feat: convert gtf to gene pred output (#477)

* Allow to convert output depending on param

* Added conversion check

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

* Fixed default conversion

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

bio/ucsc/gtfToGenePred/environment.yaml

@@ -3,4 +3,5 @@ channels:
   - conda-forge
   - defaults
 dependencies:
-  - ucsc-gtftogenepred ==377
+  - ucsc-gtftogenepred =377
+  - csvkit =1.0

bio/ucsc/gtfToGenePred/meta.yaml

@@ -1,9 +1,14 @@
 name: gtfToGenePred
 description: |
         Convert a GTF file to genePred format (see https://genome.ucsc.edu/FAQ/FAQformat.html#format9)
+url: https://hgdownload.cse.ucsc.edu/admin/exe/
 authors:
   - Brett Copeland
+  - Filipe G. Vieira
 input:
   - GTF file
 output:
   - genePred table
+notes: |
+  * The `extra` param allows for additional program arguments.
+  * The `convert_out` param allows to apply some conversions to the `refFlat` output. For example, if set to `PicardCollectRnaSeqMetrics` it makes it compatible with `Picard CollectRnaSeqMetrics` (this one also requires `extra` to be set to `-genePredExt -geneNameAsName2`).

bio/ucsc/gtfToGenePred/test/Snakefile

@@ -1,12 +1,27 @@
 rule gtfToGenePred:
     input:
         # annotations containing gene, transcript, exon, etc. data in GTF format
-        "annotation.gtf"
+        "annotation.gtf",
     output:
-        "annotation.genePred"
+        "annotation.genePred",
     log:
-        "logs/gtfToGenePred.log"
+        "logs/gtfToGenePred.log",
     params:
-        extra="-genePredExt" # optional parameters to pass to gtfToGenePred
+        extra="-genePredExt",  # optional parameters to pass to gtfToGenePred
+    wrapper:
+        "master/bio/ucsc/gtfToGenePred"
+
+
+rule gtfToGenePred_CollectRnaSeqMetrics:
+    input:
+        # annotations containing gene, transcript, exon, etc. data in GTF format
+        "annotation.gtf",
+    output:
+        "annotation.PicardCollectRnaSeqMetrics.genePred",
+    log:
+        "logs/gtfToGenePred.PicardCollectRnaSeqMetrics.log",
+    params:
+        convert_out="PicardCollectRnaSeqMetrics",
+        extra="-genePredExt -geneNameAsName2",  # optional parameters to pass to gtfToGenePred
     wrapper:
         "master/bio/ucsc/gtfToGenePred"

bio/ucsc/gtfToGenePred/wrapper.py

@@ -3,13 +3,26 @@
 __email__ = "brcopeland@ucsd.edu"
 __license__ = "MIT"
 
-
 import os
-
-
 from snakemake.shell import shell
 
+
 extra = snakemake.params.get("extra", "")
-log = snakemake.log_fmt_shell(stdout=True, stderr=True)
+convert_out = snakemake.params.get("convert_out", "raw")
+log = snakemake.log_fmt_shell(stdout=False, stderr=True)
+
+
+pipes = ""
+if convert_out == "raw":
+    pipes = ""
+elif convert_out == "PicardCollectRnaSeqMetrics":
+    pipes += " | csvcut -t -c 12,1-10 | csvformat -T"
+else:
+    raise ValueError(
+        f"Unsupported conversion mode {convert_out}. Please check wrapper documentation."
+    )
+
 
-shell("gtfToGenePred {extra} {snakemake.input} {snakemake.output} {log}")
+shell(
+    "(gtfToGenePred {extra} {snakemake.input} /dev/stdout {pipes} > {snakemake.output}) {log}"
+)

test.py

@@ -4211,7 +4211,15 @@ def test_collectrnaseqmetrics():
 def test_gtftogenepred():
     run(
         "bio/ucsc/gtfToGenePred",
-        ["snakemake", "--cores", "1", "--use-conda", "-F"],
+        ["snakemake", "--cores", "1", "annotation.genePred", "--use-conda", "-F"],
+    )
+
+
+@skip_if_not_modified
+def test_gtftogenepred_picard_collectrnaseqmetrics():
+    run(
+        "bio/ucsc/gtfToGenePred",
+        ["snakemake", "--cores", "1", "annotation.PicardCollectRnaSeqMetrics.genePred", "--use-conda", "-F"],
     )