feat: added ref as an optional input file (#473)

* Added reference as an optional input

* Added ref to example Snakefile

bio/picard/collectrnaseqmetrics/meta.yaml

@@ -1,15 +1,17 @@
 name: picard CollectRnaSeqMetrics
 description: |
         Run picard CollectRnaSeqMetrics to generate QC metrics for RNA-seq data.
+url: https://broadinstitute.github.io/picard/command-line-overview.html#CollectRnaSeqMetrics
 authors:
   - Brett Copeland
+  - Filipe G. Vieira
 input:
   - BAM file of RNA-seq data aligned to genome
   - REF_FLAT formatted file of transcriptome annotations
+  - reference FASTA (optional)
 output:
   - RNA-Seq metrics text file
 notes: |
   * The `java_opts` param allows for additional arguments to be passed to the java compiler, e.g. "-XX:ParallelGCThreads=10" (not for `-XmX` or `-Djava.io.tmpdir`, since they are handled automatically).
   * The `extra` param allows for additional program arguments.
   * `--TMP_DIR` is automatically set by `resources.tmpdir`
-  * For more information, see https://broadinstitute.github.io/picard/command-line-overview.html#CollectRnaSeqMetrics

bio/picard/collectrnaseqmetrics/test/Snakefile

@@ -2,6 +2,8 @@ rule alignment_summary:
     input:
         # BAM aligned, splicing-aware, to reference genome
         bam="mapped/a.bam",
+	# Reference genome
+        #ref="ref.fasta",
         # Annotation file containing transcript, gene, and exon data
         refflat="annotation.refFlat",
     output:
@@ -14,10 +16,6 @@ rule alignment_summary:
         extra="--VALIDATION_STRINGENCY STRICT",
     log:
         "logs/picard/rnaseq-metrics/a.log",
-    # optional specification of memory usage of the JVM that snakemake will respect with global
-    # resource restrictions (https://snakemake.readthedocs.io/en/latest/snakefiles/rules.html#resources)
-    # and which can be used to request RAM during cluster job submission as `{resources.mem_mb}`:
-    # https://snakemake.readthedocs.io/en/latest/executing/cluster.html#job-properties
     resources:
         mem_mb=1024,
     wrapper:

bio/picard/collectrnaseqmetrics/wrapper.py

@@ -15,14 +15,20 @@
 java_opts = get_java_opts(snakemake)
 
 
+ref = snakemake.input.get("ref", "")
+if ref:
+    ref = f"--REFERENCE_SEQUENCE {ref}"
+
+
 with tempfile.TemporaryDirectory() as tmpdir:
     shell(
         "picard CollectRnaSeqMetrics"
         " {java_opts} {extra}"
         " --INPUT {snakemake.input.bam}"
-        " --TMP_DIR {tmpdir}"
-        " --OUTPUT {snakemake.output}"
+        " {ref}"
         " --REF_FLAT {snakemake.input.refflat}"
         " --STRAND_SPECIFICITY {strand}"
+        " --TMP_DIR {tmpdir}"
+        " --OUTPUT {snakemake.output}"
         " {log}"
     )