Release 1.19

samtools · Dec 12, 2023 · bb75b76 · bb75b76
2 parents 6c2c1e9 + 37cf779
commit bb75b76
Show file tree

Hide file tree

Showing 87 changed files with 2,035 additions and 743 deletions.
diff --git a/Makefile b/Makefile
@@ -104,7 +104,7 @@ endif
 
 include config.mk
 
-PACKAGE_VERSION = 1.18
+PACKAGE_VERSION = 1.19
 
 # If building from a Git repository, replace $(PACKAGE_VERSION) with the Git
 # description of the working tree: either a release tag with the same value
@@ -233,28 +233,31 @@ abuf_h = abuf.h $(htslib_vcf_h)
 dbuf_h = dbuf.h $(htslib_vcf_h)
 bam2bcf_h = bam2bcf.h $(htslib_hts_h) $(htslib_vcf_h)
 bam_sample_h = bam_sample.h $(htslib_sam_h)
+cigar_state_h = cigar_state.h $(htslib_hts_h) $(htslib_sam_h)
+read_consensus_h = read_consensus.h $(htslib_hts_h) $(htslib_sam_h)
+str_finder_h = str_finder.h utlist.h
 
-str_finder.o: str_finder.h utlist.h
+str_finder.o: str_finder.c $(str_finder_h) utlist.h
 main.o: main.c $(htslib_hts_h) config.h version.h $(bcftools_h)
 vcfannotate.o: vcfannotate.c $(htslib_vcf_h) $(htslib_synced_bcf_reader_h) $(htslib_kseq_h) $(htslib_khash_str2int_h) $(bcftools_h) vcmp.h $(filter_h) $(convert_h) $(smpl_ilist_h) regidx.h $(htslib_khash_h) $(dbuf_h)
 vcfplugin.o: vcfplugin.c config.h $(htslib_vcf_h) $(htslib_synced_bcf_reader_h) $(htslib_kseq_h) $(htslib_khash_str2int_h) $(bcftools_h) vcmp.h $(filter_h)
 vcfcall.o: vcfcall.c $(htslib_vcf_h) $(htslib_kfunc_h) $(htslib_synced_bcf_reader_h) $(htslib_khash_str2int_h) $(bcftools_h) $(call_h) $(prob1_h) $(ploidy_h) $(gvcf_h) regidx.h $(vcfbuf_h)
 vcfconcat.o: vcfconcat.c $(htslib_vcf_h) $(htslib_synced_bcf_reader_h) $(htslib_kseq_h) $(htslib_bgzf_h) $(htslib_tbx_h) $(htslib_thread_pool_h) $(bcftools_h)
 vcfconvert.o: vcfconvert.c $(htslib_faidx_h) $(htslib_vcf_h) $(htslib_bgzf_h) $(htslib_synced_bcf_reader_h) $(htslib_vcfutils_h) $(htslib_kseq_h) $(bcftools_h) $(filter_h) $(convert_h) $(tsv2vcf_h)
 vcffilter.o: vcffilter.c $(htslib_vcf_h) $(htslib_synced_bcf_reader_h) $(htslib_vcfutils_h) $(bcftools_h) $(filter_h) rbuf.h regidx.h
-vcfgtcheck.o: vcfgtcheck.c $(htslib_vcf_h) $(htslib_synced_bcf_reader_h) $(htslib_vcfutils_h) $(htslib_kbitset_h) $(htslib_hts_os_h) $(bcftools_h) extsort.h
+vcfgtcheck.o: vcfgtcheck.c $(htslib_vcf_h) $(htslib_synced_bcf_reader_h) $(htslib_vcfutils_h) $(htslib_kbitset_h) $(htslib_hts_os_h) $(htslib_bgzf_h) $(bcftools_h) extsort.h filter.h
 vcfindex.o: vcfindex.c $(htslib_vcf_h) $(htslib_tbx_h) $(htslib_kstring_h) $(htslib_bgzf_h) $(bcftools_h)
