r655: options to map to one strand of the ref lh3#91

eskutkaan · Jan 16, 2018 · 33f8157 · 33f8157
1 parent eecc060
commit 33f8157
Show file tree

Hide file tree

Showing 5 changed files with 29 additions and 3 deletions.
diff --git a/align.c b/align.c
@@ -696,7 +696,7 @@ mm_reg1_t *mm_align_skeleton(void *km, const mm_mapopt_t *opt, const mm_idx_t *m
 				regs[i].p->trans_strand = opt->flag&MM_F_SPLICE_FOR? 1 : 2;
 		}
 		if (r2.cnt > 0) regs = mm_insert_reg(&r2, i, &n_regs, regs);
-		if (!(opt->flag&MM_F_SPLICE) && !(opt->flag&MM_F_SR) && i > 0) { // don't try inversion alignment for -xsplice or -xsr
+		if (!(opt->flag&(MM_F_SPLICE|MM_F_SR)) && !(opt->flag&(MM_F_FOR_ONLY|MM_F_REV_ONLY)) && i > 0) { // don't try inversion alignment for -xsplice or -xsr, or --for-only/rev-only
 			if (mm_align1_inv(km, opt, mi, qlen, qseq0, &regs[i-1], &regs[i], &r2, &ez)) {
 				regs = mm_insert_reg(&r2, i, &n_regs, regs);
 				++i; // skip the inserted INV alignment

diff --git a/main.c b/main.c
@@ -6,7 +6,7 @@
 #include "mmpriv.h"
 #include "getopt.h"
 
-#define MM_VERSION "2.7-r654"
+#define MM_VERSION "2.7-r655-dirty"
 
 #ifdef __linux__
 #include <sys/resource.h>
@@ -45,6 +45,8 @@ static struct option long_options[] = {
 	{ "splice-flank",   optional_argument, 0, 0 },
 	{ "idx-no-seq",     no_argument,       0, 0 },
 	{ "end-seed-pen",   required_argument, 0, 0 },   // 21
+	{ "for-only",       no_argument,       0, 0 },   // 22
+	{ "rev-only",       no_argument,       0, 0 },   // 23
 	{ "help",           no_argument,       0, 'h' },
 	{ "max-intron-len", required_argument, 0, 'G' },
 	{ "version",        no_argument,       0, 'V' },
@@ -142,6 +144,8 @@ int main(int argc, char *argv[])
 		else if (c == 0 && long_idx ==18) opt.flag |= MM_F_INDEPEND_SEG; // --no-pairing
 		else if (c == 0 && long_idx ==20) ipt.flag |= MM_I_NO_SEQ; // --idx-no-seq
 		else if (c == 0 && long_idx ==21) opt.anchor_ext_shift = atoi(optarg); // --end-seed-pen
+		else if (c == 0 && long_idx ==22) opt.flag |= MM_F_FOR_ONLY; // --for-only
+		else if (c == 0 && long_idx ==23) opt.flag |= MM_F_REV_ONLY; // --rev-only
 		else if (c == 0 && long_idx == 14) { // --frag
 			if (optarg == 0 || strcmp(optarg, "yes") == 0 || strcmp(optarg, "y") == 0)
 				opt.flag |= MM_F_FRAG_MODE;

diff --git a/map.c b/map.c
@@ -117,6 +117,11 @@ int mm_set_opt(const char *preset, mm_idxopt_t *io, mm_mapopt_t *mo)
 
 int mm_check_opt(const mm_idxopt_t *io, const mm_mapopt_t *mo)
 {
+	if ((mo->flag & MM_F_FOR_ONLY) && (mo->flag & MM_F_REV_ONLY)) {
+		if (mm_verbose >= 1)
+			fprintf(stderr, "[ERROR]\033[1;31m --for-only and --rev-only can't be applied at the same time\033[0m\n");
+		return -3;
+	}
 	if ((mo->q != mo->q2 || mo->e != mo->e2) && !(mo->e > mo->e2 && mo->q + mo->e < mo->q2 + mo->e2)) {
 		if (mm_verbose >= 1)
 			fprintf(stderr, "[ERROR]\033[1;31m dual gap penalties violating E1>E2 and O1+E1<O2+E2\033[0m\n");
@@ -245,6 +250,13 @@ static mm128_t *collect_seed_hits(void *km, const mm_mapopt_t *opt, int max_occ,
 				if ((opt->flag&MM_F_AVA) && cmp > 0) // all-vs-all mode: map once
 					continue;
 			}
+			if (opt->flag & (MM_F_FOR_ONLY|MM_F_REV_ONLY)) {
+				if ((r[k]&1) == (q->qpos&1)) { // forward strand
+					if (opt->flag & MM_F_REV_ONLY) continue;
+				} else {
+					if (opt->flag & MM_F_FOR_ONLY) continue;
+				}
+			}
 			p = &a[(*n_a)++];
 			if ((r[k]&1) == (q->qpos&1)) { // forward strand
 				p->x = (r[k]&0xffffffff00000000ULL) | rpos;

diff --git a/minimap.h b/minimap.h
@@ -25,6 +25,8 @@
 #define MM_F_INDEPEND_SEG  0x20000
 #define MM_F_SPLICE_FLANK  0x40000
 #define MM_F_SOFTCLIP      0x80000
+#define MM_F_FOR_ONLY      0x100000
+#define MM_F_REV_ONLY      0x200000
 
 #define MM_I_HPC          0x1
 #define MM_I_NO_SEQ       0x2

diff --git a/minimap2.1 b/minimap2.1
@@ -1,4 +1,4 @@
-.TH minimap2 1 "9 January 2018" "minimap2-2.7 (r654)" "Bioinformatics tools"
+.TH minimap2 1 "16 January 2018" "minimap2-2.7-dirty (r655)" "Bioinformatics tools"
 .SH NAME
 .PP
 minimap2 - mapping and alignment between collections of DNA sequences
@@ -206,6 +206,14 @@ seeds with ungapped alignment.
 .TP
 .BR --frag [= no | yes ]
 Whether to enable the fragment mode [no]
+.TP
+.B --for-only
+Only map to the forward strand of the reference sequences. For paired-end
+reads in the forward-reverse orientation, the first read is mapped to forward
+strand of the reference and the second read to the reverse stand.
+.TP
+.B --rev-only
+Only map to the reverse complement strand of the reference sequences.
 .SS Alignment options
 .TP 10
 .BI -A \ INT