minimap2 0.2.24.6 → 0.2.25.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 5a1518fb8048d902865ee6771fedc9cb9b42693c984ec6616c2d1407597a9f26
-  data.tar.gz: 83501abbd0cedb037edb96c6a630b7c93adff87597950ef03359be41dad0710a
+  metadata.gz: f58943e39da8f734af4ee4d16b5d335825ee7cf94cc45d9cf88a41d7adfe6afe
+  data.tar.gz: 2cb372b02bcb2cc763fb3a9fcd82219c653e61ac7f28a039e0a4d03b054aab35
 SHA512:
-  metadata.gz: d62d29fd4f5f8254f7fdaa9943cb1141a1fb2b832c33b30568fe659c6b4299a4827f596806c0d38368af53c63a48f1e1dcb2fe9562be7534fa3b1697a8b6b3de
-  data.tar.gz: 86e8179090acf840d615b3172fd1aa92e39c3b106c7629d079dfc473bb1a81180a922c13a19e60e41b54c6fda37534c6e61d9107f756bb87410ffa3fd87b93ce
+  metadata.gz: 52c827db192ac69bf99cfa1e8ff701a4d87965b7f443a82cdd10d109eebf31a6ac2ca966cc5b4a9d3bdcf1fdb4180f51a0f1c78f1bc6c5e937419ad3a78fa5d3
+  data.tar.gz: 95fd63410ffc2aa088877c9545566aa32326899658ff5fb9ec92ac9cc1c8d89c28c6a849e50bd50d5fce4bc33c6af8b3f40a65c0270f7a6ccec181375c549fb1

data/README.md

@@ -175,9 +175,8 @@ ruby-minimap2 is a library under development and there are many points to be imp
 
 Please feel free to report [bugs](https://github.com/kojix2/ruby-minimap2/issues) and [pull requests](https://github.com/kojix2/ruby-minimap2/pulls)!
 
-    Do you need commit rights to my repository?
-    Do you want to get admin rights and take over the project?
-    If so, please feel free to contact me @kojix2.
+Many OSS projects become abandoned because only the founder has commit rights to the original repository. 
+If you need commit rights to ruby-minimap2 repository or want to get admin rights and take over the project, please feel free to contact me @kojix2.
 
 ## License
 

data/ext/minimap2/Makefile

@@ -8,6 +8,10 @@ PROG=		minimap2
 PROG_EXTRA=	sdust minimap2-lite
 LIBS=		-lm -lz -lpthread
 
+ifneq ($(aarch64),)
+	arm_neon=1
+endif
+
 ifeq ($(arm_neon),) # if arm_neon is not defined
 ifeq ($(sse2only),) # if sse2only is not defined
 	OBJS+=ksw2_extz2_sse41.o ksw2_extd2_sse41.o ksw2_exts2_sse41.o ksw2_extz2_sse2.o ksw2_extd2_sse2.o ksw2_exts2_sse2.o ksw2_dispatch.o
@@ -26,12 +30,12 @@ endif
 
 ifneq ($(asan),)
 	CFLAGS+=-fsanitize=address
-	LIBS+=-fsanitize=address
+	LIBS+=-fsanitize=address -ldl
 endif
 
 ifneq ($(tsan),)
 	CFLAGS+=-fsanitize=thread
-	LIBS+=-fsanitize=thread
+	LIBS+=-fsanitize=thread -ldl
 endif
 
 .PHONY:all extra clean depend

data/ext/minimap2/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)
 -------------------------------------
 

data/ext/minimap2/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
@@ -350,6 +350,11 @@ If you use minimap2 in your work, please cite:
 > Li, H. (2018). Minimap2: pairwise alignment for nucleotide sequences.
 > *Bioinformatics*, **34**:3094-3100. [doi:10.1093/bioinformatics/bty191][doi]
 
+and/or:
+
+> Li, H. (2021). New strategies to improve minimap2 alignment accuracy.
+> *Bioinformatics*, **37**:4572-4574. [doi:10.1093/bioinformatics/btab705][doi2]
+
 ## <a name="dguide"></a>Developers' Guide
 
 Minimap2 is not only a command line tool, but also a programming library.
@@ -399,5 +404,6 @@ mappy` or [from BioConda][mappyconda] via `conda install -c bioconda mappy`.
 [manpage]: https://lh3.github.io/minimap2/minimap2.html
 [manpage-cs]: https://lh3.github.io/minimap2/minimap2.html#10
 [doi]: https://doi.org/10.1093/bioinformatics/bty191
-[smide]: https://github.com/nemequ/simde
+[doi2]: https://doi.org/10.1093/bioinformatics/btab705
+[simde]: https://github.com/nemequ/simde
 [unimap]: https://github.com/lh3/unimap