 vcfisec.o: vcfisec.c $(htslib_vcf_h) $(htslib_synced_bcf_reader_h) $(htslib_vcfutils_h) $(htslib_hts_os_h) $(bcftools_h) $(filter_h)
-vcfmerge.o: vcfmerge.c $(htslib_vcf_h) $(htslib_synced_bcf_reader_h) $(htslib_vcfutils_h) $(htslib_faidx_h) regidx.h $(bcftools_h) vcmp.h $(htslib_khash_h)
-vcfnorm.o: vcfnorm.c $(htslib_vcf_h) $(htslib_synced_bcf_reader_h) $(htslib_faidx_h) $(htslib_khash_str2int_h) $(bcftools_h) rbuf.h abuf.h gff.h
+vcfmerge.o: vcfmerge.c $(htslib_vcf_h) $(htslib_synced_bcf_reader_h) $(htslib_vcfutils_h) $(htslib_faidx_h) $(htslib_kbitset_h) $(htslib_hts_endian_h) $(bcftools_h) regidx.h vcmp.h $(htslib_khash_h) $(htslib_kbitset_h)
+vcfnorm.o: vcfnorm.c $(htslib_vcf_h) $(htslib_synced_bcf_reader_h) $(htslib_faidx_h) $(htslib_khash_str2int_h) $(bcftools_h) rbuf.h abuf.h gff.h regidx.h
 vcfquery.o: vcfquery.c $(htslib_vcf_h) $(htslib_synced_bcf_reader_h) $(htslib_khash_str2int_h) $(htslib_vcfutils_h) $(bcftools_h) $(filter_h) $(convert_h) $(smpl_ilist_h)
 vcfroh.o: vcfroh.c $(htslib_vcf_h) $(htslib_synced_bcf_reader_h) $(htslib_kstring_h) $(htslib_kseq_h) $(htslib_bgzf_h) $(bcftools_h) HMM.h $(smpl_ilist_h) $(filter_h)
 vcfcnv.o: vcfcnv.c $(htslib_vcf_h) $(htslib_synced_bcf_reader_h) $(htslib_kstring_h) $(htslib_kfunc_h) $(htslib_khash_str2int_h) $(bcftools_h) HMM.h rbuf.h
 vcfhead.o: vcfhead.c $(htslib_kstring_h) $(htslib_vcf_h) $(bcftools_h)
 vcfsom.o: vcfsom.c $(htslib_vcf_h) $(htslib_synced_bcf_reader_h) $(htslib_vcfutils_h) $(htslib_hts_os_h) $(bcftools_h)
 vcfsort.o: vcfsort.c $(htslib_vcf_h) $(htslib_kstring_h) $(htslib_hts_os_h) kheap.h $(bcftools_h)
 vcfstats.o: vcfstats.c $(htslib_vcf_h) $(htslib_synced_bcf_reader_h) $(htslib_vcfutils_h) $(htslib_faidx_h) $(bcftools_h) $(filter_h) bin.h dist.h
-vcfview.o: vcfview.c $(htslib_vcf_h) $(htslib_synced_bcf_reader_h) $(htslib_vcfutils_h) $(bcftools_h) $(filter_h) $(htslib_khash_str2int_h)
+vcfview.o: vcfview.c $(htslib_vcf_h) $(htslib_synced_bcf_reader_h) $(htslib_vcfutils_h) $(bcftools_h) $(filter_h) $(htslib_khash_str2int_h) $(htslib_kbitset_h)
 reheader.o: reheader.c $(htslib_vcf_h) $(htslib_bgzf_h) $(htslib_tbx_h) $(htslib_kseq_h) $(htslib_thread_pool_h) $(htslib_faidx_h) $(htslib_khash_str2int_h) $(bcftools_h) $(khash_str2str_h)
 tabix.o: tabix.c $(htslib_bgzf_h) $(htslib_tbx_h)
 ccall.o: ccall.c $(htslib_kfunc_h) $(call_h) kmin.h $(prob1_h)
@@ -275,12 +278,12 @@ bin.o: bin.c $(bcftools_h) bin.h
 dist.o: dist.c dist.h
 cols.o: cols.c cols.h
 regidx.o: regidx.c $(htslib_hts_h) $(htslib_kstring_h) $(htslib_kseq_h) $(htslib_khash_str2int_h) regidx.h
