minimap2 0.2.26.1 → 0.2.28.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 49b59da1af652a8a5ffbde0f5d9e98b32d94a192039d1e948aced9bb926e75d1
-  data.tar.gz: 309fe28a4a58ccc2e5bd818c751fa33a40065756c0961fc96c35af7dbc24abea
+  metadata.gz: f23caa7c5707d41b96b6df1748d257e11bed0554cbc2123d5dca31ef22b9bb05
+  data.tar.gz: 6ab72bef6ad874385871460d55503696969c8dc381896873d64c821538bbfd57
 SHA512:
-  metadata.gz: b9faab29797eecd594b2f724e3c88d38457d2c60a24f01b9dd6ab0aa17a680e12db68755cf3f47d9873427f1577d81770e798f1395db17b39bffdbaf7230c330
-  data.tar.gz: cf3a3ea389fb1cbfabfd08fc17e073643db3c7ae59e74dcc11a75649e90ca2629a5c69fcc1548fab8755a8edb99c89a49e4353077aa3ef4b60bc9c129ec88a55
+  metadata.gz: 4327be493c432ba562780e79aceff0f53d409a1ff2c5630cde48ad28b4c338fdc9bab2a333087f1e2aa8cd83e2374ce3a7feec9e5133aaeb4c01c3011b0414db
+  data.tar.gz: adc86c65a0dbeb775b89385790894cf3ad2fa1c24cdb0b0a9d94302134910ee651afc832dc0b8864c3a24b6b86577ccd694e46effb1a95ecf6bea5e968d189ad

data/README.md

@@ -1,7 +1,7 @@
 # ruby-minimap2
 
 [![Gem Version](https://img.shields.io/gem/v/minimap2?color=brightgreen)](https://rubygems.org/gems/minimap2)
-[![CI](https://github.com/kojix2/ruby-minimap2/workflows/CI/badge.svg)](https://github.com/kojix2/ruby-minimap2/actions)
+[![test](https://github.com/kojix2/ruby-minimap2/actions/workflows/ci.yml/badge.svg)](https://github.com/kojix2/ruby-minimap2/actions/workflows/ci.yml)
 [![Docs Stable](https://img.shields.io/badge/docs-stable-blue.svg)](https://rubydoc.info/gems/minimap2)
 [![Docs Latest](https://img.shields.io/badge/docs-latest-blue.svg)](https://kojix2.github.io/ruby-minimap2/)
 [![The MIT License](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE.txt)
@@ -23,7 +23,7 @@ gem install minimap2
     bundle install
     bundle exec rake minimap2:build
     bundle exec rake install
- 
+
 </details>
 
 ## Quick Start
@@ -36,6 +36,7 @@ seq     = aligner.seq("MT_human", 100, 200)
 hits    = aligner.align(seq)
 pp hits
 ```
+
 ```
 [#<Minimap2::Alignment:0x000055bbfde2d128
   @blen=100,
@@ -57,8 +58,6 @@ pp hits
   @strand=1,
   @trans_strand=0>]
 ```
- 
-</details>
 
 ## APIs Overview
 
@@ -87,7 +86,7 @@ pp hits
       - trans_strand            Returns transcript strand. +1 if on the forward strand; -1 if on the reverse strand; 0 if unknown.
       - blen                    Returns length of the alignment, including both alignment matches and gaps but excluding ambiguous bases.
       - mlen                    Returns length of the matching bases in the alignment, excluding ambiguous base matches.
-      - nm                      Returns number of mismatches, gaps and ambiguous poistions in the alignment.
+      - nm                      Returns number of mismatches, gaps and ambiguous positions in the alignment.
       - primary                 Returns if the alignment is primary (typically the best and the first to generate).
       - q_st                    Returns start positions on the query.
       - q_en                    Returns end positions on the query.
@@ -106,19 +105,20 @@ pp hits
     * MapOpt class              Mapping options.
 ```
 
-* API is based on [Mappy](https://github.com/lh3/minimap2/tree/master/python), the official Python binding for Minimap2. 
-* `Aligner#map` has been changed to `align`, because `map` means iterator in Ruby.
-* See [documentation](https://kojix2.github.io/ruby-minimap2/) for details.
+- API is based on [Mappy](https://github.com/lh3/minimap2/tree/master/python), the official Python binding for Minimap2.
+- `Aligner#map` has been changed to `align`, because `map` means iterator in Ruby.
+- See [documentation](https://kojix2.github.io/ruby-minimap2/) for details.
 
 <details>
 <summary><b>C Structures and Functions</b></summary>
 
 ### FFI
-* Ruby-Minimap2 is built on top of [Ruby-FFI](https://github.com/ffi/ffi). 
-  * Native C functions can be called from the `Minimap2::FFI` module. 
