# this file holds the commands that are run during the RNASeq Workshop
# they can be copy-pasted into an MSI terminal accessed through Open OnDemand
# any line starting with # is a command, the rest of the lines are commands
# NOTE: some commands are multi-line (end in \), copy all lines for these commands
# NOTE2: some commands must be changed to match your file names, these are described

# change directories to tutorial's fastq directory
cd /common/tutorials/bioinformatics/bulk_rnaseq/Reads/

# print the working directory (should match above)
pwd

# list the contents of the directory (should show 16 .fastq.gz files)
ls

# decompress then examine the top 8 lines of one fastq
zcat BoneMarrow-1_S23_R1_001.fastq.gz | head -n 8

# repeat with its partner fastq
zcat BoneMarrow-1_S23_R2_001.fastq.gz | head -n 8

# check the number of lines in the first fastq
zcat BoneMarrow-1_S23_R1_001.fastq.gz | wc -l

# repeat with its partner fastq
zcat BoneMarrow-1_S23_R2_001.fastq.gz | wc -l

# examine our username variable
echo $USER

# switch to your scratch directory
cd /scratch.global/$USER

# if the previous command didn't work, try this first
mkdir /scratch.global/$USER

# see what versions of churp are installed
module avail churp

# load the latest version of churp
module load churp/1.1.0

# run the basic churp command
$CHURP

# see the help for churp's rnaseq pipeline
$CHURP bulk_rnaseq --help

# change dirs to Mus musculus' bioref database
cd /common/bioref/ensembl/main/Mus_musculus-113/GRCm39/

# see what is in the directory
ls

# examine the raw fasta sequence
cd seq
ls
head -n 2 genome.fa

# examine the location of the hisat2 index
cd ..
cd hisat2
ls

# examine the gtf annotation
cd ..
cd annotation
ls
head Mus_musculus.GRCm39.113.gtf

# examine genome aliases given in churp
$CHURP genome_aliases

# return to your scratch directory and make a churp output directory, then enter it
cd /scratch.global/$USER
mkdir RNAseq_Tutorial 
cd RNAseq_Tutorial

# examine the help for churp's group_template
$CHURP group_template bulk_rnaseq --help

# generate a group template for this tutorial (make sure to copy all 3 lines)
$CHURP group_template bulk_rnaseq \
  --fq-folder /common/tutorials/bioinformatics/bulk_rnaseq/Reads/ \
  --output /scratch.global/$USER/RNAseq_Tutorial/tutorial_rnaseq_groups.xlsx
  
# create churp pipeline files but dont submit (copy all lines)
$CHURP bulk_rnaseq \
  --fq-folder /common/tutorials/bioinformatics/bulk_rnaseq/Reads/ \
  --organism mouse \
  --expr-groups /scratch.global/$USER/RNAseq_Tutorial/tutorial_rnaseq_groups.xlsx \
  --output-dir /scratch.global/$USER/RNAseq_Tutorial/Out \
  --working-dir /scratch.global/$USER/RNAseq_Tutorial/Work \
  --strand U \
  --queue msismall \
  --ppn 8 --mem 24000 --walltime 2 \
  --no-submit
  
# ALTERNATE: if you cannot currently adjust the excel file and re-upload
$CHURP bulk_rnaseq \
  --fq-folder /common/tutorials/bioinformatics/bulk_rnaseq/Reads/ \
  --organism mouse \
  --expr-groups /common/tutorials/bioinformatics/bulk_rnaseq/tutorial_rnaseq_groups.xlsx \
  --output-dir /scratch.global/$USER/RNAseq_Tutorial/Out \
  --working-dir /scratch.global/$USER/RNAseq_Tutorial/Work \
  --strand U \
  --queue msismall \
  --ppn 8 --mem 24000 --walltime 2 \
  --no-submit
  
# navigate to the Out dir and check the samplesheet
# IMPORTANT : THE THIRD COMMAND CAN'T BE COPY PASTED BECAUSE IT IS DATE DEPENDENT
cd Out
ls
head -n 2 2024-10-25.chaco001.bulk_rnaseq.samplesheet.txt

# check the # of lines in the sample sheet (REPLACE THE FILE WITH YOURS)
wc -l 2024-10-25.chaco001.bulk_rnaseq.samplesheet.txt

# submit churp (REPLACE THE FILE WITH YOURS)
bash 2024-10-30.chaco001.bulk_rnaseq.pipeline.sh 

# check your job status
squeue -u $USER

# examine the output files (when CHURP is done)
cd /scratch.global/$USER/RNAseq_Tutorial/Out
ls

# examine a bam file with samtools
cd Coordinate_Sorted_BAMs
ls
module load samtools/1.16.1-gcc-8.2.0-egljrr3 
samtools view BoneMarrow-1_MAPQFiltered_CoordSort.bam | head -3