Release minimap2-2.20 (r1061)

Ok, I am not going to re-release again...

NEWS.md

@@ -1,3 +1,15 @@
+Release 2.20-r1061 (27 May 2021)
+--------------------------------
+
+This release fixed a bug in the Python module and improves the command-line
+compatibiliity with v2.18. In v2.19, if `-r` is specified with an `asm*` preset,
+users would get alignments more fragmented than v2.18. This could be an issue
+for existing pipelines specifying `-r`. This release resolves this issue.
+
+(2.20: 27 May 2021, r1061)
+
+
+
 Release 2.19-r1057 (26 May 2021)
 --------------------------------
 
@@ -33,7 +45,7 @@ unimap for contig alignment. Unimap will remain an experimental project and is
 no longer recommended over minimap2. Sorry for reverting the recommendation in
 short time.
 
-(2.20: 26 May 2021, r1057)
+(2.19: 26 May 2021, r1057)
 
 
 

README.md

@@ -74,8 +74,8 @@ Detailed evaluations are available from the [minimap2 paper][doi] or the
 Minimap2 is optimized for x86-64 CPUs. You can acquire precompiled binaries from
 the [release page][release] with:
 ```sh
-curl -L https://github.com/lh3/minimap2/releases/download/v2.19/minimap2-2.19_x64-linux.tar.bz2 | tar -jxvf -
+curl -L https://github.com/lh3/minimap2/releases/download/v2.20/minimap2-2.20_x64-linux.tar.bz2 | tar -jxvf -
-./minimap2-2.19_x64-linux/minimap2
+./minimap2-2.20_x64-linux/minimap2
 ```
 If you want to compile from the source, you need to have a C compiler, GNU make
 and zlib development files installed. Then type `make` in the source code

