Various auxiliary BLAST utility functions. More...

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

Include dependency graph for blast_util.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.

Macros
#define	IS_residue(x) (x <= 250)
	Does character encode a residue? More...

#define	NCBI2NA_MASK 0x03
	Bit mask for obtaining a single base from a byte in ncbi2na format. More...

#define	NCBI2NA_UNPACK_BASE(x, N) (((x)>>(2*(N))) & NCBI2NA_MASK)
	Macro to extract base N from a byte x (N >= 0, N < 4) More...

#define	MAX_FULL_TRANSLATION 2100
	Maximal unpacked subject sequence length for which full translation is performed up front. More...

#define	FENCE_SENTRY 201
	This sentry value is used as a 'fence' around the valid portions of partially decoded sequences. More...

Functions
void	BlastSequenceBlkClean (BLAST_SequenceBlk *seq_blk)
	Deallocate memory only for the sequence in the sequence block. More...

BLAST_SequenceBlk *	BlastSequenceBlkFree (BLAST_SequenceBlk *seq_blk)
	Deallocate memory for a sequence block. More...

void	BlastSequenceBlkCopy (BLAST_SequenceBlk *copy, BLAST_SequenceBlk src)
	Copies contents of the source sequence block without copying sequence buffers; sets all "field_allocated" booleans to FALSE, to make sure fields are not freed on the call to BlastSequenceBlkFree. More...

Int2	BlastProgram2Number (const char program, EBlastProgramType number)
	Set number for a given program type. More...

Int2	BlastNumber2Program (EBlastProgramType number, char **program)
	Return string name for program given a number. More...

Int2	BlastSetUp_SeqBlkNew (const Uint1 buffer, Int4 length, BLAST_SequenceBlk *seq_blk, Boolean buffer_allocated)
	Allocates memory for *sequence_blk and then populates it. More...

Int2	BlastSeqBlkNew (BLAST_SequenceBlk **retval)
	Allocates a new sequence block structure. More...

Int2	BlastSeqBlkSetSequence (BLAST_SequenceBlk seq_blk, const Uint1 sequence, Int4 seqlen)
	Stores the sequence in the sequence block structure. More...

Int2	BlastSeqBlkSetCompressedSequence (BLAST_SequenceBlk seq_blk, const Uint1 sequence)
	Stores the compressed nucleotide sequence in the sequence block structure for the subject sequence when BLASTing 2 sequences. More...

Int2	BlastSeqBlkSetSeqRanges (BLAST_SequenceBlk seq_blk, SSeqRange seq_ranges, Uint4 num_seq_ranges, Boolean copy_seq_ranges, ESubjectMaskingType mask_type)
	Sets the seq_range and related fields appropriately in the BLAST_SequenceBlk structure. More...

Int2	BlastCompressBlastnaSequence (BLAST_SequenceBlk *seq_blk)
	Adds a specialized representation of sequence data to a sequence block. More...

Int4	BLAST_GetTranslation (const Uint1 query_seq, const Uint1 query_seq_rev, Int4 nt_length, Int2 frame, Uint1 buffer, const Uint1 genetic_code)
	GetTranslation to get the translation of the nucl. More...

Int4	BLAST_TranslateCompressedSequence (Uint1 translation, Int4 length, const Uint1 nt_seq, Int2 frame, Uint1 *prot_seq)
	Translate a nucleotide sequence without ambiguity codes. More...

Int2	GetReverseNuclSequence (const Uint1 sequence, Int4 length, Uint1 *rev_sequence_ptr)
	Reverse a nucleotide sequence in the blastna encoding, adding sentinel bytes on both ends. More...

Int1	BLAST_ContextToFrame (EBlastProgramType prog_number, Uint4 context_number)
	This function translates the context number of a context into the frame of the sequence. More...

Int2	BLAST_PackDNA (const Uint1 buffer, Int4 length, EBlastEncoding encoding, Uint1 *packed_seq)
	Convert a sequence in ncbi4na or blastna encoding into a packed sequence in ncbi2na encoding. More...

size_t	BLAST_GetTranslatedProteinLength (size_t nucleotide_length, unsigned int context)
	Calculates the length of frame for a translated protein. More...

Int2	BLAST_CreateMixedFrameDNATranslation (BLAST_SequenceBlk query_blk, const BlastQueryInfo query_info)
	Initialize the mixed-frame sequence for out-of-frame gapped extension. More...

Int2	BLAST_GetAllTranslations (const Uint1 nucl_seq, EBlastEncoding encoding, Int4 nucl_length, const Uint1 genetic_code, Uint1 translation_buffer_ptr, Uint4 frame_offsets_ptr, Uint1 **mixed_seq_ptr)
	Translate nucleotide into 6 frames. More...

int	Blast_GetPartialTranslation (const Uint1 nucl_seq, Int4 nucl_length, Int2 frame, const Uint1 genetic_code, Uint1 *translation_buffer_ptr, Int4 protein_length, Uint1 **mixed_seq_ptr)
	Get one frame translation - needed when only parts of subject sequences are translated. More...

