Page Comparison

ssh user123@o2.hms.harvard.edu

# set up screen software: https://wiki.rc.hms.harvard.edu/pages/viewpage.action?pageId=20676715
cp /n/shared_db/misc/rcbio/data/screenrc.template.txt ~/.screenrc

screen

srun --pty -p interactive -t 0-12:0:0 --mem 16000MB -n 2 /bin/bash

mkdir /n/scratch3/users/${USER:0:1}/$USER/testGATK4
cd /n/scratch3/users/${USER:0:1}/$USER/testGATK4

module load gcc/6.2.0 python/2.7.12 java/jdk-1.8u112 star/2.5.4a

export PATH=/n/shared_db/singularity/hmsrc-gatk/bin:/home/ld32/rcbioDev/bin:/opt/singularity/bin:$PATH

# setup database. Only need run this once. It will setup database in home, so make sure you have at least 5G free space at home.
setupDB.sh

cp /n/shared_db/singularity/hmsrc-gatk/scripts/* .

buildSampleFoldersFromSampleSheet.py sampleSheet.xlsx

runAsPipeline fastqToBamGermline.sh "sbatch -p short --mem 4G -t 1:0:0 -n 1" noTmp run 2>&1 | tee output.log

# check email or use this command to see the workflow progress
squeue -u $USER -o "%.18i %.9P %.28j %.8u %.8T %.10M %.9l %.6D %R %S"

# After all jobs finish run, run this command to start database, and keep it running in background
runDB.sh &     

for json in unmappedBams/group*/*.json; do
	echo working on $json
    [ -f $json.done ] && continue
	java -XX:+UseSerialGC -Dconfig.file=your.conf -jar /n/shared_db/singularity/hmsrc-gatk/cromwell-43.jar run gatk4-rna-germline-variant-calling.wdl -i $json 2>&1 | tee -a $json.log && touch $json.done
done

# rerun the above command if anything does not work

# find all .vcf files and create sym links in final folder. If there are dulplicate files: 
mkdir finalVCFs
ln -s  $PWD/cromwell-executions/RNAseq/*/call-VariantFiltration/execution/*.variant_filtered.vcf.gz finalVCFs/ 2>/dev/null

#merge all CVFs to single VCF file
vcfFiles=`ls finalVCFs/*.variant_filtered.vcf.gz`
module load bcftools/1.9
bcftools merge -o final.vcf --force-samples $vcfFiles

# Stop database
killall runDB.sh