Merge branch 'master' into avx

NEWS.md

@@ -1,3 +1,31 @@
+Release 2.17-r941 (4 May 2019)
+------------------------------
+
+Changes since the last release:
+
+ * Fixed flawed CIGARs like `5I6D7I` (#392).
+
+ * Bugfix: TLEN should be 0 when either end is unmapped (#373 and #365).
+
+ * Bugfix: mappy is unable to write index (#372).
+
+ * Added option `--junc-bed` to load known gene annotations in the BED12
+   format. Minimap2 prefers annotated junctions over novel junctions (#197 and
+   #348). GTF can be converted to BED12 with `paftools.js gff2bed`.
+
+ * Added option `--sam-hit-only` to suppress unmapped hits in SAM (#377).
+
+ * Added preset `splice:hq` for high-quality CCS or mRNA sequences. It applies
+   better scoring and improves the sensitivity to small exons. This preset may
+   introduce false small introns, but the overall accuracy should be higher.
+
+This version produces nearly identical alignments to v2.16, except for CIGARs
+affected by the bug mentioned above.
+
+(2.17: 5 May 2019, r941)
+
+
+
 Release 2.16-r922 (28 February 2019)
 ------------------------------------
 

README.md

@@ -18,7 +18,7 @@ cd minimap2 && make
 ./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
-./minimap2 -ax splice -uf -C5 ref.fa query.fa > aln.sam   # Final PacBio Iso-seq or traditional cDNA
+./minimap2 -ax splice:hq -uf ref.fa query.fa > aln.sam    # Final PacBio Iso-seq or traditional cDNA
 ./minimap2 -cx asm5 asm1.fa asm2.fa > aln.paf             # intra-species asm-to-asm alignment
 ./minimap2 -x ava-pb reads.fa reads.fa > overlaps.paf     # PacBio read overlap
 ./minimap2 -x ava-ont reads.fa reads.fa > overlaps.paf    # Nanopore read overlap
@@ -71,8 +71,8 @@ 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/v2.16/minimap2-2.16_x64-linux.tar.bz2 | tar -jxvf -
+curl -L https://github.com/lh3/minimap2/releases/download/v2.17/minimap2-2.17_x64-linux.tar.bz2 | tar -jxvf -
-./minimap2-2.16_x64-linux/minimap2
+./minimap2-2.17_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
@@ -139,7 +139,7 @@ Nanopore reads.
 #### <a name="map-long-splice"></a>Map long mRNA/cDNA reads
 
 ```sh
-minimap2 -ax splice -uf -C5 ref.fa iso-seq.fq > aln.sam      # PacBio Iso-seq/traditional cDNA
+minimap2 -ax splice:hq -uf ref.fa iso-seq.fq > aln.sam       # PacBio Iso-seq/traditional cDNA
 minimap2 -ax splice ref.fa nanopore-cdna.fa > aln.sam        # Nanopore 2D cDNA-seq
 minimap2 -ax splice -uf -k14 ref.fa direct-rna.fq > aln.sam  # Nanopore Direct RNA-seq
 minimap2 -ax splice --splice-flank=no SIRV.fa SIRV-seq.fa    # mapping against SIRV control

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/v2.16/minimap2-2.16_x64-linux.tar.bz2 | tar jxf -
+curl -L https://github.com/lh3/minimap2/releases/download/v2.17/minimap2-2.17_x64-linux.tar.bz2 | tar jxf -
-cp minimap2-2.16_x64-linux/{minimap2,k8,paftools.js} .  # copy executables
+cp minimap2-2.17_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

@@ -6,7 +6,7 @@
 #include "mmpriv.h"
 #include "ketopt.h"
 
