r670: added PE support to mappy

and minor code cleanup
This commit is contained in:
Heng Li
2018-01-31 11:33:08 -05:00
parent 12a5a5fa3c
commit 46d6349af4
9 changed files with 71 additions and 23 deletions
+9 -11
View File
@@ -246,7 +246,7 @@ static void chain_post(const mm_mapopt_t *opt, int max_chain_gap_ref, const mm_i
}
}
static mm_reg1_t *align_regs(const mm_mapopt_t *opt, const mm_idx_t *mi, void *km, int qlen, const char *seq, const char *qual, int *n_regs, mm_reg1_t *regs, mm128_t *a)
static mm_reg1_t *align_regs(const mm_mapopt_t *opt, const mm_idx_t *mi, void *km, int qlen, const char *seq, int *n_regs, mm_reg1_t *regs, mm128_t *a)
{
if (!(opt->flag & MM_F_CIGAR)) return regs;
regs = mm_align_skeleton(km, opt, mi, qlen, seq, n_regs, regs, a); // this calls mm_filter_regs()
@@ -258,7 +258,7 @@ static mm_reg1_t *align_regs(const mm_mapopt_t *opt, const mm_idx_t *mi, void *k
return regs;
}
void mm_map_frag(const mm_idx_t *mi, int n_segs, const int *qlens, const char **seqs, const char **quals, int *n_regs, mm_reg1_t **regs, mm_tbuf_t *b, const mm_mapopt_t *opt, const char *qname)
void mm_map_frag(const mm_idx_t *mi, int n_segs, const int *qlens, const char **seqs, int *n_regs, mm_reg1_t **regs, mm_tbuf_t *b, const mm_mapopt_t *opt, const char *qname)
{
int i, j, rep_len, qlen_sum, n_regs0, n_mini_pos;
int max_chain_gap_qry, max_chain_gap_ref, is_splice = !!(opt->flag & MM_F_SPLICE), is_sr = !!(opt->flag & MM_F_SR);
@@ -339,7 +339,7 @@ void mm_map_frag(const mm_idx_t *mi, int n_segs, const int *qlens, const char **
if (!is_sr) mm_est_err(mi, qlen_sum, n_regs0, regs0, a, n_mini_pos, mini_pos);
if (n_segs == 1) { // uni-segment
regs0 = align_regs(opt, mi, b->km, qlens[0], seqs[0], quals? quals[0] : 0, &n_regs0, regs0, a);
regs0 = align_regs(opt, mi, b->km, qlens[0], seqs[0], &n_regs0, regs0, a);
mm_set_mapq(n_regs0, regs0, opt->min_chain_score, opt->a, rep_len, is_sr);
n_regs[0] = n_regs0, regs[0] = regs0;
} else { // multi-segment
@@ -348,7 +348,7 @@ void mm_map_frag(const mm_idx_t *mi, int n_segs, const int *qlens, const char **
free(regs0);
for (i = 0; i < n_segs; ++i) {
mm_set_parent(b->km, opt->mask_level, n_regs[i], regs[i], opt->a * 2 + opt->b); // update mm_reg1_t::parent
regs[i] = align_regs(opt, mi, b->km, qlens[i], seqs[i], quals? quals[i] : 0, &n_regs[i], regs[i], seg[i].a);
regs[i] = align_regs(opt, mi, b->km, qlens[i], seqs[i], &n_regs[i], regs[i], seg[i].a);
mm_set_mapq(n_regs[i], regs[i], opt->min_chain_score, opt->a, rep_len, is_sr);
}
mm_seg_free(b->km, n_segs, seg);
@@ -376,7 +376,7 @@ void mm_map_frag(const mm_idx_t *mi, int n_segs, const int *qlens, const char **
mm_reg1_t *mm_map(const mm_idx_t *mi, int qlen, const char *seq, int *n_regs, mm_tbuf_t *b, const mm_mapopt_t *opt, const char *qname)
{
mm_reg1_t *regs;
mm_map_frag(mi, 1, &qlen, &seq, 0, n_regs, &regs, b, opt, qname);
mm_map_frag(mi, 1, &qlen, &seq, n_regs, &regs, b, opt, qname);
return regs;
}
@@ -404,11 +404,10 @@ typedef struct {
static void worker_for(void *_data, long i, int tid) // kt_for() callback
{
step_t *s = (step_t*)_data;
int qlens[MM_MAX_SEG], j, off = s->seg_off[i], pe_ori = s->p->opt->pe_ori, is_sr = !!(s->p->opt->flag & MM_F_SR);
const char *qseqs[MM_MAX_SEG], *quals[MM_MAX_SEG];
int qlens[MM_MAX_SEG], j, off = s->seg_off[i], pe_ori = s->p->opt->pe_ori;
const char *qseqs[MM_MAX_SEG];
mm_tbuf_t *b = s->buf[tid];
assert(s->n_seg[i] <= MM_MAX_SEG);
memset(quals, 0, sizeof(char*) * MM_MAX_SEG);
if (mm_dbg_flag & MM_DBG_PRINT_QNAME)
fprintf(stderr, "QR\t%s\t%d\t%d\n", s->seq[off].name, tid, s->seq[off].l_seq);
for (j = 0; j < s->n_seg[i]; ++j) {
@@ -416,13 +415,12 @@ static void worker_for(void *_data, long i, int tid) // kt_for() callback
mm_revcomp_bseq(&s->seq[off + j]);
qlens[j] = s->seq[off + j].l_seq;
qseqs[j] = s->seq[off + j].seq;
quals[j] = is_sr? s->seq[off + j].qual : 0;
}
if (s->p->opt->flag & MM_F_INDEPEND_SEG) {
for (j = 0; j < s->n_seg[i]; ++j)
mm_map_frag(s->p->mi, 1, &qlens[j], &qseqs[j], &quals[j], &s->n_reg[off+j], &s->reg[off+j], b, s->p->opt, s->seq[off+j].name);
mm_map_frag(s->p->mi, 1, &qlens[j], &qseqs[j], &s->n_reg[off+j], &s->reg[off+j], b, s->p->opt, s->seq[off+j].name);
} else {
mm_map_frag(s->p->mi, s->n_seg[i], qlens, qseqs, quals, &s->n_reg[off], &s->reg[off], b, s->p->opt, s->seq[off].name);
mm_map_frag(s->p->mi, s->n_seg[i], qlens, qseqs, &s->n_reg[off], &s->reg[off], b, s->p->opt, s->seq[off].name);
}
for (j = 0; j < s->n_seg[i]; ++j) // flip the query strand and coordinate to the original read strand
if (s->n_seg[i] == 2 && ((j == 0 && (pe_ori>>1&1)) || (j == 1 && (pe_ori&1)))) {