minimap2 0.2.25.0 → 0.2.25.2

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;

data/ext/minimap2/minimap.h

@@ -5,41 +5,45 @@
 #include <stdio.h>
 #include <sys/types.h>
 
-#define MM_F_NO_DIAG       0x001 // no exact diagonal hit
-#define MM_F_NO_DUAL       0x002 // skip pairs where query name is lexicographically larger than target name
-#define MM_F_CIGAR         0x004
-#define MM_F_OUT_SAM       0x008
-#define MM_F_NO_QUAL       0x010
-#define MM_F_OUT_CG        0x020
-#define MM_F_OUT_CS        0x040
-#define MM_F_SPLICE        0x080 // splice mode
-#define MM_F_SPLICE_FOR    0x100 // match GT-AG
-#define MM_F_SPLICE_REV    0x200 // match CT-AC, the reverse complement of GT-AG
-#define MM_F_NO_LJOIN      0x400
-#define MM_F_OUT_CS_LONG   0x800
-#define MM_F_SR            0x1000
-#define MM_F_FRAG_MODE     0x2000
-#define MM_F_NO_PRINT_2ND  0x4000
-#define MM_F_2_IO_THREADS  0x8000
-#define MM_F_LONG_CIGAR    0x10000
-#define MM_F_INDEPEND_SEG  0x20000
-#define MM_F_SPLICE_FLANK  0x40000
-#define MM_F_SOFTCLIP      0x80000
-#define MM_F_FOR_ONLY      0x100000
-#define MM_F_REV_ONLY      0x200000
-#define MM_F_HEAP_SORT     0x400000
-#define MM_F_ALL_CHAINS    0x800000
-#define MM_F_OUT_MD        0x1000000
-#define MM_F_COPY_COMMENT  0x2000000
-#define MM_F_EQX           0x4000000 // use =/X instead of M
-#define MM_F_PAF_NO_HIT    0x8000000 // output unmapped reads to PAF
-#define MM_F_NO_END_FLT    0x10000000
-#define MM_F_HARD_MLEVEL   0x20000000
-#define MM_F_SAM_HIT_ONLY  0x40000000
+#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
+#define MM_F_CIGAR         (0x004LL)
+#define MM_F_OUT_SAM       (0x008LL)
+#define MM_F_NO_QUAL       (0x010LL)
+#define MM_F_OUT_CG        (0x020LL)
+#define MM_F_OUT_CS        (0x040LL)
+#define MM_F_SPLICE        (0x080LL) // splice mode
+#define MM_F_SPLICE_FOR    (0x100LL) // match GT-AG
+#define MM_F_SPLICE_REV    (0x200LL) // match CT-AC, the reverse complement of GT-AG
+#define MM_F_NO_LJOIN      (0x400LL)
+#define MM_F_OUT_CS_LONG   (0x800LL)
+#define MM_F_SR            (0x1000LL)
+#define MM_F_FRAG_MODE     (0x2000LL)
+#define MM_F_NO_PRINT_2ND  (0x4000LL)
+#define MM_F_2_IO_THREADS  (0x8000LL)
+#define MM_F_LONG_CIGAR    (0x10000LL)
+#define MM_F_INDEPEND_SEG  (0x20000LL)
+#define MM_F_SPLICE_FLANK  (0x40000LL)
+#define MM_F_SOFTCLIP      (0x80000LL)
+#define MM_F_FOR_ONLY      (0x100000LL)
+#define MM_F_REV_ONLY      (0x200000LL)
+#define MM_F_HEAP_SORT     (0x400000LL)
+#define MM_F_ALL_CHAINS    (0x800000LL)
+#define MM_F_OUT_MD        (0x1000000LL)
+#define MM_F_COPY_COMMENT  (0x2000000LL)
+#define MM_F_EQX           (0x4000000LL) // use =/X instead of M
+#define MM_F_PAF_NO_HIT    (0x8000000LL) // output unmapped reads to PAF
+#define MM_F_NO_END_FLT    (0x10000000LL)
+#define MM_F_HARD_MLEVEL   (0x20000000LL)
+#define MM_F_SAM_HIT_ONLY  (0x40000000LL)
 #define MM_F_RMQ           (0x80000000LL)
 #define MM_F_QSTRAND       (0x100000000LL)
 #define MM_F_NO_INV        (0x200000000LL)
 #define MM_F_NO_HASH_NAME  (0x400000000LL)
+#define MM_F_SPLICE_OLD    (0x800000000LL)
+#define MM_F_SECONDARY_SEQ (0x1000000000LL)	//output SEQ field for seqondary alignments using hard clipping
 
 #define MM_I_HPC          0x1
 #define MM_I_NO_SEQ       0x2
@@ -189,6 +193,11 @@ typedef struct {
 } mm_idx_reader_t;
 
 // memory buffer for thread-local storage during mapping
+struct mm_tbuf_s {
+	void *km;
+	int rep_len, frag_gap;
+};
+
 typedef struct mm_tbuf_s mm_tbuf_t;
 
 // global variables

data/ext/minimap2/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
@@ -79,6 +79,19 @@ Minimizer k-mer length [15]
 .BI -w \ INT
 Minimizer window size [10]. A minimizer is the smallest k-mer
 in a window of w consecutive k-mers.
+.TP
+.BI -j \ INT
+Syncmer submer size [10]. Option
+.B -j
+and
+.B -w
+will override each: if
+.B -w
+is applied after
+.BR -j ,
+.B -j
+will have no effect, and vice versa.
+
 .TP
 .B -H
 Use homopolymer-compressed (HPC) minimizers. An HPC sequence is constructed by
@@ -88,16 +101,17 @@ on the HPC sequence.
 .BI -I \ NUM
 Load at most
 .I NUM
-target bases into RAM for indexing [4G]. If there are more than
+target bases into RAM for indexing [8G]. If there are more than
 .I NUM
 bases in
 .IR target.fa ,
 minimap2 needs to read
 .I query.fa
-multiple times to map it against each batch of target sequences.
+multiple times to map it against each batch of target sequences. This would create a multi-part index.
 .I NUM
 may be ending with k/K/m/M/g/G. NB: mapping quality is incorrect given a
-multi-part index.
+multi-part index. See also option
+.BR --split-prefix .
 .TP
 .B --idx-no-seq
 Don't store target sequences in the index. It saves disk space and memory but
@@ -587,7 +601,7 @@ Up to 20% sequence divergence.
 .B splice
 Long-read spliced alignment
 .RB ( -k15
-.B -w5 --splice -g2k -G200k -A1 -B2 -O2,32 -E1,0 -b0 -C9 -z200 -ub --junc-bonus=9 --cap-sw-mem=0
+.B -w5 --splice -g2k -G200k -A1 -B2 -O2,32 -E1,0 -C9 -z200 -ub --junc-bonus=9 --cap-sw-mem=0
 .BR --splice-flank=yes ).
 In the splice mode, 1) long deletions are taken as introns and represented as
 the