-#define MM_VERSION "2.16-r937-dirty"
+#define MM_VERSION "2.17-r943-dirty"
 
 #ifdef __linux__
 #include <sys/resource.h>

minimap2.1

@@ -1,4 +1,4 @@
-.TH minimap2 1 "30 April 2019" "minimap2-2.16-dirty (r938)" "Bioinformatics tools"
+.TH minimap2 1 "4 May 2019" "minimap2-2.17 (r941)" "Bioinformatics tools"
 .SH NAME
 .PP
 minimap2 - mapping and alignment between collections of DNA sequences
@@ -568,6 +568,12 @@ costs are different during chaining; 4) the computation of the
 .RB ` ms '
 tag ignores introns to demote hits to pseudogenes.
 .TP
+.B splice:hq
+Long-read splice alignment for PacBio CCS reads
+.RB ( -xsplice
+.B -C5 -O6,24
+.BR -B4 ).
+.TP
 .B sr
 Short single-end reads without splicing
 .RB ( -k21

misc/paftools.js

@@ -1,6 +1,6 @@
 #!/usr/bin/env k8
 
-var paftools_version = '2.16-r933-dirty';
+var paftools_version = '2.17-r941';
 
 /*****************************
  ***** Library functions *****

options.c

@@ -120,7 +120,7 @@ int mm_set_opt(const char *preset, mm_idxopt_t *io, mm_mapopt_t *mo)
 		mo->mid_occ = 1000;
 		mo->max_occ = 5000;
 		mo->mini_batch_size = 50000000;
-	} else if (strcmp(preset, "splice") == 0 || strcmp(preset, "cdna") == 0) {
+	} else if (strncmp(preset, "splice", 6) == 0 || strcmp(preset, "cdna") == 0) {
 		io->flag = 0, io->k = 15, io->w = 5;
 		mo->flag |= MM_F_SPLICE | MM_F_SPLICE_FOR | MM_F_SPLICE_REV | MM_F_SPLICE_FLANK;
 		mo->max_gap = 2000, mo->max_gap_ref = mo->bw = 200000;
@@ -128,6 +128,8 @@ int mm_set_opt(const char *preset, mm_idxopt_t *io, mm_mapopt_t *mo)
 		mo->noncan = 9;
 		mo->junc_bonus = 9;
 		mo->zdrop = 200, mo->zdrop_inv = 100; // because mo->a is halved
+		if (strcmp(preset, "splice:hq") == 0)
+			mo->junc_bonus = 5, mo->b = 4, mo->q = 6, mo->q2 = 24;
 	} else return -1;
 	return 0;
 }

python/mappy.pyx

@@ -3,7 +3,7 @@ from libc.stdlib cimport free
 cimport cmappy
 import sys
 
-__version__ = '2.16'
+__version__ = '2.17'
 
 cmappy.mm_reset_timer()
 

setup.py

@@ -33,7 +33,7 @@ def readme():
 
 setup(
 	name = 'mappy',
-	version = '2.16',
+	version = '2.17',
 	url = 'https://github.com/lh3/minimap2',
 	description = 'Minimap2 python binding',
 	long_description = readme(),

splitidx.c

@@ -19,9 +19,9 @@ FILE *mm_split_init(const char *prefix, const mm_idx_t *mi)
 	mm_err_fwrite(&k, 4, 1, fp);
 	mm_err_fwrite(&mi->n_seq, 4, 1, fp);
 	for (i = 0; i < mi->n_seq; ++i) {
-		uint8_t l;
+		uint32_t l;
 		l = strlen(mi->seq[i].name);
-		mm_err_fwrite(&l, 1, 1, fp);
+		mm_err_fwrite(&l, 1, 4, fp);
 		mm_err_fwrite(mi->seq[i].name, 1, l, fp);
 		mm_err_fwrite(&mi->seq[i].len, 4, 1, fp);
 	}
@@ -60,8 +60,8 @@ mm_idx_t *mm_split_merge_prep(const char *prefix, int n_splits, FILE **fp, uint3
 	for (i = j = 0; i < n_splits; ++i) {
 		uint32_t k;
 		for (k = 0; k < n_seq_part[i]; ++k, ++j) {
-			uint8_t l;
+			uint32_t l;
-			mm_err_fread(&l, 1, 1, fp[i]);
+			mm_err_fread(&l, 1, 4, fp[i]);
 			mi->seq[j].name = (char*)calloc(l + 1, 1);
 			mm_err_fread(mi->seq[j].name, 1, l, fp[i]);
 			mm_err_fread(&mi->seq[j].len, 4, 1, fp[i]);