Detailed Contents:
Definition in file blast_stat.c.
#include <algo/blast/core/blast_stat.h>
#include <algo/blast/core/ncbi_math.h>
#include "blast_psi_priv.h"
Include dependency graph for blast_stat.c:
Go to the source code of this file.
Classes | |
struct | MatrixInfo |
Used to temporarily store matrix values for retrieval. More... | |
struct | BLAST_LetterProb |
Records probability of letter appearing in sequence. More... | |
struct | Blast_ResComp |
Intermediate structure to store the composition of a sequence. More... | |
struct | SRombergCbackArgs |
Internal data structure used by Romberg integration callbacks. More... | |
Defines | |
#define | BLAST_SCORE_RANGE_MAX (BLAST_SCORE_MAX - BLAST_SCORE_MIN) |
maximum allowed range of BLAST scores. | |
#define | BLAST_KARLIN_K_SUMLIMIT_DEFAULT 0.0001 |
K_SUMLIMIT_DEFAULT == sumlimit used in BlastKarlinLHtoK(). | |
#define | BLAST_KARLIN_LAMBDA_ACCURACY_DEFAULT (1.e-5) |
LAMBDA_ACCURACY_DEFAULT == accuracy to which Lambda should be calc'd. | |
#define | BLAST_KARLIN_LAMBDA_ITER_DEFAULT 17 |
LAMBDA_ITER_DEFAULT == no. | |
#define | BLAST_KARLIN_LAMBDA0_DEFAULT 0.5 |
Initial guess for the value of Lambda in BlastKarlinLambdaNR. | |
#define | BLAST_KARLIN_K_ITER_MAX 100 |
upper limit on iterations for BlastKarlinLHtoK | |
#define | BLAST_NUM_STAT_VALUES 8 |
Number of statistical parameters in each row of the precomputed tables. | |
#define | BLOSUM45_VALUES_MAX 14 |
Number of different combinations supported for BLOSUM45. | |
#define | BLOSUM50_VALUES_MAX 16 |
Number of different combinations supported for BLOSUM50. | |
#define | BLOSUM62_VALUES_MAX 12 |
Number of different combinations supported for BLOSUM62. | |
#define | BLOSUM80_VALUES_MAX 10 |
Number of different combinations supported for BLOSUM80. | |
#define | BLOSUM90_VALUES_MAX 8 |
Number of different combinations supported for BLOSUM90. | |
#define | PAM250_VALUES_MAX 16 |
Number of different combinations supported for PAM250. | |
#define | PAM30_VALUES_MAX 7 |
Number of different combinations supported for PAM30. | |
#define | PAM70_VALUES_MAX 7 |
Number of different combinations supported for PAM70. | |
#define | STD_AMINO_ACID_FREQS Robinson_prob |
points to the standard amino acid frequencies to use. | |
Typedefs | |
typedef double | array_of_8 [8] |
Holds values (gap-opening, extension, etc. | |
typedef Int1 | CompressedReverseLookup [BLASTAA_SIZE+1][BLASTAA_SIZE+1] |
2-D array mapping compressed letters to sets of ordinary protein letters | |
Functions | |
static SBlastScoreMatrix * | SBlastScoreMatrixFree (SBlastScoreMatrix *matrix) |
Deallocates SBlastScoreMatrix structure. | |
static SBlastScoreMatrix * | SBlastScoreMatrixNew (size_t ncols, size_t nrows) |
Allocates a new SBlastScoreMatrix structure of the specified dimensions. | |
SPsiBlastScoreMatrix * | SPsiBlastScoreMatrixFree (SPsiBlastScoreMatrix *matrix) |
Deallocates a SPsiBlastScoreMatrix structure. | |
SPsiBlastScoreMatrix * | SPsiBlastScoreMatrixNew (size_t ncols) |
Allocates a new SPsiBlastScoreMatrix structure of dimensions ncols by BLASTAA_SIZE. | |
BlastScoreBlk * | BlastScoreBlkNew (Uint1 alphabet, Int4 number_of_contexts) |
Allocates and initializes BlastScoreBlk. | |
Blast_ScoreFreq * | Blast_ScoreFreqFree (Blast_ScoreFreq *sfp) |
Deallocates the score frequencies structure. | |
Blast_KarlinBlk * | Blast_KarlinBlkFree (Blast_KarlinBlk *kbp) |
Deallocates the KarlinBlk. | |
BlastScoreBlk * | BlastScoreBlkFree (BlastScoreBlk *sbp) |
Deallocates BlastScoreBlk as well as all associated structures. | |
Int2 | BLAST_ScoreSetAmbigRes (BlastScoreBlk *sbp, char ambiguous_res) |
Set the ambiguous residue (e.g, 'N', 'X') in the BlastScoreBlk*. | |
Int2 | BlastScoreBlkNuclMatrixCreate (BlastScoreBlk *sbp) |
Fill in the matrix for blastn using the penaly and rewards The query sequence alphabet is blastna, the subject sequence is ncbi2na. | |
static Int2 | BlastScoreBlkProteinMatrixRead (BlastScoreBlk *sbp, FILE *fp) |
Read in the matrix from the FILE *fp. | |
static Int2 | BlastScoreBlkMaxScoreSet (BlastScoreBlk *sbp) |
Sets maximum and minimum scores on the BlastScoreBlk for a given matrix. | |
static Int2 | BlastScoreBlkProteinMatrixLoad (BlastScoreBlk *sbp) |
Sets sbp->matrix->data field using sbp->name field using the matrices in the toolkit (util/tables/raw_scoremat.h). | |
Int2 | Blast_ScoreBlkMatrixFill (BlastScoreBlk *sbp, GET_MATRIX_PATH get_path) |
This function fills in the BlastScoreBlk structure. | |
Blast_ResFreq * | Blast_ResFreqFree (Blast_ResFreq *rfp) |
Deallocates Blast_ResFreq and prob0 element. | |
Blast_ResFreq * | Blast_ResFreqNew (const BlastScoreBlk *sbp) |
Allocates a new Blast_ResFreq structure and fills in the prob element based upon the contents of sbp. | |
static Int2 | Blast_ResFreqNormalize (const BlastScoreBlk *sbp, Blast_ResFreq *rfp, double norm) |
Normalizes all the residue frequencies and then normalizes them to "norm". | |
Int2 | Blast_GetStdAlphabet (Uint1 alphabet_code, Uint1 *residues, Uint4 residues_size) |
Fills a buffer with the 'standard' alphabet (given by STD_AMINO_ACID_FREQS[index].ch). | |
Int2 | Blast_ResFreqStdComp (const BlastScoreBlk *sbp, Blast_ResFreq *rfp) |
Calculates residues frequencies given a standard distribution. | |
static Blast_ResComp * | BlastResCompDestruct (Blast_ResComp *rcp) |
Deallocates Blast_ResComp structure and associated arrays. | |
static Blast_ResComp * | BlastResCompNew (const BlastScoreBlk *sbp) |
Allocated the Blast_ResComp* for a given alphabet. | |
static Int2 | BlastResCompStr (const BlastScoreBlk *sbp, Blast_ResComp *rcp, char *str, Int4 length) |
Store the composition of a (query) string. | |
static Int2 | Blast_ResFreqClr (const BlastScoreBlk *sbp, Blast_ResFreq *rfp) |
Sets prob elements of Blast_ResFreq to zero. | |
static Int2 | Blast_ResFreqResComp (const BlastScoreBlk *sbp, Blast_ResFreq *rfp, const Blast_ResComp *rcp) |
Calculate the residue frequencies associated with the provided ResComp This function takes into account the composition of a given sequence (expressed through rcp) rather than just doing it for a standard distribution. | |
static Int2 | Blast_ResFreqString (const BlastScoreBlk *sbp, Blast_ResFreq *rfp, char *string, Int4 length) |
Fills in residue frequences for a given sequence. | |
static Int2 | BlastScoreChk (Int4 lo, Int4 hi) |
Check that the lo and hi score are within the allowed ranges. | |
Blast_ScoreFreq * | Blast_ScoreFreqNew (Int4 score_min, Int4 score_max) |
Creates a new structure to keep track of score frequencies for a scoring system. | |
static Int2 | BlastScoreFreqCalc (const BlastScoreBlk *sbp, Blast_ScoreFreq *sfp, Blast_ResFreq *rfp1, Blast_ResFreq *rfp2) |
Calculates the score frequencies. | |
static double | BlastKarlinLHtoK (Blast_ScoreFreq *sfp, double lambda, double H) |
The following procedure computes K. | |
static double | NlmKarlinLambdaNR (double *probs, Int4 d, Int4 low, Int4 high, double lambda0, double tolx, Int4 itmax, Int4 maxNewton, Int4 *itn) |
Find positive solution to. | |
double | Blast_KarlinLambdaNR (Blast_ScoreFreq *sfp, double initialLambdaGuess) |
Calculates the parameter Lambda given an initial guess for its value. | |
static double | BlastKarlinLtoH (Blast_ScoreFreq *sfp, double lambda) |
Calculate H, the relative entropy of the p's and q's. | |
Int2 | Blast_KarlinBlkUngappedCalc (Blast_KarlinBlk *kbp, Blast_ScoreFreq *sfp) |
Computes the parameters lambda, H K for use in calculating the statistical significance of high-scoring segments or subalignments (see comment on blast_stat.c for more details). | |
Int2 | Blast_ScoreBlkKbpUngappedCalc (EBlastProgramType program, BlastScoreBlk *sbp, Uint1 *query, const BlastQueryInfo *query_info, Blast_Message **blast_message) |
Calculate and fill the ungapped Karlin-Altschul parameters in the BlastScoreBlk structure (fields kbp_std, kbp_psi, and kbp of that structure). | |
Int2 | Blast_ScoreBlkKbpIdealCalc (BlastScoreBlk *sbp) |
Calculates the Karlin-Altschul parameters assuming standard residue compositions for the query and subject sequences. | |
Blast_KarlinBlk * | Blast_KarlinBlkNew (void) |
Callocs a Blast_KarlinBlk. | |
Int2 | Blast_KarlinBlkCopy (Blast_KarlinBlk *kbp_to, Blast_KarlinBlk *kbp_from) |
Copies contents of one Karlin block to another. | |
static MatrixInfo * | MatrixInfoDestruct (MatrixInfo *matrix_info) |
Deallocates MatrixInfo as well as name string. | |
static MatrixInfo * | MatrixInfoNew (const char *name, array_of_8 *values, Int4 *prefs, Int4 max_number) |
Allocates New MatrixInfo*. | |
static ListNode * | BlastMatrixValuesDestruct (ListNode *vnp) |
Free linked list of MatrixValues and all associated data. | |
static ListNode * | BlastLoadMatrixValues (void) |
Loads all the matrix values, returns a ListNode* chain that contains MatrixInfo*'s. | |
static Int2 | Blast_GetMatrixValues (const char *matrix, Int4 **open, Int4 **extension, double **lambda, double **K, double **H, double **alpha, double **beta, Int4 **pref_flags) |
Obtains arrays of the allowed opening and extension penalties for gapped BLAST for the given matrix. | |
void | BLAST_GetAlphaBeta (const char *matrixName, double *alpha, double *beta, Boolean gapped, Int4 gap_open, Int4 gap_extend, const Blast_KarlinBlk *kbp_ungapped) |
Extract the alpha and beta settings for this matrixName, and these gap open and gap extension costs. | |
static Int2 | s_SplitArrayOf8 (const array_of_8 *input, const array_of_8 **normal, const array_of_8 **non_affine, Boolean *split) |
Splits an ArrayOf8 into two arrays of supported gap costs. | |
static Int2 | s_AdjustGapParametersByGcd (array_of_8 *normal, array_of_8 *linear, int size, Int4 *gap_existence_max, Int4 *gap_extend_max, int divisor) |
Adjust Lambda and H if reward and penalty have a non-1 gcd. | |
static Int2 | s_GetNuclValuesArray (Int4 reward, Int4 penalty, Int4 *array_size, array_of_8 **normal, array_of_8 **non_affine, Int4 *gap_open_max, Int4 *gap_extend_max, Boolean *round_down, Blast_Message **error_return) |
Returns the array of values corresponding to the given match/mismatch scores, the number of supported gap cost combinations and thresholds for the gap costs, beyond which the ungapped statistics can be applied. | |
Int2 | BLAST_GetProteinGapExistenceExtendParams (const char *matrixName, Int4 *gap_existence, Int4 *gap_extension) |
Extract the recommended gap existence and extension values. | |
Int2 | BLAST_GetNucleotideGapExistenceExtendParams (Int4 reward, Int4 penalty, Int4 *gap_existence, Int4 *gap_extension) |
Extract the recommended gap existence and extension values. | |
Boolean | BLAST_CheckRewardPenaltyScores (Int4 reward, Int4 penalty) |
