) (MIN2( (MIN2((A),(B))) ,(C)))

#define	MAX3(A, B, C) (MAX2( (MAX2((A),(B))) ,(C)))

#define	XSTR(s) STR(s)

#define	STR(s) #s

#define	FILENAME_MAX_LENGTH 80
	Maximum length of filenames that are generated by our programs. More...

#define	FILENAME_ID_LENGTH 42
	Maximum length of id taken from fasta header for filename generation. More...

Functions
void *	space (unsigned size)
	Allocate space safely. More...

void *	xrealloc (void *p, unsigned size)
	Reallocate space safely. More...

void	nrerror (const char message[])
	Die with an error message. More...

void	warn_user (const char message[])
	Print a warning message. More...

void	init_rand (void)
	Make random number seeds.

double	urn (void)
	get a random number from [0..1] More...

int	int_urn (int from, int to)
	Generates a pseudo random integer in a specified range. More...

char *	time_stamp (void)
	Get a timestamp. More...

char *	random_string (int l, const char symbols[])
	Create a random string using characters from a specified symbol set. More...

int	hamming (const char s1, const char s2)
	Calculate hamming distance between two sequences. More...

int	hamming_bound (const char s1, const char s2, int n)
	Calculate hamming distance between two sequences up to a specified length. More...

char *	get_line (FILE *fp)
	Read a line of arbitrary length from a stream. More...

unsigned int	get_input_line (char **string, unsigned int options)

unsigned int	read_record (char header, char sequence, char ***rest, unsigned int options)
	Get a data record from stdin. More...

char *	pack_structure (const char *struc)
	Pack secondary secondary structure, 5:1 compression using base 3 encoding. More...

char *	unpack_structure (const char *packed)
	Unpack secondary structure previously packed with pack_structure() More...

short *	make_pair_table (const char *structure)
	Create a pair table of a secondary structure. More...

short *	copy_pair_table (const short *pt)
	Get an exact copy of a pair table. More...

short *	alimake_pair_table (const char *structure)

short *	make_pair_table_snoop (const char *structure)

int *	make_loop_index_pt (short *pt)
	Compute the "base pair" distance between two secondary structures s1 and s2. More...

void	print_tty_input_seq (void)
	Print a line to stdout that asks for an input sequence. More...

void	print_tty_input_seq_str (const char *s)
	Print a line with a user defined string and a ruler to stdout. More...

void	print_tty_constraint_full (void)
	Print structure constraint characters to stdout (full constraint support)

void	print_tty_constraint (unsigned int option)
	Print structure constraint characters to stdout. (constraint support is specified by option parameter) More...

void	str_DNA2RNA (char *sequence)
	Convert a DNA input sequence to RNA alphabet. More...

void	str_uppercase (char *sequence)
	Convert an input sequence to uppercase. More...

int *	get_iindx (unsigned int length)
	Get an index mapper array (iindx) for accessing the energy matrices, e.g. in partition function related functions. More...

int *	get_indx (unsigned int length)
	Get an index mapper array (indx) for accessing the energy matrices, e.g. in MFE related functions. More...

void	constrain_ptypes (const char constraint, unsigned int length, char ptype, int *BP, int min_loop_size, unsigned int idx_type)
	Insert constraining pair types according to constraint structure string. More...

Variables
unsigned short	xsubi [3]
	Current 48 bit random number. More...

Detailed Description

Various utility- and helper-functions used throughout the Vienna RNA package.

Macro Definition Documentation

#define VRNA_INPUT_ERROR 1U

Output flag of get_input_line(): "An ERROR has occured, maybe EOF"

#define VRNA_INPUT_QUIT 2U

Output flag of get_input_line(): "the user requested quitting the program"

#define VRNA_INPUT_MISC 4U

Output flag of get_input_line(): "something was read"

#define VRNA_INPUT_FASTA_HEADER 8U

Input/Output flag of get_input_line():
if used as input option this tells get_input_line() that the data to be read should comply with the FASTA format

the function will return this flag if a fasta header was read

#define VRNA_INPUT_SEQUENCE 16U

Input flag for get_input_line():
Tell get_input_line() that we assume to read a nucleotide sequence

#define VRNA_INPUT_CONSTRAINT 32U

Input flag for get_input_line():
Tell get_input_line() that we assume to read a structure constraint

#define VRNA_INPUT_NO_TRUNCATION 256U

Input switch for get_input_line(): "do not trunkate the line by eliminating white spaces at end of line"

#define VRNA_INPUT_NO_REST 512U

Input switch for read_record(): "do fill rest array"