Int4	BLAST_FrameToContext (Int2 frame, EBlastProgramType program)
	Convert translation frame or strand into a context number suitable for indexing into the BlastQueryInfo::contexts array. More...

Int4	BSearchInt4 (Int4 n, Int4 *A, Int4 size)
	The following binary search routine assumes that array A is filled. More...

double *	BLAST_GetStandardAaProbabilities (void)
	Get the standard amino acid probabilities. More...

char *	BLAST_StrToUpper (const char *string)
	Returns a copy of the input string with all its characters turned to uppercase. More...

unsigned int	BLAST_GetNumberOfContexts (EBlastProgramType program)
	Get the number of contexts for a given program. More...

SBlastTargetTranslation *	BlastTargetTranslationFree (SBlastTargetTranslation *target_t)
	Free SBlastTargetTranslation. More...

Int2	BlastTargetTranslationNew (BLAST_SequenceBlk subject_blk, const Uint1 gen_code_string, EBlastProgramType program_number, Boolean is_ooframe, SBlastTargetTranslation **target)
	Sets up structure for target translation. More...

Detailed Description

Various auxiliary BLAST utility functions.

Definition in file blast_util.h.

Macro Definition Documentation

◆ FENCE_SENTRY

#define FENCE_SENTRY 201

This sentry value is used as a 'fence' around the valid portions of partially decoded sequences.

If an alignment finds this value in a subject sequence, the fence_hit flag should be used to request a refetch of the whole sequence, and the alignment restarted.

Note: this value is repeated in seqdbgeneral.hpp

Definition at line 364 of file blast_util.h.

◆ IS_residue

#define IS_residue ( x ) (x <= 250)

Does character encode a residue?

Definition at line 48 of file blast_util.h.

◆ MAX_FULL_TRANSLATION

#define MAX_FULL_TRANSLATION 2100

Maximal unpacked subject sequence length for which full translation is performed up front.

Definition at line 356 of file blast_util.h.

◆ NCBI2NA_MASK

#define NCBI2NA_MASK 0x03

Bit mask for obtaining a single base from a byte in ncbi2na format.

Definition at line 52 of file blast_util.h.

◆ NCBI2NA_UNPACK_BASE

#define NCBI2NA_UNPACK_BASE	(	x,
		N
	)	(((x)>>(2*(N))) & NCBI2NA_MASK)

Macro to extract base N from a byte x (N >= 0, N < 4)

Definition at line 55 of file blast_util.h.

Function Documentation

◆ BLAST_ContextToFrame()

Int1 BLAST_ContextToFrame	(	EBlastProgramType	prog_number,
		Uint4	context_number
	)

This function translates the context number of a context into the frame of the sequence.

Parameters

prog_number	Integer corresponding to the BLAST program
context_number	Context number

Returns: Sequence frame: -1,1 for nucleotides, -3,-2,-1,1,2,3 for translations, 0 for proteins and INT1_MAX in case of unsupported program

Definition at line 839 of file blast_util.c.

References abort(), Blast_QueryIsProtein(), eBlastTypeBlastn, eBlastTypeBlastx, eBlastTypeMapping, eBlastTypePhiBlastn, eBlastTypeRpsTblastn, eBlastTypeTblastx, INT1_MAX, NUM_FRAMES, and NUM_STRANDS.

Referenced by BLAST_GetAllTranslations(), Blast_GetSeqLocInfoVector(), BlastHSPStreamMerge(), BlastMaskLocDNAToProtein(), BlastMaskLocProteinToDNA(), BlastQueryInfoNew(), BlastTargetTranslationNew(), BOOST_AUTO_TEST_CASE(), OffsetArrayToContextOffsets(), s_AddMask(), s_BlastSearchEngineCore(), and x_TestGetSeqLocInfoVector().

◆ BLAST_CreateMixedFrameDNATranslation()

Int2 BLAST_CreateMixedFrameDNATranslation	(	BLAST_SequenceBlk *	query_blk,
		const BlastQueryInfo *	query_info
	)

Initialize the mixed-frame sequence for out-of-frame gapped extension.

Parameters

query_blk	Sequence block containing the concatenated frames of the query. The mixed-frame sequence is saved here. [in] [out]
query_info	Query information structure containing offsets into the* concatenated sequence. [in]

Definition at line 931 of file blast_util.c.

References buffer, CODON_LENGTH, context, BlastQueryInfo::contexts, i, BlastQueryInfo::last_context, malloc(), NULL, NULLB, offset, BLAST_SequenceBlk::oof_sequence, BLAST_SequenceBlk::oof_sequence_allocated, BlastContextInfo::query_length, BlastContextInfo::query_offset, QueryInfo_GetSeqBufLen(), BLAST_SequenceBlk::sequence, and TRUE.