Check the validity of the reward and penalty scores. | |
static Int2 | BlastKarlinReportAllowedValues (const char *matrix_name, Blast_Message **error_return) |
Fills in error_return with strings describing the allowed values. | |
Int2 | Blast_KarlinBlkGappedCalc (Blast_KarlinBlk *kbp, Int4 gap_open, Int4 gap_extend, const char *matrix_name, Blast_Message **error_return) |
Fills in lambda, H, and K values, as calculated by Stephen Altschul in Methods in Enzy. | |
Int2 | Blast_KarlinBlkGappedLoadFromTables (Blast_KarlinBlk *kbp, Int4 gap_open, Int4 gap_extend, const char *matrix_name) |
Attempts to fill KarlinBlk for given gap opening, extensions etc. | |
char * | BLAST_PrintMatrixMessage (const char *matrix_name) |
Prints a messages about the allowed matrices, BlastKarlinBlkGappedFill should return 1 before this is called. | |
char * | BLAST_PrintAllowedValues (const char *matrix_name, Int4 gap_open, Int4 gap_extend) |
Prints a messages about the allowed open etc values for the given matrix, BlastKarlinBlkGappedFill should return 2 before this is called. | |
Int2 | Blast_KarlinBlkNuclGappedCalc (Blast_KarlinBlk *kbp, Int4 gap_open, Int4 gap_extend, Int4 reward, Int4 penalty, Blast_KarlinBlk *kbp_ungap, Boolean *round_down, Blast_Message **error_return) |
Retrieves Karlin-Altschul parameters from precomputed tables, given the substitution and gap scores. | |
static double | s_GetUngappedBeta (Int4 reward, Int4 penalty) |
Returns the beta statistical parameter value, given the nucleotide substitution scores. | |
Int2 | Blast_GetNuclAlphaBeta (Int4 reward, Int4 penalty, Int4 gap_open, Int4 gap_extend, Blast_KarlinBlk *kbp, Boolean gapped_calculation, double *alpha, double *beta) |
Extract the alpha and beta settings for these substitution and gap scores. | |
static Int4 | BlastKarlinEtoS_simple (double E, const Blast_KarlinBlk *kbp, Int8 searchsp) |
Calculates score from expect value and search space. | |
double | BLAST_GapDecayDivisor (double decayrate, unsigned nsegs) |
Compute a divisor used to weight the evalue of a collection of "nsegs" distinct alignments. | |
Int2 | BLAST_Cutoffs (Int4 *S, double *E, Blast_KarlinBlk *kbp, Int8 searchsp, Boolean dodecay, double gap_decay_rate) |
Calculate the cutoff score from the expected number of HSPs or vice versa. | |
double | BLAST_KarlinStoE_simple (Int4 S, Blast_KarlinBlk *kbp, Int8 searchsp) |
Calculates the Expect value based upon the search space and some Karlin-Altschul parameters. | |
double | BLAST_KarlinPtoE (double p) |
Convert a P-value to an E-value. | |
double | BLAST_KarlinEtoP (double x) |
Convert an E-value to a P-value. | |
static double | s_OuterIntegralCback (double x, void *vp) |
Callback for the Romberg integration function. | |
static double | s_InnerIntegralCback (double s, void *vp) |
Callback for the Romberg integration function. | |
static double | s_BlastSumPCalc (int r, double s) |
Evaluate the following double integral, where r = number of segments. | |
static double | s_BlastSumP (Int4 r, double s) |
Estimate the Sum P-value by calculation or interpolation, as appropriate. | |
double | BLAST_SmallGapSumE (Int4 starting_points, Int2 num, double xsum, Int4 query_length, Int4 subject_length, Int8 searchsp_eff, double weight_divisor) |
Calculates the e-value for alignments with "small" gaps (typically under fifty residues/basepairs) following ideas of Stephen Altschul's. | |
double | BLAST_UnevenGapSumE (Int4 query_start_points, Int4 subject_start_points, Int2 num, double xsum, Int4 query_length, Int4 subject_length, Int8 searchsp_eff, double weight_divisor) |
Calculates the e-value of a collection multiple distinct alignments with asymmetric gaps between the alignments. | |
double | BLAST_LargeGapSumE (Int2 num, double xsum, Int4 query_length, Int4 subject_length, Int8 searchsp_eff, double weight_divisor) |
Calculates the e-value if a collection of distinct alignments with arbitrarily large gaps between the alignments. | |
void | Blast_FillResidueProbability (const Uint1 *sequence, Int4 length, double *resProb) |
Given a sequence of 'length' amino acid residues, compute the probability of each residue and put that in the array resProb Excludes ambiguity characters. | |
static double | RPSfindUngappedLambda (const char *matrixName) |
Gets the ungapped lambda calculated for the matrix in question given standard residue composition for both query and subject sequences. | |
static void | RPSFillScores (Int4 **matrix, Int4 matrixLength, double *queryProbArray, double *scoreArray, Blast_ScoreFreq *return_sfp, Int4 range, Int4 alphabet_size) |
the routine RPSFillScores computes the probability of each score weighted by the probability of each query residue and fills those probabilities into scoreArray and puts scoreArray as a field in that in the structure that is returned for indexing convenience the field storing scoreArray points to the entry for score 0, so that referring to the -k index corresponds to score -k FIXME: This can be replaced by _PSIComputeScoreProbabilities?? | |
Int4 ** | RPSRescalePssm (double scalingFactor, Int4 rps_query_length, const Uint1 *rps_query_seq, Int4 db_seq_length, Int4 **posMatrix, BlastScoreBlk *sbp) |
Rescale the PSSM, using composition-based statistics, for use with RPS BLAST. | |
static void | s_BuildCompressedTranslation (const char *trans_string, Uint1 *table, Int4 compressed_alphabet_size, CompressedReverseLookup rev_table) |
parse the string defining the conversion between the ordinary protein alphabet and a compressed alphabet | |
static Int2 | s_GetCompressedProbs (BlastScoreBlk *sbp, double *compressed_prob, Int4 compressed_alphabet_size, CompressedReverseLookup rev_table) |
Calculate conditional probability of each letter in each group. | |
static Int2 | s_BuildCompressedScoreMatrix (BlastScoreBlk *sbp, SCompressedAlphabet *new_alphabet, double matrix_scale_factor, CompressedReverseLookup rev_table) |
Compute a (non-square) score matrix for a compressed alphabet. | |
SCompressedAlphabet * | SCompressedAlphabetNew (BlastScoreBlk *sbp, Int4 compressed_alphabet_size, double matrix_scale_factor) |
Allocate a new compressed alphabet and score matrix. | |
SCompressedAlphabet * | SCompressedAlphabetFree (SCompressedAlphabet *alphabet) |
Free a compressed alphabet and score matrix. | |
Int4 | BLAST_ComputeLengthAdjustment (double K, double logK, double alpha_d_lambda, double beta, Int4 query_length, Int8 db_length, Int4 db_num_seqs, Int4 *length_adjustment) |
Computes the adjustment to the lengths of the query and database sequences that is used to compensate for edge effects when computing evalues. | |
Variables | |
static char const | rcsid [] |
static array_of_8 | blosum45_values [14] |
Supported values (gap-existence, extension, etc. | |
static Int4 | blosum45_prefs [14] |
Quality values for BLOSUM45 matrix, each element corresponds to same element number in array blosum45_values. | |
static array_of_8 | blosum50_values [16] |
Supported values (gap-existence, extension, etc. | |
static Int4 | blosum50_prefs [16] |
Quality values for BLOSUM50 matrix, each element corresponds to same element number in array blosum50_values. | |
static array_of_8 | blosum62_values [12] |
Supported values (gap-existence, extension, etc. | |
static Int4 | blosum62_prefs [12] |
Quality values for BLOSUM62 matrix, each element corresponds to same element number in array blosum62_values. | |
static array_of_8 | blosum80_values [10] |
Supported values (gap-existence, extension, etc. | |
static Int4 | blosum80_prefs [10] |
Quality values for BLOSUM80 matrix, each element corresponds to same element number in array blosum80_values. | |
static array_of_8 | blosum90_values [8] |
Supported values (gap-existence, extension, etc. | |
static Int4 | blosum90_prefs [8] |
Quality values for BLOSUM90 matrix, each element corresponds to same element number in array blosum90_values. | |
static array_of_8 | pam250_values [16] |
Supported values (gap-existence, extension, etc. | |
static Int4 | pam250_prefs [16] |
Quality values for PAM250 matrix, each element corresponds to same element number in array pam250_values. | |
static array_of_8 | pam30_values [7] |
Supported values (gap-existence, extension, etc. | |
static Int4 | pam30_prefs [7] |
Quality values for PAM30 matrix, each element corresponds to same element number in array pam30_values. | |
static array_of_8 | pam70_values [7] |
Supported values (gap-existence, extension, etc. | |
static Int4 | pam70_prefs [7] |
Quality values for PAM70 matrix, each element corresponds to same element number in array pam70_values. | |
static const array_of_8 | blastn_values_1_5 [] |
Karlin-Altschul parameter values for substitution scores 1 and -5. | |
static const array_of_8 | blastn_values_1_4 [] |
Karlin-Altschul parameter values for substitution scores 1 and -4. | |
static const array_of_8 | blastn_values_2_7 [] |
Karlin-Altschul parameter values for substitution scores 2 and -7. | |
static const array_of_8 | blastn_values_1_3 [] |
Karlin-Altschul parameter values for substitution scores 1 and -3. | |
static const array_of_8 | blastn_values_2_5 [] |
Karlin-Altschul parameter values for substitution scores 2 and -5. | |
static const array_of_8 | blastn_values_1_2 [] |
Karlin-Altschul parameter values for substitution scores 1 and -2. | |
static const array_of_8 | blastn_values_2_3 [] |
Karlin-Altschul parameter values for substitution scores 2 and -3. | |
static const array_of_8 | blastn_values_3_4 [] |
Karlin-Altschul parameter values for substitution scores 3 and -4. | |
static const array_of_8 | blastn_values_4_5 [] |
Karlin-Altschul parameter values for substitution scores 4 and -5. | |
static const array_of_8 | blastn_values_1_1 [] |
Karlin-Altschul parameter values for substitution scores 1 and -1. | |
static const array_of_8 | blastn_values_3_2 [] |
Karlin-Altschul parameter values for substitution scores 3 and -2. | |
static const array_of_8 | blastn_values_5_4 [] |
Karlin-Altschul parameter values for substitution scores 5 and -4. | |
static BLAST_LetterProb | Robinson_prob [] |
amino acid background frequencies from Robinson and Robinson | |
static BLAST_LetterProb | nt_prob [] |
nucleotide probabilities (25% each letter) | |
static const char * | s_alphabet10 = "IJLMV AST BDENZ KQR G FY P H C W" |
23-to-10 letter compressed alphabet. | |
static const char * | s_alphabet15 = "ST IJV LM KR EQZ A G BD P N F Y H C W" |
23-to-15 letter compressed alphabet. |
|
upper limit on iterations for BlastKarlinLHtoK
Definition at line 76 of file blast_stat.c. |
|
K_SUMLIMIT_DEFAULT == sumlimit used in BlastKarlinLHtoK().
