Functions for finding pattern matches in sequence (PHI-BLAST). More...

#include <algo/blast/core/ncbi_std.h>
#include <algo/blast/core/blast_export.h>
#include <algo/blast/core/blast_def.h>
#include <algo/blast/core/blast_query_info.h>

Include dependency graph for pattern.h:

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

Go to the source code of this file.

Go to the SVN repository for this file.

Classes
struct	SDNAShortPatternItems
	Structure containing auxiliary items needed for a DNA search with a pattern that fits in a single word. More...

struct	SShortPatternItems
	Auxiliary items needed for a PHI BLAST search with a pattern that fits in a single word. More...

struct	SExtraLongPatternItems
	Auxiliary items needed for a PHI BLAST search with pattern that contains pieces longer than a word. More...

struct	SDNALongPatternItems
	Auxiliary items needed for a DNA pattern search with pattern containing multiple words. More...

struct	SLongPatternItems
	Auxiliary items needed for a PHI BLAST search with pattern containing multiple words. More...

struct	SPHIPatternSearchBlk
	Structure containing all auxiliary information needed in a pattern search. More...

Macros
#define	PHI_BUF_SIZE 100
	Default size for buffers. More...

#define	PHI_ASCII_SIZE 256
	Size of ASCII alphabet. More...

#define	PHI_BITS_PACKED_PER_WORD 30
	Number of bits packed in a word. More...

#define	PHI_MAX_WORD_SIZE 11
	Maximal word size. More...

#define	PHI_MAX_PATTERN_LENGTH (PHI_BITS_PACKED_PER_WORD * PHI_MAX_WORD_SIZE)
	Threshold pattern length. More...

#define	PHI_MAX_WORDS_IN_PATTERN 100
	Maximal number of words in pattern. More...

#define	PHI_MAX_HIT 20000
	Maximal size of an array of pattern hits. More...

Typedefs
typedef enum EPatternProgram	EPatternProgram
	Options for running the pattern search. More...

typedef enum EPatternType	EPatternType
	Type of pattern: fits in single word, several words, or is very long. More...

typedef struct SDNAShortPatternItems	SDNAShortPatternItems
	Structure containing auxiliary items needed for a DNA search with a pattern that fits in a single word. More...

typedef struct SShortPatternItems	SShortPatternItems
	Auxiliary items needed for a PHI BLAST search with a pattern that fits in a single word. More...

typedef struct SExtraLongPatternItems	SExtraLongPatternItems
	Auxiliary items needed for a PHI BLAST search with pattern that contains pieces longer than a word. More...

typedef struct SDNALongPatternItems	SDNALongPatternItems
	Auxiliary items needed for a DNA pattern search with pattern containing multiple words. More...

typedef struct SLongPatternItems	SLongPatternItems
	Auxiliary items needed for a PHI BLAST search with pattern containing multiple words. More...

typedef struct SPHIPatternSearchBlk	SPHIPatternSearchBlk
	Structure containing all auxiliary information needed in a pattern search. More...

Enumerations
enum	EPatternProgram { eSeed = 1 , ePattern , ePatSeed , ePatMatch }
	Options for running the pattern search. More...

enum	EPatternType { eOneWord = 0 , eMultiWord , eVeryLong }
	Type of pattern: fits in single word, several words, or is very long. More...

Functions
Int4	FindPatternHits (Int4 hitArray, const Uint1 seq, Int4 len, Boolean is_dna, const SPHIPatternSearchBlk *patternSearch)
	Find the places where the pattern matches seq; 3 different methods are used depending on the length of the pattern. More...

SPHIQueryInfo *	SPHIQueryInfoNew (void)
	Allocates the pattern occurrences structure. More...

SPHIQueryInfo *	SPHIQueryInfoFree (SPHIQueryInfo *pat_info)
	Frees the pattern information structure. More...

SPHIQueryInfo *	SPHIQueryInfoCopy (const SPHIQueryInfo *pat_info)
	Copies the SPHIQueryInfo structure. More...

Int4	PHIGetPatternOccurrences (const SPHIPatternSearchBlk pattern_blk, const BLAST_SequenceBlk query, const BlastSeqLoc location, Boolean is_dna, BlastQueryInfo query_info)
	Finds all pattern hits in a given query and saves them in the previously allocated SPHIQueryInfo structure. More...