cookbook.md

@@ -31,8 +31,8 @@ To acquire the data used in this cookbook and to install minimap2 and paftools,
 please follow the command lines below:
 ```sh
 # install minimap2 executables
-curl -L https://github.com/lh3/minimap2/releases/download/v2.19/minimap2-2.19_x64-linux.tar.bz2 | tar jxf -
+curl -L https://github.com/lh3/minimap2/releases/download/v2.20/minimap2-2.20_x64-linux.tar.bz2 | tar jxf -
-cp minimap2-2.19_x64-linux/{minimap2,k8,paftools.js} .  # copy executables
+cp minimap2-2.20_x64-linux/{minimap2,k8,paftools.js} .  # copy executables
 export PATH="$PATH:"`pwd`                               # put the current directory on PATH
 # download example datasets
 curl -L https://github.com/lh3/minimap2/releases/download/v2.10/cookbook-data.tgz | tar zxf -

main.c

@@ -7,7 +7,7 @@
 #include "mmpriv.h"
 #include "ketopt.h"
 
-#define MM_VERSION "2.19-r1057"
+#define MM_VERSION "2.20-r1061"
 
 #ifdef __linux__
 #include <sys/resource.h>
@@ -317,7 +317,7 @@ int main(int argc, char *argv[])
 		fprintf(fp_help, "    -g NUM       stop chain enlongation if there are no minimizers in INT-bp [%d]\n", opt.max_gap);
 		fprintf(fp_help, "    -G NUM       max intron length (effective with -xsplice; changing -r) [200k]\n");
 		fprintf(fp_help, "    -F NUM       max fragment length (effective with -xsr or in the fragment mode) [800]\n");
-		fprintf(fp_help, "    -r NUM       bandwidth used in chaining and DP-based alignment [%d]\n", opt.bw);
+		fprintf(fp_help, "    -r NUM[,NUM] chaining/alignment bandwidth and long-join bandwidth [%d,%d]\n", opt.bw, opt.bw_long);
 		fprintf(fp_help, "    -n INT       minimal number of minimizers on a chain [%d]\n", opt.min_cnt);
 		fprintf(fp_help, "    -m INT       minimal chaining score (matching bases minus log gap penalty) [%d]\n", opt.min_chain_score);
 //		fprintf(fp_help, "    -T INT       SDUST threshold; 0 to disable SDUST [%d]\n", opt.sdust_thres); // TODO: this option is never used; might be buggy

map.c

@@ -277,7 +277,17 @@ void mm_map_frag(const mm_idx_t *mi, int n_segs, const int *qlens, const char **
 						 opt->chain_gap_scale * 0.01 * mi->k, 0.0f, is_splice, n_segs, n_a, a, &n_regs0, &u, b->km);
 	}
 
-	if (opt->max_occ > opt->mid_occ && rep_len > 0 && !(opt->flag & MM_F_RMQ)) {
+	if (opt->bw_long > opt->bw && (opt->flag & (MM_F_SPLICE|MM_F_SR|MM_F_NO_LJOIN)) == 0 && n_segs == 1 && n_regs0 > 1) { // re-chain/long-join for long sequences
+		int32_t st = (int32_t)a[0].y, en = (int32_t)a[(int32_t)u[0] - 1].y;
+		if (qlen_sum - (en - st) > opt->rmq_rescue_size || en - st > qlen_sum * opt->rmq_rescue_ratio) {
+			int32_t i;
+			for (i = 0, n_a = 0; i < n_regs0; ++i) n_a += (int32_t)u[i];
+			kfree(b->km, u);
+			radix_sort_128x(a, a + n_a);
+			a = mg_lchain_rmq(opt->max_gap, opt->rmq_inner_dist, opt->bw_long, opt->max_chain_skip, opt->rmq_size_cap, opt->min_cnt, opt->min_chain_score,
+							  opt->chain_gap_scale * 0.01 * mi->k, 0.0f, n_a, a, &n_regs0, &u, b->km);
+		}
+	} else if (opt->max_occ > opt->mid_occ && rep_len > 0 && !(opt->flag & MM_F_RMQ)) { // re-chain, mostly for short reads
 		int rechain = 0;
 		if (n_regs0 > 0) { // test if the best chain has all the segments
 			int n_chained_segs = 1, max = 0, max_i = -1, max_off = -1, off = 0;
@@ -300,16 +310,6 @@ void mm_map_frag(const mm_idx_t *mi, int n_segs, const int *qlens, const char **
 			a = mg_lchain_dp(max_chain_gap_ref, max_chain_gap_qry, opt->bw, opt->max_chain_skip, opt->max_chain_iter, opt->min_cnt, opt->min_chain_score,
 							 opt->chain_gap_scale * 0.01 * mi->k, 0.0f, is_splice, n_segs, n_a, a, &n_regs0, &u, b->km);
 		}
-	} else if (opt->bw_long > opt->bw && (opt->flag & (MM_F_RMQ|MM_F_NO_LJOIN)) == 0 && n_segs == 1 && n_regs0 > 1) {
-		int32_t st = (int32_t)a[0].y, en = (int32_t)a[(int32_t)u[0] - 1].y;