Definition at line 68 of file blast_stat.c. |
|
Initial guess for the value of Lambda in BlastKarlinLambdaNR.
Definition at line 74 of file blast_stat.c. Referenced by Blast_KarlinBlkUngappedCalc(). |
|
LAMBDA_ACCURACY_DEFAULT == accuracy to which Lambda should be calc'd.
Definition at line 70 of file blast_stat.c. |
|
LAMBDA_ITER_DEFAULT == no. of iterations in LambdaBis = ln(accuracy)/ln(2) Definition at line 72 of file blast_stat.c. |
|
Number of statistical parameters in each row of the precomputed tables.
Definition at line 79 of file blast_stat.c. |
|
maximum allowed range of BLAST scores.
Definition at line 60 of file blast_stat.c. Referenced by BlastScoreChk(), and RPSRescalePssm(). |
|
Number of different combinations supported for BLOSUM45.
Definition at line 167 of file blast_stat.c. Referenced by BlastLoadMatrixValues(). |
|
Number of different combinations supported for BLOSUM50.
Definition at line 203 of file blast_stat.c. Referenced by BlastLoadMatrixValues(). |
|
Number of different combinations supported for BLOSUM62.
Definition at line 242 of file blast_stat.c. Referenced by BlastLoadMatrixValues(). |
|
Number of different combinations supported for BLOSUM80.
Definition at line 274 of file blast_stat.c. Referenced by BlastLoadMatrixValues(). |
|
Number of different combinations supported for BLOSUM90.
Definition at line 301 of file blast_stat.c. Referenced by BlastLoadMatrixValues(). |
|
Number of different combinations supported for PAM250.
Definition at line 324 of file blast_stat.c. Referenced by BlastLoadMatrixValues(). |
|
Number of different combinations supported for PAM30.
Definition at line 363 of file blast_stat.c. Referenced by BlastLoadMatrixValues(). |
|
Number of different combinations supported for PAM70.
Definition at line 385 of file blast_stat.c. Referenced by BlastLoadMatrixValues(). |
|
points to the standard amino acid frequencies to use.
Definition at line 1465 of file blast_stat.c. Referenced by Blast_GetStdAlphabet(), and Blast_ResFreqStdComp(). |
|
Holds values (gap-opening, extension, etc. ) for a matrix. Definition at line 82 of file blast_stat.c. |
|
2-D array mapping compressed letters to sets of ordinary protein letters
Definition at line 4277 of file blast_stat.c. |
|
Check the validity of the reward and penalty scores. Only to be used with blastn searches.
Definition at line 3098 of file blast_stat.c. References FALSE, s_GetNuclValuesArray(), and sfree. Referenced by BlastScoringOptionsValidate(). |
|
Computes the adjustment to the lengths of the query and database sequences that is used to compensate for edge effects when computing evalues. The length adjustment is an integer-valued approximation to the fixed point of the function f(ell) = beta + (alpha/lambda) * (log K + log((m - ell)*(n - N ell))) where m is the query length n is the length of the database and N is the number of sequences in the database. The values beta, alpha, lambda and K are statistical, Karlin-Altschul parameters. The value of the length adjustment computed by this routine, A, will always be an integer smaller than the fixed point of f(ell). Usually, it will be the largest such integer. However, the computed length adjustment, A, will also be so small that K * (m - A) * (n - N * A) > MAX(m,n). Moreover, an iterative method is used to compute A, and under unusual circumstances the iterative method may not converge.
Definition at line 4553 of file blast_stat.c. References FALSE, MAX, and TRUE. Referenced by BLAST_CalcEffLengths(). |
|
Calculate the cutoff score from the expected number of HSPs or vice versa.
Definition at line 3606 of file blast_stat.c. References BLAST_GapDecayDivisor(), BLAST_KarlinStoE_simple(), BlastKarlinEtoS_simple(), FALSE, Blast_KarlinBlk::H, Blast_KarlinBlk::K, Blast_KarlinBlk::Lambda, and TRUE. Referenced by BlastHitSavingParametersUpdate(), BlastInitialWordParametersUpdate(), and BOOST_AUTO_TEST_CASE(). |
|
Given a sequence of 'length' amino acid residues, compute the probability of each residue and put that in the array resProb Excludes ambiguity characters.
Definition at line 4090 of file blast_stat.c. References AMINOACID_TO_NCBISTDAA, and BLASTAA_SIZE. Referenced by RPSRescalePssm(). |
|
Compute a divisor used to weight the evalue of a collection of "nsegs" distinct alignments. These divisors are used to compensate for the effect of choosing the best among multiple collections of alignments. See Stephen F. Altschul. Evaluating the statitical significance of multiple distinct local alignments. In Suhai, editior, Theoretical and Computational Methods in Genome Research, pages 1-14. Plenum Press, New York, 1997. The "decayrate" parameter of this routine is a value in the interval (0,1). Typical values of decayrate are .1 and .5.
Definition at line 3595 of file blast_stat.c. References BLAST_Powi(). Referenced by BLAST_Cutoffs(), Blast_HSPListGetEvalues(), and s_SumHSPEvalue(). |
|
Extract the alpha and beta settings for this matrixName, and these gap open and gap extension costs.
Definition at line 2738 of file blast_stat.c. References Blast_GetMatrixValues(), and BLAST_MATRIX_BEST. Referenced by BLAST_CalcEffLengths(). |
|
Obtains arrays of the allowed opening and extension penalties for gapped BLAST for the given matrix. Also obtains arrays of Lambda, K, and H. Any of these fields that are not required should be set to NULL. The Int2 return value is the length of the arrays.
Definition at line 2657 of file blast_stat.c. References BlastLoadMatrixValues(), FALSE, MatrixInfo::max_number_values, MatrixInfo::name, ListNode::next, MatrixInfo::prefs, ListNode::ptr, strcasecmp, TRUE, and MatrixInfo::values. Referenced by BLAST_GetAlphaBeta(), BLAST_GetProteinGapExistenceExtendParams(), and RPSfindUngappedLambda(). |
|
Extract the alpha and beta settings for these substitution and gap scores. If substitution or gap costs are not found in the tables, assume an ungapped search. Then alpha is computed using the formula Alpha = Lambda/H, and beta is equal to 0 except for some special cases.
Definition at line 3481 of file blast_stat.c. References ASSERT, FALSE, s_GetNuclValuesArray(), and TRUE. Referenced by BLAST_CalcEffLengths(). |
|
Extract the recommended gap existence and extension values. Only to be used with blastn searches.
Definition at line 3046 of file blast_stat.c. References FALSE, s_GetNuclValuesArray(), sfree, and TRUE. Referenced by BOOST_AUTO_UNIT_TEST(). |
|
Extract the recommended gap existence and extension values. Only to be used with protein matrices.
Definition at line 3018 of file blast_stat.c. References Blast_GetMatrixValues(), and BLAST_MATRIX_BEST. Referenced by BOOST_AUTO_UNIT_TEST(), and CGenericSearchArgs::ExtractAlgorithmOptions(). |
|
Fills a buffer with the 'standard' alphabet (given by STD_AMINO_ACID_FREQS[index].ch). < points to the standard amino acid frequencies to use. < points to the standard amino acid frequencies to use. < points to the standard amino acid frequencies to use. < points to the standard amino acid frequencies to use. Definition at line 1510 of file blast_stat.c. References AMINOACID_TO_NCBISTDAA, BLASTAA_SEQ_CODE, DIM, and STD_AMINO_ACID_FREQS. Referenced by _PSIComputeScoreProbabilities(), and Blast_ResFreqStdComp(). |
|
Copies contents of one Karlin block to another. Both must be allocated before this function is called.
Definition at line 2522 of file blast_stat.c. References Blast_KarlinBlk::H, Blast_KarlinBlk::K, Blast_KarlinBlk::Lambda, Blast_KarlinBlk::logK, and Blast_KarlinBlk::paramC. Referenced by Blast_ScoreBlkKbpGappedCalc(), Blast_ScoreBlkKbpUngappedCalc(), CBlastAncillaryData::do_copy(), s_InitializeKarlinBlk(), and s_RestoreSearch(). |
|
Deallocates the KarlinBlk.
Definition at line 850 of file blast_stat.c. References sfree. Referenced by Blast_ScoreBlkKbpUngappedCalc(), BlastScoreBlkFree(), BOOST_AUTO_UNIT_TEST(), MakeSomeInvalidKBP(), MakeSomeValidKBP(), s_SavedParametersFree(), SPsiBlastScoreMatrixFree(), and CBlastAncillaryData::~CBlastAncillaryData(). |
|
Fills in lambda, H, and K values, as calculated by Stephen Altschul in Methods in Enzy. (vol 266, page 474).