data/ext/minimap2/align.c

@@ -326,9 +326,11 @@ static void mm_align_pair(void *km, const mm_mapopt_t *opt, int qlen, const uint
 	if (opt->max_sw_mat > 0 && (int64_t)tlen * qlen > opt->max_sw_mat) {
 		ksw_reset_extz(ez);
 		ez->zdropped = 1;
-	} else if (opt->flag & MM_F_SPLICE)
-		ksw_exts2_sse(km, qlen, qseq, tlen, tseq, 5, mat, opt->q, opt->e, opt->q2, opt->noncan, zdrop, opt->junc_bonus, flag, junc, ez);
-	else if (opt->q == opt->q2 && opt->e == opt->e2)
+	} else if (opt->flag & MM_F_SPLICE) {
+		int flag_tmp = flag;
+		if (!(opt->flag & MM_F_SPLICE_OLD)) flag_tmp |= KSW_EZ_SPLICE_CMPLX;
+		ksw_exts2_sse(km, qlen, qseq, tlen, tseq, 5, mat, opt->q, opt->e, opt->q2, opt->noncan, zdrop, opt->junc_bonus, flag_tmp, junc, ez);
+	} else if (opt->q == opt->q2 && opt->e == opt->e2)
 		ksw_extz2_sse(km, qlen, qseq, tlen, tseq, 5, mat, opt->q, opt->e, w, zdrop, end_bonus, flag, ez);
 	else
 		ksw_extd2_sse(km, qlen, qseq, tlen, tseq, 5, mat, opt->q, opt->e, opt->q2, opt->e2, w, zdrop, end_bonus, flag, ez);

data/ext/minimap2/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 -

data/ext/minimap2/format.c

@@ -119,6 +119,7 @@ int mm_write_sam_hdr(const mm_idx_t *idx, const char *rg, const char *ver, int a
 {
 	kstring_t str = {0,0,0};
 	int ret = 0;
+	mm_sprintf_lite(&str, "@HD\tVN:1.6\tSO:unsorted\tGO:query\n");
 	if (idx) {
 		uint32_t i;
 		for (i = 0; i < idx->n_seq; ++i)
@@ -369,14 +370,16 @@ static void write_sam_cigar(kstring_t *s, int sam_flag, int in_tag, int qlen, co
 		clip_len[0] = r->rev? qlen - r->qe : r->qs;
 		clip_len[1] = r->rev? r->qs : qlen - r->qe;
 		if (in_tag) {
-			int clip_char = (sam_flag&0x800) && !(opt_flag&MM_F_SOFTCLIP)? 5 : 4;
+			int clip_char = (((sam_flag&0x800) || ((sam_flag&0x100) && (opt_flag&MM_F_SECONDARY_SEQ))) &&
+							 !(opt_flag&MM_F_SOFTCLIP)) ? 5 : 4;
 			mm_sprintf_lite(s, "\tCG:B:I");
 			if (clip_len[0]) mm_sprintf_lite(s, ",%u", clip_len[0]<<4|clip_char);
 			for (k = 0; k < r->p->n_cigar; ++k)
 				mm_sprintf_lite(s, ",%u", r->p->cigar[k]);
 			if (clip_len[1]) mm_sprintf_lite(s, ",%u", clip_len[1]<<4|clip_char);
 		} else {
-			int clip_char = (sam_flag&0x800) && !(opt_flag&MM_F_SOFTCLIP)? 'H' : 'S';
+			int clip_char = (((sam_flag&0x800) || ((sam_flag&0x100) && (opt_flag&MM_F_SECONDARY_SEQ))) &&
+							 !(opt_flag&MM_F_SOFTCLIP)) ? 'H' : 'S';
 			assert(clip_len[0] < qlen && clip_len[1] < qlen);
 			if (clip_len[0]) mm_sprintf_lite(s, "%d%c", clip_len[0], clip_char);
 			for (k = 0; k < r->p->n_cigar; ++k)
@@ -451,7 +454,7 @@ void mm_write_sam3(kstring_t *s, const mm_idx_t *mi, const mm_bseq1_t *t, int se
 		if (cigar_in_tag) {
 			int slen;
 			if ((flag & 0x900) == 0 || (opt_flag & MM_F_SOFTCLIP)) slen = t->l_seq;
-			else if (flag & 0x100) slen = 0;
+			else if ((flag & 0x100) && !(opt_flag & MM_F_SECONDARY_SEQ)) slen = 0;
 			else slen = r->qe - r->qs;
 			mm_sprintf_lite(s, "%dS%dN", slen, r->re - r->rs);
 		} else write_sam_cigar(s, flag, 0, t->l_seq, r, opt_flag);
@@ -492,7 +495,7 @@ void mm_write_sam3(kstring_t *s, const mm_idx_t *mi, const mm_bseq1_t *t, int se
 			mm_sprintf_lite(s, "\t");
 			if (t->qual) sam_write_sq(s, t->qual, t->l_seq, r->rev, 0);
 			else mm_sprintf_lite(s, "*");
-		} else if (flag & 0x100) {
+		} else if ((flag & 0x100) && !(opt_flag & MM_F_SECONDARY_SEQ)){
 			mm_sprintf_lite(s, "*\t*");
 		} else {
 			sam_write_sq(s, t->seq + r->qs, r->qe - r->qs, r->rev, r->rev);

