Release 1.20

Author: daviesrob

LICENSE

@@ -9,7 +9,7 @@ the INSTALL document), the use of this software is governed by the GPL license.
 
 The MIT/Expat License
 
-Copyright (C) 2012-2023 Genome Research Ltd.
+Copyright (C) 2012-2024 Genome Research Ltd.
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal
@@ -772,3 +772,28 @@ PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
 LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
 NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
 SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+-----------------------------------------------------------------------------
+
+License for edlib.[ch]
+
+The MIT License (MIT)
+
+Copyright (c) 2014 Martin Šošić
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of
+this software and associated documentation files (the "Software"), to deal in
+the Software without restriction, including without limitation the rights to
+use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of
+the Software, and to permit persons to whom the Software is furnished to do so,
+subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS
+FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR
+COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER
+IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

Makefile

@@ -40,9 +40,10 @@ OBJS     = main.o vcfindex.o tabix.o \
            vcfcall.o mcall.o vcmp.o gvcf.o reheader.o convert.o vcfconvert.o tsv2vcf.o \
            vcfcnv.o vcfhead.o HMM.o consensus.o ploidy.o bin.o hclust.o version.o \
            regidx.o smpl_ilist.o csq.o vcfbuf.o \
-           mpileup.o bam2bcf.o bam2bcf_indel.o bam2bcf_iaux.o read_consensus.o bam_sample.o \
+           mpileup.o bam2bcf.o bam2bcf_indel.o bam2bcf_iaux.o bam2bcf_edlib.o \
+	   read_consensus.o bam_sample.o \
            vcfsort.o cols.o extsort.o dist.o abuf.o \
-           ccall.o em.o prob1.o kmin.o str_finder.o gff.o
+           ccall.o em.o prob1.o kmin.o str_finder.o gff.o edlib.o
 PLUGIN_OBJS = vcfplugin.o
 
 prefix      = /usr/local
@@ -104,7 +105,7 @@ endif
 
 include config.mk
 
-PACKAGE_VERSION = 1.19
+PACKAGE_VERSION = 1.20
 
 # 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
@@ -142,7 +143,9 @@ print-version:
 ifdef USE_GPL
     main.o : EXTRA_CPPFLAGS += -DUSE_GPL
     OBJS += polysomy.o peakfit.o
-    GSL_LIBS ?= -lgsl -lcblas
+    ifndef GSL_LIBS
+        GSL_LIBS += -lgsl -lcblas
+    endif
 endif
 
 print-%:
@@ -232,6 +235,7 @@ vcfbuf_h = vcfbuf.h $(htslib_vcf_h)
 abuf_h = abuf.h $(htslib_vcf_h)
 dbuf_h = dbuf.h $(htslib_vcf_h)
 bam2bcf_h = bam2bcf.h $(htslib_hts_h) $(htslib_vcf_h)
+edlib.h = edlib.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)
@@ -242,8 +246,8 @@ 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)
+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) $(htslib_hts_endian_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) $(htslib_hts_endian_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) $(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)
@@ -261,10 +265,10 @@ vcfview.o: vcfview.c $(htslib_vcf_h) $(htslib_synced_bcf_reader_h) $(htslib_vcfu
 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)
-convert.o: convert.c $(htslib_vcf_h) $(htslib_synced_bcf_reader_h) $(htslib_vcfutils_h) $(htslib_kfunc_h) $(htslib_khash_str2int_h) $(bcftools_h) $(variantkey_h) $(convert_h) $(filter_h)
+convert.o: convert.c $(htslib_vcf_h) $(htslib_synced_bcf_reader_h) $(htslib_vcfutils_h) $(htslib_kfunc_h) $(htslib_khash_str2int_h) $(htslib_hts_endian_h) $(bcftools_h) $(variantkey_h) $(convert_h) $(filter_h)
 tsv2vcf.o: tsv2vcf.c $(tsv2vcf_h)
 em.o: em.c $(htslib_vcf_h) kmin.h $(call_h)
-filter.o: filter.c $(htslib_khash_str2int_h) $(htslib_hts_defs_h) $(htslib_vcfutils_h) $(htslib_kfunc_h) config.h $(filter_h) $(bcftools_h)
+filter.o: filter.c $(htslib_khash_str2int_h) $(htslib_hts_defs_h) $(htslib_vcfutils_h) $(htslib_kfunc_h) $(htslib_hts_endian_h) config.h $(filter_h) $(bcftools_h)
 	$(CC) $(CFLAGS) $(ALL_CPPFLAGS) $(EXTRA_CPPFLAGS) $(PERL_CFLAGS) -c -o $@ $<
 gvcf.o: gvcf.c $(gvcf_h) $(bcftools_h)
 kmin.o: kmin.c kmin.h
@@ -283,6 +287,7 @@ mpileup.o: mpileup.c $(htslib_sam_h) $(htslib_faidx_h) $(htslib_kstring_h) $(hts
 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) $(bcftools_h) $(bam2bcf_h) $(htslib_ksort_h) $(read_consensus_h) $(cigar_state_h)
+bam2bcf_edlib.o: bam2bcf_edlib.c $(htslib_hts_h) $(htslib_sam_h) $(htslib_khash_str2int_h) $(bcftools_h) $(bam2bcf_h) $(htslib_ksort_h) $(read_consensus_h) $(cigar_state_h) $(edlib.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