Referenced by BLAST_MainSetUp(), and BOOST_AUTO_TEST_CASE().

◆ BLAST_FrameToContext()

Int4 BLAST_FrameToContext	(	Int2	frame,
		EBlastProgramType	program
	)

Convert translation frame or strand into a context number suitable for indexing into the BlastQueryInfo::contexts array.

Parameters

frame	Frame (allowed values: 1,2,3,-1,-2,-3, 0) [in]
program	Type of BLAST program [in]

Returns: context number: 0 or 1 for nucleotide query/subjects, a value between 0 and 5 (inclusive) for translated query/subjects, and 0 for protein query/subjects.

Definition at line 1211 of file blast_util.c.

References ASSERT, Blast_QueryIsNucleotide(), Blast_QueryIsTranslated(), Blast_SubjectIsNucleotide(), and Blast_SubjectIsTranslated().

Referenced by BLAST_GetGappedScore(), Blast_HSPGetTargetTranslation(), BLAST_SmithWatermanGetGappedScore(), Blast_TracebackFromHSPList(), BlastRPSWordFinder(), and s_BlastHSPListRPSUpdate().

◆ BLAST_GetAllTranslations()

Int2 BLAST_GetAllTranslations	(	const Uint1 *	nucl_seq,
		EBlastEncoding	encoding,
		Int4	nucl_length,
		const Uint1 *	genetic_code,
		Uint1 **	translation_buffer_ptr,
		Uint4 **	frame_offsets_ptr,
		Uint1 **	mixed_seq_ptr
	)

Translate nucleotide into 6 frames.

All frames are put into a translation buffer, with sentinel NULLB bytes in between. Array of offsets into the translation buffer is also returned. For out-of-frame gapping option, a mixed frame sequence is created.

Parameters

nucl_seq	The nucleotide sequence [in]
encoding	Sequence encoding: ncbi2na or ncbi4na [in]
nucl_length	Length of the nucleotide sequence [in]
genetic_code	The genetic code to be used for translations, in ncbistdaa encoding [in]
translation_buffer_ptr	Buffer to hold the frames of the translated sequence. [out]
frame_offsets_ptr	Offsets into the translation buffer for each frame. [out]
mixed_seq_ptr	Pointer to buffer for the mixed frame sequence [out]

Definition at line 1045 of file blast_util.c.

References BLAST_ContextToFrame(), BLAST_GetTranslation(), BLAST_TranslateCompressedSequence(), CODON_LENGTH, context, eBlastEncodingNcbi2na, eBlastEncodingNcbi4na, eBlastTypeBlastx, FALSE, free(), GetReverseNuclSequence(), i, malloc(), NULL, NULLB, NUM_FRAMES, offset, s_BlastGetTranslationTable(), sfree, and TRUE.

Referenced by BlastTargetTranslationNew(), BOOST_AUTO_TEST_CASE(), and s_BlastSearchEngineCore().

◆ BLAST_GetNumberOfContexts()

unsigned int BLAST_GetNumberOfContexts ( EBlastProgramType program )

Get the number of contexts for a given program.

This corresponds to the number of translation frames or strands whenever applicable.

Returns: 0 on unsupported program, non-zero otherwise

Definition at line 1373 of file blast_util.c.

References Blast_ProgramIsValid(), Blast_QueryIsNucleotide(), Blast_QueryIsTranslated(), NUM_FRAMES, and NUM_STRANDS.

Referenced by BlastHSPStreamMerge(), BlastQueryInfoGetEffSearchSpace(), BlastQueryInfoGetQueryLength(), BlastQueryInfoNew(), BlastQueryInfoSetEffSearchSpace(), BlastSetUp_GetFilteringLocations(), CBlastAncillaryData::CBlastAncillaryData(), GetNumberOfContexts(), and CBlastQueryFilteredFrames::GetNumFrames().

◆ Blast_GetPartialTranslation()

int Blast_GetPartialTranslation	(	const Uint1 *	nucl_seq,
		Int4	nucl_length,
		Int2	frame,
		const Uint1 *	genetic_code,
		Uint1 **	translation_buffer_ptr,
		Int4 *	protein_length,
		Uint1 **	mixed_seq_ptr
	)

Get one frame translation - needed when only parts of subject sequences are translated.

Parameters

nucl_seq	Pointer to start of nucleotide sequence to be translated [in]
nucl_length	Length of nucleotide sequence to be translated [in]
frame	What frame to translate into [in]
genetic_code	What genetic code to use? [in]
translation_buffer_ptr	Pointer to buffer with translated sequence [out]
protein_length	Length of the translation buffer [out]
mixed_seq_ptr	Pointer to buffer with mixed frame sequence, in case of out-of-frame gapping; buffer filled only if argument not NULL. [out]

Definition at line 1141 of file blast_util.c.