data/ext/minimap2/kalloc.c

@@ -40,7 +40,8 @@ void *km_init2(void *km_par, size_t min_core_size)
 	kmem_t *km;
 	km = (kmem_t*)kcalloc(km_par, 1, sizeof(kmem_t));
 	km->par = km_par;
-	km->min_core_size = min_core_size > 0? min_core_size : 0x80000;
+	if (km_par) km->min_core_size = min_core_size > 0? min_core_size : ((kmem_t*)km_par)->min_core_size - 2;
+	else km->min_core_size = min_core_size > 0? min_core_size : 0x80000;
 	return (void*)km;
 }
 
@@ -183,6 +184,16 @@ void *krealloc(void *_km, void *ap, size_t n_bytes) // TODO: this can be made mo
 	return q;
 }
 
+void *krelocate(void *km, void *ap, size_t n_bytes)
+{
+	void *p;
+	if (km == 0 || ap == 0) return ap;
+	p = kmalloc(km, n_bytes);
+	memcpy(p, ap, n_bytes);
+	kfree(km, ap);
+	return p;
+}
+
 void km_stat(const void *_km, km_stat_t *s)
 {
 	kmem_t *km = (kmem_t*)_km;
@@ -203,3 +214,11 @@ void km_stat(const void *_km, km_stat_t *s)
 		s->largest = s->largest > size? s->largest : size;
 	}
 }
+
+void km_stat_print(const void *km)
+{
+	km_stat_t st;
+	km_stat(km, &st);
+	fprintf(stderr, "[km_stat] cap=%ld, avail=%ld, largest=%ld, n_core=%ld, n_block=%ld\n",
+			st.capacity, st.available, st.largest, st.n_blocks, st.n_cores);
+}

data/ext/minimap2/kalloc.h

@@ -13,6 +13,7 @@ typedef struct {
 
 void *kmalloc(void *km, size_t size);
 void *krealloc(void *km, void *ptr, size_t size);
+void *krelocate(void *km, void *ap, size_t n_bytes);
 void *kcalloc(void *km, size_t count, size_t size);
 void kfree(void *km, void *ptr);
 
@@ -20,11 +21,21 @@ void *km_init(void);
 void *km_init2(void *km_par, size_t min_core_size);
 void km_destroy(void *km);
 void km_stat(const void *_km, km_stat_t *s);
+void km_stat_print(const void *km);
 
 #ifdef __cplusplus
 }
 #endif
 
+#define Kmalloc(km, type, cnt)       ((type*)kmalloc((km), (cnt) * sizeof(type)))
+#define Kcalloc(km, type, cnt)       ((type*)kcalloc((km), (cnt), sizeof(type)))
+#define Krealloc(km, type, ptr, cnt) ((type*)krealloc((km), (ptr), (cnt) * sizeof(type)))
+
+#define Kexpand(km, type, a, m) do { \
+		(m) = (m) >= 4? (m) + ((m)>>1) : 16; \
+		(a) = Krealloc(km, type, (a), (m)); \
+	} while (0)
+
 #define KMALLOC(km, ptr, len) ((ptr) = (__typeof__(ptr))kmalloc((km), (len) * sizeof(*(ptr))))
 #define KCALLOC(km, ptr, len) ((ptr) = (__typeof__(ptr))kcalloc((km), (len), sizeof(*(ptr))))
 #define KREALLOC(km, ptr, len) ((ptr) = (__typeof__(ptr))krealloc((km), (ptr), (len) * sizeof(*(ptr))))
@@ -50,7 +61,7 @@ void km_stat(const void *_km, km_stat_t *s);
 	} kmp_##name##_t; \
 	SCOPE kmp_##name##_t *kmp_init_##name(void *km) { \
 		kmp_##name##_t *mp; \
-		KCALLOC(km, mp, 1); \
+		mp = Kcalloc(km, kmp_##name##_t, 1); \
 		mp->km = km; \
 		return mp; \
 	} \
@@ -66,7 +77,7 @@ void km_stat(const void *_km, km_stat_t *s);
 	} \
 	SCOPE void kmp_free_##name(kmp_##name##_t *mp, kmptype_t *p) { \
 		--mp->cnt; \
-		if (mp->n == mp->max) KEXPAND(mp->km, mp->buf, mp->max); \
+		if (mp->n == mp->max) Kexpand(mp->km, kmptype_t*, mp->buf, mp->max); \
 		mp->buf[mp->n++] = p; \
 	}
 

data/ext/minimap2/ksw2.h

@@ -15,6 +15,7 @@
 #define KSW_EZ_SPLICE_FOR  0x100
 #define KSW_EZ_SPLICE_REV  0x200
 #define KSW_EZ_SPLICE_FLANK 0x400
+#define KSW_EZ_SPLICE_CMPLX 0x800
 