-  * Native C structure members can be accessed.
-  * Bitfields are supported by [ffi-bitfield](https://github.com/kojix2/ffi-bitfield) gems.
- 
+
+- Ruby-Minimap2 is built on top of [Ruby-FFI](https://github.com/ffi/ffi).
+  - Native C functions can be called from the `Minimap2::FFI` module.
+  - Native C structure members can be accessed.
+  - Bitfields are supported by [ffi-bitfield](https://github.com/kojix2/ffi-bitfield) gems.
+
 ```ruby
 aligner.idx_opt.members
 # => [:k, :w, :flag, :bucket_bits, :mini_batch_size, :batch_size]
@@ -130,7 +130,7 @@ aligner.idx_opt[:k] = 14
 aligner.idx_opt[:k]
 # => 14
 ```
- 
+
 </details>
 
 ## Contributing
@@ -138,7 +138,7 @@ aligner.idx_opt[:k]
 <details>
 <summary><b>Development</b></summary>
 
- Fork your repository.
+Fork your repository.
 then clone.
 
 ```sh
@@ -184,7 +184,7 @@ 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)!
 
-Many OSS projects become abandoned because only the founder has commit rights to the original repository. 
+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/Rakefile

@@ -51,10 +51,8 @@ namespace :minimap2 do
     end
   end
 
-  task cleanall: [:clean]
-
   desc "`make clean` and remove shared lib"
-  task :cleanall do
+  task cleanall: [:clean] do
     Dir.chdir(minimap2_dir) do
       sh "rm #{target_path}" if File.exist?(target_path)
     end

data/ext/minimap2/NEWS.md

@@ -1,9 +1,76 @@
+Release 2.28-r1209 (27 March 2024)
+----------------------------------
+
+Notable changes to minimap2:
+
+ * Bugfix: `--MD` was not working properly due to the addition of `--ds` in the
+   last release (#1181 and #1182).
+
+ * New feature: added an experimental preset `lq:hqae` for aligning accurate
+   long reads back to their assembly. It has been observed that `map-hifi` and
+   `lr:hq` may produce many wrong alignments around centromeres when accurate
+   long reads (PacBio HiFi or Nanopore duplex/Q20+) are mapped to a diploid
+   assembly constructed from them. This new preset produces much more accurate
+   alignment. It is still experimental and may be subjective to changes in
+   future.
+
+ * Change: reduced the default `--cap-kalloc` to 500m to lower the peak
+   memory consumption (#855).
+
+Notable changes to mappy:
+
+ * Bugfix: mappy option struct was out of sync with minimap2 (#1177).
+
+Minimap2 should output identical alignments to v2.27.
+
+(2.28: 27 March 2024, r1209)
+
+
+
+Release 2.27-r1193 (12 March 2024)
+----------------------------------
+
+Notable changes to minimap2:
+
+ * New feature: added the `lr:hq` preset for accurate long reads at ~1% error
+   rate. This was suggested by Oxford Nanopore developers (#1127). It is not
+   clear if this preset also works well for PacBio HiFi reads.
+
+ * New feature: added the `map-iclr` preset for Illumina Complete Long Reads
+   (#1069), provided by Illumina developers.
+
+ * New feature: added option `-b` to specify mismatch penalty for base
+   transitions (i.e. A-to-G or C-to-T changes).
+
+ * New feature: added option `--ds` to generate a new `ds:Z` tag that
+   indicates uncertainty in INDEL positions. It is an extension to `cs`. The
+   `mgutils-es6.js` script in minigraph parses `ds`.
+
+ * Bugfix: avoided a NULL pointer dereference (#1154). This would not have an
+   effect on most systems but would still be good to fix.
+
+ * Bugfix: reverted the value of `ms:i` to pre-2.22 versions (#1146). This was
+   an oversight. See fcd4df2 for details.
+
+Notable changes to paftools.js and mappy:
+
+ * New feature: expose `bw_long` to mappy's Aligner class (#1124).
+
+ * Bugfix: fixed several compatibility issues with k8 v1.0 (#1161 and #1166).
+   Subcommands "call", "pbsim2fq" and "mason2fq" were not working with v1.0.
+
+Minimap2 should output identical alignments to v2.26, except the ms tag.
+
+(2.27: 12 March 2024, r1193)
+
+
+
 Release 2.26-r1175 (29 April 2023)
 ----------------------------------
 
 Fixed the broken Python package. This is the only change.
