pipeline

#!/bin/bash

# Install required tools (This section is commented out since installation commands vary by system)
# echo "Installing required tools..."
# sudo apt-get update
# sudo apt-get install -y sra-toolkit trimmomatic fastqc star subread

# Create directories and navigate to the samples directory
echo "Creating and navigating to samples directory..."
mkdir -p ~/samples
cd ~/samples

# Prefetch the data
echo "Prefetching data..."
prefetch SRR8986990

# Navigate to the data directory
cd SRR8986990

# Change permissions for the downloaded files
chmod 777 SRR8986990.sra

# Convert SRA to FASTQ
echo "Converting SRA to FASTQ..."
fastq-dump --split-3 SRR8986990.sra

# Navigate back to the samples directory
cd ..

# Run FastQC on the FASTQ files
echo "Running FastQC..."
fastqc SRR8986990_1.fastq SRR8986990_2.fastq

# Trimming using Trimmomatic
echo "Trimming reads with Trimmomatic..."
java -jar ~/trimmomatic-0.39.jar PE \
  SRR8986990_1.fastq SRR8986990_2.fastq \
  SRR8986990_1_trimmed_paired.fastq SRR8986990_1_trimmed_unpaired.fastq \
  SRR8986990_2_trimmed_paired.fastq SRR8986990_2_trimmed_unpaired.fastq \
  TRAILING:2 SLIDINGWINDOW:4:15 MINLEN:36

# Copy reference genome and GTF files to the index directory
echo "Copying reference files..."
mkdir -p ~/samples/index
cp /mnt/c/Users/achir/Downloads/Ecoli.fasta ~/samples/index/
cp /mnt/c/Users/achir/Downloads/genomic_2.gtf ~/samples/index/

# Run STAR for mapping
echo "Mapping reads with STAR..."
STAR --runThreadN 8 \
  --readFilesIn SRR8986990_1_trimmed_paired.fastq SRR8986990_2_trimmed_paired.fastq \
  --genomeDir ~/samples/index \
  --outSAMtype BAM SortedByCoordinate \
  --outFileNamePrefix ~/samples/mapping

# Set up Conda environment for featureCounts
echo "Setting up Conda environment..."
mkdir -p ~/miniconda3
bash ~/miniconda3/miniconda.sh -b -u -p ~/miniconda3
rm -rf ~/miniconda3/miniconda.sh
~/miniconda3/bin/conda init bash
source ~/.bashrc

echo "Creating and activating Conda environment..."
conda create -n bioinfo python=3.8 -y
conda activate bioinfo
conda install -c bioconda subread -y

# Run featureCounts
echo "Running featureCounts..."
featureCounts -a ~/samples/index/genomic_2.gtf -o ~/samples/counts_file.txt ~/samples/mappingAligned.sortedByCoord.out.bam

# Deactivate Conda environment
echo "Deactivating Conda environment..."
conda deactivate

# Print the head of the counts file
echo "Output of the counts file:"
head ~/samples/counts_file.txt

echo "Pipeline completed."