Release miniprot-0.14 (r265)

Author: lh3

NEWS.md

@@ -1,3 +1,24 @@
+Release 0.14-r265 (7 March 2025)
+--------------------------------
+
+Notable changes:
+
+ * Bug fix: support chromosomes longer than 2Gbp (#59)
+
+ * EXPERIMENTAL feature: read splice scores from a file specified by `--spsc`
+   and consider the scores during residue alignment. The feature makes it
+   possible to apply advanced splice models and to improve miniprot alignment.
+
+ * Improvement: documented the C APIs and added an example program on using the
+   APIs (#69).
+
+This version produces alignment identical to v0.13, except for long chromosomes
+or when the new feature is used.
+
+(0.14: 7 March 2025, r265)
+
+
+
 Release 0.13-r248 (6 March 2024)
 --------------------------------
 

main.c

@@ -81,8 +81,8 @@ static void print_usage(FILE *fp, const mp_idxopt_t *io, const mp_mapopt_t *mo,
 	fprintf(fp, "    -C FLOAT     weight of splice penalty; 0 to ignore splice signals [%g]\n", mo->sp_scale);
 	fprintf(fp, "    -B INT       bonus score for alignment reaching query ends [%d]\n", mo->end_bonus);
 	fprintf(fp, "    -j INT       splice model: 2=mammal, 1=general, 0=none (see manual) [%d]\n", mo->sp_model);
-	fprintf(fp, "    --spsc=FILE  splice score []\n");
-	fprintf(fp, "    --spsc0=INT  splice penalty for sites not in --spsc [%d]\n", mo->sp_null_bonus);
+	fprintf(fp, "    --spsc=FILE  splice score file in format \"ctg offset +|- D|A score\" []\n");
+	fprintf(fp, "    --spsc0=INT  splice score for sites not in --spsc [%d]\n", mo->sp_null_bonus);
 	fprintf(fp, "  Input/output:\n");
 	fprintf(fp, "    -t INT       number of threads [%d]\n", n_threads);
 	fprintf(fp, "    --gff        output in the GFF3 format\n");

miniprot.1

@@ -1,4 +1,4 @@
-.TH miniprot 1 "5 March 2024" "miniprot-0.13 (r248)" "Bioinformatics tools"
+.TH miniprot 1 "7 March 2025" "miniprot-0.14 (r265)" "Bioinformatics tools"
 .SH NAME
 .PP
 miniprot - protein-to-genome alignment with splicing and frameshifts
@@ -135,6 +135,19 @@ exon and the poly-Y close to the acceptor may not be conserved in some species.
 The general model takes `|GTR...YAG|' as the optimal sequence. Both models also
 consider less frequent splice sites including `G|GC...YAG|' and `|AT...AC|'.
 .TP
+.BI --spsc \ FILE
+Splice score file []. Each line is TAB-delimited, consisting of contig name,
+offset of the splice junction, strand (`+' or `-'), donor or acceptor (`D' or
+`A') and an integer score. The score is added the donor/acceptor score function.
+It can be positive or negative and needs to be compatible with the scoring system.
+.TP
+.BI --spsc0 \ INT
+Splice score for positions not in the
+.B --spsc
+file [-7]. This option has no effect if
+.B --spsc
+is not specified.
+.TP
 .BI --io-coef \ FLOAT
 Logarithm intron length penalty (EXPERIMENTAL) [0.5]
 .SS Input/Output options

miniprot.h

@@ -3,7 +3,7 @@
 
 #include <stdint.h>
 
-#define MP_VERSION "0.13-r264-dirty"
+#define MP_VERSION "0.14-r265"
 
 #define MP_F_NO_SPLICE    0x1
 #define MP_F_NO_ALIGN     0x2