In yangjl/huskeR: Genomic and Genetic analysis Pipeline on HPC

knitr::opts_knit$set(root.dir=normalizePath('../'))
knitr::opts_knit$set(warnings = TRUE, include=TRUE, echo=TRUE)
library("huskeR")

Test run_GATK

#?run_GATK

inputdf <- data.frame(fq1="fq_1.fq", fq2="f1_2.fq", out="mysample",
                 group="g1", sample="s1", PL="illumina", LB="lib1", PU="unit1")

run_GATK(inputdf, runbwa=TRUE, markDup=TRUE, addRG=FALSE,rungatk=TRUE,
         ref.fa="~/dbcenter/Ecoli/reference/Ecoli_k12_MG1655.fasta",
         gatkpwd="$HOME/bin/GenomeAnalysisTK-3.5/GenomeAnalysisTK.jar",
         picardpwd="$HOME/bin/picard-tools-2.1.1/picard.jar",
         minscore=5,
         realignInDels=FALSE, indels.vcf="indels.vcf",
         recalBases=FALSE, dbsnp.vcf="dbsnp.vcf",
         shbase="slurm-script/run_test_", jobid="runarray",
         email=NULL, runinfo = c(FALSE, "batch", 1, 1.5, "10:00:00"))

Add a new chunk by clicking the Insert Chunk button on the toolbar or by pressing Cmd+Option+I.

When you save the notebook, an HTML file containing the code and output will be saved alongside it (click the Preview button or press Cmd+Shift+K to preview the HTML file).

Test run_GBSv2

library("huskeR")
run_GBSv2(outdir = "largedata/gbs", shfile="slurm-script/gbs.sh", fqdir="fq.gz", keyfile="myket.txt", 
          bt2_idx="mz.idx", sam="output.sam", ref="mz.ref.fa", snpqc_file="gbs/qc.txt",
          db = "gbs.db", mem=50, cpu=50, kmerlen = 64, enzyme= "ApeKI", 
          production=FALSE, seq2tag = TRUE, tag2fq = TRUE, bt2 = TRUE, snpcall = TRUE)

set_slurm_job(slurmsh = "slurm-script/run_gbs.sh",
  shcode = "sh slurm-script/gbs.sh", wd = NULL, jobid = "gbsjob",
  email = "yangjl0930@gmail.com", runinfo = c(TRUE, "jclarke", "50", "100G", "8:00:00"))


#####
run_GBSv2(outdir = "largedata/gbs", shfile="slurm-script/gbs_prod.sh", fqdir="fq.gz", keyfile="myket.txt", 
          bt2_idx="mz.idx", sam="output.sam", ref="mz.ref.fa", snpqc_file="gbs/qc.txt", h5="out.h5",
          db = NULL, mem=50, cpu=50, kmerlen = 64, enzyme= "ApeKI", 
          production=TRUE, seq2tag = TRUE, tag2fq = TRUE, bt2 = TRUE, snpcall = TRUE)

set_slurm_job(slurmsh = "slurm-script/run_gbs.sh",
  shcode = "sh slurm-script/gbs.sh", wd = NULL, jobid = "gbsjob",
  email = "yangjl0930@gmail.com", runinfo = c(F, "jclarke", "50", "100G", "8:00:00"))