SRR_fasta_download_trim_alignment

Usan_script.sh

#!/bin/bash

# 12th June 2020
# workshop by Usan Ong

# Environment settings
analysis_dir=${PWD}
trimmomatic=/Users/kevin/Downloads/Trimmomatic-0.39/trimmomatic-0.39.jar
hisat2=/Users/kevin/Downloads/hisat2-2.2.0/hisat2
#downloaded from hisat2 website
grch38_dir=/Users/kevin/Downloads/grch38


# Move to the directory
cd ${analysis_dir}

# Download fasta using parallel-fastq-dump
# https://github.com/rvalieris/parallel-fastq-dump
parallel-fastq-dump \
    --sra-id SRR7868778 SRR7868777 SRR7868776 SRR7868775 SRR7868774 SRR7868773 \
    --threads 4 \
    --outdir ./ \
    --split-files —gzip


# Unzip the downloaded fasta files
for gzip_file in *gz
do
    echo unziping ${gzip_file}
    gunzip ${gzip_file}
done


# QC here using FastQC


# Trim out adaptor sequences
for unzipped_file in *fastq
do
    echo trimming ${unzipped_file}
    trimmed_file_name="${unzipped_file%.*}_trimmed.fastaq"
    java -jar ${trimmomatic} \
        SE -phred33 \
        ${unzipped_file} \
        ${trimmed_file_name} \
        ILLUMINACLIP:TruSeq3-SE.fa:2:30:10 \
        LEADING:3 TRAILING:3 \
        SLIDINGWINDOW:4:15 \
        MINLEN:36

done


# Alignment
for trimmed_file in *_trimmed.fastaq
do
    echo aligning ${trimmed_file}
    sam_file="${trimmed_file%.*}.sam"

    # set python2 as the environment
    export PATH=/usr/bin:${PATH}

    # alignment
    ${hisat2} -x ${grch38_dir}/genome -U ${trimmed_file} -S ${sam_file}
done