References BLAST_GetTranslation(), CODON_LENGTH, GetReverseNuclSequence(), malloc(), NULL, offset, and sfree.

Referenced by Blast_HSPGetPartialSubjectTranslation(), and s_SequenceGetTranslatedRange().

◆ BLAST_GetStandardAaProbabilities()

double* BLAST_GetStandardAaProbabilities ( void )

Get the standard amino acid probabilities.

This is basically a wrapper for BlastScoreBlkNew() and Blast_ResFreqStdComp() from blast_stat.c with a more intention-revealing name :) Caller is responsible for deallocating return value via sfree().

Returns: NULL if there is not enough memory otherwise an array of length BLASTAA_SIZE, where each index corresponds to an amino acid as specified in the NCBIstdaa encoding.

Definition at line 1323 of file blast_util.c.

References BlastScoreBlk::alphabet_code, BlastScoreBlk::alphabet_size, Blast_ResFreqFree(), Blast_ResFreqNew(), Blast_ResFreqStdComp(), BLASTAA_SEQ_CODE, BLASTAA_SIZE, i, malloc(), NULL, Blast_ResFreq::prob, BlastScoreBlk::protein_alphabet, and TRUE.

Referenced by _PSISequenceWeightsNew(), CConservationScoringMethod::CConservationScoringMethod(), ColumnResidueProfile::getBackgroundResFreq(), GetStandardProbability(), Kappa_compactSearchItemsNew(), PSICreatePssmFromFrequencyRatios(), s_GetPosBasedStartFreqRatios(), and CConservationScoringMethod::x_Init().

◆ BLAST_GetTranslatedProteinLength()

size_t BLAST_GetTranslatedProteinLength	(	size_t	nucleotide_length,
		unsigned int	context
	)

Calculates the length of frame for a translated protein.

Parameters

nucleotide_length	Length of the nucleotide sequence translated [in]
context	Index of the translated frame (values: 0 to 5, inclusive) [in]

Returns: The requested length, or 0 if the nucleotide length is 0

Definition at line 923 of file blast_util.c.

References CODON_LENGTH, and context.

Referenced by SetupQueryInfo_OMF().

◆ BLAST_GetTranslation()

Int4 BLAST_GetTranslation	(	const Uint1 *	query_seq,
		const Uint1 *	query_seq_rev,
		Int4	nt_length,
		Int2	frame,
		Uint1 *	buffer,
		const Uint1 *	genetic_code
	)

GetTranslation to get the translation of the nucl.

sequence in the appropriate frame and with the appropriate GeneticCode. The function return an allocated char*, the caller must delete this. The first and last spaces of this char* contain NULLB's.

Parameters

query_seq	Forward strand of the nucleotide sequence [in]
query_seq_rev	Reverse strand of the nucleotide sequence [in]
nt_length	Length of the nucleotide sequence [in]
frame	What frame to translate into? [in]
buffer	Preallocated buffer for the translated sequence [in][out]
genetic_code	Genetic code to use for translation, in ncbistdaa encoding [in]

Returns: Length of the translated protein sequence.

Definition at line 428 of file blast_util.c.

References ABS, CODON_LENGTH, FENCE_SENTRY, IS_residue, NULLB, and s_CodonToAA().

Referenced by BLAST_GetAllTranslations(), Blast_GetPartialTranslation(), Blast_HSPGetTargetTranslation(), BlastTargetTranslationNew(), and SetupQueries_OMF().

◆ BLAST_PackDNA()

Int2 BLAST_PackDNA	(	const Uint1 *	buffer,
		Int4	length,
		EBlastEncoding	encoding,
		Uint1 **	packed_seq
	)

Convert a sequence in ncbi4na or blastna encoding into a packed sequence in ncbi2na encoding.

Needed for 2 sequences BLASTn comparison.

Parameters

buffer	original sequence data (one base per byte) [in]
length	length of the sequence data above [in]
encoding	source encoding of the sequence data above [in]
packed_seq	output buffer containing compressed sequence. Its length will be (length/COMPRESSION_RATIO + 1), caller is responsible for deallocating it [out]

Returns: 0 in case of success, -1 in case of memory allocation failure

Definition at line 870 of file blast_util.c.

References abort(), buffer, COMPRESSION_RATIO, eBlastEncodingNucleotide, malloc(), NCBI2NA_MASK, and NCBI4NA_TO_BLASTNA.

◆ BLAST_StrToUpper()

char* BLAST_StrToUpper ( const char * string )

Returns a copy of the input string with all its characters turned to uppercase.

Useful for saving score matrix names. Caller is responsible for deallocating return value.