 // The subset of CIGAR operators used by ksw code.
 // Use MM_CIGAR_* from minimap.h if you need the full list.

data/ext/minimap2/ksw2_extd2_sse.c

@@ -358,7 +358,7 @@ void ksw_extd2_sse(void *km, int qlen, const uint8_t *query, int tlen, const uin
 			} else H[0] = v8[0] - qe, max_H = H[0], max_t = 0; // special casing r==0
 			// update ez
 			if (en0 == tlen - 1 && H[en0] > ez->mte)
-				ez->mte = H[en0], ez->mte_q = r - en;
+				ez->mte = H[en0], ez->mte_q = r - en0;
 			if (r - st0 == qlen - 1 && H[st0] > ez->mqe)
 				ez->mqe = H[st0], ez->mqe_t = st0;
 			if (ksw_apply_zdrop(ez, 1, max_H, r, max_t, zdrop, e2)) break;

data/ext/minimap2/ksw2_exts2_sse.c

@@ -71,6 +71,7 @@ void ksw_exts2_sse(void *km, int qlen, const uint8_t *query, int tlen, const uin
 
 	ksw_reset_extz(ez);
 	if (m <= 1 || qlen <= 0 || tlen <= 0 || q2 <= q + e) return;
+	assert((flag & KSW_EZ_SPLICE_FOR) == 0 || (flag & KSW_EZ_SPLICE_REV) == 0); // can't be both set
 
 	zero_   = _mm_set1_epi8(0);
 	q_      = _mm_set1_epi8(q);
@@ -118,55 +119,93 @@ void ksw_exts2_sse(void *km, int qlen, const uint8_t *query, int tlen, const uin
 
