diff options
| -rw-r--r-- | biology/Makefile | 1 | ||||
| -rw-r--r-- | biology/vcf-split/Makefile | 23 | ||||
| -rw-r--r-- | biology/vcf-split/distinfo | 3 | ||||
| -rw-r--r-- | biology/vcf-split/pkg-descr | 8 |
4 files changed, 35 insertions, 0 deletions
diff --git a/biology/Makefile b/biology/Makefile index 294c24aa9c6e..cba970a40784 100644 --- a/biology/Makefile +++ b/biology/Makefile @@ -179,6 +179,7 @@ SUBDIR += trimadap SUBDIR += trimmomatic SUBDIR += ugene + SUBDIR += vcf-split SUBDIR += vcflib SUBDIR += vcftools SUBDIR += velvet diff --git a/biology/vcf-split/Makefile b/biology/vcf-split/Makefile new file mode 100644 index 000000000000..16a46e71b4a0 --- /dev/null +++ b/biology/vcf-split/Makefile @@ -0,0 +1,23 @@ +# $FreeBSD$ + +PORTNAME= vcf-split +DISTVERSION= 0.1.1 +CATEGORIES= biology + +MAINTAINER= jwb@FreeBSD.org +COMMENT= Split a multi-sample VCF into single-sample VCFs + +LICENSE= BSD2CLAUSE +LICENSE_FILE= ${WRKSRC}/LICENSE + +BUILD_DEPENDS= biolibc>=0.1.1:biology/biolibc + +USE_GITHUB= yes +GH_ACCOUNT= auerlab + +PLIST_FILES= bin/vcf-split man/man1/vcf-split.1.gz + +pre-build: + (cd ${WRKSRC} && ${MAKE} LOCALBASE=${LOCALBASE} depend) + +.include <bsd.port.mk> diff --git a/biology/vcf-split/distinfo b/biology/vcf-split/distinfo new file mode 100644 index 000000000000..d72992f743f0 --- /dev/null +++ b/biology/vcf-split/distinfo @@ -0,0 +1,3 @@ +TIMESTAMP = 1616331493 +SHA256 (auerlab-vcf-split-0.1.1_GH0.tar.gz) = 07fb3aff5bf6038b251baa6c0cbff0600487766838b497468ab06d300488f310 +SIZE (auerlab-vcf-split-0.1.1_GH0.tar.gz) = 14226 diff --git a/biology/vcf-split/pkg-descr b/biology/vcf-split/pkg-descr new file mode 100644 index 000000000000..689705295fcb --- /dev/null +++ b/biology/vcf-split/pkg-descr @@ -0,0 +1,8 @@ +Vcf-split splits a multi-sample VCF into single-sample VCFs, writing thousands +of output files simultaneously. Parsing the TOPMed human chromosome 1 BCF +with bcftools takes two days, so extracting the 137,977 samples one at a time +or using thousands of parallel readers of the same file is impractical. +Vcf-split solves this by generating thousands of single-sample outputs during +a single sweep through the multi-sample input. + +WWW: https://github.com/auerlab/vcf-split |