Parameters

string string to copy [in]

Returns: newly allocated string in upper case or NULL if string is NULL or out of memory

Definition at line 1352 of file blast_util.c.

References NULL, NULLB, strdup, and toupper().

Referenced by Blast_ScoreBlkMatrixInit(), and BLAST_ValidateOptions().

◆ BLAST_TranslateCompressedSequence()

Int4 BLAST_TranslateCompressedSequence	(	Uint1 *	translation,
		Int4	length,
		const Uint1 *	nt_seq,
		Int2	frame,
		Uint1 *	prot_seq
	)

Translate a nucleotide sequence without ambiguity codes.

This is used for the first-pass translation of the database. The genetic code to be used is determined by the translation_table This function translates a packed (ncbi2na) nucl. alphabet. It views a basepair as being in one of four sets of 2-bits: |0|1|2|3||0|1|2|3||0|1|2|3||...

1st byte | 2 byte | 3rd byte...

A codon that starts at the beginning of the above sequence starts in state "0" and includes basepairs 0, 1, and 2. The next codon, in the same frame, after that starts in state "3" and includes 3, 0, and 1.

Optimization: changed the single main loop to

advance to state 0,
optimized inner loop does two (3 byte->4 codon) translation per iteration (loads are moved earlier so they can be done in advance.)
do remainder

Parameters

translation	The translation table [in]
length	Length of the nucleotide sequence [in]
nt_seq	The original nucleotide sequence [in]
frame	What frame to translate to? [in]
prot_seq	Preallocated buffer for the (translated) protein sequence, with NULLB sentinels on either end. [out]

Definition at line 508 of file blast_util.c.

References ABS, CODON_LENGTH, NULL, and NULLB.

Referenced by BLAST_GetAllTranslations().

◆ BlastCompressBlastnaSequence()

Int2 BlastCompressBlastnaSequence ( BLAST_SequenceBlk * seq_blk )

Adds a specialized representation of sequence data to a sequence block.

In the specialized representation, the byte at offset i packs together nucleotide bases i to i+3

Parameters

seq_blk structure containing sequence data. Data is assumed to be in blastna format [in][out]

Definition at line 459 of file blast_util.c.

References BLAST_SequenceBlk::compressed_nuc_seq, BLAST_SequenceBlk::compressed_nuc_seq_start, i, len, BLAST_SequenceBlk::length, malloc(), MIN, and BLAST_SequenceBlk::sequence.

Referenced by s_BlastSmallNaLookupFinalize().

◆ BlastNumber2Program()

Int2 BlastNumber2Program	(	EBlastProgramType	number,
		char **	program
	)

Return string name for program given a number.

Return is zero on success.

Parameters

number	Enumerated value of program [in]
program	string name of program (memory should be deallocated by called) [out]

Definition at line 312 of file blast_util.c.

References eBlastTypeBlastn, eBlastTypeBlastp, eBlastTypeBlastx, eBlastTypeMapping, eBlastTypePhiBlastn, eBlastTypePhiBlastp, eBlastTypePsiBlast, eBlastTypePsiTblastn, eBlastTypeRpsBlast, eBlastTypeRpsTblastn, eBlastTypeTblastn, eBlastTypeTblastx, NULL, number, and strdup.

Referenced by Blast_ProgramNameFromType(), CRedoAlignmentTestFixture::runRedoAlignmentCoreUnitTest(), and s_ImportSearchStrategy().

◆ BlastProgram2Number()

Int2 BlastProgram2Number	(	const char *	program,
		EBlastProgramType *	number
	)

Set number for a given program type.

Return is zero on success.

Parameters

program	string name of program [in]
number	Enumerated value of program [out]

Definition at line 278 of file blast_util.c.

References eBlastTypeBlastn, eBlastTypeBlastp, eBlastTypeBlastx, eBlastTypeMapping, eBlastTypePhiBlastn, eBlastTypePhiBlastp, eBlastTypePsiBlast, eBlastTypePsiTblastn, eBlastTypeRpsBlast, eBlastTypeRpsTblastn, eBlastTypeTblastn, eBlastTypeTblastx, eBlastTypeUndefined, NULL, number, and strcasecmp.

Referenced by NetworkProgram2BlastProgramType().

◆ BlastSeqBlkNew()

Int2 BlastSeqBlkNew ( BLAST_SequenceBlk ** retval )

Allocates a new sequence block structure.

Parameters

retval Pointer to where the sequence block structure will be allocated [out]

Definition at line 133 of file blast_util.c.

References calloc().

