### In this script, replace "ec-USERNAME" to your fox login username



####################################################################



# Login to FOX

$ ssh ec-USERNAME@fox.educloud.no



# In Fox, login to the interactive node

$ ssh int-1

# You can also use int-2, int-3 and int-4 instead of int-1



# Move to your home directory

$ cd 

$ pwd

# This should show something similar to /fp/homes01/u01/ec-USERNAME/



# Create a folder for the course

$ mkdir in-biosx000



# Create a folder for preprocessing within the above folder for this hands-on session

$ mkdir in-biosx000/preprocessing



# Move there

$ cd in-biosx000/preprocessing/

$ pwd

# This should show something similar to /fp/homes01/u01/ec-USERNAME/in-biosx000/preprocessing/



# Copy the data (files and folders) necessary for this session

$ rsync -rauPW /projects/ec34/in-biosx000/preprocessing/* .

$ ls

# This should list the following 8 files and 2 folders

## Arabidopsis_sample1.fq.gz

## Arabidopsis_sample2.fq.gz

## Arabidopsis_sample3.fq.gz

## Arabidopsis_sample4.fq.gz

## SalmoSalar_RNA_R1.fastq.gz

## SalmoSalar_RNA_R2.fastq.gz

## SRR2584863_250k_R1.fq.gz

## SRR2584863_250k_R2.fq.gz

## adapters/

## extra/



# Load relevant modules - FastQC, Trimmomatic, MultiQC and FASTX toolkit

$ module load FastQC/0.11.9-Java-11

$ module load Trimmomatic/0.39-Java-11

$ module load MultiQC/1.12-foss-2021b

$ module load FASTX-Toolkit/0.0.14-GCC-11.3.0



# QC on raw data

$ fastqc -t 8 *gz



# Create a folder and move FastQC outputs

$ mkdir raw_data_QC

$ mv *zip *html raw_data_QC/



# Move into the folder and run MultiQC

$ cd raw_data_QC

$ multiqc -m fastqc .



# Go one level up for trimmomatic session

$ cd ..

$ pwd

# This should show something similar to /fp/homes01/u01/ec-USERNAME/in-biosx000/preprocessing/



# Perform cleanup using trimmomatic (single end data)

$ java -jar $EBROOTTRIMMOMATIC/trimmomatic-0.39.jar SE -phred33 Arabidopsis_sample1.fq.gz Arabidopsis_sample1_clean.fq.gz ILLUMINACLIP:adapters/TruSeq3-SE.fa:2:30:10 LEADING:3 TRAILING:3 SLIDINGWINDOW:4:15 MINLEN:36

$ java -jar $EBROOTTRIMMOMATIC/trimmomatic-0.39.jar SE -phred33 Arabidopsis_sample2.fq.gz Arabidopsis_sample2_clean.fq.gz ILLUMINACLIP:adapters/TruSeq3-SE.fa:2:30:10 LEADING:3 TRAILING:3 SLIDINGWINDOW:4:15 MINLEN:36

$ java -jar $EBROOTTRIMMOMATIC/trimmomatic-0.39.jar SE -phred33 Arabidopsis_sample3.fq.gz Arabidopsis_sample3_clean.fq.gz ILLUMINACLIP:adapters/TruSeq3-SE.fa:2:30:10 LEADING:3 TRAILING:3 SLIDINGWINDOW:4:15 MINLEN:36

$ java -jar $EBROOTTRIMMOMATIC/trimmomatic-0.39.jar SE -phred33 Arabidopsis_sample4.fq.gz Arabidopsis_sample4_clean.fq.gz ILLUMINACLIP:adapters/TruSeq3-SE.fa:2:30:10 LEADING:3 TRAILING:3 SLIDINGWINDOW:4:15 MINLEN:36



# Perform cleanup using trimmomatic (paired end data)

$ java -jar $EBROOTTRIMMOMATIC/trimmomatic-0.39.jar PE -phred33 SRR2584863_250k_R1.fq.gz SRR2584863_250k_R2.fq.gz SRR2584863_250k_clean_R1.fq.gz SRR2584863_250k_unpair_R1.fq.gz SRR2584863_250k_clean_R2.fq.gz SRR2584863_250k_unpair_R2.fq.gz ILLUMINACLIP:adapters/TruSeq3-PE-2.fa:2:30:10 LEADING:3 TRAILING:3 SLIDINGWINDOW:4:15 MINLEN:36

$ java -jar $EBROOTTRIMMOMATIC/trimmomatic-0.39.jar PE -phred33 SalmoSalar_RNA_R1.fastq.gz SalmoSalar_RNA_R2.fastq.gz SalmoSalar_RNA_clean_R1.fq.gz SalmoSalar_RNA_unpair_R1.fq.gz SalmoSalar_RNA_clean_R2.fq.gz SalmoSalar_RNA_unpair_R2.fq.gz ILLUMINACLIP:adapters/TruSeq3-PE-2.fa:2:30:10 LEADING:3 TRAILING:3 SLIDINGWINDOW:4:15 MINLEN:36



# QC on clean data (we are ignoring the singleton "unpaired" files)

$ fastqc -t 8 *clean*



# Create a folder and move FastQC outputs

$ mkdir clean_data_QC

$ mv *zip *html clean_data_QC/



# Move into the folder and run MultiQC

$ cd clean_data_QC

$ multiqc -m fastqc .



####################################################################



# Try to use FASTX-toolkit (refer to your homepage on the internet) tools to manipulate and vislualise fastq files



####################################################################



## Transfer the two folders - raw_data_QC and clean_data_QC to your laptop to view the html files



# From your Laptop and NOT within FOX. You can use "scp -r" instead of "rsync -rauPW" to copy if you do not have rsync available on your laptop

$ rsync -rauPW ec-USERNAME@fox.educloud.no:/fp/homes01/u01/ec-USERNAME/in-biosx000/preprocessing/raw_data_QC .

$ rsync -rauPW ec-USERNAME@fox.educloud.no:/fp/homes01/u01/ec-USERNAME/in-biosx000/preprocessing/clean_data_QC .



# Explore the HTML files from FastQC output and HTML files from MultiQC output



####################################################################