r1161: merged the simple and complex models

This commit is contained in:
Heng Li
2023-04-06 23:42:50 -04:00
parent 7ced0f16a0
commit 1834b1fd42
3 changed files with 14 additions and 44 deletions
+9 -39
View File
@@ -68,7 +68,6 @@ void ksw_exts2_sse(void *km, int qlen, const uint8_t *query, int tlen, const uin
uint8_t *qr, *sf, *mem, *mem2 = 0;
__m128i q_, q2_, qe_, zero_, sc_mch_, sc_mis_, sc_N_, m1_;
__m128i *u, *v, *x, *y, *x2, *s, *p = 0, *donor, *acceptor;
const int sp0[4] = { 8, 15, 21, 30 };
ksw_reset_extz(ez);
if (m <= 1 || qlen <= 0 || tlen <= 0 || q2 <= q + e) return;
@@ -119,45 +118,16 @@ void ksw_exts2_sse(void *km, int qlen, const uint8_t *query, int tlen, const uin
memcpy(sf, target, tlen);
// set the donor and acceptor arrays. TODO: this assumes 0/1/2/3 encoding!
if ((flag & (KSW_EZ_SPLICE_FOR|KSW_EZ_SPLICE_REV)) && !(flag & KSW_EZ_SPLICE_CMPLX)) {
int semi_cost = flag&KSW_EZ_SPLICE_FLANK? -noncan/2 : 0; // GTr or yAG is worth 0.5 bit; see PMID:18688272
memset(donor, -noncan, tlen_ * 16);
memset(acceptor, -noncan, tlen_ * 16);
if (!(flag & KSW_EZ_REV_CIGAR)) {
for (t = 0; t < tlen - 4; ++t) {
int can_type = 0; // type of canonical site: 0=none, 1=GT/AG only, 2=GTr/yAG
if ((flag & KSW_EZ_SPLICE_FOR) && target[t+1] == 2 && target[t+2] == 3) can_type = 1; // GTr...
if ((flag & KSW_EZ_SPLICE_REV) && target[t+1] == 1 && target[t+2] == 3) can_type = 1; // CTr...
if (can_type && (target[t+3] == 0 || target[t+3] == 2)) can_type = 2;
if (can_type) ((int8_t*)donor)[t] = can_type == 2? 0 : semi_cost;
}
for (t = 2; t < tlen; ++t) {
int can_type = 0;
if ((flag & KSW_EZ_SPLICE_FOR) && target[t-1] == 0 && target[t] == 2) can_type = 1; // ...yAG
if ((flag & KSW_EZ_SPLICE_REV) && target[t-1] == 0 && target[t] == 1) can_type = 1; // ...yAC
if (can_type && (target[t-2] == 1 || target[t-2] == 3)) can_type = 2;
if (can_type) ((int8_t*)acceptor)[t] = can_type == 2? 0 : semi_cost;
}
} else {
for (t = 0; t < tlen - 4; ++t) {
int can_type = 0; // type of canonical site: 0=none, 1=GT/AG only, 2=GTr/yAG
if ((flag & KSW_EZ_SPLICE_FOR) && target[t+1] == 2 && target[t+2] == 0) can_type = 1; // GAy...
if ((flag & KSW_EZ_SPLICE_REV) && target[t+1] == 1 && target[t+2] == 0) can_type = 1; // CAy...
if (can_type && (target[t+3] == 1 || target[t+3] == 3)) can_type = 2;
if (can_type) ((int8_t*)donor)[t] = can_type == 2? 0 : semi_cost;
}
for (t = 2; t < tlen; ++t) {
int can_type = 0;
if ((flag & KSW_EZ_SPLICE_FOR) && target[t-1] == 3 && target[t] == 2) can_type = 1; // ...rTG
if ((flag & KSW_EZ_SPLICE_REV) && target[t-1] == 3 && target[t] == 1) can_type = 1; // ...rTC
if (can_type && (target[t-2] == 0 || target[t-2] == 2)) can_type = 2;
if (can_type) ((int8_t*)acceptor)[t] = can_type == 2? 0 : semi_cost;
}
}
} else if (flag & (KSW_EZ_SPLICE_FOR|KSW_EZ_SPLICE_REV)) { // use the complex splice model
if (flag & (KSW_EZ_SPLICE_FOR|KSW_EZ_SPLICE_REV)) {
const int sp0[4] = { 8, 15, 21, 30 };
int sp[4];
for (t = 0; t < 4; ++t)
sp[t] = (int)((double)sp0[t] / 4. + .499);
if (flag & KSW_EZ_SPLICE_CMPLX) {
for (t = 0; t < 4; ++t)
sp[t] = (int)((double)sp0[t] / 4. + .499);
} else {
sp[0] = flag&KSW_EZ_SPLICE_FLANK? noncan / 2 : 0;
sp[1] = sp[2] = sp[3] = noncan;
}
memset(donor, -sp[3], tlen_ * 16);
memset(acceptor, -sp[3], tlen_ * 16);
if (!(flag & KSW_EZ_REV_CIGAR)) {