Referenced by AascanTestFixture::AascanTestFixture(), BlastSetUp_SeqBlkNew(), BOOST_AUTO_TEST_CASE(), CompressedAascanTestFixture::CompressedAascanTestFixture(), CompressedAalookupTestFixture::GetSeqBlk(), AalookupTestFixture::GetSeqBlk(), InitializeBlastScoreBlk(), s_SetupSequencesForGappedReevaluateTest(), s_SetupSequencesForUngappedReevaluateNucl(), s_SetupSequencesForUngappedReevaluateTransl(), SetupQueries_OMF(), NtlookupTestFixture::SetUpQuery(), TestFixture::SetUpQuery(), NuclWordFinderTextFixture::setupSequences(), TestFixture::SetUpSubject(), SetupSubjects_OMF(), CPssmEngine::x_InitializeScoreBlock(), CRandomlyFailMockBlastSeqSrc::x_PopulateBLAST_SequenceBlk(), and CPhiblastTestFixture::x_SetupSequenceBlk().

◆ BlastSeqBlkSetCompressedSequence()

Int2 BlastSeqBlkSetCompressedSequence	(	BLAST_SequenceBlk *	seq_blk,
		const Uint1 *	sequence
	)

Stores the compressed nucleotide sequence in the sequence block structure for the subject sequence when BLASTing 2 sequences.

This sequence should be encoded in eBlastEncodingNcbi2na and NOT have sentinel bytes (as this encoding doesn't allow them).

Parameters

seq_blk	The sequence block structure to modify [in/out]
sequence	Actual sequence buffer. [in]

Definition at line 167 of file blast_util.c.

References NULL, BLAST_SequenceBlk::oof_sequence, BLAST_SequenceBlk::sequence, BLAST_SequenceBlk::sequence_allocated, and TRUE.

Referenced by BOOST_AUTO_TEST_CASE(), NuclWordFinderTextFixture::setupSequences(), TestFixture::SetUpSubject(), and SetupSubjects_OMF().

◆ BlastSeqBlkSetSeqRanges()

Int2 BlastSeqBlkSetSeqRanges	(	BLAST_SequenceBlk *	seq_blk,
		SSeqRange *	seq_ranges,
		Uint4	num_seq_ranges,
		Boolean	copy_seq_ranges,
		ESubjectMaskingType	mask_type
	)

Sets the seq_range and related fields appropriately in the BLAST_SequenceBlk structure.

Parameters

seq_blk	The sequence block structure to modify [in/out]
seq_ranges	sequence ranges to copy [in]
num_seq_ranges	number of elements in array above [in]
copy_seq_ranges	set to TRUE if seq_ranges should be copied to the
mask_type	either kSoftDBMask or kHardDBMask [in] BLAST_SequenceBlk and assume its ownership, set to FALSE if the pointer should be copied and the ownership of the seq_ranges remains in the caller's possession.

Note: this function will free the memory previously allocated to BLAST_SequenceBlk::seq_ranges (if applicable) and overwrite it with the seq_ranges argument. This might invalidate BLAST_SequenceBlk structures that were copied off of this one.

Definition at line 182 of file blast_util.c.

References ASSERT, calloc(), FALSE, BLAST_SequenceBlk::length, BLAST_SequenceBlk::mask_type, BLAST_SequenceBlk::num_seq_ranges, s_BlastSequenceBlkFreeSeqRanges(), BLAST_SequenceBlk::seq_ranges, BLAST_SequenceBlk::seq_ranges_allocated, tmp, and TRUE.

Referenced by AascanTestFixture::AascanTestFixture(), BOOST_AUTO_TEST_CASE(), CompressedAascanTestFixture::CompressedAascanTestFixture(), s_SeqDbGetSequence(), SetupSubjects_OMF(), and TestFixture::SkipMaskedRangesCore().

◆ BlastSeqBlkSetSequence()

Int2 BlastSeqBlkSetSequence	(	BLAST_SequenceBlk *	seq_blk,
		const Uint1 *	sequence,
		Int4	seqlen
	)

Stores the sequence in the sequence block structure.

Parameters

seq_blk	The sequence block structure to modify [in/out]
sequence	Actual sequence buffer. The first byte must be a sentinel byte [in]
seqlen	Length of the sequence buffer above [in]

Definition at line 147 of file blast_util.c.

References FALSE, BLAST_SequenceBlk::length, BLAST_SequenceBlk::nomask_allocated, NULL, BLAST_SequenceBlk::oof_sequence, BLAST_SequenceBlk::sequence, BLAST_SequenceBlk::sequence_nomask, BLAST_SequenceBlk::sequence_start, BLAST_SequenceBlk::sequence_start_allocated, BLAST_SequenceBlk::sequence_start_nomask, and TRUE.

