r524: reverted to bwa-mem end bonus

and reduced the cost of clipping when filtering by identity
moold · Oct 20, 2017 · bd04372 · bd04372
1 parent 15ed071
commit bd04372
Show file tree

Hide file tree

Showing 4 changed files with 9 additions and 5 deletions.
diff --git a/hit.c b/hit.c
@@ -286,7 +286,7 @@ void mm_filter_by_identity(void *km, int n_regs, mm_reg1_t *regs, float min_iden
 		mm_reg1_t *r = &regs[(int32_t)aux[i]];
 		if (r->qs > en) {
 			for (j = en; j < r->qs; ++j)
-				n_diff += qual == 0 || qual[j] >= 53? 0.5f : 0.025f * (qual[j] - 33);
+				n_diff += qual == 0 || qual[j] >= 53? .25f : .05f * .25f * (qual[j] - 33);
 			blen += r->qs - en;
 		}
 		assert(r->p);
@@ -295,7 +295,7 @@ void mm_filter_by_identity(void *km, int n_regs, mm_reg1_t *regs, float min_iden
 		en = en > r->qe? en : r->qe;
 	}
 	for (j = en; j < qlen; ++j)
-		n_diff += qual == 0 || qual[j] >= 53? 0.5f : 0.025f * (qual[j] - 33);
+		n_diff += qual == 0 || qual[j] >= 53? .25f : .05f * .25f * (qual[j] - 33);
 	blen += qlen - en;
 	kfree(km, aux);
 	if (1.0f - n_diff / blen < min_iden)

diff --git a/main.c b/main.c
@@ -6,7 +6,7 @@
 #include "mmpriv.h"
 #include "getopt.h"
 
-#define MM_VERSION "2.2-r523-dirty"
+#define MM_VERSION "2.2-r524-dirty"
 
 #ifdef __linux__
 #include <sys/resource.h>

diff --git a/map.c b/map.c
@@ -85,7 +85,7 @@ int mm_set_opt(const char *preset, mm_idxopt_t *io, mm_mapopt_t *mo)
 		mo->pe_ori = 0<<1|1; // FR
 		mo->a = 2, mo->b = 8, mo->q = 12, mo->e = 2, mo->q2 = 24, mo->e2 = 1;
 		mo->zdrop = 100;
-		mo->end_bonus = 15;
+		mo->end_bonus = 10;
 		mo->max_frag_len = 800;
 		mo->max_gap = 100;
 		mo->bw = 100;

diff --git a/tex/minimap2.tex b/tex/minimap2.tex
@@ -512,7 +512,11 @@ \subsection{Aligning short genomic reads}
 SNAP~\citep{Zaharia:2011aa}. Minimap2 is 3--4 times as fast as Bowtie2 and
 BWA-MEM, but is 1.3 times slower than SNAP. Minimap2 is more accurate on this
 simulated data set than Bowtie2 and SNAP but less accurate than BWA-MEM
-(Fig.~\ref{fig:eval}b).
+(Fig.~\ref{fig:eval}b). Closer investigation reveals that BWA-MEM achieves
+a higher accuracy partly because it tries to locally align a read in a small
+region close to its mate. If we disable this feature, BWA-MEM becomes slightly
+less accurate than minimap2. We might consider to implement a similar heuristic
+in minimap2 in future.
 
 \section{Conclusion}