feat: added wrapper for bgzip (#195)

* added bgzip compression

* reformatted with snakefmt, added test case

* bgzip test case updated to look for test.vcf.gz

* bgzip works in place by default

* replaced test with minimal vcf from https://www.internationalgenome.org

* default behavior is to send output to stdout

* incremented to v1.12

bio/bgzip/environment.yaml

@@ -0,0 +1,5 @@
+channels:
+  - bioconda
+  - conda-forge
+dependencies:
+  - htslib ==1.12

bio/bgzip/meta.yaml

@@ -0,0 +1,9 @@
+name: bgzip
+description: Block compression/decompression utility
+url: https://github.com/samtools/htslib
+authors:
+  - William Rowell
+input:
+  - file to be compressed or decompressed
+output:
+  - compressed or decompressed output

bio/bgzip/test/Snakefile

@@ -0,0 +1,12 @@
+rule bgzip:
+    input:
+        "{prefix}.vcf",
+    output:
+        "{prefix}.vcf.gz",
+    params:
+        extra="", # optional
+    threads: 1
+    log:
+        "logs/bgzip/{prefix}.log",
+    wrapper:
+        "master/bio/bgzip"

bio/bgzip/test/test.vcf

@@ -0,0 +1,23 @@
+##fileformat=VCFv4.0
+##fileDate=20090805
+##source=https://www.internationalgenome.org/wiki/Analysis/vcf4.0/
+##reference=1000GenomesPilot-NCBI36
+##phasing=partial
+##INFO=<ID=NS,Number=1,Type=Integer,Description="Number of Samples With Data">
+##INFO=<ID=DP,Number=1,Type=Integer,Description="Total Depth">
+##INFO=<ID=AF,Number=.,Type=Float,Description="Allele Frequency">
+##INFO=<ID=AA,Number=1,Type=String,Description="Ancestral Allele">
+##INFO=<ID=DB,Number=0,Type=Flag,Description="dbSNP membership, build 129">
+##INFO=<ID=H2,Number=0,Type=Flag,Description="HapMap2 membership">
+##FILTER=<ID=q10,Description="Quality below 10">
+##FILTER=<ID=s50,Description="Less than 50% of samples have data">
+##FORMAT=<ID=GT,Number=1,Type=String,Description="Genotype">
+##FORMAT=<ID=GQ,Number=1,Type=Integer,Description="Genotype Quality">
+##FORMAT=<ID=DP,Number=1,Type=Integer,Description="Read Depth">
+##FORMAT=<ID=HQ,Number=2,Type=Integer,Description="Haplotype Quality">
+#CHROM POS     ID        REF ALT    QUAL FILTER INFO                              FORMAT      NA00001        NA00002        NA00003
+20     14370   rs6054257 G      A       29   PASS   NS=3;DP=14;AF=0.5;DB;H2           GT:GQ:DP:HQ 0|0:48:1:51,51 1|0:48:8:51,51 1/1:43:5:.,.
+20     17330   .         T      A       3    q10    NS=3;DP=11;AF=0.017               GT:GQ:DP:HQ 0|0:49:3:58,50 0|1:3:5:65,3   0/0:41:3
+20     1110696 rs6040355 A      G,T     67   PASS   NS=2;DP=10;AF=0.333,0.667;AA=T;DB GT:GQ:DP:HQ 1|2:21:6:23,27 2|1:2:0:18,2   2/2:35:4
+20     1230237 .         T      .       47   PASS   NS=3;DP=13;AA=T                   GT:GQ:DP:HQ 0|0:54:7:56,60 0|0:48:4:51,51 0/0:61:2
+20     1234567 microsat1 GTCT   G,GTACT 50   PASS   NS=3;DP=9;AA=G                    GT:GQ:DP    0/1:35:4       0/2:17:2       1/1:40:3

bio/bgzip/wrapper.py

@@ -0,0 +1,17 @@
+__author__ = "William Rowell"
+__copyright__ = "Copyright 2020, William Rowell"
+__email__ = "wrowell@pacb.com"
+__license__ = "MIT"
+
+
+from snakemake.shell import shell
+
+extra = snakemake.params.get("extra", "")
+log = snakemake.log_fmt_shell(stdout=True, stderr=True)
+
+shell(
+    """
+    (bgzip -c {extra} --threads {snakemake.threads} \
+        {snakemake.input} > {snakemake.output}) {log}
+    """
+)

test.py

@@ -919,6 +919,14 @@ def test_bedtools_slop():
     )
 
 
+@skip_if_not_modified
+def test_bgzip():
+    run(
+        "bio/bgzip",
+        ["snakemake", "--cores", "1", "test.vcf.gz", "--use-conda", "-F"]
+    )
+
+
 @skip_if_not_modified
 def test_blast_makeblastdb_nucleotide():
     run(