Referenced by AascanTestFixture::AascanTestFixture(), BOOST_AUTO_TEST_CASE(), CompressedAascanTestFixture::CompressedAascanTestFixture(), CompressedAalookupTestFixture::GetSeqBlk(), AalookupTestFixture::GetSeqBlk(), InitializeBlastScoreBlk(), s_SetupSequencesForGappedReevaluateTest(), s_SetupSequencesForUngappedReevaluateNucl(), s_SetupSequencesForUngappedReevaluateTransl(), SetupQueries_OMF(), NtlookupTestFixture::SetUpQuery(), TestFixture::SetUpQuery(), NuclWordFinderTextFixture::setupSequences(), SetupSubjects_OMF(), CPssmEngine::x_InitializeScoreBlock(), CRandomlyFailMockBlastSeqSrc::x_PopulateBLAST_SequenceBlk(), and CPhiblastTestFixture::x_SetupSequenceBlk().

◆ BlastSequenceBlkClean()

void BlastSequenceBlkClean ( BLAST_SequenceBlk * seq_blk )

Deallocate memory only for the sequence in the sequence block.

Definition at line 220 of file blast_util.c.

References FALSE, BLAST_SequenceBlk::nomask_allocated, BLAST_SequenceBlk::oof_sequence, BLAST_SequenceBlk::oof_sequence_allocated, s_BlastSequenceBlkFreeSeqRanges(), BLAST_SequenceBlk::sequence, BLAST_SequenceBlk::sequence_allocated, BLAST_SequenceBlk::sequence_start, BLAST_SequenceBlk::sequence_start_allocated, BLAST_SequenceBlk::sequence_start_nomask, and sfree.

Referenced by BlastSequenceBlkFree(), BOOST_AUTO_TEST_CASE(), s_SeqDbGetSequence(), and s_VDBSRC_GetSequence().

◆ BlastSequenceBlkCopy()

void BlastSequenceBlkCopy	(	BLAST_SequenceBlk **	copy,
		BLAST_SequenceBlk *	src
	)

Copies contents of the source sequence block without copying sequence buffers; sets all "field_allocated" booleans to FALSE, to make sure fields are not freed on the call to BlastSequenceBlkFree.

Parameters

copy	New sequence block [out]
src	Input sequence block [in]

Definition at line 259 of file blast_util.c.

References ASSERT, BlastMemDup(), copy(), and FALSE.

Referenced by s_MultiSeqGetSequence(), and s_QueryFactoryGetSequence().

◆ BlastSequenceBlkFree()

BLAST_SequenceBlk* BlastSequenceBlkFree ( BLAST_SequenceBlk * seq_blk )

Deallocate memory for a sequence block.

Definition at line 245 of file blast_util.c.

References BlastMaskLocFree(), BlastSequenceBlkClean(), BLAST_SequenceBlk::compressed_nuc_seq_start, BLAST_SequenceBlk::lcase_mask, BLAST_SequenceBlk::lcase_mask_allocated, NULL, and sfree.

Referenced by BLAST_ComputeTraceback_MT(), BLAST_PreliminarySearchEngine(), BOOST_AUTO_TEST_CASE(), NaHashLookupThreadDataFree(), CRandomlyFailMockBlastSeqSrc::ReleaseSequence(), CSeedTop::Run(), s_checkDbSeqSrcFunctions(), s_ComputeNumIdentities(), s_MatchingSequenceRelease(), s_RPSComputeTraceback(), s_RPSPreliminarySearchEngine(), s_ScanSubjectForWordCounts(), SetupSubjects_OMF(), TestFixture::TearDownQuery(), TestFixture::TearDownSubject(), AalookupTestFixture::~AalookupTestFixture(), AascanTestFixture::~AascanTestFixture(), CMultiSeqInfo::~CMultiSeqInfo(), CompressedAalookupTestFixture::~CompressedAalookupTestFixture(), CompressedAascanTestFixture::~CompressedAascanTestFixture(), CQueryFactoryInfo::~CQueryFactoryInfo(), NtlookupTestFixture::~NtlookupTestFixture(), and NuclWordFinderTextFixture::~NuclWordFinderTextFixture().

◆ BlastSetUp_SeqBlkNew()

Int2 BlastSetUp_SeqBlkNew	(	const Uint1 *	buffer,
		Int4	length,
		BLAST_SequenceBlk **	seq_blk,
		Boolean	buffer_allocated
	)

Allocates memory for *sequence_blk and then populates it.

Parameters

buffer	start of sequence [in]
length	query sequence length [in]
seq_blk	SequenceBlk to be allocated and filled in [out]
buffer_allocated	Is the buffer allocated? If yes, 'sequence_start' is the start of the sequence, otherwise it is 'sequence'. [in]

Deprecated:: Use BlastSeqBlkNew and BlastSeqBlkSet* functions instead

Definition at line 101 of file blast_util.c.

References ASSERT, BlastSeqBlkNew(), buffer, FALSE, NULL, and TRUE.

Referenced by NtlookupTestFixture::debruijnInit(), AalookupTestFixture::GetSeqBlk(), s_SeqDbGetSequence(), and s_VDBSRC_GetSequence().