 
-(2.25: 25 April 2023, r1173)
+(2.26: 25 April 2023, r1173)
 
 
 

data/ext/minimap2/README.md

@@ -15,7 +15,7 @@ cd minimap2 && make
 ./minimap2 -ax map-pb ref.fa pacbio.fq.gz > aln.sam       # PacBio CLR genomic reads
 ./minimap2 -ax map-ont ref.fa ont.fq.gz > aln.sam         # Oxford Nanopore genomic reads
 ./minimap2 -ax map-hifi ref.fa pacbio-ccs.fq.gz > aln.sam # PacBio HiFi/CCS genomic reads (v2.19 or later)
-./minimap2 -ax asm20 ref.fa pacbio-ccs.fq.gz > aln.sam    # PacBio HiFi/CCS genomic reads (v2.18 or earlier)
+./minimap2 -ax lr:hq ref.fa ont-Q20.fq.gz > aln.sam       # Nanopore Q20 genomic reads (v2.27 or later)
 ./minimap2 -ax sr ref.fa read1.fa read2.fa > aln.sam      # short genomic paired-end reads
 ./minimap2 -ax splice ref.fa rna-reads.fa > aln.sam       # spliced long reads (strand unknown)
 ./minimap2 -ax splice -uf -k14 ref.fa reads.fa > aln.sam  # noisy Nanopore Direct RNA-seq
@@ -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/v2.26/minimap2-2.26_x64-linux.tar.bz2 | tar -jxvf -
-./minimap2-2.26_x64-linux/minimap2
+curl -L https://github.com/lh3/minimap2/releases/download/v2.28/minimap2-2.28_x64-linux.tar.bz2 | tar -jxvf -
+./minimap2-2.28_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
@@ -139,12 +139,15 @@ parameters at the same time. The default setting is the same as `map-ont`.
 ```sh
 minimap2 -ax map-pb  ref.fa pacbio-reads.fq > aln.sam   # for PacBio CLR reads
 minimap2 -ax map-ont ref.fa ont-reads.fq > aln.sam      # for Oxford Nanopore reads
+minimap2 -ax map-iclr ref.fa iclr-reads.fq > aln.sam    # for Illumina Complete Long Reads
 ```
 The difference between `map-pb` and `map-ont` is that `map-pb` uses
 homopolymer-compressed (HPC) minimizers as seeds, while `map-ont` uses ordinary
-minimizers as seeds. Emperical evaluation suggests HPC minimizers improve
+minimizers as seeds. Empirical evaluation suggests HPC minimizers improve
 performance and sensitivity when aligning PacBio CLR reads, but hurt when aligning
-Nanopore reads.
+Nanopore reads. `map-iclr` uses an adjusted alignment scoring matrix that
+accounts for the low overall error rate in the reads, with transversion errors
+being less frequent than transitions.
 
 #### <a name="map-long-splice"></a>Map long mRNA/cDNA reads
 

data/ext/minimap2/align.c

@@ -21,6 +21,18 @@ static void ksw_gen_simple_mat(int m, int8_t *mat, int8_t a, int8_t b, int8_t sc
 		mat[(m - 1) * m + j] = sc_ambi;
 }
 
+static void ksw_gen_ts_mat(int m, int8_t *mat, int8_t a, int8_t b, int8_t transition, int8_t sc_ambi)
+{
+	assert(m == 5);
+	ksw_gen_simple_mat(m, mat, a, b, sc_ambi);
+	if (transition == 0 || transition == b) return;
+	transition = transition > 0? -transition : transition;
+	mat[0 * m + 2] = transition;  // A->G
+	mat[1 * m + 3] = transition;  // C->T
+	mat[2 * m + 0] = transition;  // G->A
+	mat[3 * m + 1] = transition;  // T->C
+}
+
 static inline void mm_seq_rev(uint32_t len, uint8_t *seq)
 {
 	uint32_t i;
@@ -283,7 +295,7 @@ static void mm_update_extra(mm_reg1_t *r, const uint8_t *qseq, const uint8_t *ts
 			toff += len;
 		}
 	}
-	p->dp_max = (int32_t)(max + .499);
+	p->dp_max = p->dp_max0 = (int32_t)(max + .499);
 	assert(qoff == r->qe - r->qs && toff == r->re - r->rs);
 	if (is_eqx) mm_update_cigar_eqx(r, qseq, tseq); // NB: it has to be called here as changes to qseq and tseq are not returned
 }
