Release minimap2-2.23 (r1111)

NEWS.md

@@ -1,3 +1,21 @@
+Release 2.23-r1111 (18 November 2021)
+-------------------------------------
+
+Notable changes:
+
+ * Bugfix: fixed missing alignments around long inversions (#806 and #816).
+   This bug affected v2.19 through v2.22.
+
+ * Improvement: avoid extremely long mapping time for pathologic reads with
+   highly repeated k-mers not in the reference (#771). Use --q-occ-frac=0
+   to disable the new heuristic.
+
+ * Change: use --cap-kalloc=1g by default.
+
+(2.23: 18 November 2021, r1111)
+
+
+
 Release 2.22-r1101 (7 August 2021)
 ----------------------------------
 

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/v2.22/minimap2-2.22_x64-linux.tar.bz2 | tar -jxvf -
+curl -L https://github.com/lh3/minimap2/releases/download/v2.23/minimap2-2.23_x64-linux.tar.bz2 | tar -jxvf -
-./minimap2-2.22_x64-linux/minimap2
+./minimap2-2.23_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

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/v2.22/minimap2-2.22_x64-linux.tar.bz2 | tar jxf -
+curl -L https://github.com/lh3/minimap2/releases/download/v2.23/minimap2-2.23_x64-linux.tar.bz2 | tar jxf -
-cp minimap2-2.22_x64-linux/{minimap2,k8,paftools.js} .  # copy executables
+cp minimap2-2.23_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

@@ -7,7 +7,7 @@
 #include "mmpriv.h"
 #include "ketopt.h"
 
-#define MM_VERSION "2.22-r1110-dirty"
+#define MM_VERSION "2.23-r1111"
 
 #ifdef __linux__
 #include <sys/resource.h>

minimap2.1

@@ -1,4 +1,4 @@
-.TH minimap2 1 "7 August 2021" "minimap2-2.22 (r1101)" "Bioinformatics tools"
+.TH minimap2 1 "18 November 2021" "minimap2-2.23 (r1111)" "Bioinformatics tools"
 .SH NAME
 .PP
 minimap2 - mapping and alignment between collections of DNA sequences
@@ -159,7 +159,7 @@ in earlier versions of minimap2.
 Discard a query minimizer if its occurrence is higher than
 .I FLOAT
 fraction of query minimizers and than the reference occurrence threshold
-[0.02]. Set 0 to disable. Available since r1105.
+[0.01]. Set 0 to disable. Available since r1105.
 .TP
 .BI -e \ INT
 Sample a high-frequency minimizer every

misc/paftools.js

@@ -1,6 +1,6 @@
 #!/usr/bin/env k8
 
-var paftools_version = '2.22-r1101';
+var paftools_version = '2.23-r1111';
 
 /*****************************
  ***** Library functions *****
@@ -1532,12 +1532,13 @@ function paf_view(args)
 
 function paf_gff2bed(args)
 {
-	var c, fn_ucsc_fai = null, is_short = false, keep_gff = false, print_junc = false;
+	var c, fn_ucsc_fai = null, is_short = false, keep_gff = false, print_junc = false, output_gene = false;
-	while ((c = getopt(args, "u:sgj")) != null) {
+	while ((c = getopt(args, "u:sgjG")) != null) {
 		if (c == 'u') fn_ucsc_fai = getopt.arg;
 		else if (c == 's') is_short = true;
 		else if (c == 'g') keep_gff = true;
 		else if (c == 'j') print_junc = true;
+		else if (c == 'G') output_gene = true;
 	}
 
 	if (getopt.ind == args.length) {
@@ -1605,8 +1606,10 @@ function paf_gff2bed(args)
 		print(a[0][0], st, en, name, 1000, a[0][3], cds_st, cds_en, color, a.length, sizes.join(",") + ",", starts.join(",") + ",");
 	}
 
-	var re_gtf = /\b(transcript_id|transcript_type|transcript_biotype|gene_name|gene_id|gbkey|transcript_name) "([^"]+)";/g;
+	var re_gtf  = /\b(transcript_id|transcript_type|transcript_biotype|gene_name|gene_id|gbkey|transcript_name) "([^"]+)";/g;
 	var re_gff3 = /\b(transcript_id|transcript_type|transcript_biotype|gene_name|gene_id|gbkey|transcript_name)=([^;]+)/g;
+	var re_gtf_gene  = /\b(gene_id|gene_type|gene_name) "([^;]+)";/g;
+	var re_gff3_gene = /\b(gene_id|gene_type|source_gene|gene_biotype|gene_name)=([^;]+);/g;
 	var buf = new Bytes();
 	var file = args[getopt.ind] == '-'? new File() : new File(args[getopt.ind]);
 
@@ -1620,6 +1623,26 @@ function paf_gff2bed(args)
 			continue;
 		}
 		if (t[0].charAt(0) == '#') continue;
+		if (output_gene) {
+			var id = null, src = null, biotype = null, type = "", name = "N/A";
+			if (t[2] != "gene") continue;
+			while ((m = re_gtf_gene.exec(t[8])) != null) {
+				if (m[1] == "gene_id") id = m[2];
+				else if (m[1] == "gene_type") type = m[2];
+				else if (m[1] == "gene_name") name = m[2];
+			}
+			while ((m = re_gff3_gene.exec(t[8])) != null) {
+				if (m[1] == "gene_id") id = m[2];
+				else if (m[1] == "source_gene") src = m[2];
+				else if (m[1] == "gene_type") type = m[2];
+				else if (m[1] == "gene_biotype") biotype = m[2];
+				else if (m[1] == "gene_name") name = m[2];
+			}
+			if (src != null) id = src;
+			if (type == "" && biotype != null) type = biotype;
+			print(t[0], parseInt(t[3]) - 1, t[4], [id, type, name].join("|"), 1000, t[6]);
+			continue;
+		}
 		if (t[2] != "CDS" && t[2] != "exon") continue;
 		t[3] = parseInt(t[3]) - 1;
 		t[4] = parseInt(t[4]);

python/mappy.pyx

@@ -3,7 +3,7 @@ from libc.stdlib cimport free
 cimport cmappy
 import sys
 
-__version__ = '2.22'
+__version__ = '2.23'
 
 cmappy.mm_reset_timer()
 

setup.py

@@ -23,7 +23,7 @@ def readme():
 
 setup(
 	name = 'mappy',
-	version = '2.22',
+	version = '2.23',
 	url = 'https://github.com/lh3/minimap2',
 	description = 'Minimap2 python binding',
 	long_description = readme(),