more accurate SAM flag

This commit is contained in:
Heng Li 2017-10-05 10:59:38 -04:00
parent 7cc4f6f965
commit 5ab99eb26e
5 changed files with 30 additions and 16 deletions

View File

@ -240,9 +240,10 @@ static void sam_write_sq(kstring_t *s, char *seq, int l, int rev, int comp)
} else str_copy(s, seq, seq + l);
}
void mm_write_sam2(kstring_t *s, const mm_idx_t *mi, const mm_bseq1_t *t, int seg_idx, int reg_idx, int n_seg, const int *n_regss, const mm_reg1_t *const* regss, void *km)
void mm_write_sam2(kstring_t *s, const mm_idx_t *mi, const mm_bseq1_t *t, int seg_idx, int reg_idx, int n_seg, const int *n_regss, const mm_reg1_t *const* regss, void *km, int opt_flag)
{
int flag = n_seg > 1? 0x1 : 0x0, n_regs = n_regss[seg_idx];
int flag, n_regs = n_regss[seg_idx];
int next_sid = n_seg > 1? (seg_idx + 1) % n_seg : -1;
const mm_reg1_t *regs = regss[seg_idx];
const mm_reg1_t *r = n_regs > 0 && reg_idx < n_regs && reg_idx >= 0? &regs[reg_idx] : NULL;
@ -251,19 +252,28 @@ void mm_write_sam2(kstring_t *s, const mm_idx_t *mi, const mm_bseq1_t *t, int se
mm_sprintf_lite(s, "%s", t->name);
if (n_seg > 1) s->l = mm_qname_len(t->name); // trim the suffix like /1 or /2
// write up to CIGAR
// write flag
flag = n_seg > 1? 0x1 : 0x0;
if (n_seg > 1) {
if (r && r->proper_frag) flag |= 0x2; // FIXME: this doesn't work when there are more than 2 segments
if (seg_idx == 0) flag |= 0x40;
else if (seg_idx == n_seg - 1) flag |= 0x80;
if (n_regss[next_sid] == 0) flag |= 0x8;
}
if (r == 0) {
mm_sprintf_lite(s, "\t4\t*\t0\t0\t*\t");
flag |= 0x4;
} else {
if (r->rev) flag |= 0x10;
if (r->parent != r->id) flag |= 0x100;
else if (!r->sam_pri) flag |= 0x800;
if (n_seg > 1) {
if (seg_idx == 0) flag |= 0x40;
else if (seg_idx == n_seg - 1) flag |= 0x80;
// TODO: set 0x2!!!
}
mm_sprintf_lite(s, "\t%d\t%s\t%d\t%d\t", flag, mi->seq[r->rid].name, r->rs+1, r->mapq);
}
mm_sprintf_lite(s, "\t%d", flag);
// write up to CIGAR
if (r == 0) {
mm_sprintf_lite(s, "\t*\t0\t0\t*\t");
} else {
mm_sprintf_lite(s, "\t%s\t%d\t%d\t", mi->seq[r->rid].name, r->rs+1, r->mapq);
if (r->p) { // actually this should always be true for SAM output
uint32_t k, clip_len = r->rev? t->l_seq - r->qe : r->qs;
int clip_char = (flag&0x800)? 'H' : 'S';
@ -332,6 +342,8 @@ void mm_write_sam2(kstring_t *s, const mm_idx_t *mi, const mm_bseq1_t *t, int se
}
}
}
if (r->p && (opt_flag & MM_F_OUT_CS))
write_cs(km, s, mi, t, r, MM_F_CS_NO_EQUAL);
}
s->s[s->l] = 0; // we always have room for an extra byte (see str_enlarge)
@ -342,5 +354,5 @@ void mm_write_sam(kstring_t *s, const mm_idx_t *mi, const mm_bseq1_t *t, const m
int i;
for (i = 0; i < n_regs; ++i)
if (r == &regs[i]) break;
mm_write_sam2(s, mi, t, 0, i, 1, &n_regs, &regs, NULL);
mm_write_sam2(s, mi, t, 0, i, 1, &n_regs, &regs, NULL, 0);
}