@@ -323,6 +335,8 @@ static void mm_align_pair(void *km, const mm_mapopt_t *opt, int qlen, const uint
 		for (i = 0; i < qlen; ++i) fputc("ACGTN"[qseq[i]], stderr);
 		fputc('\n', stderr);
 	}
+	if (opt->transition != 0 && opt->b != opt->transition)
+		flag |= KSW_EZ_GENERIC_SC;
 	if (opt->max_sw_mat > 0 && (int64_t)tlen * qlen > opt->max_sw_mat) {
 		ksw_reset_extz(ez);
 		ez->zdropped = 1;
@@ -586,7 +600,7 @@ static void mm_align1(void *km, const mm_mapopt_t *opt, const mm_idx_t *mi, int
 
 	r2->cnt = 0;
 	if (r->cnt == 0) return;
-	ksw_gen_simple_mat(5, mat, opt->a, opt->b, opt->sc_ambi);
+	ksw_gen_ts_mat(5, mat, opt->a, opt->b, opt->transition, opt->sc_ambi);
 	bw = (int)(opt->bw * 1.5 + 1.);
 	bw_long = (int)(opt->bw_long * 1.5 + 1.);
 	if (bw_long < bw) bw_long = bw;
@@ -844,7 +858,7 @@ static int mm_align1_inv(void *km, const mm_mapopt_t *opt, const mm_idx_t *mi, i
 	if (ql < opt->min_chain_score || ql > opt->max_gap) return 0;
 	if (tl < opt->min_chain_score || tl > opt->max_gap) return 0;
 
-	ksw_gen_simple_mat(5, mat, opt->a, opt->b, opt->sc_ambi);
+	ksw_gen_ts_mat(5, mat, opt->a, opt->b, opt->transition, opt->sc_ambi);
 	tseq = (uint8_t*)kmalloc(km, tl);
 	mm_idx_getseq(mi, r1->rid, r1->re, r2->rs, tseq);
 	qseq = r1->rev? &qseq0[0][r2->qe] : &qseq0[1][qlen - r2->qs];
@@ -919,14 +933,14 @@ double mm_event_identity(const mm_reg1_t *r)
 static int32_t mm_recal_max_dp(const mm_reg1_t *r, double b2, int32_t match_sc)
 {
 	uint32_t i;
-	int32_t n_gap = 0, n_gapo = 0, n_mis;
+	int32_t n_gap = 0, n_mis;
 	double gap_cost = 0.0;
 	if (r->p == 0) return -1;
 	for (i = 0; i < r->p->n_cigar; ++i) {
 		int32_t op = r->p->cigar[i] & 0xf, len = r->p->cigar[i] >> 4;
 		if (op == MM_CIGAR_INS || op == MM_CIGAR_DEL) {
 			gap_cost += b2 + (double)mg_log2(1.0 + len);
-			++n_gapo, n_gap += len;
+			n_gap += len;
 		}
 	}
 	n_mis = r->blen + r->p->n_ambi - r->mlen - n_gap;

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/v2.26/minimap2-2.26_x64-linux.tar.bz2 | tar jxf -
-cp minimap2-2.26_x64-linux/{minimap2,k8,paftools.js} .  # copy executables
+curl -L https://github.com/lh3/minimap2/releases/download/v2.28/minimap2-2.28_x64-linux.tar.bz2 | tar jxf -
+cp minimap2-2.28_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

@@ -139,10 +139,48 @@ int mm_write_sam_hdr(const mm_idx_t *idx, const char *rg, const char *ver, int a
 	return ret;
 }
 
-static void write_cs_core(kstring_t *s, const uint8_t *tseq, const uint8_t *qseq, const mm_reg1_t *r, char *tmp, int no_iden, int write_tag)
+static void write_indel_ds(kstring_t *str, int64_t len, const uint8_t *seq, int64_t ll, int64_t lr) // write an indel to ds; adapted from minigraph
 {
-	int i, q_off, t_off;
-	if (write_tag) mm_sprintf_lite(s, "\tcs:Z:");
+	int64_t i;
+	if (ll + lr >= len) {
+		mm_sprintf_lite(str, "[");
+		for (i = 0; i < len; ++i)
+			mm_sprintf_lite(str, "%c", "acgtn"[seq[i]]);
+		mm_sprintf_lite(str, "]");
+	} else {
+		int64_t k = 0;
+		if (ll > 0) {
+			mm_sprintf_lite(str, "[");
+			for (i = 0; i < ll; ++i)
+				mm_sprintf_lite(str, "%c", "acgtn"[seq[k+i]]);
+			mm_sprintf_lite(str, "]");
+			k += ll;
+		}
+		for (i = 0; i < len - lr - ll; ++i)
+			mm_sprintf_lite(str, "%c", "acgtn"[seq[k+i]]);
+		k += len - lr - ll;
+		if (lr > 0) {
+			mm_sprintf_lite(str, "[");
+			for (i = 0; i < lr; ++i)
+				mm_sprintf_lite(str, "%c", "acgtn"[seq[k+i]]);
