R script options

Setup jobs

setup_jobs.R -h
#  Usage: /home/BioApps/hciR/setup_jobs.R [options]
#  
#  Creates a cmd.txt file and sample directories with Fastq file links in order to run STAR,
#  featureCounts and quality metrics on the CHPC clusters using pysano.  The default is to align
#  to single-end 50 bp reads the human reference.
#  
#  Options:
#   -e EMAIL, --email=EMAIL
#       #e email or hci user name for pysano directive, required
#  
#   -c CLUSTER, --cluster=CLUSTER
#       #c cluster name for pysano with at least 64 GB of RAM, default kingspeak
#  
#   -s SEQUENCING, --sequencing=SEQUENCING
#       single, paired, novaseq, qiagen, NEB or metagenome
#  
#   -i INPUT, --input=INPUT
#       Input directory with Fastq files (either absolute path or relative path in current directory)
#  
#   -f FASTQ, --fastq=FASTQ
#       Match fastq files ending in default .gz
#  
#   -m MODIFIED, --modified=MODIFIED
#       Only link fastq files with modified time >= YYYY-MM-DD
#  
#   -r RUN, --run=RUN
#       Run ID in /Repository/MicroarryData, optional
#  
#   -a ANALYSIS, --analysis=ANALYSIS
#       Save files to /Repository/AnalysisData, optional
#  
#   -v VERSION, --version=VERSION
#       Ensembl release, default 96, only 90, 92, 94 and 96 available
#  
#   -d DATABASE, --database=DATABASE
#       Reference database, default human or mouse, elephant, fly, worm, pig,
#       rat, rabbit, sheep, yeast, zebrafish
#  
#   -l LENGTH, --length=LENGTH
#       Read length for STAR reference, default 50 or 125
#  
#   -h, --help
#       Show this help message and exit

Add README

add_readme.R -h
#  Usage: /home/BioApps/hciR/add_readme.R [options]
#  
#  Creates a README.Rmd file for single, paired or miRNA sequencing workflows at HCI using defaults
#  in the cmd.txt files from setup_jobs.R.  Run 'render.R -f README.Rmd' to create the html report.
#  
#  
#  Options:
#   -s SEQUENCING, --sequencing=SEQUENCING
#       single, paired or miRNA sequencing
#  
#   -r RUN, --run=RUN
#       Run ID for report title
#  
#   -i ID, --id=ID
#       Sample ID prefix, will use run ID with X1 ending if missing
#  
#   -f FASTQ, --fastq=FASTQ
#       Sample fastq file name, will check /Repository/MicroarrayData with run ID if missing
#  
#   -d DATABASE, --database=DATABASE
#       Reference database, default human or mouse, elephant, fly, worm, pig,
#       rat, rabbit, sheep, vervet, yeast, zebrafish
#  
#   -v VERSION, --version=VERSION
#       Ensembl release, default 96
#  
#   -n NCPU, --ncpu=NCPU
#       Number CPUs, pysano will use the maximum number, default 24
#  
#   -a ALIGN, --align=ALIGN
#       Directory name with cmd.txt output, default Alignments
#  
#   -l LENGTH, --length=LENGTH
#       Read length, default 50
#  
#   -h, --help
#       Show this help message and exit

Combine featureCounts

read_featureCounts.R -h
#  Usage: /home/BioApps/hciR/read_featureCounts.R [options]
#  
#  Combine featureCount output files into a single count matix
#  
#  Options:
#   -d DIRECTORY, --directory=DIRECTORY
#       Directory with featuerCounts output files
#  
#   -p PATTERN, --pattern=PATTERN
#       Pattern for matching output files
#  
#   -o OUTPUT, --output=OUTPUT
#       Output file name, default counts.txt
#  
#   -h, --help
#       Show this help message and exit

Run DESeq2

add_deseq.R -h
#  Usage: /home/BioApps/hciR/add_deseq.R [options]
#  
#  Create a DESeq markdown file with commands to run DESeq2
#  
#  
#  Options:
#   -r RUN, --run=RUN
#       Run ID for report title
#  
#   -d DATABASE, --database=DATABASE
#       Annotation database, default human or mouse, elephant, fly, pig,
#       rat, rabbit, sheep,  worm, vervet, yeast or zebrafish
#  
#   -v VERSION, --version=VERSION
#       Ensembl release, default 96
#  
#   -s SAMPLES, --samples=SAMPLES
#       Tab-delimited file with ids in column 1 matching count column names
#       and a treatment column for contrasts, default samples.txt
#  
#   -t TRT, --trt=TRT
#       Name of treatment column in sample table, default trt.
#  
#   -c COUNTS, --counts=COUNTS
#       Tab-delimited count matrix file, default counts.txt
#  
#   -f FILTER, --filter=FILTER
#       Low count cutoff to filter counts, default 5
#  
#   -p PADJ, --padj=PADJ
#       Adjusted p-value cutoff, default 0.05
#  
#   -x VS, --vs=VS
#       Compare groups to a specific treatment, default is all vs. all
#  
#   -l LEVELS, --levels=LEVELS
#       A comma-separated list to reorder treatments.  By default treatments are sorted
#       alphabetically, so use 'C,B,A' to compare C vs A, C vs B and B vs A
#  
#   -m MOUSEOVER, --mouseover=MOUSEOVER
#       A comma-separated list of sample column names for tooltips in PCA plot, default is id column
#  
#   -h, --help
#       Show this help message and exit

Render HTML reports

render.R -h
#  Usage: /home/BioApps/hciR/render.R [options]
#  
#  Render an R markdown file
#  
#  
#  Options:
#   -f FILE, --file=FILE
#       R markdown file to render
#  
#   -h, --help
#       Show this help message and exit