NEWS

@@ -1,3 +1,99 @@
+## Release 1.20 (15th April 2024)
+
+
+Changes affecting the whole of bcftools, or multiple commands:
+
+* Add short option -W for --write-index. The option now accepts an optional parameter
+  which allows to choose between TBI and CSI index format.
+
+
+Changes affecting specific commands:
+
+* bcftools consensus
+
+    - Add new --regions-overlap option which allows to take into account overlapping deletions
+      that start out of the fasta file target region.
+
+* bcftools isec
+
+    - Add new option `-l, --file-list` to read the list of file names from a file
+
+* bcftools merge
+
+    - Add new option `--force-single` to support single-file edge case (#2100)
+
+* bcftools mpileup
+
+    - Add new option --indels-cns for an alternative indel calling model, which should increase
+      the speed on long read data (thanks to using edlib) and the precision (thanks to a number
+      of heuristics).
+
+* bcftools norm
+
+    - Change the order of atomization and multiallelic splitting (when both -a,-m are given)
+      from "atomize first, then split" to "split first, then atomize". This usually results
+      in a simpler VCF representation. The previous behaviour can be achieved by explicitly
+      streaming the output of the --atomize command into the --multiallelics splitting command.
+
+    - Fix Type=String multiallelic splitting for Number=A,R,G tags with incorrect number
+      of values.
+
+    - Merging into multiallelic sites with `bcftools norm -m +indels` did not work. This is
+      now fixed and the merging is now more strict about variant types, for example complex
+      events, such as AC>TGA, are not considered as indels anymore (#2084)
+
+* bcftools reheader
+
+    - Allow reading the input file from a stream with --fai (#2088)
+
+* bcftools +setGT
+
+    - Support for custom genotypes based on the allele with higher depth, such
+      as `--new-gt c:0/X` custom genotypes (#2065)
+
+* bcftools +split-vep
+
+    - When only one of the tags is present, automatically choose INFO/BCSQ (the default
+      tag name produced by `bcftools csq`) or INFO/CSQ (produced by VEP). When both
+      tags are present, use the default INFO/CSQ.
+
+    - Transcript selection by MANE, PICK, and user-defined transcripts, for example
+
+        --select CANONICAL=YES
+        --select MANE_SELECT!=""
+        --select PolyPhen~probably_damaging
+
+    - Select all matching transcripts via --select, not just one
+
+    - Change automatic type parsing of VEP fields DNA_position, CDS_position, and Protein_position
+      from Integer to String, as it can be of the form "8586-8599/9231". The type Integer can be
+      still enforced with `-c cDNA_position:int,CDS_position:int,Protein_position:int`.
+
+    - Recognize `-c field:str`, not just `-c field:string`, as advertised in the usage page
+
+    - Fix a bug which made filtering expression containing missing values crash (#2098)
+
+* bcftools stats
+
+    - When GT is missing but AD is present, the program determines the alternate allele from AD.
+      However, if the AD tag has incorrect number of values, the program would exit with an error
+      printing "Requested allele outside valid range". This is now fixed by taking into account
+      the actual number of ALT alleles.
+
+* bcftools +tag2tag
+
+    - Support for conversion from tags using localized alleles (e.g. LPL, LAD) to the family of
+      standard tags (PL, AD)
+
+* bcftools +trio-dnm2
+
+    - Extend --strictly-novel to exclude cases where the non-Mendelian allele
+      is the reference allele. The change is motivated by the observation that
+      this class of variants is enriched for errors (especially for indels),
+      and better corresponds with the option name.
+
+
+
 ## Release 1.19 (12th December 2023)
 