+			mm_sprintf_lite(str, "]");
+		}
+	}
+}
+
+static void write_cs_ds_core(kstring_t *s, const uint8_t *tseq, const uint8_t *qseq, const mm_reg1_t *r, char *tmp, int no_iden, int is_ds, int write_tag)
+{
+	int i, q_off, t_off, q_len = 0, t_len = 0;
+	if (write_tag) mm_sprintf_lite(s, "\t%cs:Z:", is_ds? 'd' : 'c');
+	for (i = 0; i < (int)r->p->n_cigar; ++i) {
+		int op = r->p->cigar[i]&0xf, len = r->p->cigar[i]>>4;
+		if (op == MM_CIGAR_MATCH || op == MM_CIGAR_EQ_MATCH || op == MM_CIGAR_X_MISMATCH)
+			q_len += len, t_len += len;
+		else if (op == MM_CIGAR_INS)
+			q_len += len;
+		else if (op == MM_CIGAR_DEL || op == MM_CIGAR_N_SKIP)
+			t_len += len;
+	}
 	for (i = q_off = t_off = 0; i < (int)r->p->n_cigar; ++i) {
 		int j, op = r->p->cigar[i]&0xf, len = r->p->cigar[i]>>4;
 		assert((op >= MM_CIGAR_MATCH && op <= MM_CIGAR_N_SKIP) || op == MM_CIGAR_EQ_MATCH || op == MM_CIGAR_X_MISMATCH);
@@ -168,14 +206,42 @@ static void write_cs_core(kstring_t *s, const uint8_t *tseq, const uint8_t *qseq
 			}
 			q_off += len, t_off += len;
 		} else if (op == MM_CIGAR_INS) {
-			for (j = 0, tmp[len] = 0; j < len; ++j)
-				tmp[j] = "acgtn"[qseq[q_off + j]];
-			mm_sprintf_lite(s, "+%s", tmp);
+			if (is_ds) {
+				int z, ll, lr, y = q_off;
+				for (z = 1; z <= len; ++z)
+					if (y - z < 0 || qseq[y + len - z] != qseq[y - z])
+						break;
+				lr = z - 1;
+				for (z = 0; z < len; ++z)
+					if (y + len + z >= q_len || qseq[y + len + z] != qseq[y + z])
+						break;
+				ll = z;
+				mm_sprintf_lite(s, "+");
+				write_indel_ds(s, len, &qseq[y], ll, lr);
+			} else {
+				for (j = 0, tmp[len] = 0; j < len; ++j)
+					tmp[j] = "acgtn"[qseq[q_off + j]];
+				mm_sprintf_lite(s, "+%s", tmp);
+			}
 			q_off += len;
 		} else if (op == MM_CIGAR_DEL) {
-			for (j = 0, tmp[len] = 0; j < len; ++j)
-				tmp[j] = "acgtn"[tseq[t_off + j]];
-			mm_sprintf_lite(s, "-%s", tmp);
+			if (is_ds) {
+				int z, ll, lr, x = t_off;
+				for (z = 1; z <= len; ++z)
+					if (x - z < 0 || tseq[x + len - z] != tseq[x - z])
+						break;
+				lr = z - 1;
+				for (z = 0; z < len; ++z)
+					if (x + len + z >= t_len || tseq[x + z] != tseq[x + len + z])
+						break;
+				ll = z;
+				mm_sprintf_lite(s, "-");
+				write_indel_ds(s, len, &tseq[x], ll, lr);
+			} else {
+				for (j = 0, tmp[len] = 0; j < len; ++j)
+					tmp[j] = "acgtn"[tseq[t_off + j]];
+				mm_sprintf_lite(s, "-%s", tmp);
+			}
 			t_off += len;
 		} else { // intron
 			assert(len >= 2);
@@ -218,7 +284,7 @@ static void write_MD_core(kstring_t *s, const uint8_t *tseq, const uint8_t *qseq
 	assert(t_off == r->re - r->rs && q_off == r->qe - r->qs);
 }
 
-static void write_cs_or_MD(void *km, kstring_t *s, const mm_idx_t *mi, const mm_bseq1_t *t, const mm_reg1_t *r, int no_iden, int is_MD, int write_tag, int is_qstrand)
+static void write_cs_ds_or_MD(void *km, kstring_t *s, const mm_idx_t *mi, const mm_bseq1_t *t, const mm_reg1_t *r, int no_iden, int is_MD, int is_ds, int write_tag, int is_qstrand)
 {
 	extern unsigned char seq_nt4_table[256];
 	int i;
@@ -245,7 +311,7 @@ static void write_cs_or_MD(void *km, kstring_t *s, const mm_idx_t *mi, const mm_
 		}
 	}
 	if (is_MD) write_MD_core(s, tseq, qseq, r, tmp, write_tag);
-	else write_cs_core(s, tseq, qseq, r, tmp, no_iden, write_tag);
+	else write_cs_ds_core(s, tseq, qseq, r, tmp, no_iden, is_ds, write_tag);
 	kfree(km, qseq); kfree(km, tseq); kfree(km, tmp);
