1_clean_trim_QC.txt

#warming_AK

#Adriana L. Romero-Olivares' protocol for processing RNAseq data of soil 
#Section 1
#File name: 1_clean_trim_QC
#Step: Cleaning-trimming of raw reads


#This protocol begins with raw reads from Illumina HiSeq-1TB, method: low input RNAseq with rRNA depletion using ribozero, 80-189 million reads (varies per sample)
#sequencing conducted at the JGI 
#raw reads format .gz downloaded from JGI platform to UCI cluster 


#unzip .gz files 

gunzip < file.gz > unzippedfile 

#fastQC of samples 

module load fastqc/0.11.2
fastqc sample 

#separate files into r1 and r2

paste - - - - < nameoffile.fq \
| tee >(awk 'BEGIN{FS="\t"; OFS="\n"} {if (match($1, " 1:N")) print $1,$2,$3,$4}' > file.r1.fq ) \
| awk 'BEGIN{FS="\t"; OFS="\n"} {if (match($1, " 2:N")) print $1,$2,$3,$4}' > file.r2.fq

#trim samples to remove adapters and delete low-quality sequences 

module load trimmomatic/0.35
java -jar /data/apps/trimmomatic/0.35/trimmomatic-0.35.jar PE file.r1.fq file.r2.fq file_trimmed.r1_paired.fq file_trimmed.r1_unpaired.fq file_trimmed.r2_paired.fq file_trimmed.r2_unpaired.fq ILLUMINACLIP:TruSeq3-PE.fa:2:30:10 LEADING:5 TRAILING:5 SLIDINGWINDOW:4:15 MINLEN:25

#fastQC of trimmed samples 
#make sure adapters were removed 
#for downstream analysis will use sample file_trimmed.r1_paired.fq and file_trimmed.r2_paired.fq

module load fastqc/0.11.2
fastqc file_trimmed.r1_paired.fq
fastqc file_trimmed.r2_paired.fq

#if adapters were removed and quality of samples is good, continue to downstream analyses