 	// set the donor and acceptor arrays. TODO: this assumes 0/1/2/3 encoding!
 	if (flag & (KSW_EZ_SPLICE_FOR|KSW_EZ_SPLICE_REV)) {
-		int semi_cost = flag&KSW_EZ_SPLICE_FLANK? -noncan/2 : 0; // GTr or yAG is worth 0.5 bit; see PMID:18688272
-		memset(donor, -noncan, tlen_ * 16);
-		memset(acceptor, -noncan, tlen_ * 16);
+		const int sp0[4] = { 8, 15, 21, 30 };
+		int sp[4];
+		if (flag & KSW_EZ_SPLICE_CMPLX) {
+			for (t = 0; t < 4; ++t)
+				sp[t] = (int)((double)sp0[t] / 3. + .499);
+		} else {
+			sp[0] = flag&KSW_EZ_SPLICE_FLANK? noncan / 2 : 0;
+			sp[1] = sp[2] = sp[3] = noncan;
+		}
+		memset(donor,    -sp[3], tlen_ * 16);
+		memset(acceptor, -sp[3], tlen_ * 16);
 		if (!(flag & KSW_EZ_REV_CIGAR)) {
 			for (t = 0; t < tlen - 4; ++t) {
-				int can_type = 0; // type of canonical site: 0=none, 1=GT/AG only, 2=GTr/yAG
-				if ((flag & KSW_EZ_SPLICE_FOR) && target[t+1] == 2 && target[t+2] == 3) can_type = 1; // GTr...
-				if ((flag & KSW_EZ_SPLICE_REV) && target[t+1] == 1 && target[t+2] == 3) can_type = 1; // CTr...
-				if (can_type && (target[t+3] == 0 || target[t+3] == 2)) can_type = 2;
-				if (can_type) ((int8_t*)donor)[t] = can_type == 2? 0 : semi_cost;
+				int z = 3;
+				if (flag & KSW_EZ_SPLICE_FOR) {
+					if (target[t+1] == 2 && target[t+2] == 3)             // |GT.
+						z = target[t+3] == 0 || target[t+3] == 2? -1 : 0; // |GTr or not
+					else if (target[t+1] == 2 && target[t+2] == 1) z = 1; // |GC.
+					else if (target[t+1] == 0 && target[t+2] == 3) z = 2; // |AT.
+				} else if (flag & KSW_EZ_SPLICE_REV) {
+					if (target[t+1] == 1 && target[t+2] == 3)             // |CT. (revcomp of .AG|)
+						z = target[t+3] == 0 || target[t+3] == 2? -1 : 0;
+					else if (target[t+1] == 2 && target[t+2] == 3) z = 2; // |GT. (revcomp of .AC|)
+				}
+				((int8_t*)donor)[t] = z < 0? 0 : -sp[z];
 			}
-			if (junc)
-				for (t = 0; t < tlen - 1; ++t)
-					if (((flag & KSW_EZ_SPLICE_FOR) && (junc[t+1]&1)) || ((flag & KSW_EZ_SPLICE_REV) && (junc[t+1]&8)))
-						((int8_t*)donor)[t] += junc_bonus;
 			for (t = 2; t < tlen; ++t) {
-				int can_type = 0;
-				if ((flag & KSW_EZ_SPLICE_FOR) && target[t-1] == 0 && target[t] == 2) can_type = 1; // ...yAG
-				if ((flag & KSW_EZ_SPLICE_REV) && target[t-1] == 0 && target[t] == 1) can_type = 1; // ...yAC
-				if (can_type && (target[t-2] == 1 || target[t-2] == 3)) can_type = 2;
-				if (can_type) ((int8_t*)acceptor)[t] = can_type == 2? 0 : semi_cost;
+				int z = 3;
+				if (flag & KSW_EZ_SPLICE_FOR) {
+					if (target[t-1] == 0 && target[t] == 2)               // .AG|
+						z = target[t-2] == 1 || target[t-2] == 3? -1 : 0; // yAG| or not
+					else if (target[t-1] == 0 && target[t] == 1) z = 2;   // .AC|
+				} else if (flag & KSW_EZ_SPLICE_REV) {
+					if (target[t-1] == 0 && target[t] == 1)               // .AC| (revcomp of |GT.)
+						z = target[t-2] == 1 || target[t-2] == 3? -1 : 0; // yAC| or not
+					else if (target[t-1] == 2 && target[t] == 1) z = 1;   // .GC| (revcomp of |GC.)
+					else if (target[t-1] == 0 && target[t] == 3) z = 2;   // .AT| (revcomp of |AT.)
+				}
+				((int8_t*)acceptor)[t] = z < 0? 0 : -sp[z];
 			}
-			if (junc)
-				for (t = 0; t < tlen; ++t)
-					if (((flag & KSW_EZ_SPLICE_FOR) && (junc[t]&2)) || ((flag & KSW_EZ_SPLICE_REV) && (junc[t]&4)))
-						((int8_t*)acceptor)[t] += junc_bonus;
 		} else {
 			for (t = 0; t < tlen - 4; ++t) {
-				int can_type = 0; // type of canonical site: 0=none, 1=GT/AG only, 2=GTr/yAG
-				if ((flag & KSW_EZ_SPLICE_FOR) && target[t+1] == 2 && target[t+2] == 0) can_type = 1; // GAy...
-				if ((flag & KSW_EZ_SPLICE_REV) && target[t+1] == 1 && target[t+2] == 0) can_type = 1; // CAy...
-				if (can_type && (target[t+3] == 1 || target[t+3] == 3)) can_type = 2;
-				if (can_type) ((int8_t*)donor)[t] = can_type == 2? 0 : semi_cost;
+				int z = 3;
+				if (flag & KSW_EZ_SPLICE_FOR) {
+					if (target[t+1] == 2 && target[t+2] == 0)             // |GA. (rev of .AG|)
+						z = target[t+3] == 1 || target[t+3] == 3? -1 : 0;
+					else if (target[t+1] == 1 && target[t+2] == 0) z = 2; // |CA. (rev of .AC|)
+				} else if (flag & KSW_EZ_SPLICE_REV) {
+					if (target[t+1] == 1 && target[t+2] == 0)             // |CA. (comp of |GT.)
+						z = target[t+3] == 1 || target[t+3] == 3? -1 : 0;
+					else if (target[t+1] == 1 && target[t+2] == 2) z = 1; // |CG. (comp of |GC.)
+					else if (target[t+1] == 3 && target[t+2] == 0) z = 2; // |TA. (comp of |AT.)
+				}
+				((int8_t*)donor)[t] = z < 0? 0 : -sp[z];
 			}
-			if (junc)
-				for (t = 0; t < tlen - 1; ++t)
-					if (((flag & KSW_EZ_SPLICE_FOR) && (junc[t+1]&2)) || ((flag & KSW_EZ_SPLICE_REV) && (junc[t+1]&4)))
-						((int8_t*)donor)[t] += junc_bonus;
 			for (t = 2; t < tlen; ++t) {
-				int can_type = 0;
-				if ((flag & KSW_EZ_SPLICE_FOR) && target[t-1] == 3 && target[t] == 2) can_type = 1; // ...rTG
-				if ((flag & KSW_EZ_SPLICE_REV) && target[t-1] == 3 && target[t] == 1) can_type = 1; // ...rTC
-				if (can_type && (target[t-2] == 0 || target[t-2] == 2)) can_type = 2;
-				if (can_type) ((int8_t*)acceptor)[t] = can_type == 2? 0 : semi_cost;
+				int z = 3;
+				if (flag & KSW_EZ_SPLICE_FOR) {
+					if (target[t-1] == 3 && target[t] == 2)               // .TG| (rev of |GT.)
+						z = target[t-2] == 0 || target[t-2] == 2? -1 : 0;
+					else if (target[t-1] == 1 && target[t] == 2) z = 1;   // .CG| (rev of |GC.)
+					else if (target[t-1] == 3 && target[t] == 0) z = 2;   // .TA| (rev of |AT.)
+				} else if (flag & KSW_EZ_SPLICE_REV) {
+					if (target[t-1] == 3 && target[t] == 1)               // .TC| (comp of .AG|)
+						z = target[t-2] == 0 || target[t-2] == 2? -1 : 0;
+					else if (target[t-1] == 3 && target[t] == 2) z = 2;   // .TG| (comp of .AC|)
+				}
+				((int8_t*)acceptor)[t] = z < 0? 0 : -sp[z];
 			}
-			if (junc)
-				for (t = 0; t < tlen; ++t)
-					if (((flag & KSW_EZ_SPLICE_FOR) && (junc[t]&1)) || ((flag & KSW_EZ_SPLICE_REV) && (junc[t]&8)))
-						((int8_t*)acceptor)[t] += junc_bonus;
+		}
+	}
+
+	if (junc) {
+		if (!(flag & KSW_EZ_REV_CIGAR)) {
+			for (t = 0; t < tlen - 1; ++t)
+				if (((flag & KSW_EZ_SPLICE_FOR) && (junc[t+1]&1)) || ((flag & KSW_EZ_SPLICE_REV) && (junc[t+1]&8)))
+					((int8_t*)donor)[t] += junc_bonus;
+			for (t = 0; t < tlen; ++t)
+				if (((flag & KSW_EZ_SPLICE_FOR) && (junc[t]&2)) || ((flag & KSW_EZ_SPLICE_REV) && (junc[t]&4)))
+					((int8_t*)acceptor)[t] += junc_bonus;
+		} else {
+			for (t = 0; t < tlen - 1; ++t)
+				if (((flag & KSW_EZ_SPLICE_FOR) && (junc[t+1]&2)) || ((flag & KSW_EZ_SPLICE_REV) && (junc[t+1]&4)))
+					((int8_t*)donor)[t] += junc_bonus;
+			for (t = 0; t < tlen; ++t)
+				if (((flag & KSW_EZ_SPLICE_FOR) && (junc[t]&1)) || ((flag & KSW_EZ_SPLICE_REV) && (junc[t]&8)))
+					((int8_t*)acceptor)[t] += junc_bonus;
 		}
 	}
 