 
@@ -338,7 +434,7 @@ Changes affecting specific commands:
 
 * bcftools norm
 
-    - New --multi-overlaps option allows to set overlapping alleles either to the
+    - New --multi-overlaps option allows setting overlapping alleles either to the
       ref allele (the current default) or to a missing allele (#1764 and #1802)
 
     - Fixed a bug in `-m -` which does not split missing FORMAT values correctly and
@@ -509,7 +605,7 @@ Changes affecting specific commands:
     - In addition to `--rename-annots`, which requires a file with name mappings,
       it is now possible to do the same on the command line `-c NEW_TAG:=OLD_TAG`
 
-    - Add new option --min-overlap which allows to specify the minimum required
+    - Add new option --min-overlap to specify the minimum required
       overlap of intersecting regions
 
     - Allow to transfer ALT from VCF with or without replacement using
@@ -569,7 +665,7 @@ Changes affecting specific commands:
 * bcftools query
 
     - Make the `--samples` and `--samples-file` options work also in the `--list-samples`
-      mode. Add a new `--force-samples` option which allows to proceed even when some of
+      mode. Add a new `--force-samples` option which enables proceeding even when some of
       the requested samples are not present in the VCF (#1631)
 
 * bcftools +setGT
@@ -682,7 +778,7 @@ Changes affecting specific commands:
 
 * bcftools mpileup:
 
-    - new --indel-size option which allows to increase the maximum considered
+    - new --indel-size option which allows increase of the maximum considered
       indel size considered, large deletions in long read data are otherwise
       lost.
 
@@ -903,7 +999,7 @@ Changes affecting specific commands:
 
     - New `--rename-annots` option to help fix broken VCFs (#1335)
 
-    - New -C option allows to read a long list of options from a file to
+    - New -C option allows a long list of options to be read from a file to
       prevent very long command lines.
 
     - New `append-missing` logic allows annotations to be added for each ALT
@@ -1114,7 +1210,7 @@ Changes affecting specific commands:
 
     - Preserve the case of the genome reference. (#1150)
 
-    - Add new `-a, --absent` option which allows to set positions with no
+    - Add new `-a, --absent` option which allows setting positions with no
       supporting evidence to "N" (or any other character). (#848; #940)
 
 * bcftools convert:
@@ -1162,7 +1258,7 @@ Changes affecting specific commands:
     - Local alleles merging that produce LAA and LPL when requested, a draft
       implementation of https://github.com/samtools/hts-specs/pull/434 (#1138)
 
-    - New `--no-index` which allows to merge unindexed files. Requires the input
+    - New `--no-index` which allows unindexed files to be merged. Requires the input
       files to have chromosomes in th same order and consistent with the order
       of sequences in the header. (PR #1253; samtools/htslib#1089)
 

abuf.c

@@ -1,6 +1,6 @@
 /* The MIT License
 
-   Copyright (c) 2021-2023 Genome Research Ltd.
+   Copyright (c) 2021-2024 Genome Research Ltd.
 
    Author: Petr Danecek <[email protected]>
 
@@ -418,6 +418,14 @@ static void _split_table_set_history(abuf_t *buf)
 {
     int i,j,ret;
     bcf1_t *rec = buf->split.rec;
+
+    // Don't update if the tag already exists. This is to prevent -a from overwriting -m
+    int m = 0;
+    char *tmp = NULL;
+    ret = bcf_get_info_string(buf->hdr,rec,buf->split.info_tag,&tmp,&m);
+    free(tmp);
+    if ( ret>0 ) return;
+
     buf->tmps.l = 0;
     ksprintf(&buf->tmps,"%s|%"PRIhts_pos"|%s|",bcf_seqname(buf->hdr,rec),rec->pos+1,rec->d.allele[0]);
     for (i=1; i<rec->n_allele; i++)