fix: create tabix index sub-wrapper (#501)

* Created index sub-wrapper

* Fixed tests, paths, updated version, and added extra info

Co-authored-by: Johannes Köster <johannes.koester@uni-due.de>

bio/tabix/environment.yaml → bio/tabix/index/environment.yaml

@@ -3,4 +3,4 @@ channels:
   - bioconda
   - nodefaults
 dependencies:
-  - htslib ==1.10
+  - htslib =1.15

bio/tabix/index/meta.yaml

@@ -0,0 +1,11 @@
+name: tabix
+description: Process given file with tabix (e.g., create index).
+url: https://www.htslib.org/doc/tabix.html#INDEXING_OPTIONS
+authors:
+  - Johannes Köster
+input:
+  - Bgzip compressed file (e.g. BED.gz, GFF.gz, or VCF.gz)
+output:
+  - Tabix index file
+notes: |
+  * Specify tabix index params (e.g. `-p vcf`) through `params`.

bio/tabix/index/test/Snakefile

@@ -0,0 +1,12 @@
+rule tabix:
+    input:
+        "{prefix}.vcf.gz",
+    output:
+        "{prefix}.vcf.gz.tbi",
+    log:
+        "logs/tabix/{prefix}.log",
+    params:
+        # pass arguments to tabix (e.g. index a vcf)
+        "-p vcf",
+    wrapper:
+        "master/bio/tabix/index"

bio/tabix/query/environment.yaml

@@ -3,4 +3,4 @@ channels:
   - bioconda
   - nodefaults
 dependencies:
-  - htslib==1.12
+  - htslib =1.15

bio/tabix/query/meta.yaml

@@ -1,11 +1,13 @@
 name: tabix
 description: Query given file with tabix.
-url: https://github.com/samtools/htslib
+url: https://www.htslib.org/doc/tabix.html#QUERYING_AND_OTHER_OPTIONS
 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
+notes: |
+  * The `region` param (required) allows to specify region of interest to retrieve.
+  * The `extra` param allows for additional program arguments.

bio/tabix/query/test/Snakefile

@@ -1,14 +1,15 @@
 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
+        "{prefix}.bed.gz",
+        "{prefix}.bed.gz.tbi",
     output:
-        "{prefix}.output.bed"
-    params:
-        region = "1"
+        "{prefix}.output.bed",
     log:
-        "logs/tabix/query/{prefix}.log"
+        "logs/tabix/query/{prefix}.log",
+    params:
+        region="1",
+        extra="",
     wrapper:
         "master/bio/tabix/query"

test.py

@@ -3924,9 +3924,9 @@ def test_bismark_bismark2bedgraph():
 
 
 @skip_if_not_modified
-def test_tabix():
+def test_tabix_index():
     run(
-        "bio/tabix",
+        "bio/tabix/index",
         ["snakemake", "--cores", "1", "--use-conda", "-F", "test.vcf.gz.tbi"],
     )