#define VRNA_INPUT_NO_SPAN 1024U

Input switch for read_record(): "never allow data to span more than one line"

#define VRNA_INPUT_NOSKIP_BLANK_LINES 2048U

Input switch for read_record(): "do not skip empty lines"

#define VRNA_INPUT_BLANK_LINE 4096U

Output flag for read_record(): "read an empty line"

#define VRNA_INPUT_NOSKIP_COMMENTS 128U

Input switch for get_input_line(): "do not skip comment lines"

#define VRNA_INPUT_COMMENT 8192U

Output flag for read_record(): "read a comment"

#define VRNA_CONSTRAINT_PIPE 1U

pipe sign '|' switch for structure constraints (paired with another base)

#define VRNA_CONSTRAINT_DOT 2U

dot '.' switch for structure constraints (no constraint at all)

#define VRNA_CONSTRAINT_X 4U

'x' switch for structure constraint (base must not pair)

#define VRNA_CONSTRAINT_ANG_BRACK 8U

angle brackets '<', '>' switch for structure constraint (paired downstream/upstream)

#define VRNA_CONSTRAINT_RND_BRACK 16U

round brackets '(',')' switch for structure constraint (base i pairs base j)

#define VRNA_CONSTRAINT_MULTILINE 32U

constraint may span over several lines

#define VRNA_CONSTRAINT_NO_HEADER 64U

do not print the header information line

#define VRNA_CONSTRAINT_ALL 128U

placeholder for all constraining characters

#define VRNA_CONSTRAINT_G 256U

'+' switch for structure constraint (base is involved in a gquad)

#define VRNA_OPTION_MULTILINE 32U

Tell a function that an input is assumed to span several lines if used as input-option A function might also be returning this state telling that it has read data from multiple lines.

See Also: extract_record_rest_structure(), read_record(), getConstraint()

#define MIN2	(	A,
		B
	)	((A) < (B) ? (A) : (B))

Get the minimum of two comparable values

#define MAX2	(	A,
		B
	)	((A) > (B) ? (A) : (B))

Get the maximum of two comparable values

#define MIN3	(	A,
		B,
		C
	)	(MIN2( (MIN2((A),(B))) ,(C)))

Get the minimum of three comparable values

#define MAX3	(	A,
		B,
		C
	)	(MAX2( (MAX2((A),(B))) ,(C)))

Get the maximum of three comparable values

#define XSTR ( s ) STR(s)

Stringify a macro after expansion

#define STR ( s ) #s

Stringify a macro argument

#define FILENAME_MAX_LENGTH 80

Maximum length of filenames that are generated by our programs.

This definition should be used throughout the complete ViennaRNA package wherever a static array holding filenames of output files is declared.

#define FILENAME_ID_LENGTH 42

Maximum length of id taken from fasta header for filename generation.

this has to be smaller than FILENAME_MAX_LENGTH since in most cases, some suffix will be appended to the ID

Function Documentation

void* space ( unsigned size )

Allocate space safely.

Parameters

size	The size of the memory to be allocated in bytes

Returns: A pointer to the allocated memory

void* xrealloc	(	void *	p,
		unsigned	size
	)

Reallocate space safely.

Parameters

p	A pointer to the memory region to be reallocated
size	The size of the memory to be allocated in bytes

Returns: A pointer to the newly allocated memory

void nrerror ( const char message[] )

Die with an error message.

See Also: warn_user()

Parameters

message The error message to be printed before exiting with 'FAILURE'

void warn_user ( const char message[] )

Print a warning message.

Print a warning message to stderr

Parameters

message The warning message

double urn ( void )

get a random number from [0..1]

Note: Usually implemented by calling erand48().

Returns: A random number in range [0..1]

int int_urn	(	int	from,
		int	to
	)

Generates a pseudo random integer in a specified range.

Parameters

from	The first number in range
to	The last number in range

Returns: A pseudo random number in range [from, to]

char* time_stamp ( void )

Get a timestamp.

Returns a string containing the current date in the format

Fri Mar 19 21:10:57 1993

Returns: A string containing the timestamp

char* random_string	(	int	l,
		const char	symbols[]
	)

Create a random string using characters from a specified symbol set.

Parameters

l	The length of the sequence
symbols	The symbol set

Returns: A random string of length 'l' containing characters from the symbolset

int hamming	(	const char *	s1,
		const char *	s2
	)

Calculate hamming distance between two sequences.

Calculate the number of positions in which

Parameters

s1	The first sequence
s2	The second sequence

Returns: The hamming distance between s1 and s2

int hamming_bound	(	const char *	s1,
		const char *	s2,
		int	n
	)

Calculate hamming distance between two sequences up to a specified length.