◆ BlastTargetTranslationFree()

SBlastTargetTranslation* BlastTargetTranslationFree ( SBlastTargetTranslation * target_t )

Free SBlastTargetTranslation.

Parameters

target_t object to be freed [in]

Definition at line 1248 of file blast_util.c.

References NULL, SBlastTargetTranslation::num_frames, SBlastTargetTranslation::range, sfree, and SBlastTargetTranslation::translations.

Referenced by Blast_HSPListReevaluateUngapped(), Blast_TracebackFromHSPList(), BOOST_AUTO_TEST_CASE(), and s_ComputeNumIdentities().

◆ BlastTargetTranslationNew()

Int2 BlastTargetTranslationNew	(	BLAST_SequenceBlk *	subject_blk,
		const Uint1 *	gen_code_string,
		EBlastProgramType	program_number,
		Boolean	is_ooframe,
		SBlastTargetTranslation **	target
	)

Sets up structure for target translation.

Parameters

subject_blk	Target sequence information [in]
gen_code_string	Genetic code translation information [in]
program_number	BLAST program [in]
is_ooframe	Out-of-frame translation if true [in]
target	Structure being set up. [out]

Definition at line 1268 of file blast_util.c.

References BLAST_ContextToFrame(), BLAST_GetAllTranslations(), BLAST_GetTranslation(), calloc(), context, eBlastEncodingNcbi4na, eBlastTypeBlastx, SBlastTargetTranslation::gen_code_string, GetReverseNuclSequence(), BLAST_SequenceBlk::length, malloc(), NULL, NUM_FRAMES, SBlastTargetTranslation::num_frames, BLAST_SequenceBlk::oof_sequence, BLAST_SequenceBlk::oof_sequence_allocated, SBlastTargetTranslation::partial, SBlastTargetTranslation::program_number, SBlastTargetTranslation::range, BLAST_SequenceBlk::sequence_start, sfree, SBlastTargetTranslation::subject_blk, SBlastTargetTranslation::translations, and TRUE.

Referenced by Blast_HSPListReevaluateUngapped(), Blast_TracebackFromHSPList(), BOOST_AUTO_TEST_CASE(), and s_ComputeNumIdentities().

◆ BSearchInt4()

Int4 BSearchInt4	(	Int4	n,
		Int4 *	A,
		Int4	size
	)

The following binary search routine assumes that array A is filled.

Definition at line 1231 of file blast_util.c.

References A, b, n, and ncbi::grid::netcache::search::fields::size.

◆ GetReverseNuclSequence()

Int2 GetReverseNuclSequence	(	const Uint1 *	sequence,
		Int4	length,
		Uint1 **	rev_sequence_ptr
	)

Reverse a nucleotide sequence in the blastna encoding, adding sentinel bytes on both ends.

Parameters

sequence	Forward strand of the sequence [in]
length	Length of the sequence plus 1 for the sentinel byte [in]
rev_sequence_ptr	Reverse strand of the sequence [out]

Definition at line 807 of file blast_util.c.

References FENCE_SENTRY, malloc(), and NULLB.

Referenced by BLAST_GetAllTranslations(), Blast_GetPartialTranslation(), Blast_HSPGetTargetTranslation(), and BlastTargetTranslationNew().

Macros

Functions

Detailed Description

Macro Definition Documentation

◆ FENCE_SENTRY

◆ IS_residue

◆ MAX_FULL_TRANSLATION

◆ NCBI2NA_MASK

◆ NCBI2NA_UNPACK_BASE

Function Documentation

◆ BLAST_ContextToFrame()

◆ BLAST_CreateMixedFrameDNATranslation()

◆ BLAST_FrameToContext()

◆ BLAST_GetAllTranslations()

◆ BLAST_GetNumberOfContexts()

◆ Blast_GetPartialTranslation()

◆ BLAST_GetStandardAaProbabilities()

◆ BLAST_GetTranslatedProteinLength()

◆ BLAST_GetTranslation()

◆ BLAST_PackDNA()

◆ BLAST_StrToUpper()

◆ BLAST_TranslateCompressedSequence()

◆ BlastCompressBlastnaSequence()

◆ BlastNumber2Program()

◆ BlastProgram2Number()

◆ BlastSeqBlkNew()

◆ BlastSeqBlkSetCompressedSequence()

◆ BlastSeqBlkSetSeqRanges()

◆ BlastSeqBlkSetSequence()

◆ BlastSequenceBlkClean()

◆ BlastSequenceBlkCopy()

◆ BlastSequenceBlkFree()

◆ BlastSetUp_SeqBlkNew()

◆ BlastTargetTranslationFree()

◆ BlastTargetTranslationNew()

◆ BSearchInt4()

◆ GetReverseNuclSequence()