-consensus.o: consensus.c $(htslib_vcf_h) $(htslib_kstring_h) $(htslib_synced_bcf_reader_h) $(htslib_kseq_h) $(htslib_bgzf_h) regidx.h $(bcftools_h) rbuf.h $(filter_h)
+consensus.o: consensus.c $(htslib_vcf_h) $(htslib_kstring_h) $(htslib_synced_bcf_reader_h) $(htslib_kseq_h) $(htslib_bgzf_h) regidx.h $(bcftools_h) rbuf.h $(filter_h) $(smpl_ilist_h)
 mpileup.o: mpileup.c $(htslib_sam_h) $(htslib_faidx_h) $(htslib_kstring_h) $(htslib_khash_str2int_h) $(htslib_hts_os_h) regidx.h $(bcftools_h) $(bam2bcf_h) $(bam_sample_h) $(gvcf_h)
 bam2bcf.o: bam2bcf.c $(htslib_hts_h) $(htslib_sam_h) $(htslib_kstring_h) $(htslib_kfunc_h) $(bam2bcf_h) mw.h
-bam2bcf_indel.o: bam2bcf_indel.c $(htslib_hts_h) $(htslib_sam_h) $(htslib_khash_str2int_h) $(bam2bcf_h) $(htslib_ksort_h) str_finder.h
-bam2bcf_iaux.o: bam2bcf_iaux.c $(htslib_hts_h) $(htslib_sam_h) $(htslib_khash_str2int_h) $(bam2bcf_h) $(htslib_ksort_h) str_finder.h read_consensus.h cigar_state.h
-read_consensus.o: read_consensus.c read_consensus.h cigar_state.h $(htslib_hts_h) $(htslib_sam_h)
+bam2bcf_indel.o: bam2bcf_indel.c $(htslib_hts_h) $(htslib_sam_h) $(htslib_khash_str2int_h) $(bam2bcf_h) $(htslib_ksort_h) $(str_finder_h)
+bam2bcf_iaux.o: bam2bcf_iaux.c $(htslib_hts_h) $(htslib_sam_h) $(htslib_khash_str2int_h) $(bcftools_h) $(bam2bcf_h) $(htslib_ksort_h) $(read_consensus_h) $(cigar_state_h)
+read_consensus.o: read_consensus.c $(read_consensus_h) $(cigar_state_h) $(bcftools_h) kheap.h
 bam_sample.o: bam_sample.c $(htslib_hts_h) $(htslib_kstring_h) $(htslib_khash_str2int_h) $(khash_str2str_h) $(bam_sample_h) $(bcftools_h)
 version.o: version.h version.c
 hclust.o: hclust.c $(htslib_hts_h) $(htslib_kstring_h) $(bcftools_h) hclust.h
@@ -289,8 +292,8 @@ vcfbuf.o: vcfbuf.c $(htslib_vcf_h) $(htslib_vcfutils_h) $(htslib_hts_os_h) $(bcf
 abuf.o: abuf.c $(htslib_vcf_h) $(bcftools_h) rbuf.h abuf.h
 extsort.o: extsort.c $(bcftools_h) extsort.h kheap.h
 smpl_ilist.o: smpl_ilist.c $(bcftools_h) $(smpl_ilist_h)
-gff.o: gff.c gff.h regidx.h
-csq.o: csq.c $(htslib_hts_h) $(htslib_vcf_h) $(htslib_synced_bcf_reader_h) $(htslib_khash_h) $(htslib_khash_str2int_h) $(htslib_kseq_h) $(htslib_faidx_h) $(bcftools_h) $(filter_h) regidx.h kheap.h $(smpl_ilist_h) rbuf.h
+gff.o: gff.c $(htslib_hts_h) $(htslib_khash_h)  $(htslib_khash_str2int_h) $(htslib_kseq_h) $(htslib_bgzf_h) $(bcftools_h) gff.h regidx.h
+csq.o: csq.c $(htslib_hts_h) $(htslib_vcf_h) $(htslib_synced_bcf_reader_h) $(htslib_khash_h) $(htslib_khash_str2int_h) $(htslib_kseq_h) $(htslib_faidx_h) $(htslib_bgzf_h) $(bcftools_h) $(filter_h) regidx.h kheap.h $(smpl_ilist_h) rbuf.h gff.h
 
