fork/minimap2
1
0
Fork 0
mirror of https://github.com/lh3/minimap2.git synced 2026-10-01 10:28:11 +08:00
Code Issues Packages Projects Releases Wiki Activity

r512: option to filter poorly aligned reads

Browse Source
This commit is contained in:
Heng Li
2017-10-16 10:38:22 -04:00
parent 858213d513
commit e6f525edaf
8 changed files with 131 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files
align.c
+37 -19
View File
@@ -117,7 +117,7 @@ static void mm_fix_cigar(mm_reg1_t *r, const uint8_t *qseq, const uint8_t *tseq,
}
}
static void mm_update_extra(mm_reg1_t *r, const uint8_t *qseq, const uint8_t *tseq, const int8_t *mat, int8_t q, int8_t e)
static void mm_update_extra(mm_reg1_t *r, const uint8_t *qseq, const uint8_t *qual, const uint8_t *tseq, const int8_t *mat, int8_t q, int8_t e)
{
uint32_t k, l, toff = 0, qoff = 0;
int32_t s = 0, max = 0, qshift, tshift;
@@ -128,21 +128,30 @@ static void mm_update_extra(mm_reg1_t *r, const uint8_t *qseq, const uint8_t *ts
for (k = 0; k < p->n_cigar; ++k) {
uint32_t op = p->cigar[k]&0xf, len = p->cigar[k]>>4;
if (op == 0) { // match/mismatch
int n_ambi = 0, n_diff = 0;
float n_diff2 = 0.0f;
for (l = 0; l < len; ++l) {
int cq = qseq[qoff + l], ct = tseq[toff + l];
if (ct > 3 || cq > 3) ++p->n_ambi;
else if (ct != cq) ++p->n_diff;
if (ct > 3 || cq > 3) ++n_ambi;
else if (ct != cq) {
++n_diff;
n_diff2 += qual == 0 || qual[qoff + l] >= 20? 1.0f : .05f * qual[qoff + l];
}
s += mat[ct * 5 + cq];
if (s < 0) s = 0;
else max = max > s? max : s;
}
p->n_ambi += n_ambi;
p->n_diff += n_diff;
toff += len, qoff += len, p->blen += len;
p->n_diff2 += n_diff2, p->blen2 += len - n_ambi;
} else if (op == 1) { // insertion
int n_ambi = 0;
for (l = 0; l < len; ++l)
if (qseq[qoff + l] > 3) ++n_ambi;
qoff += len, p->blen += len;
p->n_ambi += n_ambi, p->n_diff += len - n_ambi;
p->n_diff2 += 1.0f, ++p->blen2;
s -= q + e * len;
if (s < 0) s = 0;
} else if (op == 2) { // deletion
@@ -151,6 +160,7 @@ static void mm_update_extra(mm_reg1_t *r, const uint8_t *qseq, const uint8_t *ts
if (tseq[toff + l] > 3) ++n_ambi;
toff += len, p->blen += len;
p->n_ambi += n_ambi, p->n_diff += len - n_ambi;
p->n_diff2 += 1.0f, ++p->blen2;
s -= q + e * len;
if (s < 0) s = 0;
} else if (op == 3) { // intron
@@ -335,7 +345,7 @@ static void mm_max_stretch(const mm_mapopt_t *opt, const mm_reg1_t *r, const mm1
*as = max_i, *cnt = max_len;
}
static void mm_align1(void *km, const mm_mapopt_t *opt, const mm_idx_t *mi, int qlen, uint8_t *qseq0[2], mm_reg1_t *r, mm_reg1_t *r2, int n_a, mm128_t *a, ksw_extz_t *ez, int splice_flag)
static void mm_align1(void *km, const mm_mapopt_t *opt, const mm_idx_t *mi, int qlen, uint8_t *qseq0[2], uint8_t *qual0[2], mm_reg1_t *r, mm_reg1_t *r2, int n_a, mm128_t *a, ksw_extz_t *ez, int splice_flag)
{