This function is similar to hamming() but instead of comparing both sequences up to their actual length only the first 'n' characters are taken into account

Parameters

s1	The first sequence
s2	The second sequence

Returns: The hamming distance between s1 and s2

char* get_line ( FILE * fp )

Read a line of arbitrary length from a stream.

Returns a pointer to the resulting string. The necessary memory is allocated and should be released using free() when the string is no longer needed.

Parameters

fp	A file pointer to the stream where the function should read from

Returns: A pointer to the resulting string

unsigned int get_input_line	(	char **	string,
		unsigned int	options
	)

Retrieve a line from 'stdin' savely while skipping comment characters and other features This function returns the type of input it has read if recognized. An option argument allows to switch between different reading modes.
Currently available options are:
#VRNA_INPUT_NOPRINT_COMMENTS, VRNA_INPUT_NOSKIP_COMMENTS, #VRNA_INPUT_NOELIM_WS_SUFFIX

pass a collection of options as one value like this:

get_input_line(string, option_1 | option_2 | option_n)

If the function recognizes the type of input, it will report it in the return value. It also reports if a user defined 'quit' command (@-sign on 'stdin') was given. Possible return values are:
VRNA_INPUT_FASTA_HEADER, VRNA_INPUT_ERROR, VRNA_INPUT_MISC, VRNA_INPUT_QUIT

Parameters

string	A pointer to the character array that contains the line read
options	A collection of options for switching the functions behavior

Returns: A flag with information about what has been read

unsigned int read_record	(	char **	header,
		char **	sequence,
		char ***	rest,
		unsigned int	options
	)

Get a data record from stdin.

This function may be used to obtain complete datasets from stdin. A dataset is always
defined to contain at least a sequence. If data on stdin starts with a fasta header,
i.e. a line like

>some header info

then read_record() will assume that the sequence that follows the header may span over several lines. To disable this behavior and to assign a single line to the argument 'sequence' one can pass VRNA_INPUT_NO_SPAN in the 'options' argument. If no fasta header is read in the beginning of a data block, a sequence must not span over multiple lines!
Unless the options VRNA_INPUT_NOSKIP_COMMENTS or VRNA_INPUT_NOSKIP_BLANK_LINES are passed, a sequence may be interrupted by lines starting with a comment character or empty lines.
A sequence is regarded as completely read if it was either assumed to not span over multiple lines, a secondary structure or structure constraint follows the sequence on the next line or a new header marks the beginning of a new sequence...
All lines following the sequence (this includes comments) and not initiating a new dataset are available through the line-array 'rest'. Here one can usually find the structure constraint or other information belonging to the current dataset. Filling of 'rest' may be prevented by passing VRNA_INPUT_NO_REST to the options argument.

Note

This function will exit any program with an error message if no sequence could be read!

The main purpose of this function is to be able to easily parse blocks of data from stdin
in the header of a loop where all calculations for the appropriate data is done inside the
loop. The loop may be then left on certain return values, e.g.:

char *id, *seq, **rest;
int  i;
while(!(read_record(&id, &seq, &rest, 0) & (VRNA_INPUT_ERROR | VRNA_INPUT_QUIT))){
  if(id) printf("%s\n", id);
  printf("%s\n", seq);
  if(rest)
    for(i=0;rest[i];i++)
      printf("%s\n", rest[i]);
}

In the example above, the while loop will be terminated when read_record() returns either an
error or a user initiated quit request.\n
As long as data is read from stdin, the id is printed if it is available for the current block
of data. The sequence will be printed in any case and if some more lines belong to the current
block of data each line will be printed as well.

Do not forget to free the memory occupied by header, sequence and rest!

Parameters

header	A pointer which will be set such that it points to the header of the record
sequence	A pointer which will be set such that it points to the sequence of the record
rest	A pointer which will be set such that it points to an array of lines which also belong to the record
options	Some options which may be passed to alter the behavior of the function, use 0 for no options

Returns: A flag with information about what the function actually did read

char* pack_structure ( const char * struc )

Pack secondary secondary structure, 5:1 compression using base 3 encoding.

Returns a binary string encoding of the secondary structure using a 5:1 compression scheme. The string is NULL terminated and can therefore be used with standard string functions such as strcmp(). Useful for programs that need to keep many structures in memory.

Parameters

struc The secondary structure in dot-bracket notation

Returns: The binary encoded structure

char* unpack_structure ( const char * packed )

Unpack secondary structure previously packed with pack_structure()

Translate a compressed binary string produced by pack_structure() back into the familiar dot-bracket notation.

