Release minimap2-2.25 (r1173)

NEWS.md

@@ -1,3 +1,41 @@
+Release 2.25-r1173 (25 April 2023)
+----------------------------------
+
+Notable changes:
+
+ * Improvement: use the miniprot splice model for RNA-seq alignment by default.
+   This model considers non-GT-AG splice sites and leads to slightly higher
+   (<0.1%) accuracy and sensitivity on real human data.
+
+ * Change: increased the default `-I` to `8G` such that minimap2 would create a
+   uni-part index for a pair of mammalian genomes. This change may increase the
+   memory for all-vs-all read overlap alignment given large datasets.
+
+ * New feature: output the sequences in secondary alignments with option
+   `--secondary-seq` (#687).
+
+ * Bugfix: --rmq was not parsed correctly (#1010)
+
+ * Bugfix: possibly incorrect coordinate when applying end bonus to the target
+   sequence (#1025). This is a ksw2 bug. It does not affect minimap2 as
+   minimap2 is not using the affected feature.
+
+ * Improvement: incorporated several changes for better compatibility with
+   Windows (#1051) and for minimap2 integration at Oxford Nanopore Technologies
+   (#1048 and #1033).
+
+ * Improvement: output the HD-line in SAM output (#1019).
+
+ * Improvement: check minimap2 index file in mappy to prevent segmentation
+   fault for certain indices (#1008).
+
+For genomic sequences, minimap2 should give identical output to v2.24.
+Long-read RNA-seq alignment may occasionally differ from previous versions.
+
+(2.25: 25 April 2023, r1173)
+
+
+
 Release 2.24-r1122 (26 December 2021)
 -------------------------------------
 

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/v2.24/minimap2-2.24_x64-linux.tar.bz2 | tar -jxvf -
-./minimap2-2.24_x64-linux/minimap2
+curl -L https://github.com/lh3/minimap2/releases/download/v2.25/minimap2-2.25_x64-linux.tar.bz2 | tar -jxvf -
+./minimap2-2.25_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/v2.24/minimap2-2.24_x64-linux.tar.bz2 | tar jxf -
-cp minimap2-2.24_x64-linux/{minimap2,k8,paftools.js} .  # copy executables
+curl -L https://github.com/lh3/minimap2/releases/download/v2.25/minimap2-2.25_x64-linux.tar.bz2 | tar jxf -
+cp minimap2-2.25_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 -

index.c

@@ -358,7 +358,7 @@ static void *worker_pipeline(void *shared, int step, void *in)
 		for (i = 0; i < s->n_seq; ++i) {
 			mm_bseq1_t *t = &s->seq[i];
 			if (t->l_seq > 0)
-				mm_sketch2(0, t->seq, t->l_seq, p->mi->w, p->mi->k, t->rid, p->mi->flag&MM_I_HPC, p->mi->flag&MM_I_SYNCMER, &s->a);
+				mm_sketch(0, t->seq, t->l_seq, p->mi->w, p->mi->k, t->rid, p->mi->flag&MM_I_HPC, &s->a);
 			else if (mm_verbose >= 2)
 				fprintf(stderr, "[WARNING] the length database sequence '%s' is 0\n", t->name);
 			free(t->seq); free(t->name);
@@ -446,7 +446,7 @@ mm_idx_t *mm_idx_str(int w, int k, int is_hpc, int bucket_bits, int n, const cha
 		sum_len += p->len;
 		if (p->len > 0) {
 			a.n = 0;
-			mm_sketch2(0, s, p->len, w, k, i, is_hpc, 0, &a); // TODO: mm_idx_str() doesn't support syncmer
+			mm_sketch(0, s, p->len, w, k, i, is_hpc, &a);
 			mm_idx_add(mi, a.n, a.a);
 		}
 	}

main.c

@@ -120,7 +120,7 @@ static inline void yes_or_no(mm_mapopt_t *opt, int64_t flag, int long_idx, const
 
 int main(int argc, char *argv[])
 {
-	const char *opt_str = "2aSDw:k:K:t:r:f:Vv:g:G:I:d:XT:s:x:Hcp:M:n:z:A:B:O:E:m:N:Qu:R:hF:LC:yYPo:e:U:j:J:";
+	const char *opt_str = "2aSDw:k:K:t:r:f:Vv:g:G:I:d:XT:s:x:Hcp:M:n:z:A:B:O:E:m:N:Qu:R:hF:LC:yYPo:e:U:J:";
 	ketopt_t o = KETOPT_INIT;
 	mm_mapopt_t opt;
 	mm_idxopt_t ipt;
@@ -152,8 +152,7 @@ int main(int argc, char *argv[])
 	o = KETOPT_INIT;
 