int is_sr = !!(opt->flag & MM_F_SR), is_splice = !!(opt->flag & MM_F_SPLICE);
int32_t rid = a[r->as].x<<1>>33, rev = a[r->as].x>>63, as1, cnt1;
@@ -381,10 +391,10 @@ static void mm_align1(void *km, const mm_mapopt_t *opt, const mm_idx_t *mi, int
if (is_sr) {
qs0 = 0, qe0 = qlen;
l = qs;
l += l * opt->a > opt->q? (l * opt->a - opt->q) / opt->e : 0;
l += l * opt->a + opt->end_bonus > opt->q? (l * opt->a + opt->end_bonus - opt->q) / opt->e : 0;
rs0 = rs - l > 0? rs - l : 0;
l = qlen - qe;
l += l * opt->a > opt->q? (l * opt->a - opt->q) / opt->e : 0;
l += l * opt->a + opt->end_bonus > opt->q? (l * opt->a + opt->end_bonus - opt->q) / opt->e : 0;
re0 = re + l < mi->seq[rid].len? re + l : mi->seq[rid].len;
} else {
// compute rs0 and qs0
@@ -523,7 +533,7 @@ static void mm_align1(void *km, const mm_mapopt_t *opt, const mm_idx_t *mi, int
assert(re1 - rs1 <= re0 - rs0);
if (r->p) {
mm_idx_getseq(mi, rid, rs1, re1, tseq);
mm_update_extra(r, &qseq0[r->rev][qs1], tseq, mat, opt->q, opt->e);
mm_update_extra(r, &qseq0[r->rev][qs1], qual0[r->rev]? &qual0[r->rev][qs1] : 0, tseq, mat, opt->q, opt->e);
if (rev && r->p->trans_strand)
r->p->trans_strand ^= 3; // flip to the read strand
}
@@ -531,10 +541,10 @@ static void mm_align1(void *km, const mm_mapopt_t *opt, const mm_idx_t *mi, int
kfree(km, tseq);
}
static int mm_align1_inv(void *km, const mm_mapopt_t *opt, const mm_idx_t *mi, int qlen, uint8_t *qseq0[2], const mm_reg1_t *r1, const mm_reg1_t *r2, mm_reg1_t *r_inv, ksw_extz_t *ez)
static int mm_align1_inv(void *km, const mm_mapopt_t *opt, const mm_idx_t *mi, int qlen, uint8_t *qseq0[2], uint8_t *qual0[2], const mm_reg1_t *r1, const mm_reg1_t *r2, mm_reg1_t *r_inv, ksw_extz_t *ez)
{
int tl, ql, score, ret = 0, q_off, t_off;
uint8_t *tseq, *qseq;
uint8_t *tseq, *qseq, *qual;
int8_t mat[25];
void *qp;
@@ -552,6 +562,7 @@ static int mm_align1_inv(void *km, const mm_mapopt_t *opt, const mm_idx_t *mi, i
tseq = (uint8_t*)kmalloc(km, tl);
mm_idx_getseq(mi, r1->rid, r1->re, r2->rs, tseq);
qseq = &qseq0[!r1->rev][qlen - r2->qs];
qual = qual0[!r1->rev]? &qseq0[!r1->rev][qlen - r2->qs] : 0;
mm_seq_rev(ql, qseq);
mm_seq_rev(tl, tseq);
@@ -573,7 +584,7 @@ static int mm_align1_inv(void *km, const mm_mapopt_t *opt, const mm_idx_t *mi, i
r_inv->rid = r1->rid;
r_inv->qs = r1->qe + q_off, r_inv->qe = r_inv->qs + ez->max_q + 1;
r_inv->rs = r1->re + t_off, r_inv->re = r_inv->rs + ez->max_t + 1;
mm_update_extra(r_inv, qseq + q_off, tseq + t_off, mat, opt->q, opt->e);
mm_update_extra(r_inv, &qseq[q_off], qual? &qual[q_off] : 0, &tseq[t_off], mat, opt->q, opt->e);
ret = 1;
end_align1_inv:
kfree(km, tseq);
@@ -590,20 +601,26 @@ static inline mm_reg1_t *mm_insert_reg(const mm_reg1_t *r, int i, int *n_regs, m
return regs;
}
mm_reg1_t *mm_align_skeleton(void *km, const mm_mapopt_t *opt, const mm_idx_t *mi, int qlen, const char *qstr, int *n_regs_, mm_reg1_t *regs, mm128_t *a)
