fork/minimap2
1
0
Fork 0
mirror of https://github.com/lh3/minimap2.git synced 2026-09-15 13:07:55 +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

28
map.c
View File

@@ -85,9 +85,9 @@ int mm_set_opt(const char *preset, mm_idxopt_t *io, mm_mapopt_t *mo)
io->is_hpc = 0, io->k = 21, io->w = 11;
mo->flag |= MM_F_SR | MM_F_FRAG_MODE | MM_F_NO_PRINT_2ND | MM_F_2_IO_THREADS;
mo->pe_ori = 0<<1|1; // FR
mo->a = 2, mo->b = 8, mo->q = 12, mo->e = 2, mo->q2 = 32, mo->e2 = 1;
mo->a = 2, mo->b = 8, mo->q = 12, mo->e = 2, mo->q2 = 24, mo->e2 = 1;
mo->zdrop = 100;
mo->end_bonus = 11;
mo->end_bonus = 15;
mo->max_frag_len = 800;
mo->max_gap = 100;
mo->bw = 100;
@@ -251,10 +251,10 @@ 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, 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, const char *qual, 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()
regs = mm_align_skeleton(km, opt, mi, qlen, seq, qual, n_regs, regs, a); // this calls mm_filter_regs()
if (!(opt->flag & MM_F_AVA)) {
mm_set_parent(km, opt->mask_level, *n_regs, regs, opt->a * 2 + opt->b);
mm_select_sub(km, opt->pri_ratio, mi->k*2, opt->best_n, n_regs, regs);
@@ -263,7 +263,7 @@ 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, 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, const char **quals, 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;
int max_chain_gap_qry, max_chain_gap_ref, is_splice = !!(opt->flag & MM_F_SPLICE);
@@ -340,7 +340,7 @@ void mm_map_frag(const mm_idx_t *mi, int n_segs, const int *qlens, const char **
chain_post(opt, max_chain_gap_ref, mi, b->km, qlen_sum, n_segs, qlens, &n_regs0, regs0, a);
if (n_segs == 1) { // uni-segment
regs0 = align_regs(opt, mi, b->km, qlens[0], seqs[0], &n_regs0, regs0, a);
regs0 = align_regs(opt, mi, b->km, qlens[0], seqs[0], quals? quals[0] : 0, &n_regs0, regs0, a);
mm_set_mapq(n_regs0, regs0, opt->min_chain_score, opt->a, rep_len);
n_regs[0] = n_regs0, regs[0] = regs0;
} else { // multi-segment
@@ -349,13 +349,16 @@ 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], &n_regs[i], regs[i], seg[i].a);
regs[i] = align_regs(opt, mi, b->km, qlens[i], seqs[i], quals? quals[i] : 0, &n_regs[i], regs[i], seg[i].a);
mm_set_mapq(n_regs[i], regs[i], opt->min_chain_score, opt->a, rep_len);
}
mm_seg_free(b->km, n_segs, seg);
if (n_segs == 2 && opt->pe_ori >= 0 && (opt->flag&MM_F_CIGAR))
mm_pair(b->km, max_chain_gap_ref, opt->pe_bonus, opt->a * 2 + opt->b, opt->a, qlens, n_regs, regs); // pairing
}
if (opt->min_iden > 0.0f)
for (i = 0; i < n_segs; ++i)
mm_filter_by_identity(b->km, n_regs[i], regs[i], opt->min_iden, qlens[i], quals[i]);
kfree(b->km, a);
kfree(b->km, u);
@@ -364,7 +367,7 @@ 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, n_regs, &regs, b, opt, qname);
mm_map_frag(mi, 1, &qlen, &seq, 0, n_regs, &regs, b, opt, qname);
return regs;
}
@@ -392,20 +395,22 @@ typedef struct {
static void worker_for(void *_data, long i, int tid) // kt_for() callback
{
step_t *s = (step_t*)_data;
int *qlens, j, off = s->seg_off[i], pe_ori = s->p->opt->pe_ori;
const char **qseqs;
int *qlens, 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, **quals = 0;
mm_tbuf_t *b = s->buf[tid];
if (mm_dbg_flag & MM_DBG_PRINT_QNAME)
fprintf(stderr, "QR\t%s\t%d\n", s->seq[off].name, tid);
qlens = (int*)kmalloc(b->km, s->n_seg[i] * sizeof(int));
qseqs = (const char**)kmalloc(b->km, s->n_seg[i] * sizeof(const char**));
quals = (const char**)kmalloc(b->km, s->n_seg[i] * sizeof(const char**));
for (j = 0; j < s->n_seg[i]; ++j) {
if (s->n_seg[i] == 2 && ((j == 0 && (pe_ori>>1&1)) || (j == 1 && (pe_ori&1))))
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;
}
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);
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);
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)))) {
int k, t;
@@ -420,6 +425,7 @@ static void worker_for(void *_data, long i, int tid) // kt_for() callback
}
kfree(b->km, qlens);
kfree(b->km, qseqs);
kfree(b->km, quals);
}
static void *worker_pipeline(void *shared, int step, void *in)