 }
 
@@ -256,7 +322,7 @@ int mm_gen_cs_or_MD(void *km, char **buf, int *max_len, const mm_idx_t *mi, cons
 	str.s = *buf, str.l = 0, str.m = *max_len;
 	t.l_seq = strlen(seq);
 	t.seq = (char*)seq;
-	write_cs_or_MD(km, &str, mi, &t, r, no_iden, is_MD, 0, is_qstrand);
+	write_cs_ds_or_MD(km, &str, mi, &t, r, no_iden, is_MD, 0, 0, is_qstrand);
 	*max_len = str.m;
 	*buf = str.s;
 	return str.l;
@@ -278,7 +344,7 @@ static inline void write_tags(kstring_t *s, const mm_reg1_t *r)
 	if (r->id == r->parent) type = r->inv? 'I' : 'P';
 	else type = r->inv? 'i' : 'S';
 	if (r->p) {
-		mm_sprintf_lite(s, "\tNM:i:%d\tms:i:%d\tAS:i:%d\tnn:i:%d", r->blen - r->mlen + r->p->n_ambi, r->p->dp_max, r->p->dp_score, r->p->n_ambi);
+		mm_sprintf_lite(s, "\tNM:i:%d\tms:i:%d\tAS:i:%d\tnn:i:%d", r->blen - r->mlen + r->p->n_ambi, r->p->dp_max0, r->p->dp_score, r->p->n_ambi);
 		if (r->p->trans_strand == 1 || r->p->trans_strand == 2)
 			mm_sprintf_lite(s, "\tts:A:%c", "?+-?"[r->p->trans_strand]);
 	}
@@ -326,8 +392,8 @@ void mm_write_paf3(kstring_t *s, const mm_idx_t *mi, const mm_bseq1_t *t, const
 		for (k = 0; k < r->p->n_cigar; ++k)
 			mm_sprintf_lite(s, "%d%c", r->p->cigar[k]>>4, MM_CIGAR_STR[r->p->cigar[k]&0xf]);
 	}
-	if (r->p && (opt_flag & (MM_F_OUT_CS|MM_F_OUT_MD)))
-		write_cs_or_MD(km, s, mi, t, r, !(opt_flag&MM_F_OUT_CS_LONG), opt_flag&MM_F_OUT_MD, 1, !!(opt_flag&MM_F_QSTRAND));
+	if (r->p && (opt_flag & (MM_F_OUT_CS|MM_F_OUT_DS|MM_F_OUT_MD)))
+		write_cs_ds_or_MD(km, s, mi, t, r, !(opt_flag&MM_F_OUT_CS_LONG), !!(opt_flag&MM_F_OUT_MD), !!(opt_flag&MM_F_OUT_DS), 1, !!(opt_flag&MM_F_QSTRAND));
 	if ((opt_flag & MM_F_COPY_COMMENT) && t->comment)
 		mm_sprintf_lite(s, "\t%s", t->comment);
 }
@@ -535,8 +601,8 @@ void mm_write_sam3(kstring_t *s, const mm_idx_t *mi, const mm_bseq1_t *t, int se
 				}
 			}
 		}
-		if (r->p && (opt_flag & (MM_F_OUT_CS|MM_F_OUT_MD)))
-			write_cs_or_MD(km, s, mi, t, r, !(opt_flag&MM_F_OUT_CS_LONG), opt_flag&MM_F_OUT_MD, 1, 0);
+		if (r->p && (opt_flag & (MM_F_OUT_CS|MM_F_OUT_DS|MM_F_OUT_MD)))
+			write_cs_ds_or_MD(km, s, mi, t, r, !(opt_flag&MM_F_OUT_CS_LONG), opt_flag&MM_F_OUT_MD, !!(opt_flag&MM_F_OUT_DS), 1, 0);
 		if (cigar_in_tag)
 			write_sam_cigar(s, flag, 1, t->l_seq, r, opt_flag);
 	}

data/ext/minimap2/index.c

@@ -192,6 +192,7 @@ int32_t mm_idx_cal_max_occ(const mm_idx_t *mi, float f)
 	if (f <= 0.) return INT32_MAX;
 	for (i = 0; i < 1<<mi->b; ++i)
 		if (mi->B[i].h) n += kh_size((idxhash_t*)mi->B[i].h);
+	if (n == 0) return INT32_MAX;
 	a = (uint32_t*)malloc(n * 4);
 	for (i = n = 0; i < 1<<mi->b; ++i) {
 		idxhash_t *h = (idxhash_t*)mi->B[i].h;

data/ext/minimap2/lchain.c

@@ -149,7 +149,7 @@ mm128_t *mg_lchain_dp(int max_dist_x, int max_dist_y, int bw, int max_skip, int
 					  int is_cdna, int n_seg, int64_t n, mm128_t *a, int *n_u_, uint64_t **_u, void *km)
 { // TODO: make sure this works when n has more than 32 bits
 	int32_t *f, *t, *v, n_u, n_v, mmax_f = 0, max_drop = bw;
-	int64_t *p, i, j, max_ii, st = 0, n_iter = 0;
+	int64_t *p, i, j, max_ii, st = 0;
 	uint64_t *u;
 
 	if (_u) *_u = 0, *n_u_ = 0;
@@ -174,7 +174,6 @@ mm128_t *mg_lchain_dp(int max_dist_x, int max_dist_y, int bw, int max_skip, int
 		for (j = i - 1; j >= st; --j) {
 			int32_t sc;
 			sc = comput_sc(&a[i], &a[j], max_dist_x, max_dist_y, bw, chn_pen_gap, chn_pen_skip, is_cdna, n_seg);