 # test programs
 
@@ -300,7 +303,7 @@ csq.o: csq.c $(htslib_hts_h) $(htslib_vcf_h) $(htslib_synced_bcf_reader_h) $(hts
 #
 # If using MSYS, avoid poor shell expansion via:
 #    MSYS2_ARG_CONV_EXCL="*" make check
-check test-no-plugins: $(PROGRAMS) $(TEST_PROGRAMS) $(BGZIP) $(TABIX)
+check-no-plugins test-no-plugins: $(PROGRAMS) $(TEST_PROGRAMS) $(BGZIP) $(TABIX)
 	./test/test-rbuf
 	./test/test-regidx
 	REF_PATH=: ./test/test.pl --exec bgzip=$(BGZIP) --exec tabix=$(TABIX) --htsdir=$(HTSDIR) $${TEST_OPTS:-}

diff --git a/NEWS b/NEWS
@@ -1,5 +1,127 @@
-## Release 1.18 (25th July 2023)
+## Release 1.19 (12th December 2023)
+
+
+Changes affecting the whole of bcftools, or multiple commands:
+
+* Filtering expressions can be given a file with list of strings to match, this
+  was previously possible only for the ID column. For example
+
+    ID=@file            .. selects lines with ID present in the file
+    INFO/TAG=@file.txt  .. selects lines where TAG has a string value listed in the file
+    INFO/TAG!=@file.txt .. TAG must not have a string value listed in the file
+
+  Allow to query REF,ALT columns directly, for example
+
+    -e 'REF="N"'
+
+
+Changes affecting specific commands:
+
+* bcftools annotate
+
+    - Fix `bcftools annotate --mark-sites`, VCF sites overlapping regions in a BED file
+      were not annotated (#1989)
+
+    - Add flexibility to FILTER column transfers and allow transfers within the same file,
+      across files, and in combination. For examples see
+        http://samtools.github.io/bcftools/howtos/annotate.html#transfer_filter_to_info
+
+* bcftools call
+
+    - Output MIN_DP rather than MinDP in gVCF mode
+
+    - New `-*, --keep-unseen-allele` option to output the unobserved allele <*>,
+      intended for gVCF.
+
+* bcftools head
+
+    - New `-s, --samples` option to include the #CHROM header line with samples.
+
+* bcftools gtcheck
+
+    - Add output options `-o, --output` and `-O, --output-type`
+
+    - Add filtering options `-i, --include` and `-e, --exclude`
+
+    - Rename the short option `-e, --error-probability` from lower case to upper
+      case `-E, --error-probability`
+
+    - Changes to the output format, replace the DC section with DCv2:
+
+        - adds a new column for the number of matching genotypes
+
+        - The --error-probability is newly interpreted as the probability of erroneous
+          allele rather than genotype. In other words, the calculation of the discordance
+          score now considers the probability of genotyping error to be different
+          for HOM and HET genotypes, i.e. P(0/1|dsg=0) > P(1/1|dsg=0).
+
+        - fixes in HWE score calculation plus output average HWE score rather
+          than absolute HWE score
+
+        - better description of fields
 
+* bcftools merge
+
+    - Add `-m` modifiers to suppress the output of the unseen allele <*> or <NON_REF>
+      at variant sites (e.g. `-m both,*`) or all sites (e.g. `-m both,**`)
+
+* bcftools mpileup
+
+    - Output MIN_DP rather than MinDP in gVCF mode
+
+* bcftools norm
+
+    - Add the number of joined lines to the summary output, for example
+
+        Lines   total/split/joined/realigned/skipped:	6/0/3/0/0
+
+    - Allow combining -m and -a with --old-rec-tag (#2020)
+
+    - Symbolic <DEL> alleles caused norm to expand REF to the full length of the deletion.
+      This was not intended and problematic for long deletions, the REF allele should list
+      one base only (#2029)
+
+* bcftools query
+
+    - Add new `-N, --disable-automatic-newline` option for pre-1.18 query formatting behavior
+      when newline would not be added when missing
+
+    - Make the automatic addition of the newline character in a more predictable way and,
+      when missing, always put it at the end of the expression. In version 1.18 it could
+      be added at the end of the expression (for per-site expressions) or inside the square
+      brackets (for per-sample expressions). The new behavior is:
+
+        - if the formatting expression contains a newline character, do nothing
+        - if there is no newline character and -N, --disable-automatic-newline is given, do nothing
+        - if there is no newline character and -N is not given, insert newline at the end of the expression
+
+      See #1969 for details
+
+    - Add new `-F, --print-filtered` option to output a default string for samples that would otherwise
+      be filtered by `-i/-e` expressions.
+
+    - Include sample name in the output header with `-H` whenever it makes sense (#1992)
+
+* bcftools +spit-vep
+
+    - Fix on the fly filtering involving numeric subfields, e.g. `-i 'MAX_AF<0.001'` (#2039)
+
+    - Interpret default column type names (--columns-types) as entire strings, rather than
+      substrings to avoid unexpected spurious matches (i.e. internally add ^ and $ to all
+      field names)
+
+* bcftools +trio-dnm2
+
+    - Do not flag paternal genotyping errors as de novo mutations. Specifically, when father's
+      chrX genotype is 0/1 and mother's 0/0, 0/1 in the child will not be marked as DNM.
+
+* bcftools view
+
+    - Add new `-A, --trim-unseen-allele` option to remove the unseen allele <*> or <NON_REF>
+      at variant sites (`-A`) or all sites (`-AA`)
+
+
+## Release 1.18 (25th July 2023)
 