Definition at line 3171 of file blast_stat.c. References Blast_KarlinBlkGappedLoadFromTables(), Blast_MessageWrite(), BlastKarlinReportAllowedValues(), BlastLoadMatrixValues(), BlastMatrixValuesDestruct(), eBlastSevError, kBlastMessageNoContext, MatrixInfo::name, ListNode::next, and ListNode::ptr. Referenced by Blast_ScoreBlkKbpGappedCalc(). |
|
Attempts to fill KarlinBlk for given gap opening, extensions etc.
Definition at line 3221 of file blast_stat.c. References BLAST_Nint(), BlastLoadMatrixValues(), FALSE, MatrixInfo::max_number_values, MatrixInfo::name, ListNode::next, ListNode::ptr, strcasecmp, TRUE, and MatrixInfo::values. Referenced by Blast_KarlinBlkGappedCalc(), BlastScoringOptionsValidate(), and CMultiAligner::x_ComputeTree(). |
|
Callocs a Blast_KarlinBlk.
Definition at line 2512 of file blast_stat.c. Referenced by Blast_ScoreBlkKbpGappedCalc(), Blast_ScoreBlkKbpIdealCalc(), Blast_ScoreBlkKbpUngappedCalc(), CBlastAncillaryData::CBlastAncillaryData(), CBlastAncillaryData::do_copy(), MakeSomeInvalidKBP(), MakeSomeValidKBP(), s_FillScoreBlkWithBadKbp(), s_InitializeKarlinBlk(), s_PHIScoreBlkFill(), s_RecordInitialSearch(), and SPsiBlastScoreMatrixNew(). |
|
Retrieves Karlin-Altschul parameters from precomputed tables, given the substitution and gap scores. Gap cost values greater than any of those listed in the tables ("greater" meaning that both values are greater than or equal, and at least one is strictly greater), are treated as infinite, and parameters values are copied from the ungapped Karlin block.
Definition at line 3368 of file blast_stat.c. References ASSERT, Blast_KarlinBlk::H, Blast_KarlinBlk::K, Blast_KarlinBlk::Lambda, Blast_KarlinBlk::logK, s_GetNuclValuesArray(), and sfree. Referenced by Blast_ScoreBlkKbpGappedCalc(). |
|
Computes the parameters lambda, H K for use in calculating the statistical significance of high-scoring segments or subalignments (see comment on blast_stat.c for more details). < Initial guess for the value of Lambda in BlastKarlinLambdaNR Definition at line 2346 of file blast_stat.c. References BLAST_KARLIN_LAMBDA0_DEFAULT, Blast_KarlinLambdaNR(), BlastKarlinLHtoK(), BlastKarlinLtoH(), Blast_KarlinBlk::H, Blast_KarlinBlk::K, Blast_KarlinBlk::Lambda, and Blast_KarlinBlk::logK. Referenced by _PSIUpdateLambdaK(), Blast_ScoreBlkKbpIdealCalc(), and Blast_ScoreBlkKbpUngappedCalc(). |
|
Convert an E-value to a P-value. E-values and P-values may either represent statistics of a database search or represent statistics on the two sequences being compared. If given a database E-value, this routine will return a database P-value; if given a pairwise E-value, it will return a pairwise P-value. In the context of a database search, the available E-value is typically a database E-value, whereas the desired P-value is a pairwise P-value. When this is the case, the E-value should be divided by the effective length of the database and multiplied by the effective length of the subject, before BLAST_KarlinEtoP is called.
Definition at line 3705 of file blast_stat.c. References BLAST_Expm1(). Referenced by s_AdjustEvaluesForComposition(). |
|
Calculates the parameter Lambda given an initial guess for its value. < LAMBDA_ACCURACY_DEFAULT == accuracy to which Lambda should be calc'd < LAMBDA_ITER_DEFAULT == no. of iterations in LambdaBis = ln(accuracy)/ln(2) Definition at line 2214 of file blast_stat.c. References BLAST_Gcd(), BlastScoreChk(), Blast_ScoreFreq::obs_max, Blast_ScoreFreq::obs_min, Blast_ScoreFreq::score_avg, and Blast_ScoreFreq::sprob. Referenced by Blast_KarlinBlkUngappedCalc(), and RPSRescalePssm(). |
|
Convert a P-value to an E-value. P-values and E-values may either represent statistics of a database search or represent statistics on the two sequences being compared. If given a database P-value, this routine will return a database E-value; if given a pairwise P-value, it will return a pairwise E-value. In the context of a database search, the available P-value is often a pairwise P-value, whereas the desired E-value is a database E-value. When this it the case, the value returned by this routine should be multiplied by the effective length of the database and divided by the effective length of the subject.
Definition at line 3691 of file blast_stat.c. References BLAST_Log1p(), INT4_MAX, and INT4_MIN. Referenced by BLAST_LargeGapSumE(), BLAST_SmallGapSumE(), BLAST_UnevenGapSumE(), and s_AdjustEvaluesForComposition(). |
|
Calculates the Expect value based upon the search space and some Karlin-Altschul parameters. It is "simple" as it does not use sum-statistics.
Definition at line 3673 of file blast_stat.c. References Blast_KarlinBlk::H, H, Blast_KarlinBlk::K, Blast_KarlinBlk::Lambda, and Blast_KarlinBlk::logK. Referenced by BLAST_Cutoffs(), Blast_HSPListGetEvalues(), and CScoreBuilder::GetBlastEValue(). |
|
Calculates the e-value if a collection of distinct alignments with arbitrarily large gaps between the alignments.
Definition at line 4045 of file blast_stat.c. References BLAST_KarlinPtoE(), BLAST_LnFactorial(), INT4_MAX, and s_BlastSumP(). |
|
Prints a messages about the allowed open etc values for the given matrix, BlastKarlinBlkGappedFill should return 2 before this is called.
Definition at line 3319 of file blast_stat.c. References BLAST_Nint(), BlastLoadMatrixValues(), FALSE, MatrixInfo::max_number_values, MatrixInfo::name, ListNode::next, ListNode::ptr, strcasecmp, TRUE, and MatrixInfo::values. Referenced by BlastScoringOptionsValidate(). |
|
Prints a messages about the allowed matrices, BlastKarlinBlkGappedFill should return 1 before this is called.
Definition at line 3292 of file blast_stat.c. References BlastLoadMatrixValues(), BlastMatrixValuesDestruct(), MatrixInfo::name, ListNode::next, and ListNode::ptr. Referenced by BlastScoringOptionsValidate(). |
|
Sets prob elements of Blast_ResFreq to zero.
Definition at line 1671 of file blast_stat.c. References BlastScoreBlk::alphabet_size, BlastScoreBlk::alphabet_start, and Blast_ResFreq::prob. Referenced by Blast_ResFreqResComp(). |
|
Deallocates Blast_ResFreq and prob0 element.
Definition at line 1336 of file blast_stat.c. References Blast_ResFreq::prob0, and sfree. Referenced by BLAST_GetStandardAaProbabilities(), Blast_ResFreqNew(), Blast_ScoreBlkKbpIdealCalc(), and Blast_ScoreBlkKbpUngappedCalc(). |
|
Allocates a new Blast_ResFreq structure and fills in the prob element based upon the contents of sbp.
Definition at line 1355 of file blast_stat.c. References BlastScoreBlk::alphabet_code, Blast_ResFreq::alphabet_code, BlastScoreBlk::alphabet_size, BlastScoreBlk::alphabet_start, Blast_ResFreqFree(), Blast_ResFreq::prob, and Blast_ResFreq::prob0. Referenced by BLAST_GetStandardAaProbabilities(), Blast_ScoreBlkKbpIdealCalc(), Blast_ScoreBlkKbpUngappedCalc(), s_GetCompressedProbs(), SPHIPatternSearchBlkNew(), and CMultiAligner::x_AssignDefaultResFreqs(). |
|
Normalizes all the residue frequencies and then normalizes them to "norm". If "norm" is one, then they will all sum to one.
Definition at line 1482 of file blast_stat.c. References BlastScoreBlk::alphabet_size, BlastScoreBlk::alphabet_start, and Blast_ResFreq::prob. |
|
Calculate the residue frequencies associated with the provided ResComp This function takes into account the composition of a given sequence (expressed through rcp) rather than just doing it for a standard distribution.
Definition at line 1691 of file blast_stat.c. References Blast_ResComp::alphabet_code, Blast_ResFreq::alphabet_code, BlastScoreBlk::alphabet_size, BlastScoreBlk::alphabet_start, Blast_ResFreqClr(), Blast_ResComp::comp, and Blast_ResFreq::prob. Referenced by Blast_ResFreqString(). |
|
Calculates residues frequencies given a standard distribution. < points to the standard amino acid frequencies to use. < points to the standard amino acid frequencies to use. < points to the standard amino acid frequencies to use. < points to the standard amino acid frequencies to use. Definition at line 1534 of file blast_stat.c. References BlastScoreBlk::alphabet_code, Blast_GetStdAlphabet(), DIM, Blast_ResFreq::prob, BlastScoreBlk::protein_alphabet, sfree, STD_AMINO_ACID_FREQS, and TRUE. Referenced by BLAST_GetStandardAaProbabilities(), Blast_ScoreBlkKbpIdealCalc(), Blast_ScoreBlkKbpUngappedCalc(), s_GetCompressedProbs(), SPHIPatternSearchBlkNew(), and CMultiAligner::x_AssignDefaultResFreqs(). |
|
Fills in residue frequences for a given sequence.
Definition at line 1725 of file blast_stat.c. References Blast_ResFreqResComp(), BlastResCompDestruct(), BlastResCompNew(), and BlastResCompStr(). Referenced by Blast_ScoreBlkKbpUngappedCalc(). |
|
Calculates the Karlin-Altschul parameters assuming standard residue compositions for the query and subject sequences. It populates the kbp_ideal field of its sbp argument. This is used if the query is translated and the calculated (real) Karlin parameters are bad, as they're calculated for non-coding regions.
Definition at line 2483 of file blast_stat.c. References Blast_KarlinBlkNew(), Blast_KarlinBlkUngappedCalc(), Blast_ResFreqFree(), Blast_ResFreqNew(), Blast_ResFreqStdComp(), Blast_ScoreFreqFree(), Blast_ScoreFreqNew(), BlastScoreFreqCalc(), BlastScoreBlk::hiscore, BlastScoreBlk::kbp_ideal, and BlastScoreBlk::loscore. Referenced by Blast_ScoreBlkKbpUngappedCalc(), and s_PHIScoreBlkFill(). |
|
|
This function fills in the BlastScoreBlk structure. Tasks are: -read in the matrix -set maxscore
Definition at line 1275 of file blast_stat.c. References BlastScoreBlk::alphabet_code, BLASTNA_SEQ_CODE, BlastScoreBlkMaxScoreSet(), BlastScoreBlkNuclMatrixCreate(), BlastScoreBlkProteinMatrixLoad(), BlastScoreBlkProteinMatrixRead(), FALSE, fp, BlastScoreBlk::name, BlastScoreBlk::read_in_matrix, sfree, and TRUE. Referenced by Blast_ScoreBlkMatrixInit(), and s_PHIScoreBlkFill(). |
|
Deallocates the score frequencies structure.