@@ -376,7 +415,7 @@ void ksw_exts2_sse(void *km, int qlen, const uint8_t *query, int tlen, const uin
 			} else H[0] = v8[0] - qe, max_H = H[0], max_t = 0; // special casing r==0
 			// update ez
 			if (en0 == tlen - 1 && H[en0] > ez->mte)
-				ez->mte = H[en0], ez->mte_q = r - en;
+				ez->mte = H[en0], ez->mte_q = r - en0;
 			if (r - st0 == qlen - 1 && H[st0] > ez->mqe)
 				ez->mqe = H[st0], ez->mqe_t = st0;
 			if (ksw_apply_zdrop(ez, 1, max_H, r, max_t, zdrop, 0)) break;

data/ext/minimap2/ksw2_extz2_sse.c

@@ -269,7 +269,7 @@ void ksw_extz2_sse(void *km, int qlen, const uint8_t *query, int tlen, const uin
 			} else H[0] = v8[0] - qe - qe, max_H = H[0], max_t = 0; // special casing r==0
 			// update ez
 			if (en0 == tlen - 1 && H[en0] > ez->mte)
-				ez->mte = H[en0], ez->mte_q = r - en;
+				ez->mte = H[en0], ez->mte_q = r - en0;
 			if (r - st0 == qlen - 1 && H[st0] > ez->mqe)
 				ez->mqe = H[st0], ez->mqe_t = st0;
 			if (ksw_apply_zdrop(ez, 1, max_H, r, max_t, zdrop, e)) break;

