feat: added wrapper for using tabix to query an indexed file (#203)

* added wrapper for using tabix to query an indexed file

* updated htslib version and added test

bio/tabix/query/environment.yaml

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

bio/tabix/query/meta.yaml

@@ -0,0 +1,11 @@
+name: tabix
+description: Query given file with tabix.
+url: https://github.com/samtools/htslib
+authors:
+  - William Rowell
+input:
+  - Bgzip compressed file (e.g. BED.gz, GFF.gz, or VCF.gz)
+  - Tabix index file
+  - Region of interest to retrieve (params.region)
+output:
+  - Uncompressed subset of the input file from the given region

bio/tabix/query/test/Snakefile

@@ -0,0 +1,14 @@
+rule tabix:
+    input:
+        "{prefix}.bed.gz",
+        "{prefix}.bed.gz.tbi"
+        ## list the VCF/BCF as the first input
+        ## and the index as the second input
+    output:
+        "{prefix}.output.bed"
+    params:
+        region = "1"
+    log:
+        "logs/tabix/query/{prefix}.log"
+    wrapper:
+        "master/bio/tabix/query"

bio/tabix/query/wrapper.py

@@ -0,0 +1,13 @@
+__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=False, stderr=True)
+
+shell(
+    "tabix {extra} {snakemake.input[0]} {snakemake.params.region} > {snakemake.output} {log}"
+)

test.py

@@ -3732,6 +3732,14 @@ def test_tabix():
     )
 
 
+@skip_if_not_modified
+def test_tabix_query():
+    run(
+        "bio/tabix/query",
+        ["snakemake", "--cores", "1", "--use-conda", "-F", "A.output.bed"],
+    )
+
+
 @skip_if_not_modified
 def test_msisensor_scan():
     run(