Definition at line 835 of file blast_stat.c. References sfree, and Blast_ScoreFreq::sprob0. Referenced by _PSIUpdateLambdaK(), Blast_ScoreBlkKbpIdealCalc(), Blast_ScoreBlkKbpUngappedCalc(), Blast_ScoreFreqNew(), and BlastScoreBlkFree(). |
|
Creates a new structure to keep track of score frequencies for a scoring system.
Definition at line 1760 of file blast_stat.c. References Blast_ScoreFreqFree(), BlastScoreChk(), Blast_ScoreFreq::obs_max, Blast_ScoreFreq::obs_min, Blast_ScoreFreq::score_avg, Blast_ScoreFreq::score_max, Blast_ScoreFreq::score_min, Blast_ScoreFreq::sprob, and Blast_ScoreFreq::sprob0. Referenced by Blast_ScoreBlkKbpIdealCalc(), Blast_ScoreBlkKbpUngappedCalc(), and s_PHIScoreBlkFill(). |
|
Set the ambiguous residue (e.g, 'N', 'X') in the BlastScoreBlk*. Convert from ncbieaa to sbp->alphabet_code (i.e., ncbistdaa) first.
Definition at line 900 of file blast_stat.c. References BlastScoreBlk::ambig_occupy, BlastScoreBlk::ambig_size, BlastScoreBlk::ambiguous_res, and sfree. Referenced by Blast_ScoreBlkMatrixInit(). |
|
Calculates the e-value for alignments with "small" gaps (typically under fifty residues/basepairs) following ideas of Stephen Altschul's.
Definition at line 3933 of file blast_stat.c. References BLAST_KarlinPtoE(), BLAST_LnFactorial(), INT4_MAX, and s_BlastSumP(). |
|
Calculates the e-value of a collection multiple distinct alignments with asymmetric gaps between the alignments. The gaps in one (protein) sequence are typically small (like in BLAST_SmallGapSumE) gap an the gaps in the other (translated DNA) sequence are possibly large (up to 4000 bp.) This routine is used for linking HSPs representing exons in the DNA sequence that are separated by introns.
Definition at line 4005 of file blast_stat.c. References BLAST_KarlinPtoE(), BLAST_LnFactorial(), INT4_MAX, and s_BlastSumP(). Referenced by s_SumHSPEvalue(). |
|
Calculates score from expect value and search space.
Definition at line 3556 of file blast_stat.c. References BLAST_SCORE_MIN, Blast_KarlinBlk::H, H, Blast_KarlinBlk::K, Blast_KarlinBlk::Lambda, and MAX. Referenced by BLAST_Cutoffs(). |
|
The following procedure computes K. The input includes Lambda, H, and an array of probabilities for each score. There are distinct closed form for three cases: 1. high score is 1 low score is -1 2. high score is 1 low score is not -1 3. low score is -1, high score is not 1 Otherwise, in most cases the value is computed as: -exp(-2.0*outerSum) / ((H/lambda)*(exp(-lambda) - 1) The last term (exp(-lambda) - 1) can be computed in two different ways depending on whether lambda is small or not. outerSum is a sum of the terms innerSum/j, where j is denoted by iterCounter in the code. The sum is truncated when the new term innersum/j i sufficiently small. innerSum is a weighted sum of the probabilities of of achieving a total score i in a gapless alignment, which we denote by P(i,j). of exactly j characters. innerSum(j) has two parts Sum over i < 0 P(i,j)exp(-i * lambda) + Sum over i >=0 P(i,j) The terms P(i,j) are computed by dynamic programming. An earlier version was flawed in that ignored the special case 1 and tried to replace the tail of the computation of outerSum by a geometric series, but the base of the geometric series was not accurately estimated in some cases.
< upper limit on iterations for BlastKarlinLHtoK Definition at line 1894 of file blast_stat.c. References BLAST_Gcd(), Blast_ScoreFreq::obs_max, Blast_ScoreFreq::obs_min, Blast_ScoreFreq::score_avg, and Blast_ScoreFreq::sprob. Referenced by Blast_KarlinBlkUngappedCalc(). |
|
Calculate H, the relative entropy of the p's and q's.
Definition at line 2254 of file blast_stat.c. References BlastScoreChk(), H, Blast_ScoreFreq::obs_max, Blast_ScoreFreq::obs_min, and Blast_ScoreFreq::sprob. Referenced by Blast_KarlinBlkUngappedCalc(). |
|
Fills in error_return with strings describing the allowed values.
Definition at line 3122 of file blast_stat.c. References Blast_MessageWrite(), BLAST_Nint(), BlastLoadMatrixValues(), eBlastSevError, FALSE, kBlastMessageNoContext, MatrixInfo::max_number_values, MatrixInfo::name, ListNode::next, ListNode::ptr, strcasecmp, TRUE, and MatrixInfo::values. Referenced by Blast_KarlinBlkGappedCalc(). |
|
Loads all the matrix values, returns a ListNode* chain that contains MatrixInfo*'s.
< Number of different combinations supported for BLOSUM62. < Number of different combinations supported for BLOSUM50. < Number of different combinations supported for BLOSUM45. < Number of different combinations supported for PAM250. < Number of different combinations supported for BLOSUM90. < Number of different combinations supported for PAM30. < Number of different combinations supported for PAM70. Definition at line 2603 of file blast_stat.c. References blosum45_prefs, blosum45_values, BLOSUM45_VALUES_MAX, blosum50_prefs, blosum50_values, BLOSUM50_VALUES_MAX, blosum62_prefs, blosum62_values, BLOSUM62_VALUES_MAX, blosum80_prefs, blosum80_values, BLOSUM80_VALUES_MAX, blosum90_prefs, blosum90_values, BLOSUM90_VALUES_MAX, ListNodeAddPointer(), MatrixInfoNew(), pam250_prefs, pam250_values, PAM250_VALUES_MAX, pam30_values, PAM30_VALUES_MAX, and PAM70_VALUES_MAX. Referenced by Blast_GetMatrixValues(), Blast_KarlinBlkGappedCalc(), Blast_KarlinBlkGappedLoadFromTables(), BLAST_PrintAllowedValues(), BLAST_PrintMatrixMessage(), and BlastKarlinReportAllowedValues(). |
|
Free linked list of MatrixValues and all associated data.
Definition at line 2580 of file blast_stat.c. References ListNodeFree(), MatrixInfoDestruct(), ListNode::next, and ListNode::ptr. Referenced by Blast_KarlinBlkGappedCalc(), and BLAST_PrintMatrixMessage(). |
|
Deallocates Blast_ResComp structure and associated arrays.
Definition at line 1581 of file blast_stat.c. References Blast_ResComp::comp0, and sfree. Referenced by Blast_ResFreqString(), and BlastResCompNew(). |
|
Allocated the Blast_ResComp* for a given alphabet. Only the alphabets ncbistdaa and ncbi4na should be used by BLAST.
Definition at line 1599 of file blast_stat.c. References BlastScoreBlk::alphabet_code, Blast_ResComp::alphabet_code, BlastScoreBlk::alphabet_size, BlastScoreBlk::alphabet_start, BlastResCompDestruct(), Blast_ResComp::comp, and Blast_ResComp::comp0. Referenced by Blast_ResFreqString(). |
|
Store the composition of a (query) string.
Definition at line 1631 of file blast_stat.c. References BlastScoreBlk::alphabet_code, Blast_ResComp::alphabet_code, BlastScoreBlk::alphabet_size, Blast_ResComp::comp, Blast_ResComp::comp0, and BlastScoreBlk::protein_alphabet. Referenced by Blast_ResFreqString(). |
|
Deallocates BlastScoreBlk as well as all associated structures.
Definition at line 859 of file blast_stat.c. References Blast_KarlinBlkFree(), Blast_ScoreFreqFree(), BlastScoreBlk::kbp_gap_psi, BlastScoreBlk::kbp_gap_std, BlastScoreBlk::kbp_psi, BlastScoreBlk::kbp_std, BlastScoreBlk::number_of_contexts, and BlastScoreBlk::sfp. Referenced by BlastScoreBlkNew(), BOOST_AUTO_TEST_CASE(), BOOST_AUTO_UNIT_TEST(), LinkHspTestFixture::freeStructures(), TestFixture::TearDownLookupTable(), CBlastTracebackSearch::x_Init(), CPssmEngine::x_InitializeScoreBlock(), CBl2Seq::x_ResetQueryDs(), AalookupTestFixture::~AalookupTestFixture(), AascanTestFixture::~AascanTestFixture(), and CScoreBuilder::~CScoreBuilder(). |
|
Sets maximum and minimum scores on the BlastScoreBlk for a given matrix.
Definition at line 1177 of file blast_stat.c. References BlastScoreBlk::alphabet_size, BLAST_SCORE_MAX, BLAST_SCORE_MIN, SBlastScoreMatrix::data, BlastScoreBlk::hiscore, BlastScoreBlk::loscore, and BlastScoreBlk::matrix. Referenced by Blast_ScoreBlkMatrixFill(). |
|
Allocates and initializes BlastScoreBlk.
Definition at line 784 of file blast_stat.c. References BlastScoreBlk::alphabet_code, BlastScoreBlk::alphabet_size, BLASTAA_SEQ_CODE, BLASTAA_SIZE, BLASTNA_SEQ_CODE, BLASTNA_SIZE, BlastScoreBlkFree(), FALSE, BlastScoreBlk::kbp_gap_psi, BlastScoreBlk::kbp_gap_std, BlastScoreBlk::kbp_psi, BlastScoreBlk::kbp_std, BlastScoreBlk::matrix, BlastScoreBlk::number_of_contexts, BlastScoreBlk::protein_alphabet, SBlastScoreMatrixNew(), BlastScoreBlk::scale_factor, BlastScoreBlk::sfp, and TRUE. Referenced by AascanTestFixture::AascanTestFixture(), BlastSetup_ScoreBlkInit(), BOOST_AUTO_TEST_CASE(), AalookupTestFixture::FillLookupTable(), s_FillScoreBlkWithBadKbp(), LinkHspTestFixture::setupScoreBlk(), and CMultiAligner::x_AssignDefaultResFreqs(). |
|
Fill in the matrix for blastn using the penaly and rewards The query sequence alphabet is blastna, the subject sequence is ncbi2na. The alphabet blastna is defined in blast_stat.h and the first four elements of blastna are identical to ncbi2na.