data/ext/minimap2/lchain.c

@@ -35,7 +35,7 @@ uint64_t *mg_chain_backtrack(void *km, int64_t n, const int32_t *f, const int64_
 	for (i = 0, n_z = 0; i < n; ++i) // precompute n_z
 		if (f[i] >= min_sc) ++n_z;
 	if (n_z == 0) return 0;
-	KMALLOC(km, z, n_z);
+	z = Kmalloc(km, mm128_t, n_z);
 	for (i = 0, k = 0; i < n; ++i) // populate z[]
 		if (f[i] >= min_sc) z[k].x = f[i], z[k++].y = i;
 	radix_sort_128x(z, z + n_z);
@@ -54,7 +54,7 @@ uint64_t *mg_chain_backtrack(void *km, int64_t n, const int32_t *f, const int64_
 			else n_v = n_v0;
 		}
 	}
-	KMALLOC(km, u, n_u);
+	u = Kmalloc(km, uint64_t, n_u);
 	memset(t, 0, n * 4);
 	for (k = n_z - 1, n_v = n_u = 0; k >= 0; --k) { // populate u[]
 		if (t[z[k].y] == 0) {
@@ -82,7 +82,7 @@ static mm128_t *compact_a(void *km, int32_t n_u, uint64_t *u, int32_t n_v, int32
 	int64_t i, j, k;
 
 	// write the result to b[]
-	KMALLOC(km, b, n_v);
+	b = Kmalloc(km, mm128_t, n_v);
 	for (i = 0, k = 0; i < n_u; ++i) {
 		int32_t k0 = k, ni = (int32_t)u[i];
 		for (j = 0; j < ni; ++j)
@@ -91,13 +91,13 @@ static mm128_t *compact_a(void *km, int32_t n_u, uint64_t *u, int32_t n_v, int32
 	kfree(km, v);
 
 	// sort u[] and a[] by the target position, such that adjacent chains may be joined
-	KMALLOC(km, w, n_u);
+	w = Kmalloc(km, mm128_t, n_u);
 	for (i = k = 0; i < n_u; ++i) {
 		w[i].x = b[k].x, w[i].y = (uint64_t)k<<32|i;
 		k += (int32_t)u[i];
 	}
 	radix_sort_128x(w, w + n_u);
-	KMALLOC(km, u2, n_u);
+	u2 = Kmalloc(km, uint64_t, n_u);
 	for (i = k = 0; i < n_u; ++i) {
 		int32_t j = (int32_t)w[i].y, n = (int32_t)u[j];
 		u2[i] = u[j];
@@ -138,7 +138,7 @@ static inline int32_t comput_sc(const mm128_t *ai, const mm128_t *aj, int32_t ma
 }
 
 /* Input:
- *   a[].x: tid<<33 | rev<<32 | tpos
+ *   a[].x: rev<<63 | tid<<32 | tpos
  *   a[].y: flags<<40 | q_span<<32 | q_pos
  * Output:
  *   n_u: #chains
@@ -160,10 +160,10 @@ mm128_t *mg_lchain_dp(int max_dist_x, int max_dist_y, int bw, int max_skip, int
 	if (max_dist_x < bw) max_dist_x = bw;
 	if (max_dist_y < bw && !is_cdna) max_dist_y = bw;
 	if (is_cdna) max_drop = INT32_MAX;
-	KMALLOC(km, p, n);
-	KMALLOC(km, f, n);
-	KMALLOC(km, v, n);
-	KCALLOC(km, t, n);
+	p = Kmalloc(km, int64_t, n);
+	f = Kmalloc(km, int32_t, n);
+	v = Kmalloc(km, int32_t, n);
+	t = Kcalloc(km, int32_t, n);
 
 	// fill the score and backtrack arrays
 	for (i = 0, max_ii = -1; i < n; ++i) {
@@ -251,7 +251,7 @@ mm128_t *mg_lchain_rmq(int max_dist, int max_dist_inner, int bw, int max_chn_ski
 					   int64_t n, mm128_t *a, int *n_u_, uint64_t **_u, void *km)
 {
 	int32_t *f,*t, *v, n_u, n_v, mmax_f = 0, max_rmq_size = 0, max_drop = bw;
-	int64_t *p, i, i0, st = 0, st_inner = 0, n_iter = 0;
+	int64_t *p, i, i0, st = 0, st_inner = 0;
 	uint64_t *u;
 	lc_elem_t *root = 0, *root_inner = 0;
 	void *mem_mp = 0;
@@ -264,10 +264,10 @@ mm128_t *mg_lchain_rmq(int max_dist, int max_dist_inner, int bw, int max_chn_ski
 	}
 	if (max_dist < bw) max_dist = bw;
 	if (max_dist_inner <= 0 || max_dist_inner >= max_dist) max_dist_inner = 0;
-	KMALLOC(km, p, n);
-	KMALLOC(km, f, n);
-	KCALLOC(km, t, n);
-	KMALLOC(km, v, n);
+	p = Kmalloc(km, int64_t, n);
+	f = Kmalloc(km, int32_t, n);
+	t = Kcalloc(km, int32_t, n);
+	v = Kmalloc(km, int32_t, n);
 	mem_mp = km_init2(km, 0x10000);
 	mp = kmp_init_rmq(mem_mp);
 
