r940: added the splice:hq preset

for high-quality CCS/mRNA splice alignment

Author: lh3

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
@@ -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

main.c

@@ -6,7 +6,7 @@
 #include "mmpriv.h"
 #include "ketopt.h"
 
-#define MM_VERSION "2.16-r937-dirty"
+#define MM_VERSION "2.16-r940-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" "minimap2-2.16-dirty (r940)" "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

options.c

@@ -120,14 +120,16 @@ 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;
 		mo->a = 1, mo->b = 2, mo->q = 2, mo->e = 1, mo->q2 = 32, mo->e2 = 0;
 		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;
 }