Definition at line 948 of file blast_stat.c. References BlastScoreBlk::alphabet_size, ASSERT, BLASTNA_SIZE, BLASTNA_TO_NCBI4NA, SBlastScoreMatrix::data, BlastScoreBlk::matrix, SBlastScoreMatrix::ncols, SBlastScoreMatrix::nrows, BlastScoreBlk::penalty, and BlastScoreBlk::reward. Referenced by Blast_ScoreBlkMatrixFill(). |
|
Sets sbp->matrix->data field using sbp->name field using the matrices in the toolkit (util/tables/raw_scoremat.h).
Definition at line 1216 of file blast_stat.c. References BlastScoreBlk::alphabet_size, ASSERT, BLAST_SCORE_MIN, BLASTAA_SIZE, SBlastScoreMatrix::data, BlastScoreBlk::matrix, BlastScoreBlk::name, NCBISM_GetStandardMatrix(), SBlastScoreMatrix::ncols, and SBlastScoreMatrix::nrows. Referenced by Blast_ScoreBlkMatrixFill(). |
|
Read in the matrix from the FILE *fp. This function ASSUMES that the matrices are in the ncbistdaa
Definition at line 1028 of file blast_stat.c. References BlastScoreBlk::alphabet_code, BlastScoreBlk::alphabet_size, ASSERT, BLAST_SCORE_MIN, BLASTAA_SIZE, BLASTNA_SEQ_CODE, buf, SBlastScoreMatrix::data, BlastScoreBlk::matrix, SBlastScoreMatrix::ncols, and SBlastScoreMatrix::nrows. Referenced by Blast_ScoreBlkMatrixFill(). |
|
Check that the lo and hi score are within the allowed ranges.
Definition at line 1747 of file blast_stat.c. References BLAST_SCORE_MAX, and BLAST_SCORE_RANGE_MAX. Referenced by Blast_KarlinLambdaNR(), Blast_ScoreFreqNew(), and BlastKarlinLtoH(). |
|
Calculates the score frequencies.
Definition at line 1798 of file blast_stat.c. References BlastScoreBlk::alphabet_size, BlastScoreBlk::alphabet_start, SBlastScoreMatrix::data, BlastScoreBlk::hiscore, BlastScoreBlk::loscore, BlastScoreBlk::matrix, Blast_ResFreq::prob, Blast_ScoreFreq::score_max, Blast_ScoreFreq::score_min, and Blast_ScoreFreq::sprob. Referenced by Blast_ScoreBlkKbpIdealCalc(), and Blast_ScoreBlkKbpUngappedCalc(). |
|
Deallocates MatrixInfo as well as name string.
Definition at line 2541 of file blast_stat.c. References MatrixInfo::name, and sfree. Referenced by BlastMatrixValuesDestruct(). |
|
Allocates New MatrixInfo*.
Definition at line 2561 of file blast_stat.c. References MatrixInfo::max_number_values, MatrixInfo::name, MatrixInfo::prefs, strdup, and MatrixInfo::values. Referenced by BlastLoadMatrixValues(). |
|
Find positive solution to. sum_{i=low}^{high} exp(i lambda) * probs[i] = 1. Note that this solution does not exist unless the average score is negative and the largest score that occurs with nonzero probability is positive.
phi(lamdba) = exp(u lambda) f( exp(-lambda) ) where f(x) is a polynomial that has exactly two zeros, one at x = 1 and one at x = exp(-lamdba). It is simpler to solve this problem in x = exp(-lambda) than it is to solve it in lambda, because we know that for x, a solution lies in [0,1], and because Newton's method is generally more stable and efficient for polynomials than it is for exponentials. For the most part, this function is a standard safeguarded Newton iteration: define an interval of uncertainty [a,b] with f(a) > 0 and f(b) < 0 (except for the initial value b = 1, where f(b) = 0); evaluate the function and use the sign of that value to shrink the interval of uncertainty; compute a Newton step; and if the Newton step suggests a point outside the interval of uncertainty or fails to decrease the function sufficiently, then bisect. There are three further details needed to understand the algorithm: 1) If y the unique solution in [0,1], then f is positive to the left of y, and negative to the right. Therefore, we may determine whether the Newton step -f(x)/f'(x) is moving toward, or away from, y by examining the sign of f'(x). If f'(x) >= 0, we bisect instead of taking the Newton step. 2) There is a neighborhood around x = 1 for which f'(x) >= 0, so (1) prevents convergence to x = 1 (and for a similar reason prevents convergence to x = 0, if the function is incorrectly called with probs[high] == 0). 3) Conditions like fabs(p) < lambda_tolerance * x * (1-x) are used in convergence criteria because these values translate to a bound on the relative error in lambda. This is proved in the "Blast Scoring Parameters" document that accompanies the BLAST code. The iteration on f(x) is robust and doesn't overflow; defining a robust safeguarded Newton iteration on phi(lambda) that cannot converge to lambda = 0 and that is protected against overflow is more difficult. So (despite the length of this comment) the Newton iteration on f(x) is the simpler solution. Definition at line 2138 of file blast_stat.c. |
|
the routine RPSFillScores computes the probability of each score weighted by the probability of each query residue and fills those probabilities into scoreArray and puts scoreArray as a field in that in the structure that is returned for indexing convenience the field storing scoreArray points to the entry for score 0, so that referring to the -k index corresponds to score -k FIXME: This can be replaced by _PSIComputeScoreProbabilities??
Definition at line 4161 of file blast_stat.c. References AMINOACID_TO_NCBISTDAA, and BLAST_SCORE_MIN. Referenced by RPSRescalePssm(). |
|
Gets the ungapped lambda calculated for the matrix in question given standard residue composition for both query and subject sequences.
Definition at line 4123 of file blast_stat.c. References Blast_GetMatrixValues(), and sfree. Referenced by RPSRescalePssm(), and s_BuildCompressedScoreMatrix(). |
|
Rescale the PSSM, using composition-based statistics, for use with RPS BLAST. < maximum allowed range of BLAST scores. < maximum allowed range of BLAST scores. Definition at line 4205 of file blast_stat.c. References _PSIAllocateMatrix(), AMINOACID_TO_NCBISTDAA, ASSERT, Blast_FillResidueProbability(), Blast_KarlinLambdaNR(), BLAST_SCORE_MIN, BLAST_SCORE_RANGE_MAX, BlastScoreBlk::name, SBlastScoreMatrix::nrows, BlastScoreBlk::psi_matrix, SPsiBlastScoreMatrix::pssm, RPSFillScores(), RPSfindUngappedLambda(), and sfree. Referenced by s_RPSComputeTraceback(). |
|
Adjust Lambda and H if reward and penalty have a non-1 gcd. the two arrays (normal and linear) should be filled in with values already.
Definition at line 2830 of file blast_stat.c. Referenced by s_GetNuclValuesArray(). |
|
Estimate the Sum P-value by calculation or interpolation, as appropriate. Approx. 2-1/2 digits accuracy minimum throughout the range of r, s.
Definition at line 3873 of file blast_stat.c. References BLAST_Expm1(), BLAST_LnGammaInt(), DIM, and s_BlastSumPCalc(). Referenced by BLAST_LargeGapSumE(), BLAST_SmallGapSumE(), and BLAST_UnevenGapSumE(). |
|
Evaluate the following double integral, where r = number of segments. and s = the adjusted score in nats: (r-2) oo oo Prob(r,s) = r - - (r-2) ------------- | exp(-y) | x exp(-exp(x - y/r)) dx dy (r-1)! (r-2)! U U s 0
Definition at line 3785 of file blast_stat.c. References BLAST_Expm1(), BLAST_LnGammaInt(), BLAST_RombergIntegrate(), and s_InnerIntegralCback(). Referenced by s_BlastSumP(). |
|
Compute a (non-square) score matrix for a compressed alphabet.
Definition at line 4386 of file blast_stat.c. References _PSIMatrixFrequencyRatiosFree(), _PSIMatrixFrequencyRatiosNew(), BLAST_Nint(), BLAST_SCORE_MIN, SCompressedAlphabet::compressed_alphabet_size, SFreqRatios::data, SBlastScoreMatrix::data, SCompressedAlphabet::matrix, BlastScoreBlk::name, RPSfindUngappedLambda(), s_GetCompressedProbs(), and SBlastScoreMatrixNew(). Referenced by SCompressedAlphabetNew(). |
|
parse the string defining the conversion between the ordinary protein alphabet and a compressed alphabet
Definition at line 4291 of file blast_stat.c. Referenced by SCompressedAlphabetNew(). |
|
Calculate conditional probability of each letter in each group.
Definition at line 4329 of file blast_stat.c. References Blast_ResFreqNew(), Blast_ResFreqStdComp(), letter(), and Blast_ResFreq::prob. Referenced by s_BuildCompressedScoreMatrix(). |
|
Returns the array of values corresponding to the given match/mismatch scores, the number of supported gap cost combinations and thresholds for the gap costs, beyond which the ungapped statistics can be applied.
Definition at line 2882 of file blast_stat.c. References BLAST_Gcd(), Blast_MessageWrite(), BlastMemDup(), eBlastSevError, FALSE, kBlastMessageNoContext, s_AdjustGapParametersByGcd(), s_SplitArrayOf8(), and TRUE. Referenced by BLAST_CheckRewardPenaltyScores(), Blast_GetNuclAlphaBeta(), BLAST_GetNucleotideGapExistenceExtendParams(), and Blast_KarlinBlkNuclGappedCalc(). |
|
Returns the beta statistical parameter value, given the nucleotide substitution scores.
Definition at line 3471 of file blast_stat.c. |
|
Callback for the Romberg integration function. This is the first of the double integrals that BlastSumPCalc calculates. This is the integral described in the paragraph after eqn. 4 of Karlin and Altschul, PNAS USA, 90, 5873-5877 (1993).
Definition at line 3758 of file blast_stat.c. References SRombergCbackArgs::adj1, SRombergCbackArgs::adj2, BLAST_RombergIntegrate(), SRombergCbackArgs::epsilon, SRombergCbackArgs::num_hsps, s_OuterIntegralCback(), and SRombergCbackArgs::sdvir. Referenced by s_BlastSumPCalc(). |
|
Callback for the Romberg integration function. This is the second of the double integrals that BlastSumPCalc calculates This is eqn. 4 of Karlin and Altschul, PNAS USA, 90, 5873-5877 (1993).
Definition at line 3732 of file blast_stat.c. References SRombergCbackArgs::adj2, SRombergCbackArgs::num_hsps_minus_2, and SRombergCbackArgs::sdvir. Referenced by s_InnerIntegralCback(). |
|
Splits an ArrayOf8 into two arrays of supported gap costs. One is for non-affine (megablast linear values) and the other is for standard (typically affine) values.
Definition at line 2796 of file blast_stat.c. Referenced by s_GetNuclValuesArray(). |
|
Deallocates SBlastScoreMatrix structure.