 	while ((c = ketopt(&o, argc, argv, 1, opt_str, long_options)) >= 0) {
-		if (c == 'w') ipt.w = atoi(o.arg), ipt.flag &= ~MM_I_SYNCMER;
-		else if (c == 'j') ipt.w = atoi(o.arg), ipt.flag |= MM_I_SYNCMER;
+		if (c == 'w') ipt.w = atoi(o.arg);
 		else if (c == 'k') ipt.k = atoi(o.arg);
 		else if (c == 'H') ipt.flag |= MM_I_HPC;
 		else if (c == 'd') fnw = o.arg; // the above are indexing related options, except -I
@@ -329,7 +328,6 @@ int main(int argc, char *argv[])
 		fprintf(fp_help, "    -H           use homopolymer-compressed k-mer (preferrable for PacBio)\n");
 		fprintf(fp_help, "    -k INT       k-mer size (no larger than 28) [%d]\n", ipt.k);
 		fprintf(fp_help, "    -w INT       minimizer window size [%d]\n", ipt.w);
-//		fprintf(fp_help, "    -j INT       syncmer submer size (overriding -w) []\n");
 		fprintf(fp_help, "    -I NUM       split index for every ~NUM input bases [8G]\n");
 		fprintf(fp_help, "    -d FILE      dump index to FILE []\n");
 		fprintf(fp_help, "  Mapping:\n");

map.c

@@ -62,7 +62,7 @@ static void collect_minimizers(void *km, const mm_mapopt_t *opt, const mm_idx_t
 	mv->n = 0;
 	for (i = n = 0; i < n_segs; ++i) {
 		size_t j;
-		mm_sketch2(km, seqs[i], qlens[i], mi->w, mi->k, i, mi->flag&MM_I_HPC, mi->flag&MM_I_SYNCMER, mv);
+		mm_sketch(km, seqs[i], qlens[i], mi->w, mi->k, i, mi->flag&MM_I_HPC, mv);
 		for (j = n; j < mv->n; ++j)
 			mv->a[j].y += sum << 1;
 		if (opt->sdust_thres > 0) // mask low-complexity minimizers

minimap.h

@@ -5,7 +5,7 @@
 #include <stdio.h>
 #include <sys/types.h>
 
-#define MM_VERSION "2.24-r1171-dirty"
+#define MM_VERSION "2.25-r1173"
 
 #define MM_F_NO_DIAG       (0x001LL) // no exact diagonal hit
 #define MM_F_NO_DUAL       (0x002LL) // skip pairs where query name is lexicographically larger than target name
@@ -48,7 +48,6 @@
 #define MM_I_HPC          0x1
 #define MM_I_NO_SEQ       0x2
 #define MM_I_NO_NAME      0x4
-#define MM_I_SYNCMER      0x8
 
 #define MM_IDX_MAGIC   "MMI\2"
 

minimap2.1

@@ -1,4 +1,4 @@
-.TH minimap2 1 "18 December 2021" "minimap2-2.24 (r1122)" "Bioinformatics tools"
+.TH minimap2 1 "25 April 2023" "minimap2-2.25 (r1173)" "Bioinformatics tools"
 .SH NAME
 .PP
 minimap2 - mapping and alignment between collections of DNA sequences

misc/paftools.js

@@ -1,6 +1,6 @@
 #!/usr/bin/env k8
 
-var paftools_version = '2.24-r1152-dirty';
+var paftools_version = '2.25-r1173';
 