-		if (qlen_sum - (en - st) > opt->rmq_rescue_size || en - st > qlen_sum * opt->rmq_rescue_ratio) {
-			int32_t i;
-			for (i = 0, n_a = 0; i < n_regs0; ++i) n_a += (int32_t)u[i];
-			kfree(b->km, u);
-			radix_sort_128x(a, a + n_a);
-			a = mg_lchain_rmq(opt->max_gap, opt->rmq_inner_dist, opt->bw_long, opt->max_chain_skip, opt->rmq_size_cap, opt->min_cnt, opt->min_chain_score,
-							  opt->chain_gap_scale * 0.01 * mi->k, 0.0f, n_a, a, &n_regs0, &u, b->km);
-		}
 	}
 	b->frag_gap = max_chain_gap_ref;
 	b->rep_len = rep_len;

minimap2.1

@@ -1,4 +1,4 @@
-.TH minimap2 1 "26 May 2021" "minimap2-2.19 (r1057)" "Bioinformatics tools"
+.TH minimap2 1 "27 May 2021" "minimap2-2.20 (r1061)" "Bioinformatics tools"
 .SH NAME
 .PP
 minimap2 - mapping and alignment between collections of DNA sequences
@@ -165,9 +165,12 @@ Stop chain enlongation if there are no minimizers within
 .IR NUM -bp
 [10k].
 .TP
-.BI -r \ NUM
+.BI -r \ NUM1 [, NUM2 ]
-Bandwidth used in chaining and DP-based alignment [500,20k]. This option
+Bandwidth for chaining and base alignment [500,20k].
-approximately controls the maximum gap size.
+.I NUM1
+is used for initial chaining and alignment extension;
+.I NUM2
+for RMQ-based re-chaining and closing gaps in alignments.
 .TP
 .BI -n \ INT
 Discard chains consisting of

misc/paftools.js

@@ -1,6 +1,6 @@
 #!/usr/bin/env k8
 
-var paftools_version = '2.19-r1057';
+var paftools_version = '2.20-r1061';
 
 /*****************************
  ***** Library functions *****

options.c

@@ -75,7 +75,7 @@ void mm_mapopt_update(mm_mapopt_t *opt, const mm_idx_t *mi)
 void mm_mapopt_max_intron_len(mm_mapopt_t *opt, int max_intron_len)
 {
 	if ((opt->flag & MM_F_SPLICE) && max_intron_len > 0)
-		opt->max_gap_ref = opt->bw = max_intron_len;
+		opt->max_gap_ref = opt->bw = opt->bw_long = max_intron_len;
 }
 
 int mm_set_opt(const char *preset, mm_idxopt_t *io, mm_mapopt_t *mo)
@@ -109,7 +109,7 @@ int mm_set_opt(const char *preset, mm_idxopt_t *io, mm_mapopt_t *mo)
 		io->flag = 0, io->k = 19, io->w = 19;
 		mo->bw = mo->bw_long = 100000;
 		mo->max_gap = 10000;
-		mo->flag |= MM_F_RMQ | MM_F_NO_LJOIN;
+		mo->flag |= MM_F_RMQ;
 		mo->min_mid_occ = 50, mo->max_mid_occ = 500;
 		mo->min_dp_max = 200;
 		mo->best_n = 50;
@@ -156,6 +156,11 @@ int mm_set_opt(const char *preset, mm_idxopt_t *io, mm_mapopt_t *mo)
 
 int mm_check_opt(const mm_idxopt_t *io, const mm_mapopt_t *mo)
 {
+	if (mo->bw > mo->bw_long) {
+		if (mm_verbose >= 1)
+			fprintf(stderr, "[ERROR]\033[1;31m with '-rNUM1,NUM2', NUM1 (%d) can't be larger than NUM2 (%d)\033[0m\n", mo->bw, mo->bw_long);
+		return -8;
+	}
 	if ((mo->flag & MM_F_RMQ) && (mo->flag & (MM_F_SR|MM_F_SPLICE))) {
 		if (mm_verbose >= 1)
 			fprintf(stderr, "[ERROR]\033[1;31m --rmq doesn't work with --sr or --splice\033[0m\n");

python/mappy.pyx

@@ -3,7 +3,7 @@ from libc.stdlib cimport free
 cimport cmappy
 import sys
 
-__version__ = '2.19'
+__version__ = '2.20'
 
 cmappy.mm_reset_timer()
 

setup.py

@@ -23,7 +23,7 @@ def readme():
 
 setup(
 	name = 'mappy',
-	version = '2.19',
+	version = '2.20',
 	url = 'https://github.com/lh3/minimap2',
 	description = 'Minimap2 python binding',
 	long_description = readme(),
@@ -33,7 +33,7 @@ setup(
 	keywords = 'sequence-alignment',
 	scripts = ['python/minimap2.py'],
 	ext_modules = [Extension('mappy',
-		sources = ['python/mappy.pyx', 'align.c', 'bseq.c', 'lchain.c', 'format.c', 'hit.c', 'index.c', 'pe.c', 'options.c',
+		sources = ['python/mappy.pyx', 'align.c', 'bseq.c', 'lchain.c', 'seed.c', 'format.c', 'hit.c', 'index.c', 'pe.c', 'options.c',
 				   'ksw2_extd2_sse.c', 'ksw2_exts2_sse.c', 'ksw2_extz2_sse.c', 'ksw2_ll_sse.c',
 				   'kalloc.c', 'kthread.c', 'map.c', 'misc.c', 'sdust.c', 'sketch.c', 'esterr.c', 'splitidx.c'],
 		depends = ['minimap.h', 'bseq.h', 'kalloc.h', 'kdq.h', 'khash.h', 'kseq.h', 'ksort.h',