Definition at line 690 of file blast_stat.c. References _PSIDeallocateMatrix(), SBlastScoreMatrix::data, SBlastScoreMatrix::ncols, and sfree. Referenced by SBlastScoreMatrixNew(), SCompressedAlphabetFree(), and SPsiBlastScoreMatrixFree(). |
|
Allocates a new SBlastScoreMatrix structure of the specified dimensions.
Definition at line 712 of file blast_stat.c. References _PSIAllocateMatrix(), SBlastScoreMatrix::data, SBlastScoreMatrix::ncols, SBlastScoreMatrix::nrows, and SBlastScoreMatrixFree(). Referenced by BlastScoreBlkNew(), s_BuildCompressedScoreMatrix(), and SPsiBlastScoreMatrixNew(). |
|
Free a compressed alphabet and score matrix.
Definition at line 4503 of file blast_stat.c. References SCompressedAlphabet::compress_table, SCompressedAlphabet::matrix, SBlastScoreMatrixFree(), and sfree. Referenced by SCompressedAlphabetNew(). |
|
Allocate a new compressed alphabet and score matrix.
Definition at line 4467 of file blast_stat.c. References ASSERT, BLASTAA_SIZE, SCompressedAlphabet::compress_table, SCompressedAlphabet::compressed_alphabet_size, s_BuildCompressedScoreMatrix(), s_BuildCompressedTranslation(), and SCompressedAlphabetFree(). Referenced by BlastCompressedAaLookupTableNew(). |
|
Deallocates a SPsiBlastScoreMatrix structure.
Definition at line 731 of file blast_stat.c. References _PSIDeallocateMatrix(), Blast_KarlinBlkFree(), SPsiBlastScoreMatrix::freq_ratios, SPsiBlastScoreMatrix::kbp, SBlastScoreMatrix::ncols, SPsiBlastScoreMatrix::pssm, SBlastScoreMatrixFree(), and sfree. Referenced by SPsiBlastScoreMatrixNew(). |
|
Allocates a new SPsiBlastScoreMatrix structure of dimensions ncols by BLASTAA_SIZE.
Definition at line 750 of file blast_stat.c. References _PSIAllocateMatrix(), Blast_KarlinBlkNew(), BLASTAA_SIZE, SPsiBlastScoreMatrix::freq_ratios, SPsiBlastScoreMatrix::kbp, SPsiBlastScoreMatrix::pssm, SBlastScoreMatrixNew(), and SPsiBlastScoreMatrixFree(). |
|
Initial value: { { 3, 2, 1.09, 0.31, 0.55, 2.0, -2, 99 }, { 2, 2, 1.07, 0.27, 0.49, 2.2, -3, 97 }, { 1, 2, 1.02, 0.21, 0.36, 2.8, -6, 92 }, { 0, 2, 0.80, 0.064, 0.17, 4.8, -16, 72 }, { 4, 1, 1.08, 0.28, 0.54, 2.0, -2, 98 }, { 3, 1, 1.06, 0.25, 0.46, 2.3, -4, 96 }, { 2, 1, 0.99, 0.17, 0.30, 3.3, -10, 90 } }
Definition at line 664 of file blast_stat.c. |
|
Initial value: { { 0, 0, 1.28, 0.46, 0.85, 1.5, -2, 96 }, { 2, 2, 1.33, 0.62, 1.1, 1.2, 0, 99 }, { 1, 2, 1.30, 0.52, 0.93, 1.4, -2, 97 }, { 0, 2, 1.19, 0.34, 0.66, 1.8, -3, 89 }, { 3, 1, 1.32, 0.57, 1.0, 1.3, -1, 99 }, { 2, 1, 1.29, 0.49, 0.92, 1.4, -1, 96 }, { 1, 1, 1.14, 0.26, 0.52, 2.2, -5, 85 } }
Definition at line 618 of file blast_stat.c. |
|
Initial value: { { 0, 0, 1.374, 0.711, 1.31, 1.05, 0, 100 }, { 2, 2, 1.37, 0.70, 1.2, 1.1, 0, 99 }, { 1, 2, 1.35, 0.64, 1.1, 1.2, -1, 98 }, { 0, 2, 1.25, 0.42, 0.83, 1.5, -2, 91 }, { 2, 1, 1.34, 0.60, 1.1, 1.2, -1, 97 }, { 1, 1, 1.21, 0.34, 0.71, 1.7, -2, 88 } }
Definition at line 596 of file blast_stat.c. |
|
Initial value: { { 0, 0, 1.383, 0.738, 1.36, 1.02, 0, 100 }, { 1, 2, 1.36, 0.67, 1.2, 1.1, 0, 98 }, { 0, 2, 1.26, 0.43, 0.90, 1.4, -1, 91 }, { 2, 1, 1.35, 0.61, 1.1, 1.2, -1, 98 }, { 1, 1, 1.22, 0.35, 0.72, 1.7, -3, 88 } }
Definition at line 575 of file blast_stat.c. |
|
Initial value: { { 0, 0, 1.39, 0.747, 1.38, 1.00, 0, 100 }, { 3, 3, 1.39, 0.747, 1.38, 1.00, 0, 100 } }
Definition at line 569 of file blast_stat.c. |
|
Initial value: { { 0, 0, 0.55, 0.21, 0.46, 1.2, -5, 87 }, { 4, 4, 0.63, 0.42, 0.84, 0.75, -2, 99 }, { 2, 4, 0.615, 0.37, 0.72, 0.85, -3, 97 }, { 0, 4, 0.55, 0.21, 0.46, 1.2, -5, 87 }, { 3, 3, 0.615, 0.37, 0.68, 0.9, -3, 97 }, { 6, 2, 0.63, 0.42, 0.84, 0.75, -2, 99 }, { 5, 2, 0.625, 0.41, 0.78, 0.8, -2, 99 }, { 4, 2, 0.61, 0.35, 0.68, 0.9, -3, 96 }, { 2, 2, 0.515, 0.14, 0.33, 1.55, -9, 81 } } These parameters can only be applied to even scores. Any odd score must be rounded down to the nearest even number before calculating the e-value. Definition at line 632 of file blast_stat.c. |
|
Initial value: { { 0, 0, 0.675, 0.65, 1.1, 0.6, -1, 99 }, { 2, 4, 0.67, 0.59, 1.1, 0.6, -1, 98 }, { 0, 4, 0.62, 0.39, 0.78, 0.8, -2, 91 }, { 4, 2, 0.67, 0.61, 1.0, 0.65, -2, 98 }, { 2, 2, 0.56, 0.32, 0.59, 0.95, -4, 82 } } These parameters can only be applied to even scores. Any odd score must be rounded down to the nearest even number before calculating the e-value. Definition at line 609 of file blast_stat.c. |
|
Initial value: { { 0, 0, 0.69, 0.73, 1.34, 0.515, 0, 100 }, { 2, 4, 0.68, 0.67, 1.2, 0.55, 0, 99 }, { 0, 4, 0.63, 0.43, 0.90, 0.7, -1, 91 }, { 4, 2, 0.675, 0.62, 1.1, 0.6, -1, 98 }, { 2, 2, 0.61, 0.35, 0.72, 1.7, -3, 88 } } These parameters can only be applied to even scores. Any odd score must be rounded down to the nearest even number before calculating the e-value. Definition at line 587 of file blast_stat.c. |
|
Initial value: { { 5, 5, 0.208, 0.030, 0.072, 2.9, -47, 77} }
Definition at line 675 of file blast_stat.c. |
|
Initial value: { { 6, 3, 0.389, 0.25, 0.56, 0.7, -5, 95}, { 5, 3, 0.375, 0.21, 0.47, 0.8, -6, 92}, { 4, 3, 0.351, 0.14, 0.35, 1.0, -9, 86}, { 6, 2, 0.362, 0.16, 0.45, 0.8, -4, 88}, { 5, 2, 0.330, 0.092, 0.28, 1.2, -13, 81}, { 4, 2, 0.281, 0.046, 0.16, 1.8, -23, 69} }
Definition at line 645 of file blast_stat.c. |
|
Initial value: { { 0, 0, 0.22, 0.061, 0.22, 1.0, -15, 74 }, { 6, 5, 0.28, 0.21, 0.47, 0.6 , -7, 93 }, { 5, 5, 0.27, 0.17, 0.39, 0.7, -9, 90 }, { 4, 5, 0.25, 0.10, 0.31, 0.8, -10, 83 }, { 3, 5, 0.23, 0.065, 0.25, 0.9, -11, 76 } }
Definition at line 655 of file blast_stat.c. |
|
Initial value: { { 10, 6, 0.163, 0.068, 0.16, 1.0, -19, 85 }, { 8, 6, 0.146, 0.039, 0.11, 1.3, -29, 76 } }
Definition at line 680 of file blast_stat.c. |
|
Initial value: { BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_BEST, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL }
Definition at line 185 of file blast_stat.c. Referenced by BlastLoadMatrixValues(). |
|
Initial value: { {(double) INT2_MAX, (double) INT2_MAX, (double) INT2_MAX, 0.2291, 0.0924, 0.2514, 0.9113, -5.7}, {13, 3, (double) INT2_MAX, 0.207, 0.049, 0.14, 1.5, -22}, {12, 3, (double) INT2_MAX, 0.199, 0.039, 0.11, 1.8, -34}, {11, 3, (double) INT2_MAX, 0.190, 0.031, 0.095, 2.0, -38}, {10, 3, (double) INT2_MAX, 0.179, 0.023, 0.075, 2.4, -51}, {16, 2, (double) INT2_MAX, 0.210, 0.051, 0.14, 1.5, -24}, {15, 2, (double) INT2_MAX, 0.203, 0.041, 0.12, 1.7, -31}, {14, 2, (double) INT2_MAX, 0.195, 0.032, 0.10, 1.9, -36}, {13, 2, (double) INT2_MAX, 0.185, 0.024, 0.084, 2.2, -45}, {12, 2, (double) INT2_MAX, 0.171, 0.016, 0.061, 2.8, -65}, {19, 1, (double) INT2_MAX, 0.205, 0.040, 0.11, 1.9, -43}, {18, 1, (double) INT2_MAX, 0.198, 0.032, 0.10, 2.0, -43}, {17, 1, (double) INT2_MAX, 0.189, 0.024, 0.079, 2.4, -57}, {16, 1, (double) INT2_MAX, 0.176, 0.016, 0.063, 2.8, -67}, } ) for BLOSUM45. Definition at line 168 of file blast_stat.c. Referenced by BlastLoadMatrixValues(). |
|
Initial value: { BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_BEST, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL }
Definition at line 223 of file blast_stat.c. Referenced by BlastLoadMatrixValues(). |
|