-			++n_iter;
 			if (sc == INT32_MIN) continue;
 			sc += f[j];
 			if (sc > max_f) {
@@ -204,6 +203,7 @@ mm128_t *mg_lchain_dp(int max_dist_x, int max_dist_y, int bw, int max_skip, int
 		if (max_ii < 0 || (a[i].x - a[max_ii].x <= (int64_t)max_dist_x && f[max_ii] < f[i]))
 			max_ii = i;
 		if (mmax_f < max_f) mmax_f = max_f;
+		//fprintf(stderr, "X1\t%ld\t%ld:%d\t%ld\t%ld:%d\t%ld\t%ld\n", (long)i, (long)(a[i].x>>32), (int32_t)a[i].x, (long)max_j, max_j<0?-1L:(long)(a[max_j].x>>32), max_j<0?-1:(int32_t)a[max_j].x, (long)max_f, (long)v[i]);
 	}
 
 	u = mg_chain_backtrack(km, n, f, p, v, t, min_cnt, min_sc, max_drop, &n_u, &n_v);
@@ -263,7 +263,8 @@ mm128_t *mg_lchain_rmq(int max_dist, int max_dist_inner, int bw, int max_chn_ski
 		return 0;
 	}
 	if (max_dist < bw) max_dist = bw;
-	if (max_dist_inner <= 0 || max_dist_inner >= max_dist) max_dist_inner = 0;
+	if (max_dist_inner < 0) max_dist_inner = 0;
+	if (max_dist_inner > max_dist) max_dist_inner = max_dist;
 	p = Kmalloc(km, int64_t, n);
 	f = Kmalloc(km, int32_t, n);
 	t = Kcalloc(km, int32_t, n);
@@ -325,12 +326,11 @@ mm128_t *mg_lchain_rmq(int max_dist, int max_dist_inner, int bw, int max_chn_ski
 				krmq_interval(lc_elem, root_inner, &s, &lo, &hi);
 				if (lo) {
 					const lc_elem_t *q;
-					int32_t width, n_rmq_iter = 0;
+					int32_t width;
 					krmq_itr_t(lc_elem) itr;
 					krmq_itr_find(lc_elem, root_inner, lo, &itr);
 					while ((q = krmq_at(&itr)) != 0) {
 						if (q->y < (int32_t)a[i].y - max_dist_inner) break;
-						++n_rmq_iter;
 						j = q->i;
 						sc = f[j] + comput_sc_simple(&a[i], &a[j], chn_pen_gap, chn_pen_skip, 0, &width);
 						if (width <= bw) {

data/ext/minimap2/main.c

@@ -77,6 +77,9 @@ static ko_longopt_t long_options[] = {
 	{ "print-chains",   ko_no_argument,       352 },
 	{ "no-hash-name",   ko_no_argument,       353 },
 	{ "secondary-seq",  ko_no_argument,       354 },
+	{ "ds",             ko_no_argument,       355 },
+	{ "rmq-inner",      ko_required_argument, 356 },
+	{ "dbg-seed-occ",   ko_no_argument,       501 },
 	{ "help",           ko_no_argument,       'h' },
 	{ "max-intron-len", ko_required_argument, 'G' },
 	{ "version",        ko_no_argument,       'V' },
@@ -120,7 +123,7 @@ 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:";
+	const char *opt_str = "2aSDw:k:K:t:r:f:Vv:g:G:I:d:XT:s:x:Hcp:M:n:z:A:B: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;
@@ -178,6 +181,7 @@ int main(int argc, char *argv[])
 		else if (c == 'm') opt.min_chain_score = atoi(o.arg);
 		else if (c == 'A') opt.a = atoi(o.arg);
 		else if (c == 'B') opt.b = atoi(o.arg);
+		else if (c == 'b') opt.transition = atoi(o.arg);
 		else if (c == 's') opt.min_dp_max = atoi(o.arg);
 		else if (c == 'C') opt.noncan = atoi(o.arg);
 		else if (c == 'I') ipt.batch_size = mm_parse_num(o.arg);
@@ -242,6 +246,9 @@ int main(int argc, char *argv[])
 		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 == 355) opt.flag |= MM_F_OUT_DS; // --ds
+		else if (c == 356) opt.rmq_inner_dist = mm_parse_num(o.arg); // --rmq-inner
+		else if (c == 501) mm_dbg_flag |= MM_DBG_SEED_FREQ; // --dbg-seed-occ
 		else if (c == 330) {
 			fprintf(stderr, "[WARNING] \033[1;31m --lj-min-ratio has been deprecated.\033[0m\n");
 		} else if (c == 314) { // --frag
@@ -358,6 +365,7 @@ int main(int argc, char *argv[])
