Add STAR wrapper.

bio/star/align/environment.yaml

@@ -0,0 +1,5 @@
+channels:
+  - bioconda
+  - r
+dependencies:
+  - star ==2.5.2b

bio/star/align/meta.yaml

@@ -0,0 +1,4 @@
+name: "star"
+description: Map reads with STAR.
+authors:
+  - Johannes Köster

bio/star/align/test/Snakefile

@@ -0,0 +1,16 @@
+rule star:
+    input:
+        sample=["reads/{sample}.1.fastq", "reads/{sample}.2.fastq"]
+    output:
+        # see STAR manual for additional output files
+        "star/{sample}/Aligned.out.bam"
+    log:
+        "logs/star/{sample}.log"
+    params:
+        # path to STAR reference genome index
+        index="index/",
+        # optional parameters
+        extra=""
+    threads: 8
+    wrapper:
+        "master/bio/star/align"

bio/star/align/test/genome.fasta

@@ -0,0 +1,2 @@
+>Sheila
+GCTAGCTCAGAAAAAAAAAA

bio/star/align/test/index/chrLength.txt

@@ -0,0 +1 @@
+20

bio/star/align/test/index/chrName.txt

@@ -0,0 +1 @@
+Sheila

bio/star/align/test/index/chrNameLength.txt

@@ -0,0 +1 @@
+Sheila	20

bio/star/align/test/index/chrStart.txt

@@ -0,0 +1,2 @@
+0
+262144

bio/star/align/test/index/genomeParameters.txt

@@ -0,0 +1,14 @@
+### STAR   --runMode genomeGenerate   --genomeDir index   --genomeFastaFiles genome.fasta   
+versionGenome	20201
+genomeFastaFiles	genome.fasta 
+genomeSAindexNbases	14
+genomeChrBinNbits	18
+genomeSAsparseD	1
+sjdbOverhang	0
+sjdbFileChrStartEnd	- 
+sjdbGTFfile	-
+sjdbGTFchrPrefix	-
+sjdbGTFfeatureExon	exon
+sjdbGTFtagExonParentTranscript	transcript_id
+sjdbGTFtagExonParentGene	gene_id
+sjdbInsertSave	Basic

bio/star/align/test/reads/a.1.fastq

@@ -0,0 +1,4 @@
+@1
+ACGGCAT
++
+!!!!!!!

bio/star/align/test/reads/a.2.fastq

@@ -0,0 +1,4 @@
+@1
+ACGGCAT
++
+!!!!!!!

bio/star/align/test_wrapper.py

@@ -0,0 +1,8 @@
+import subprocess
+import os
+
+def setup_module():
+    os.chdir(os.path.join(os.path.dirname(__file__), "test"))
+
+def test():
+    subprocess.check_call(["snakemake", "mapped/a/Aligned.out.bam", "--use-conda", "-F"])

bio/star/align/wrapper.py

@@ -0,0 +1,34 @@
+__author__ = "Johannes Köster"
+__copyright__ = "Copyright 2016, Johannes Köster"
+__email__ = "koester@jimmy.harvard.edu"
+__license__ = "MIT"
+
+
+import os
+from snakemake.shell import shell
+
+extra = snakemake.params.get("extra", "")
+log = snakemake.log_fmt_shell(stdout=True, stderr=True)
+
+n = len(snakemake.input.sample)
+assert n == 1 or n == 2, "input->sample must have 1 (single-end) or 2 (paired-end) elements."
+
+if snakemake.input.sample[0].endswith(".gz"):
+    readcmd = "--readFilesCommand zcat"
+else:
+    readcmd = ""
+
+
+outprefix = os.path.dirname(snakemake.output[0])
+
+
+shell(
+    "(STAR "
+    "{snakemake.params.extra} "
+    "--runThreadN {snakemake.threads} "
+    "--genomeDir {snakemake.params.index} "
+    "--readFilesIn {snakemake.input.sample} "
+    "{readcmd} "
+    "--outSAMtype BAM "
+    "--outFileNamePrefix {outprefix} "
+    "--outStd Log")