Initial value: { {(double) INT2_MAX, (double) INT2_MAX, (double) INT2_MAX, 0.2318, 0.112, 0.3362, 0.6895, -4.0}, {13, 3, (double) INT2_MAX, 0.212, 0.063, 0.19, 1.1, -16}, {12, 3, (double) INT2_MAX, 0.206, 0.055, 0.17, 1.2, -18}, {11, 3, (double) INT2_MAX, 0.197, 0.042, 0.14, 1.4, -25}, {10, 3, (double) INT2_MAX, 0.186, 0.031, 0.11, 1.7, -34}, {9, 3, (double) INT2_MAX, 0.172, 0.022, 0.082, 2.1, -48}, {16, 2, (double) INT2_MAX, 0.215, 0.066, 0.20, 1.05, -15}, {15, 2, (double) INT2_MAX, 0.210, 0.058, 0.17, 1.2, -20}, {14, 2, (double) INT2_MAX, 0.202, 0.045, 0.14, 1.4, -27}, {13, 2, (double) INT2_MAX, 0.193, 0.035, 0.12, 1.6, -32}, {12, 2, (double) INT2_MAX, 0.181, 0.025, 0.095, 1.9, -41}, {19, 1, (double) INT2_MAX, 0.212, 0.057, 0.18, 1.2, -21}, {18, 1, (double) INT2_MAX, 0.207, 0.050, 0.15, 1.4, -28}, {17, 1, (double) INT2_MAX, 0.198, 0.037, 0.12, 1.6, -33}, {16, 1, (double) INT2_MAX, 0.186, 0.025, 0.10, 1.9, -42}, {15, 1, (double) INT2_MAX, 0.171, 0.015, 0.063, 2.7, -76}, } ) for BLOSUM50. Definition at line 204 of file blast_stat.c. Referenced by BlastLoadMatrixValues(). |
|
Initial value: { BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_BEST, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, }
Definition at line 258 of file blast_stat.c. Referenced by BlastLoadMatrixValues(). |
|
Initial value: { {(double) INT2_MAX, (double) INT2_MAX, (double) INT2_MAX, 0.3176, 0.134, 0.4012, 0.7916, -3.2}, {11, 2, (double) INT2_MAX, 0.297, 0.082, 0.27, 1.1, -10}, {10, 2, (double) INT2_MAX, 0.291, 0.075, 0.23, 1.3, -15}, {9, 2, (double) INT2_MAX, 0.279, 0.058, 0.19, 1.5, -19}, {8, 2, (double) INT2_MAX, 0.264, 0.045, 0.15, 1.8, -26}, {7, 2, (double) INT2_MAX, 0.239, 0.027, 0.10, 2.5, -46}, {6, 2, (double) INT2_MAX, 0.201, 0.012, 0.061, 3.3, -58}, {13, 1, (double) INT2_MAX, 0.292, 0.071, 0.23, 1.2, -11}, {12, 1, (double) INT2_MAX, 0.283, 0.059, 0.19, 1.5, -19}, {11, 1, (double) INT2_MAX, 0.267, 0.041, 0.14, 1.9, -30}, {10, 1, (double) INT2_MAX, 0.243, 0.024, 0.10, 2.5, -44}, {9, 1, (double) INT2_MAX, 0.206, 0.010, 0.052, 4.0, -87}, } ) for BLOSUM62. Definition at line 243 of file blast_stat.c. Referenced by BlastLoadMatrixValues(). |
|
Initial value: { BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_BEST, BLAST_MATRIX_NOMINAL }
Definition at line 288 of file blast_stat.c. Referenced by BlastLoadMatrixValues(). |
|
Initial value: { {(double) INT2_MAX, (double) INT2_MAX, (double) INT2_MAX, 0.3430, 0.177, 0.6568, 0.5222, -1.6}, {25, 2, (double) INT2_MAX, 0.342, 0.17, 0.66, 0.52, -1.6}, {13, 2, (double) INT2_MAX, 0.336, 0.15, 0.57, 0.59, -3}, {9, 2, (double) INT2_MAX, 0.319, 0.11, 0.42, 0.76, -6}, {8, 2, (double) INT2_MAX, 0.308, 0.090, 0.35, 0.89, -9}, {7, 2, (double) INT2_MAX, 0.293, 0.070, 0.27, 1.1, -14}, {6, 2, (double) INT2_MAX, 0.268, 0.045, 0.19, 1.4, -19}, {11, 1, (double) INT2_MAX, 0.314, 0.095, 0.35, 0.90, -9}, {10, 1, (double) INT2_MAX, 0.299, 0.071, 0.27, 1.1, -14}, {9, 1, (double) INT2_MAX, 0.279, 0.048, 0.20, 1.4, -19}, } ) for BLOSUM80. Definition at line 275 of file blast_stat.c. Referenced by BlastLoadMatrixValues(). |
|
Initial value: { BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_BEST, BLAST_MATRIX_NOMINAL }
Definition at line 313 of file blast_stat.c. Referenced by BlastLoadMatrixValues(). |
|
Initial value: { {(double) INT2_MAX, (double) INT2_MAX, (double) INT2_MAX, 0.3346, 0.190, 0.7547, 0.4434, -1.4}, {9, 2, (double) INT2_MAX, 0.310, 0.12, 0.46, 0.67, -6}, {8, 2, (double) INT2_MAX, 0.300, 0.099, 0.39, 0.76, -7}, {7, 2, (double) INT2_MAX, 0.283, 0.072, 0.30, 0.93, -11}, {6, 2, (double) INT2_MAX, 0.259, 0.048, 0.22, 1.2, -16}, {11, 1, (double) INT2_MAX, 0.302, 0.093, 0.39, 0.78, -8}, {10, 1, (double) INT2_MAX, 0.290, 0.075, 0.28, 1.04, -15}, {9, 1, (double) INT2_MAX, 0.265, 0.044, 0.20, 1.3, -19}, } ) for BLOSUM90. Definition at line 302 of file blast_stat.c. Referenced by BlastLoadMatrixValues(). |
|
Initial value: { { 'A', 25.00 }, { 'C', 25.00 }, { 'G', 25.00 }, { 'T', 25.00 } }
Definition at line 1467 of file blast_stat.c. |
|
Initial value: { BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_BEST, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL }
Definition at line 344 of file blast_stat.c. Referenced by BlastLoadMatrixValues(). |
|
Initial value: { {(double) INT2_MAX, (double) INT2_MAX, (double) INT2_MAX, 0.2252, 0.0868, 0.2223, 0.98, -5.0}, {15, 3, (double) INT2_MAX, 0.205, 0.049, 0.13, 1.6, -23}, {14, 3, (double) INT2_MAX, 0.200, 0.043, 0.12, 1.7, -26}, {13, 3, (double) INT2_MAX, 0.194, 0.036, 0.10, 1.9, -31}, {12, 3, (double) INT2_MAX, 0.186, 0.029, 0.085, 2.2, -41}, {11, 3, (double) INT2_MAX, 0.174, 0.020, 0.070, 2.5, -48}, {17, 2, (double) INT2_MAX, 0.204, 0.047, 0.12, 1.7, -28}, {16, 2, (double) INT2_MAX, 0.198, 0.038, 0.11, 1.8, -29}, {15, 2, (double) INT2_MAX, 0.191, 0.031, 0.087, 2.2, -44}, {14, 2, (double) INT2_MAX, 0.182, 0.024, 0.073, 2.5, -53}, {13, 2, (double) INT2_MAX, 0.171, 0.017, 0.059, 2.9, -64}, {21, 1, (double) INT2_MAX, 0.205, 0.045, 0.11, 1.8, -34}, {20, 1, (double) INT2_MAX, 0.199, 0.037, 0.10, 1.9, -35}, {19, 1, (double) INT2_MAX, 0.192, 0.029, 0.083, 2.3, -52}, {18, 1, (double) INT2_MAX, 0.183, 0.021, 0.070, 2.6, -60}, {17, 1, (double) INT2_MAX, 0.171, 0.014, 0.052, 3.3, -86}, } ) for PAM250. Definition at line 325 of file blast_stat.c. Referenced by BlastLoadMatrixValues(). |
|
Initial value: { BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_BEST, BLAST_MATRIX_NOMINAL, }
Definition at line 374 of file blast_stat.c. |
|
Initial value: { {(double) INT2_MAX, (double) INT2_MAX, (double) INT2_MAX, 0.3400, 0.283, 1.754, 0.1938, -0.3}, {7, 2, (double) INT2_MAX, 0.305, 0.15, 0.87, 0.35, -3}, {6, 2, (double) INT2_MAX, 0.287, 0.11, 0.68, 0.42, -4}, {5, 2, (double) INT2_MAX, 0.264, 0.079, 0.45, 0.59, -7}, {10, 1, (double) INT2_MAX, 0.309, 0.15, 0.88, 0.35, -3}, {9, 1, (double) INT2_MAX, 0.294, 0.11, 0.61, 0.48, -6}, {8, 1, (double) INT2_MAX, 0.270, 0.072, 0.40, 0.68, -10}, } ) for PAM30. Definition at line 364 of file blast_stat.c. Referenced by BlastLoadMatrixValues(). |
|
Initial value: { BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_NOMINAL, BLAST_MATRIX_BEST, BLAST_MATRIX_NOMINAL }
Definition at line 396 of file blast_stat.c. |
|
Initial value: { {(double) INT2_MAX, (double) INT2_MAX, (double) INT2_MAX, 0.3345, 0.229, 1.029, 0.3250, -0.7}, {8, 2, (double) INT2_MAX, 0.301, 0.12, 0.54, 0.56, -5}, {7, 2, (double) INT2_MAX, 0.286, 0.093, 0.43, 0.67, -7}, {6, 2, (double) INT2_MAX, 0.264, 0.064, 0.29, 0.90, -12}, {11, 1, (double) INT2_MAX, 0.305, 0.12, 0.52, 0.59, -6}, {10, 1, (double) INT2_MAX, 0.291, 0.091, 0.41, 0.71, -9}, {9, 1, (double) INT2_MAX, 0.270, 0.060, 0.28, 0.97, -14}, } ) for PAM70. Definition at line 386 of file blast_stat.c. |
|
Initial value:
"$Id: blast_stat.c 144802 2008-11-03 20:57:20Z camacho $"
Definition at line 52 of file blast_stat.c. |
|
Initial value: { { 'A', 78.05 }, { 'C', 19.25 }, { 'D', 53.64 }, { 'E', 62.95 }, { 'F', 38.56 }, { 'G', 73.77 }, { 'H', 21.99 }, { 'I', 51.42 }, { 'K', 57.44 }, { 'L', 90.19 }, { 'M', 22.43 }, { 'N', 44.87 }, { 'P', 52.03 }, { 'Q', 42.64 }, { 'R', 51.29 }, { 'S', 71.20 }, { 'T', 58.41 }, { 'V', 64.41 }, { 'W', 13.30 }, { 'Y', 32.16 } }
Definition at line 1442 of file blast_stat.c. |
|
23-to-10 letter compressed alphabet. Based on SE-V(10) Definition at line 4462 of file blast_stat.c. |
|
23-to-15 letter compressed alphabet. Based on SE_B(14) Definition at line 4464 of file blast_stat.c. |