 		fprintf(fp_help, "    -R STR       SAM read group line in a format like '@RG\\tID:foo\\tSM:bar' []\n");
 		fprintf(fp_help, "    -c           output CIGAR in PAF\n");
 		fprintf(fp_help, "    --cs[=STR]   output the cs tag; STR is 'short' (if absent) or 'long' [none]\n");
+		fprintf(fp_help, "    --ds         output the ds tag, which is an extension to cs\n");
 		fprintf(fp_help, "    --MD         output the MD tag\n");
 		fprintf(fp_help, "    --eqx        write =/X CIGAR operators\n");
 		fprintf(fp_help, "    -Y           use soft clipping for supplementary alignments\n");
@@ -367,12 +375,12 @@ int main(int argc, char *argv[])
 		fprintf(fp_help, "    --version    show version number\n");
 		fprintf(fp_help, "  Preset:\n");
 		fprintf(fp_help, "    -x STR       preset (always applied before other options; see minimap2.1 for details) []\n");
-		fprintf(fp_help, "                 - map-pb/map-ont - PacBio CLR/Nanopore vs reference mapping\n");
-		fprintf(fp_help, "                 - map-hifi - PacBio HiFi reads vs reference mapping\n");
-		fprintf(fp_help, "                 - ava-pb/ava-ont - PacBio/Nanopore read overlap\n");
+		fprintf(fp_help, "                 - lr:hq - accurate long reads (error rate <1%%) against a reference genome\n");
+		fprintf(fp_help, "                 - splice/splice:hq - spliced alignment for long reads/accurate long reads\n");
 		fprintf(fp_help, "                 - asm5/asm10/asm20 - asm-to-ref mapping, for ~0.1/1/5%% sequence divergence\n");
-		fprintf(fp_help, "                 - splice/splice:hq - long-read/Pacbio-CCS spliced alignment\n");
-		fprintf(fp_help, "                 - sr - genomic short-read mapping\n");
+		fprintf(fp_help, "                 - sr - short reads against a reference\n");
+		fprintf(fp_help, "                 - map-pb/map-hifi/map-ont/map-iclr - CLR/HiFi/Nanopore/ICLR vs reference mapping\n");
+		fprintf(fp_help, "                 - ava-pb/ava-ont - PacBio CLR/Nanopore read overlap\n");
 		fprintf(fp_help, "\nSee `man ./minimap2.1' for detailed description of these and other advanced command-line options.\n");
 		return fp_help == stdout? 0 : 1;
 	}

data/ext/minimap2/minimap.h

@@ -5,7 +5,7 @@
 #include <stdio.h>
 #include <sys/types.h>
 
-#define MM_VERSION "2.26-r1175"
+#define MM_VERSION "2.28-r1209"
 
 #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
@@ -44,6 +44,7 @@
 #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_F_OUT_DS        (0x2000000000LL)
 
 #define MM_I_HPC          0x1
 #define MM_I_NO_SEQ       0x2
@@ -97,6 +98,7 @@ typedef struct {
 typedef struct {
 	uint32_t capacity;                  // the capacity of cigar[]
 	int32_t dp_score, dp_max, dp_max2;  // DP score; score of the max-scoring segment; score of the best alternate mappings
+	int32_t dp_max0;                    // DP score before mm_update_dp_max() adjustment
 	uint32_t n_ambi:30, trans_strand:2; // number of ambiguous bases; transcript strand: 0 for unknown, 1 for +, 2 for -
 	uint32_t n_cigar;                   // number of cigar operations in cigar[]
 	uint32_t cigar[];
@@ -153,6 +155,7 @@ typedef struct {
 	float alt_drop;
 
 	int a, b, q, e, q2, e2; // matching score, mismatch, gap-open and gap-ext penalties
+	int transition; // transition mismatch score (A:G, C:T)
 	int sc_ambi; // score when one or both bases are "N"
 	int noncan;      // cost of non-canonical splicing sites
 	int junc_bonus;