Parameters

packed The binary encoded packed secondary structure

Returns: The unpacked secondary structure in dot-bracket notation

short* make_pair_table ( const char * structure )

Create a pair table of a secondary structure.

Returns a newly allocated table, such that table[i]=j if (i.j) pair or 0 if i is unpaired, table[0] contains the length of the structure.

Parameters

structure The secondary structure in dot-bracket notation

Returns: A pointer to the created pair_table

short* copy_pair_table ( const short * pt )

Get an exact copy of a pair table.

Parameters

pt	The pair table to be copied

Returns: A pointer to the copy of 'pt'

short* alimake_pair_table ( const char * structure )

***Pair table for snoop align

short* make_pair_table_snoop ( const char * structure )

returns a newly allocated table, such that: table[i]=j if (i.j) pair or 0 if i is unpaired, table[0] contains the length of the structure. The special pseudoknotted H/ACA-mRNA structure is taken into account.

int* make_loop_index_pt ( short * pt )

Compute the "base pair" distance between two secondary structures s1 and s2.

The sequences should have the same length. dist = number of base pairs in one structure but not in the other same as edit distance with open-pair close-pair as move-set

Parameters

str1	First structure in dot-bracket notation
str2	Second structure in dot-bracket notation

Returns: The base pair distance between str1 and str2

void print_tty_input_seq ( void )

Print a line to stdout that asks for an input sequence.

There will also be a ruler (scale line) printed that helps orientation of the sequence positions

void print_tty_input_seq_str ( const char * s )

Print a line with a user defined string and a ruler to stdout.

(usually this is used to ask for user input) There will also be a ruler (scale line) printed that helps orientation of the sequence positions

Parameters

s	A user defined string that will be printed to stdout

void print_tty_constraint ( unsigned int option )

Print structure constraint characters to stdout. (constraint support is specified by option parameter)

Currently available options are:
VRNA_CONSTRAINT_PIPE (paired with another base)
VRNA_CONSTRAINT_DOT (no constraint at all)
VRNA_CONSTRAINT_X (base must not pair)
VRNA_CONSTRAINT_ANG_BRACK (paired downstream/upstream)
VRNA_CONSTRAINT_RND_BRACK (base i pairs base j)

pass a collection of options as one value like this:

print_tty_constraint(option_1 | option_2 | option_n)

Parameters

option Option switch that tells which constraint help will be printed

void str_DNA2RNA ( char * sequence )

Convert a DNA input sequence to RNA alphabet.

This function substitudes T and t with U and u, respectively

Parameters

sequence The sequence to be converted

void str_uppercase ( char * sequence )

Convert an input sequence to uppercase.

Parameters

sequence The sequence to be converted

int* get_iindx ( unsigned int length )

Get an index mapper array (iindx) for accessing the energy matrices, e.g. in partition function related functions.

Access of a position "(i,j)" is then accomplished by using

(i,j) ~ iindx[i]-j

This function is necessary as most of the two-dimensional energy matrices are actually one-dimensional arrays throughout the ViennaRNAPackage

Consult the implemented code to find out about the mapping formula ;)

See Also: get_indx()

Parameters

length The length of the RNA sequence

Returns: The mapper array

int* get_indx ( unsigned int length )

Get an index mapper array (indx) for accessing the energy matrices, e.g. in MFE related functions.

Access of a position "(i,j)" is then accomplished by using

(i,j) ~ indx[j]+i

This function is necessary as most of the two-dimensional energy matrices are actually one-dimensional arrays throughout the ViennaRNAPackage

Consult the implemented code to find out about the mapping formula ;)

See Also: get_iindx()

Parameters

length The length of the RNA sequence

Returns: The mapper array

void constrain_ptypes	(	const char *	constraint,
		unsigned int	length,
		char *	ptype,
		int *	BP,
		int	min_loop_size,
		unsigned int	idx_type
	)

Insert constraining pair types according to constraint structure string.

See Also: get_indx(), get_iindx()

Parameters

constraint	The structure constraint string
length	The actual length of the sequence (constraint may be shorter)
ptype	A pointer to the basepair type array
min_loop_size	The minimal loop size (usually TURN )
idx_type	Define the access type for base pair type array (0 = indx, 1 = iindx)

Variable Documentation

unsigned short xsubi[3]

Current 48 bit random number.

This variable is used by urn(). These should be set to some random number seeds before the first call to urn().

See Also: urn()

Macros

Functions

Variables

Detailed Description

Macro Definition Documentation

Function Documentation

Variable Documentation