fork/minimap2
1
0
Fork 0
mirror of https://github.com/lh3/minimap2.git synced 2026-09-25 07:58:11 +08:00
Code Issues Packages Projects Releases Wiki Activity

r488: parameter to control max fragment length

Browse Source
This commit is contained in:
Heng Li
2017-10-07 23:54:32 -04:00
parent f150257a0d
commit 61e56c941d
3 changed files with 29 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files
map.c
+21 -10
View File
@@ -83,14 +83,14 @@ int mm_set_opt(const char *preset, mm_idxopt_t *io, mm_mapopt_t *mo)
mo->flag |= MM_F_SR | MM_F_FRAG_MODE | MM_F_NO_PRINT_2ND;
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->max_frag_len = 800;
mo->max_gap = 200;
mo->max_gap_ref = 1000;
mo->bw = 100;
mo->pri_ratio = 0.5f;
mo->min_cnt = 2;
mo->min_chain_score = 25;
mo->min_dp_max = 40;
mo->best_n = 20;
mo->bw = 100;
mo->mid_occ = 1000;
mo->max_occ = 5000;
mo->mini_batch_size = 50000000;
@@ -235,12 +235,12 @@ static mm128_t *collect_seed_hits(const mm_mapopt_t *opt, int max_occ, const mm_
return a;
}
static void chain_post(const mm_mapopt_t *opt, const mm_idx_t *mi, void *km, int qlen, int n_segs, const int *qlens, int *n_regs, mm_reg1_t *regs, mm128_t *a)
static void chain_post(const mm_mapopt_t *opt, int max_chain_gap_ref, const mm_idx_t *mi, void *km, int qlen, int n_segs, const int *qlens, int *n_regs, mm_reg1_t *regs, mm128_t *a)
{
if (!(opt->flag & MM_F_AVA)) { // don't choose primary mapping(s) for read overlap
mm_set_parent(km, opt->mask_level, *n_regs, regs, opt->a * 2 + opt->b);
if (n_segs <= 1) mm_select_sub(km, opt->pri_ratio, mi->k*2, opt->best_n, n_regs, regs);
else mm_select_sub_multi(km, opt->pri_ratio, 0.2f, 0.7f, opt->max_gap_ref, mi->k*2, opt->best_n, n_segs, qlens, n_regs, regs);
else mm_select_sub_multi(km, opt->pri_ratio, 0.2f, 0.7f, max_chain_gap_ref, mi->k*2, opt->best_n, n_segs, qlens, n_regs, regs);
if (!(opt->flag & MM_F_SPLICE) && !(opt->flag & MM_F_SR) && !(opt->flag & MM_F_NO_LJOIN))
mm_join_long(km, opt, qlen, n_regs, regs, a);
}
@@ -260,7 +260,8 @@ static mm_reg1_t *align_regs(const mm_mapopt_t *opt, const mm_idx_t *mi, void *k
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, max_gap_ref, rep_len, qlen_sum, n_regs0;
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);
uint32_t hash;
int64_t n_a;
uint64_t *u;
@@ -287,8 +288,18 @@ void mm_map_frag(const mm_idx_t *mi, int n_segs, const int *qlens, const char **
i == 0? 0 : ((int32_t)a[i].y - (int32_t)a[i-1].y) - ((int32_t)a[i].x - (int32_t)a[i-1].x));
}
max_gap_ref = opt->max_gap_ref >= 0? opt->max_gap_ref : opt->max_gap;
a = mm_chain_dp(max_gap_ref, opt->max_gap, opt->bw, opt->max_chain_skip, opt->min_cnt, opt->min_chain_score, !!(opt->flag&MM_F_SPLICE), n_segs, n_a, a, &n_regs0, &u, b->km);
// set max chaining gap on the query and the reference sequence
if (opt->flag & MM_F_SR)
max_chain_gap_qry = qlen_sum > opt->max_gap? qlen_sum : opt->max_gap;
else max_chain_gap_qry = opt->max_gap;
if (opt->max_gap_ref > 0) {
max_chain_gap_ref = opt->max_gap_ref; // always honor mm_mapopt_t::max_gap_ref if set
} else if (opt->max_frag_len > 0) {
max_chain_gap_ref = opt->max_frag_len - qlen_sum;
if (max_chain_gap_ref < opt->max_gap) max_chain_gap_ref = opt->max_gap;
} else max_chain_gap_ref = opt->max_gap;
a = mm_chain_dp(max_chain_gap_ref, max_chain_gap_qry, opt->bw, opt->max_chain_skip, opt->min_cnt, opt->min_chain_score, is_splice, n_segs, n_a, a, &n_regs0, &u, b->km);
if ((opt->flag & MM_F_SR) && rep_len > 0) {
int rechain = 0;
@@ -309,7 +320,7 @@ void mm_map_frag(const mm_idx_t *mi, int n_segs, const int *qlens, const char **
kfree(b->km, u);
a = collect_seed_hits(opt, opt->max_occ, mi, qname, qlen_sum, &n_a, &rep_len, b);
radix_sort_128x(a, a + n_a);
a = mm_chain_dp(max_gap_ref, opt->max_gap, opt->bw, opt->max_chain_skip, opt->min_cnt, opt->min_chain_score, !!(opt->flag&MM_F_SPLICE), n_segs, n_a, a, &n_regs0, &u, b->km);
a = mm_chain_dp(max_chain_gap_ref, max_chain_gap_qry, opt->bw, opt->max_chain_skip, opt->min_cnt, opt->min_chain_score, is_splice, n_segs, n_a, a, &n_regs0, &u, b->km);
}
}
@@ -321,7 +332,7 @@ void mm_map_frag(const mm_idx_t *mi, int n_segs, const int *qlens, const char **
fprintf(stderr, "CN\t%d\t%s\t%d\t%c\t%d\t%d\t%d\n", j, mi->seq[a[i].x<<1>>33].name, (int32_t)a[i].x, "+-"[a[i].x>>63], (int32_t)a[i].y, (int32_t)(a[i].y>>32&0xff),
i == regs0[j].as? 0 : ((int32_t)a[i].y - (int32_t)a[i-1].y) - ((int32_t)a[i].x - (int32_t)a[i-1].x));
chain_post(opt, mi, b->km, qlen_sum, n_segs, qlens, &n_regs0, regs0, a);
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);
@@ -338,7 +349,7 @@ void mm_map_frag(const mm_idx_t *mi, int n_segs, const int *qlens, const char **
}
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_gap_ref, opt->pe_bonus, opt->a * 2 + opt->b, opt->a, qlens, n_regs, regs); // pairing
mm_pair(b->km, max_chain_gap_ref, opt->pe_bonus, opt->a * 2 + opt->b, opt->a, qlens, n_regs, regs); // pairing
}
kfree(b->km, a);