@@ -345,7 +345,6 @@ mm128_t *mg_lchain_rmq(int max_dist, int max_dist_inner, int bw, int max_chn_ski
 						}
 						if (!krmq_itr_prev(lc_elem, &itr)) break;
 					}
-					n_iter += n_rmq_iter;
 				}
 			}
 		}

data/ext/minimap2/main.c

@@ -7,8 +7,6 @@
 #include "mmpriv.h"
 #include "ketopt.h"
 
-#define MM_VERSION "2.24-r1122"
-
 #ifdef __linux__
 #include <sys/resource.h>
 #include <sys/time.h>
@@ -78,6 +76,7 @@ static ko_longopt_t long_options[] = {
 	{ "chain-skip-scale",ko_required_argument,351 },
 	{ "print-chains",   ko_no_argument,       352 },
 	{ "no-hash-name",   ko_no_argument,       353 },
+	{ "secondary-seq",  ko_no_argument,       354 },
 	{ "help",           ko_no_argument,       'h' },
 	{ "max-intron-len", ko_required_argument, 'G' },
 	{ "version",        ko_no_argument,       'V' },
@@ -121,7 +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:";
+	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;
@@ -187,7 +186,12 @@ int main(int argc, char *argv[])
 		else if (c == 'R') rg = o.arg;
 		else if (c == 'h') fp_help = stdout;
 		else if (c == '2') opt.flag |= MM_F_2_IO_THREADS;
-		else if (c == 'o') {
+		else if (c == 'J') {
+			int t;
+			t = atoi(o.arg);
+			if (t == 0) opt.flag |= MM_F_SPLICE_OLD;
+			else if (t == 1) opt.flag &= ~MM_F_SPLICE_OLD;
+		} else if (c == 'o') {
 			if (strcmp(o.arg, "-") != 0) {
 				if (freopen(o.arg, "wb", stdout) == NULL) {
 					fprintf(stderr, "[ERROR]\033[1;31m failed to write the output to file '%s'\033[0m: %s\n", o.arg, strerror(errno));
@@ -237,6 +241,7 @@ int main(int argc, char *argv[])
 		else if (c == 350) opt.q_occ_frac = atof(o.arg); // --q-occ-frac
 		else if (c == 352) mm_dbg_flag |= MM_DBG_PRINT_CHAIN; // --print-chains
 		else if (c == 353) opt.flag |= MM_F_NO_HASH_NAME; // --no-hash-name
+		else if (c == 354) opt.flag |= MM_F_SECONDARY_SEQ; // --secondary-seq
 		else if (c == 330) {
 			fprintf(stderr, "[WARNING] \033[1;31m --lj-min-ratio has been deprecated.\033[0m\n");
 		} else if (c == 314) { // --frag
@@ -261,7 +266,8 @@ int main(int argc, char *argv[])
 		} else if (c == 326) { // --dual
 			yes_or_no(&opt, MM_F_NO_DUAL, o.longidx, o.arg, 0);
 		} else if (c == 347) { // --rmq
-			yes_or_no(&opt, MM_F_RMQ, o.longidx, o.arg, 1);
+			if (o.arg) yes_or_no(&opt, MM_F_RMQ, o.longidx, o.arg, 1);
+			else opt.flag |= MM_F_RMQ;
 		} else if (c == 'S') {
 			opt.flag |= MM_F_OUT_CS | MM_F_CIGAR | MM_F_OUT_CS_LONG;
 			if (mm_verbose >= 2)
@@ -322,7 +328,7 @@ 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, "    -I NUM       split index for every ~NUM input bases [4G]\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");
 		fprintf(fp_help, "    -f FLOAT     filter out top FLOAT fraction of repetitive minimizers [%g]\n", opt.mid_occ_frac);
@@ -344,6 +350,7 @@ int main(int argc, char *argv[])
 		fprintf(fp_help, "    -z INT[,INT] Z-drop score and inversion Z-drop score [%d,%d]\n", opt.zdrop, opt.zdrop_inv);
 		fprintf(fp_help, "    -s INT       minimal peak DP alignment score [%d]\n", opt.min_dp_max);
 		fprintf(fp_help, "    -u CHAR      how to find GT-AG. f:transcript strand, b:both strands, n:don't match GT-AG [n]\n");
+		fprintf(fp_help, "    -J INT       splice mode. 0: original minimap2 model; 1: miniprot model [1]\n");
 		fprintf(fp_help, "  Input/Output:\n");
 		fprintf(fp_help, "    -a           output in the SAM format (PAF by default)\n");
 		fprintf(fp_help, "    -o FILE      output alignments to FILE [stdout]\n");

data/ext/minimap2/map.c

@@ -10,11 +10,6 @@
 #include "bseq.h"
 #include "khash.h"
 
-struct mm_tbuf_s {
-	void *km;
-	int rep_len, frag_gap;
-};
-
 mm_tbuf_t *mm_tbuf_init(void)
 {
 	mm_tbuf_t *b;