 /*****************************
  ***** Library functions *****

mmpriv.h

@@ -60,8 +60,6 @@ void radix_sort_64(uint64_t *beg, uint64_t *end);
 uint32_t ks_ksmall_uint32_t(size_t n, uint32_t arr[], size_t kk);
 
 void mm_sketch(void *km, const char *str, int len, int w, int k, uint32_t rid, int is_hpc, mm128_v *p);
-void mm_sketch_syncmer(void *km, const char *str, int len, int smer, int k, uint32_t rid, int is_hpc, mm128_v *p);
-void mm_sketch2(void *km, const char *str, int len, int w, int k, uint32_t rid, int is_hpc, int is_syncmer, mm128_v *p);
 
 mm_seed_t *mm_collect_matches(void *km, int *_n_m, int qlen, int max_occ, int max_max_occ, int dist, const mm_idx_t *mi, const mm128_v *mv, int64_t *n_a, int *rep_len, int *n_mini_pos, uint64_t **mini_pos);
 void mm_seed_mz_flt(void *km, mm128_v *mv, int32_t q_occ_max, float q_occ_frac);

python/mappy.pyx

@@ -3,7 +3,7 @@ from libc.stdlib cimport free
 cimport cmappy
 import sys
 
-__version__ = '2.24'
+__version__ = '2.25'
 
 cmappy.mm_reset_timer()
 

setup.py

@@ -34,7 +34,7 @@ def compile_libminimap2(*args, **kwargs):
 
 setup(
 	name = 'mappy',
-	version = '2.24',
+	version = '2.25',
 	url = 'https://github.com/lh3/minimap2',
 	description = 'Minimap2 python binding',
 	long_description = readme(),

sketch.c

@@ -141,58 +141,3 @@ void mm_sketch(void *km, const char *str, int len, int w, int k, uint32_t rid, i
 	if (min.x != UINT64_MAX)
 		kv_push(mm128_t, km, *p, min);
 }
-
-void mm_sketch_syncmer(void *km, const char *str, int len, int smer, int k, uint32_t rid, int is_hpc, mm128_v *p)
-{
-	uint64_t shift1 = 2 * (k - 1), mask = (1ULL<<2*k) - 1, smask = (1ULL<<2*smer) - 1, kmer[2] = {0,0};
-	int i, j, l, buf_pos, min_pos, kmer_span = 0;
-	tiny_queue_t tq;
-
-	assert(len > 0 && (smer > 0 && smer <= k) && (k > 0 && k <= 28)); // 56 bits for k-mer; could use long k-mers, but 28 enough in practice
-	memset(&tq, 0, sizeof(tiny_queue_t));
-	kv_resize(mm128_t, km, *p, p->n + len/(k - smer));
-
-	for (i = l = buf_pos = min_pos = 0; i < len; ++i) {
-		int c = seq_nt4_table[(uint8_t)str[i]];
-		if (c < 4) { // not an ambiguous base
-			int z;
-			if (is_hpc) {
-				int skip_len = 1;
-				if (i + 1 < len && seq_nt4_table[(uint8_t)str[i + 1]] == c) {
-					for (skip_len = 2; i + skip_len < len; ++skip_len)
-						if (seq_nt4_table[(uint8_t)str[i + skip_len]] != c)
-							break;
-					i += skip_len - 1; // put $i at the end of the current homopolymer run
-				}
-				tq_push(&tq, skip_len);
-				kmer_span += skip_len;
-				if (tq.count > k) kmer_span -= tq_shift(&tq);
-			} else kmer_span = l + 1 < k? l + 1 : k;
-			kmer[0] = (kmer[0] << 2 | c) & mask;           // forward k-mer
-			kmer[1] = (kmer[1] >> 2) | (3ULL^c) << shift1; // reverse k-mer
-			if (kmer[0] == kmer[1]) continue; // skip "symmetric k-mers" as we don't know it strand
-			z = kmer[0] < kmer[1]? 0 : 1; // strand
-			++l;
-			if (l >= k && kmer_span < 256) {
-				uint64_t x, min = UINT64_MAX;
-				x = hash64(kmer[z], mask);
-				for (j = 0; j <= k - smer; ++j) {
-					uint64_t y = x >> (j + j) & smask;
-					min = min < y? min : y;
-				}
-				if ((x & smask) == min) {
-					mm128_t t;
-					t.x = x << 8 | kmer_span;
-					t.y = (uint64_t)rid<<32 | (uint32_t)i<<1 | z;
-					kv_push(mm128_t, km, *p, t);
-				}
-			}
-		} else l = 0, tq.count = tq.front = 0, kmer_span = 0;
-	}
-}
-
-void mm_sketch2(void *km, const char *str, int len, int w, int k, uint32_t rid, int is_hpc, int is_syncmer, mm128_v *p)
-{
-	if (is_syncmer) mm_sketch_syncmer(km, str, len, w, k, rid, is_hpc, p);
-	else mm_sketch(km, str, len, w, k, rid, is_hpc, p);
-}