4
map.c
View File

@ -458,13 +458,13 @@ static void *worker_pipeline(void *shared, int step, void *in)
if ((p->opt->flag & MM_F_NO_PRINT_2ND) && r->id != r->parent)
continue;
if (p->opt->flag & MM_F_OUT_SAM)
mm_write_sam2(&p->str, mi, t, i - seg_st, j, s->n_seg[k], &s->n_reg[seg_st], (const mm_reg1_t*const*)&s->reg[seg_st], km);
mm_write_sam2(&p->str, mi, t, i - seg_st, j, s->n_seg[k], &s->n_reg[seg_st], (const mm_reg1_t*const*)&s->reg[seg_st], km, p->opt->flag);
else
mm_write_paf(&p->str, mi, t, r, km, p->opt->flag);
puts(p->str.s);
}
if (s->n_reg[i] == 0 && (p->opt->flag & MM_F_OUT_SAM)) {
mm_write_sam2(&p->str, mi, t, i - seg_st, -1, s->n_seg[k], &s->n_reg[seg_st], (const mm_reg1_t*const*)&s->reg[seg_st], km);
mm_write_sam2(&p->str, mi, t, i - seg_st, -1, s->n_seg[k], &s->n_reg[seg_st], (const mm_reg1_t*const*)&s->reg[seg_st], km, p->opt->flag);
puts(p->str.s);
}
}

View File

@ -69,8 +69,9 @@ typedef struct {
int32_t parent, subsc; // parent==id if primary; best alternate mapping score
int32_t as; // offset in the a[] array (for internal uses only)
int32_t fuzzy_mlen, fuzzy_blen; // seeded exact match length; seeded alignment block length (approximate)
uint32_t mapq:8, split:2, sam_pri:1, n_sub:21; // mapQ; split pattern; if SAM primary; number of suboptimal mappings
uint32_t hash, dummy;
uint32_t mapq:8, split:2, n_sub:22; // mapQ; split pattern; number of suboptimal mappings
uint32_t sam_pri:1, proper_frag:1, dummy:30;
uint32_t hash;
mm_extra_t *p;
} mm_reg1_t;

View File

@ -57,7 +57,7 @@ void mm_sketch(void *km, const char *str, int len, int w, int k, uint32_t rid, i
void mm_write_sam_hdr(const mm_idx_t *mi, const char *rg, const char *ver, int argc, char *argv[]);
void mm_write_paf(kstring_t *s, const mm_idx_t *mi, const mm_bseq1_t *t, const mm_reg1_t *r, void *km, int opt_flag);
void mm_write_sam(kstring_t *s, const mm_idx_t *mi, const mm_bseq1_t *t, const mm_reg1_t *r, int n_regs, const mm_reg1_t *regs);
void mm_write_sam2(kstring_t *s, const mm_idx_t *mi, const mm_bseq1_t *t, int seg_idx, int reg_idx, int n_seg, const int *n_regs, const mm_reg1_t *const* regs, void *km);
void mm_write_sam2(kstring_t *s, const mm_idx_t *mi, const mm_bseq1_t *t, int seg_idx, int reg_idx, int n_seg, const int *n_regs, const mm_reg1_t *const* regs, void *km, int opt_flag);
void mm_idxopt_init(mm_idxopt_t *opt);
const uint64_t *mm_idx_get(const mm_idx_t *mi, uint64_t minier, int *n);

1
pe.c
View File

@ -115,6 +115,7 @@ void mm_pair(void *km, int max_gap_ref, int pe_bonus, int sub_diff, int match_sc
int n_sub = 0, mapq_pe;
mm_reg1_t *r[2];
r[0] = a[max_idx[0]].r, r[1] = a[max_idx[1]].r;
r[0]->proper_frag = r[1]->proper_frag = 1;
for (s = 0; s < 2; ++s) {
if (r[s]->id != r[s]->parent) {
mm_reg1_t *p = &regs[s][r[s]->parent];