mm_reg1_t *mm_align_skeleton(void *km, const mm_mapopt_t *opt, const mm_idx_t *mi, int qlen, const char *qstr, const char *qual, int *n_regs_, mm_reg1_t *regs, mm128_t *a)
{
extern unsigned char seq_nt4_table[256];
int32_t i, n_regs = *n_regs_, n_a;
uint8_t *qseq0[2];
uint8_t *qseq0[2], *qual0[2];
ksw_extz_t ez;
// encode the query sequence
qseq0[0] = (uint8_t*)kmalloc(km, qlen);
qseq0[1] = (uint8_t*)kmalloc(km, qlen);
qseq0[0] = (uint8_t*)kmalloc(km, qlen * 2);
qseq0[1] = qseq0[0] + qlen;
for (i = 0; i < qlen; ++i) {
qseq0[0][i] = seq_nt4_table[(uint8_t)qstr[i]];
qseq0[1][qlen - 1 - i] = qseq0[0][i] < 4? 3 - qseq0[0][i] : 4;
}
if (qual) {
qual0[0] = (uint8_t*)kmalloc(km, qlen * 2);
qual0[1] = qual0[0] + qlen;
for (i = 0; i < qlen; ++i)
qual0[0][i] = qual0[1][qlen - 1 - i] = qual[i] - 33;
} else qual0[0] = qual0[1] = 0;
// align through seed hits
n_a = mm_squeeze_a(km, n_regs, regs, a);
@@ -614,8 +631,8 @@ mm_reg1_t *mm_align_skeleton(void *km, const mm_mapopt_t *opt, const mm_idx_t *m
mm_reg1_t s[2], s2[2];
int which, trans_strand;
s[0] = s[1] = regs[i];
mm_align1(km, opt, mi, qlen, qseq0, &s[0], &s2[0], n_a, a, &ez, MM_F_SPLICE_FOR);
mm_align1(km, opt, mi, qlen, qseq0, &s[1], &s2[1], n_a, a, &ez, MM_F_SPLICE_REV);
mm_align1(km, opt, mi, qlen, qseq0, qual0, &s[0], &s2[0], n_a, a, &ez, MM_F_SPLICE_FOR);
mm_align1(km, opt, mi, qlen, qseq0, qual0, &s[1], &s2[1], n_a, a, &ez, MM_F_SPLICE_REV);
if (s[0].p->dp_score > s[1].p->dp_score) which = 0, trans_strand = 1;
else if (s[0].p->dp_score < s[1].p->dp_score) which = 1, trans_strand = 2;
else trans_strand = 3, which = (qlen + s[0].p->dp_score) & 1; // randomly choose a strand, effectively
@@ -628,20 +645,21 @@ mm_reg1_t *mm_align_skeleton(void *km, const mm_mapopt_t *opt, const mm_idx_t *m
}
regs[i].p->trans_strand = trans_strand;
} else { // one round of alignment
mm_align1(km, opt, mi, qlen, qseq0, &regs[i], &r2, n_a, a, &ez, opt->flag);
mm_align1(km, opt, mi, qlen, qseq0, qual0, &regs[i], &r2, n_a, a, &ez, opt->flag);
if (opt->flag&MM_F_SPLICE)
regs[i].p->trans_strand = opt->flag&MM_F_SPLICE_FOR? 1 : 2;
}
if (r2.cnt > 0) regs = mm_insert_reg(&r2, i, &n_regs, regs);
if (!(opt->flag&MM_F_SPLICE) && !(opt->flag&MM_F_SR) && i > 0) { // don't try inversion alignment for -xsplice or -xsr
if (mm_align1_inv(km, opt, mi, qlen, qseq0, &regs[i-1], &regs[i], &r2, &ez)) {
if (mm_align1_inv(km, opt, mi, qlen, qseq0, qual0, &regs[i-1], &regs[i], &r2, &ez)) {
regs = mm_insert_reg(&r2, i, &n_regs, regs);
++i; // skip the inserted INV alignment
}
}
}
*n_regs_ = n_regs;
kfree(km, qseq0[0]); kfree(km, qseq0[1]);
kfree(km, qseq0[0]);
if (qual0[0]) kfree(km, qual0[0]);
kfree(km, ez.cigar);
mm_filter_regs(km, opt, n_regs_, regs);
mm_hit_sort_by_dp(km, n_regs_, regs);