Release miniprot-0.12 (r237)

Author: lh3

NEWS.md

@@ -1,3 +1,22 @@
+Release 0.12-r237 (24 June 2023)
+--------------------------------
+
+Notable changes:
+
+ * New feature: added option --no-cs to disable the cs tag. This tag is not as
+   useful as the cs tag for nucleotide alignment because it does not encode the
+   matching amino acids.
+
+ * New feature: output the number of frameshifts and in-frame stop codons in
+   the PAF output. It is non-trivial to parse in-frame stop codons.
+
+ * Bugfix: fixed malformatted protein sequences when --gtf and --trans are both
+   specified (#45).
+
+(0.12: 24 June 2023, r237)
+
+
+
 Release 0.11-r234 (18 April 2023)
 ---------------------------------
 

format.c

@@ -296,10 +296,10 @@ static void mp_write_residue(kstring_t *out, const mp_idx_t *mi, const mp_mapopt
 	kfree(0, str[0]);
 }
 
-void mp_write_paf(kstring_t *s, const mp_idx_t *mi, const mp_bseq1_t *seq, const mp_reg1_t *r, int32_t gff_out)
+void mp_write_paf(kstring_t *s, const mp_idx_t *mi, const mp_mapopt_t *opt, const mp_bseq1_t *seq, const mp_reg1_t *r)
 {
 	const mp_ctg_t *ctg;
-	if (gff_out) mp_sprintf_lite(s, "##PAF\t");
+	if (opt->flag & (MP_F_GFF|MP_F_GTF)) mp_sprintf_lite(s, "##PAF\t");
 	if (r == 0) {
 		mp_sprintf_lite(s, "%s\t%d\t0\t0\t*\t*\t0\t0\t0\t0\t0\t0\n", seq->name, seq->l_seq);
 		return;
@@ -316,8 +316,10 @@ void mp_write_paf(kstring_t *s, const mp_idx_t *mi, const mp_bseq1_t *seq, const
 		for (k = 0; k < r->p->n_cigar; ++k)
 			mp_sprintf_lite(s, "%d%c", r->p->cigar[k]>>4, NS_CIGAR_STR[r->p->cigar[k]&0xf]);
 	} else mp_sprintf_lite(s, "%d\t%d\t%d", r->chn_sc, r->chn_sc_ungap, r->cnt);
-	mp_sprintf_lite(s, "\t");
-	mp_write_cs(s, mi, &seq->seq[r->qs], r);
+	if (!(opt->flag & MP_F_NO_CS)) {
+		mp_sprintf_lite(s, "\t");
+		mp_write_cs(s, mi, &seq->seq[r->qs], r);
+	}
 	mp_sprintf_lite(s, "\n");
 }
 
@@ -416,16 +418,16 @@ void mp_write_output(kstring_t *s, void *km, const mp_idx_t *mi, const mp_bseq1_
 	s->l = 0;
 	if (r == 0) {
 		if (opt->flag&MP_F_SHOW_UNMAP)
-			mp_write_paf(s, mi, seq, 0, opt->flag&MP_F_GFF);
+			mp_write_paf(s, mi, opt, seq, 0);
 	} else if (opt->flag&MP_F_GTF) {
 		if (opt->flag & (MP_F_SHOW_RESIDUE|MP_F_SHOW_TRANS)) {
-			mp_write_paf(s, mi, seq, r, opt->flag&MP_F_GTF);
+			mp_write_paf(s, mi, opt, seq, r);
 			mp_write_residue(s, mi, opt, seq->seq, r);
 		}
 		mp_write_gtf(s, km, mi, seq, r, opt->gff_prefix, id, seq->name);
 	} else {
 		if (!(opt->flag&MP_F_NO_PAF))
-			mp_write_paf(s, mi, seq, r, opt->flag&MP_F_GFF);
+			mp_write_paf(s, mi, opt, seq, r);
 		if (opt->flag & (MP_F_SHOW_RESIDUE|MP_F_SHOW_TRANS))
 			mp_write_residue(s, mi, opt, seq->seq, r);
 		if (opt->flag&MP_F_GFF)

main.c

@@ -19,6 +19,7 @@ static ko_longopt_t long_options[] = {
 	{ "outc",            ko_required_argument, 313 },
 	{ "ie-coef",         ko_required_argument, 314 },
 	{ "trans",           ko_no_argument,       315 },
+	{ "no-cs",           ko_no_argument,       316 },
 	{ "version",         ko_no_argument,       401 },
 	{ "no-kalloc",       ko_no_argument,       501 },
 	{ "dbg-qname",       ko_no_argument,       502 },
@@ -148,6 +149,7 @@ int main(int argc, char *argv[])
 		else if (c == 313) mo.out_cov = atof(o.arg); // --outc
 		else if (c == 314) mo.ie_coef = atof(o.arg); // --ie-coef
 		else if (c == 315) mo.flag |= MP_F_SHOW_TRANS; // --trans
+		else if (c == 316) mo.flag |= MP_F_NO_CS; // --no-cs
 		else if (c == 501) mp_dbg_flag |= MP_DBG_NO_KALLOC; // --no-kalloc
 		else if (c == 502) mp_dbg_flag |= MP_DBG_QNAME; // --dbg-qname
 		else if (c == 503) mp_dbg_flag |= MP_DBG_NO_REFINE; // --dbg-no-refine

miniprot.1

@@ -1,4 +1,4 @@
-.TH miniprot 1 "18 April 2023" "miniprot-0.11 (r234)" "Bioinformatics tools"
+.TH miniprot 1 "24 June 2023" "miniprot-0.12 (r237)" "Bioinformatics tools"
 .SH NAME
 .PP
 miniprot - protein-to-genome alignment with splicing and frameshifts
@@ -156,6 +156,9 @@ substitution corresponding to the `G' operator.
 .B --trans
 Output translated protein sequences on `##STA' lines.
 .TP
+.B --no-cs
+Do not output the cs tag
+.TP
 .BI --max-intron-out \ NUM
 In the
 .B --aln

miniprot.h

@@ -3,7 +3,7 @@
 
 #include <stdint.h>
 
-#define MP_VERSION "0.11-r236-dirty"
+#define MP_VERSION "0.12-r237"
 
 #define MP_F_NO_SPLICE    0x1
 #define MP_F_NO_ALIGN     0x2
@@ -14,6 +14,7 @@
 #define MP_F_NO_PRE_CHAIN 0x40
 #define MP_F_SHOW_RESIDUE 0x80
 #define MP_F_SHOW_TRANS   0x100
+#define MP_F_NO_CS        0x200
 
 #define MP_FEAT_CDS       0
 #define MP_FEAT_STOP      1