r229: a new way to prevent out-of-band backtrack

This commit is contained in:
Heng Li
2017-07-29 23:52:30 -04:00
parent fa99d28d34
commit 5934d68772
7 changed files with 47 additions and 61 deletions
+17 -5
View File
@@ -39,8 +39,8 @@ typedef struct {
* @param mat m*m scoring mattrix in one-dimension array
* @param gapo gap open penalty; a gap of length l cost "-(gapo+l*gape)"
* @param gape gap extension penalty
* @param w band width
* @param zdrop off-diagonal drop-off to stop extension (positive)
* @param w band width (<0 to disable)
* @param zdrop off-diagonal drop-off to stop extension (positive; <0 to disable)
* @param flag flag (see KSW_EZ_* macros)
* @param ez (out) scores and cigar
*/
@@ -53,6 +53,8 @@ void ksw_extd(void *km, int qlen, const uint8_t *query, int tlen, const uint8_t
void ksw_extd2_sse(void *km, int qlen, const uint8_t *query, int tlen, const uint8_t *target, int8_t m, const int8_t *mat,
int8_t gapo, int8_t gape, int8_t gapo2, int8_t gape2, int w, int zdrop, int flag, ksw_extz_t *ez);
void ksw_extf2_sse(void *km, int qlen, const uint8_t *query, int tlen, const uint8_t *target, int8_t mch, int8_t mis, int8_t e, int w, int xdrop, ksw_extz_t *ez);
/**
* Global alignment
*
@@ -104,16 +106,26 @@ static inline uint32_t *ksw_push_cigar(void *km, int *n_cigar, int *m_cigar, uin
// bit 0-2: which type gets the max - 0 for H, 1 for E, 2 for F, 3 for \tilde{E} and 4 for \tilde{F}
// bit 3/0x08: 1 if a continuation on the E state (bit 5/0x20 for a continuation on \tilde{E})
// bit 4/0x10: 1 if a continuation on the F state (bit 6/0x40 for a continuation on \tilde{F})
static inline void ksw_backtrack(void *km, int is_rot, int is_rev, const uint8_t *p, const int *off, int n_col, int i0, int j0, int *m_cigar_, int *n_cigar_, uint32_t **cigar_)
static inline void ksw_backtrack(void *km, int is_rot, int is_rev, const uint8_t *p, const int *off, const int *off_end, int n_col, int i0, int j0, int *m_cigar_, int *n_cigar_, uint32_t **cigar_)
{ // p[] - lower 3 bits: which type gets the max; bit
int n_cigar = 0, m_cigar = *m_cigar_, i = i0, j = j0, r, state = 0;
uint32_t *cigar = *cigar_, tmp;
while (i >= 0 && j >= 0) { // at the beginning of the loop, _state_ tells us which state to check
if (is_rot) r = i + j, tmp = p[r * n_col + i - off[r]];
else tmp = p[i * n_col + j - off[i]];
int force_state = -1;
if (is_rot) {
r = i + j;
if (i < off[r]) force_state = 2;
if (off_end && i > off_end[r]) force_state = 1;
tmp = force_state < 0? p[r * n_col + i - off[r]] : 0;
} else {
if (j < off[i]) force_state = 2;
if (off_end && j > off_end[i]) force_state = 1;
tmp = force_state < 0? p[i * n_col + j - off[i]] : 0;
}
if (state == 0) state = tmp & 7; // if requesting the H state, find state one maximizes it.
else if (!(tmp >> (state + 2) & 1)) state = 0; // if requesting other states, _state_ stays the same if it is a continuation; otherwise, set to H
if (state == 0) state = tmp & 7; // TODO: probably this line can be merged into the "else if" line right above; not 100% sure
if (force_state >= 0) state = force_state;
if (state == 0) cigar = ksw_push_cigar(km, &n_cigar, &m_cigar, cigar, 0, 1), --i, --j; // match
else if (state == 1 || state == 3) cigar = ksw_push_cigar(km, &n_cigar, &m_cigar, cigar, 2, 1), --i; // deletion
else cigar = ksw_push_cigar(km, &n_cigar, &m_cigar, cigar, 1, 1), --j; // insertion