Detailed Description

Functions for finding pattern matches in sequence (PHI-BLAST).

Definition in file pattern.h.

Macro Definition Documentation

◆ PHI_ASCII_SIZE

#define PHI_ASCII_SIZE 256

Size of ASCII alphabet.

Definition at line 51 of file pattern.h.

◆ PHI_BITS_PACKED_PER_WORD

#define PHI_BITS_PACKED_PER_WORD 30

Number of bits packed in a word.

Definition at line 52 of file pattern.h.

◆ PHI_BUF_SIZE

#define PHI_BUF_SIZE 100

Default size for buffers.

Definition at line 50 of file pattern.h.

◆ PHI_MAX_HIT

#define PHI_MAX_HIT 20000

Maximal size of an array of pattern hits.

Definition at line 59 of file pattern.h.

◆ PHI_MAX_PATTERN_LENGTH

#define PHI_MAX_PATTERN_LENGTH (PHI_BITS_PACKED_PER_WORD * PHI_MAX_WORD_SIZE)

Threshold pattern length.

Definition at line 55 of file pattern.h.

◆ PHI_MAX_WORD_SIZE

#define PHI_MAX_WORD_SIZE 11

Maximal word size.

Definition at line 53 of file pattern.h.

◆ PHI_MAX_WORDS_IN_PATTERN

#define PHI_MAX_WORDS_IN_PATTERN 100

Maximal number of words in pattern.

Definition at line 56 of file pattern.h.

Typedef Documentation

◆ EPatternProgram

typedef enum EPatternProgram EPatternProgram

Options for running the pattern search.

◆ EPatternType

typedef enum EPatternType EPatternType

Type of pattern: fits in single word, several words, or is very long.

◆ SDNALongPatternItems

typedef struct SDNALongPatternItems SDNALongPatternItems

Auxiliary items needed for a DNA pattern search with pattern containing multiple words.

◆ SDNAShortPatternItems

typedef struct SDNAShortPatternItems SDNAShortPatternItems

Structure containing auxiliary items needed for a DNA search with a pattern that fits in a single word.

◆ SExtraLongPatternItems

typedef struct SExtraLongPatternItems SExtraLongPatternItems

Auxiliary items needed for a PHI BLAST search with pattern that contains pieces longer than a word.

◆ SLongPatternItems

typedef struct SLongPatternItems SLongPatternItems

Auxiliary items needed for a PHI BLAST search with pattern containing multiple words.

◆ SPHIPatternSearchBlk

typedef struct SPHIPatternSearchBlk SPHIPatternSearchBlk

Structure containing all auxiliary information needed in a pattern search.

◆ SShortPatternItems

typedef struct SShortPatternItems SShortPatternItems

Auxiliary items needed for a PHI BLAST search with a pattern that fits in a single word.

Enumeration Type Documentation

◆ EPatternProgram

enum EPatternProgram

Options for running the pattern search.

Enumerator
eSeed	Use only those query occurrences that are specified in the input pattern file.
ePattern	Only find pattern occurrences in database, but do not perform alignments.
ePatSeed	Search a BLAST database using pattern occurrences as seeds.
ePatMatch	Only find pattern occurrences in query, but do not search the database.

Definition at line 62 of file pattern.h.

◆ EPatternType

enum EPatternType

Type of pattern: fits in single word, several words, or is very long.

Enumerator
eOneWord	Does pattern consist of a single word?
eMultiWord	Does pattern consist of a multiple words?
eVeryLong	Is pattern too long for a simple multi-word processing?

Definition at line 73 of file pattern.h.

Function Documentation

◆ FindPatternHits()

Int4 FindPatternHits	(	Int4 *	hitArray,
		const Uint1 *	seq,
		Int4	len,
		Boolean	is_dna,
		const SPHIPatternSearchBlk *	patternSearch
	)

Find the places where the pattern matches seq; 3 different methods are used depending on the length of the pattern.

Parameters

hitArray	Stores the results as pairs of positions in consecutive entries [out]
seq	Sequence [in]
len	Length of the sequence [in]
is_dna	Indicates whether seq is made of DNA or protein letters [in]
patternSearch	Pattern information [in]

Returns: Twice the number of hits (length of hitArray filled in)

Definition at line 468 of file pattern.c.

