# the project directory contains specific GROUP name and current DATE
GROUP=XXX
DATE=`date +"%Y%m%d"`
mkdir ~/Project/${GROUP}_${DATE}
2. Clone the repository
cd ~/Project/${GROUP}_${DATE}
git clone https://github.com/penglbio/Trinity
cd Trinity
3. Copy/Download the raw data
DATAPATH=/the/path/of/the/raw/data/on/HPC
# if you are working on the HPC, copy the raw data
./script/copy_rawdata.sh $DATAPATH
# if you are working on the local machine, download the raw data
./script/copy_rawdata.sh $DATAPATH --download
4. Rename the raw data
# dry run to check if mv command is correct
./script/rename_rawdata.sh --dry-run
# then do it
./script/rename_rawdata.sh
5. Create config.yaml and Snakefile based on the examples
# if you are working on the HPC
./run_HPC.sh
# if you are working on the local machine
./run.sh
# check the workflow progress in nohup.out file
tail nohup.log
# check the jobs on HPC
qstat
# to delete all the jobs at once
qselect -u <username> | xargs qdel
# if you get the error: Directory cannot be locked.
snakemake --unlock
9. Remove the temporary files
./clean.sh
10. Remove unwanted variation from Trinity RNA-Seq data
## remove batch effect using RUV
/cluster/home/xfu/R/3.5.1/bin/Rscript script/RUVSeq.R