 Changes affecting the whole of bcftools, or multiple commands:
 

diff --git a/abuf.c b/abuf.c
@@ -411,12 +411,12 @@ static void _split_table_set_info(abuf_t *buf, bcf_info_t *info, merge_rule_t mo
             buf->tmp2  = dst.s;
             ret = bcf_update_info(buf->out_hdr, out, tag, buf->tmp2, dst.l, type);
         }
-        if ( ret!=0 ) error("An error occurred while updating INFO/%s\n",tag);
+        if ( ret!=0 ) error("An error occurred while updating INFO/%s (errcode=%d)\n",tag,ret);
     }
 }
 static void _split_table_set_history(abuf_t *buf)
 {
-    int i,j;
+    int i,j,ret;
     bcf1_t *rec = buf->split.rec;
     buf->tmps.l = 0;
     ksprintf(&buf->tmps,"%s|%"PRIhts_pos"|%s|",bcf_seqname(buf->hdr,rec),rec->pos+1,rec->d.allele[0]);
@@ -441,8 +441,8 @@ static void _split_table_set_history(abuf_t *buf)
             kputc(',',&buf->tmps);
         }
         buf->tmps.s[--buf->tmps.l] = 0;
-        if ( (bcf_update_info_string(buf->out_hdr, out, buf->split.info_tag, buf->tmps.s))!=0 )
-            error("An error occurred while updating INFO/%s\n",buf->split.info_tag);
+        if ( (ret=bcf_update_info_string(buf->out_hdr, out, buf->split.info_tag, buf->tmps.s))!=0 )
+            error("An error occurred while updating INFO/%s (errcode=%d)\n",buf->split.info_tag,ret);
     }
 }
 static void _split_table_set_gt(abuf_t *buf)
@@ -668,7 +668,7 @@ static void _split_table_set_format(abuf_t *buf, bcf_fmt_t *fmt, merge_rule_t mo
             #undef BRANCH
             ret = bcf_update_format(buf->out_hdr, out, tag, buf->tmp2, 3*(1+star_allele)*nsmpl, type);
         }
-        if ( ret!=0 ) error("An error occurred while updating FORMAT/%s\n",tag);
+        if ( ret!=0 ) error("An error occurred while updating FORMAT/%s (errcode=%d)\n",tag,ret);
     }
 }
 static inline int _is_acgtn(char *seq)

diff --git a/bcftools.h b/bcftools.h
@@ -141,4 +141,16 @@ static inline int bcf_double_test(double d, uint64_t value)
 #define bcf_double_is_missing(x)     bcf_double_test((x),bcf_double_missing)
 #define bcf_double_is_missing_or_vector_end(x)     (bcf_double_test((x),bcf_double_missing) || bcf_double_test((x),bcf_double_vector_end))
 
+static inline int get_unseen_allele(bcf1_t *line)
+{
+    int i;
+    for (i=1; i<line->n_allele; i++)
+    {
+        if ( !strcmp(line->d.allele[i],"<*>") ) return i;
+        if ( !strcmp(line->d.allele[i],"<NON_REF>") ) return i;
+        if ( !strcmp(line->d.allele[i],"<X>") ) return i;
+    }
+    return 0;
+}
+
 #endif
diff --git a/call.h b/call.h
@@ -33,7 +33,7 @@ THE SOFTWARE.  */
 #define CALL_VARONLY        (1<<1)
 #define CALL_CONSTR_TRIO    (1<<2)
 #define CALL_CONSTR_ALLELES (1<<3)
-//
+#define CALL_KEEP_UNSEEN    (1<<4)
 #define CALL_FMT_PV4        (1<<5)
 #define CALL_FMT_GQ         (1<<6)
 #define CALL_FMT_GP         (1<<7)
@@ -125,8 +125,7 @@ call_t;
 void error(const char *format, ...);
 
 /*
- *  call() - return -1 value on critical error; -2 to skip the site; or the number of non-reference
- *            alleles on success.
+ *  call() - return -1 value on critical error; -2 to skip the site; or the number of alleles on success
  */
 int mcall(call_t *call, bcf1_t *rec);    // multiallic and rare-variant calling model
 int ccall(call_t *call, bcf1_t *rec);    // the default consensus calling model