References eMultiWord, eOneWord, SPHIPatternSearchBlk::flagPatternLength, len, s_FindHitsLong(), s_FindHitsShortHead(), and s_FindHitsVeryLong().

Referenced by PHIBlastScanSubject(), PHIGetPatternOccurrences(), and CMultiAligner::x_FindPatternHits().

◆ PHIGetPatternOccurrences()

Int4 PHIGetPatternOccurrences	(	const SPHIPatternSearchBlk *	pattern_blk,
		const BLAST_SequenceBlk *	query,
		const BlastSeqLoc *	location,
		Boolean	is_dna,
		BlastQueryInfo *	query_info
	)

Finds all pattern hits in a given query and saves them in the previously allocated SPHIQueryInfo structure.

Parameters

pattern_blk	Structure containing pattern structure. [in]
query	Query sequence(s) [in]
location	Segments in the query sequence where to look for pattern [in]
is_dna	Is this a nucleotide sequence? [in]
query_info	Used to store pattern occurrences and get length of query (for error checking) [out]

Returns: a negative number is an unknown error, INT4_MAX indicates the pattern (illegally) covered the entire query, other non-negative numbers indicate the nubmer of pattern occurrences found.

Definition at line 553 of file pattern.c.

References ASSERT, BlastQueryInfoGetQueryLength(), calloc(), eBlastTypePhiBlastn, eBlastTypePhiBlastp, FindPatternHits(), i, INT4_MAX, SSeqRange::left, location, BlastSeqLoc::next, SPHIQueryInfo::num_patterns, BlastQueryInfo::pattern_info, query, SSeqRange::right, s_PHIBlastAddPatternHit(), sfree, and BlastSeqLoc::ssr.

Referenced by Blast_SetPHIPatternInfo().

◆ SPHIQueryInfoCopy()

SPHIQueryInfo* SPHIQueryInfoCopy ( const SPHIQueryInfo * pat_info )

Copies the SPHIQueryInfo structure.

Parameters

pat_info Structure to copy [in]

Returns: New structure.

Definition at line 507 of file pattern.c.

References BlastMemDup(), NULL, SPHIQueryInfo::num_patterns, SPHIQueryInfo::occurrences, and SPHIQueryInfo::pattern.

Referenced by BlastQueryInfoDup(), and CSearchResults::CSearchResults().

◆ SPHIQueryInfoFree()

SPHIQueryInfo* SPHIQueryInfoFree ( SPHIQueryInfo * pat_info )

Frees the pattern information structure.

Parameters

pat_info Structure to free. [in]

Returns: NULL.

Definition at line 496 of file pattern.c.

References NULL, SPHIQueryInfo::occurrences, SPHIQueryInfo::pattern, and sfree.

Referenced by BlastQueryInfoFree(), BOOST_AUTO_TEST_CASE(), and CSearchResults::~CSearchResults().

◆ SPHIQueryInfoNew()

SPHIQueryInfo* SPHIQueryInfoNew ( void )

Allocates the pattern occurrences structure.

Definition at line 478 of file pattern.c.

References SPHIQueryInfo::allocated_size, calloc(), NULL, and SPHIQueryInfo::occurrences.

Referenced by Blast_SetPHIPatternInfo(), and CPhiblastTestFixture::x_SetupPatternInfo().

Classes

Macros

Typedefs

Enumerations

Functions

Detailed Description

Macro Definition Documentation

◆ PHI_ASCII_SIZE

◆ PHI_BITS_PACKED_PER_WORD

◆ PHI_BUF_SIZE

◆ PHI_MAX_HIT

◆ PHI_MAX_PATTERN_LENGTH

◆ PHI_MAX_WORD_SIZE

◆ PHI_MAX_WORDS_IN_PATTERN

Typedef Documentation

◆ EPatternProgram

◆ EPatternType

◆ SDNALongPatternItems

◆ SDNAShortPatternItems

◆ SExtraLongPatternItems

◆ SLongPatternItems

◆ SPHIPatternSearchBlk

◆ SShortPatternItems

Enumeration Type Documentation

◆ EPatternProgram

◆ EPatternType

Function Documentation

◆ FindPatternHits()

◆ PHIGetPatternOccurrences()

◆ SPHIQueryInfoCopy()

◆ SPHIQueryInfoFree()

◆ SPHIQueryInfoNew()