run_bactopia

#!/usr/bin/env bash
#Pipeline for running and organizing output from Bactopia

#Install Bactopia if not already installed:
##git clone https://github.com/bactopia/bactopia.git
##conda create -n bactopia -c conda-forge -c bioconda bactopia
##bactopia datasets
#Make sure Docker is installed; if you don't have Docker, you can still run Bactopia, but you will need to edit this script

#Within the Bactopia directory, there should be a directory called "reads" (make it if it is not already there)
#Download your fastq files into the "reads" directory

#If there is an error, check the following:
##Sample names must end in R1.fastq.gz or R2.fastq.gz or else the samplesheet will not be created properly; this script should prepare the reads files into this format, but if it doesn't, this may have to be done manually
##The reads files must be in the format .fastq.gz 
##This script is for running Illumina paired-end reads; modifications will need to be made for long-read or hybrid assembly
##Make sure all paths are correct 

#Before running this script, activate your Bactopia Conda environment: conda activate bactopia

#Paths
home=/home/mdungsmain/Janis/Programs/bactopia/
reads=/home/mdungsmain/Janis/Programs/bactopia/reads/
datasets=/home/mdungsmain/.bactopia/datasets/

#Navigate to the reads directory
cd ${reads}

#Move all the fastq files out of their sub-directories
find . -mindepth 2 -type f -exec mv {} . \;

#Delete any file in /reads that doesn't end with ".fastq.gz"
for filename in *; do
	if [[ ${filename} != *.fastq.gz ]]; then
		rm -r ${filename}
	fi
done

#Rename the fastq files so they end with R1.fastq.gz or R2.fastq.gz
for file in *; do
	if [[ "$file" == *R1* ]]; then
		new_name="${file%%R1*}R1.fastq.gz"
		mv "$file" "$new_name"
	fi
done

for file in *; do
	if [[ "$file" == *R2* ]]; then
		new_name="${file%%R2*}R2.fastq.gz"
		mv "$file" "$new_name"
	fi
done

#Navigate back to /bactopia
cd ${home}

#Make the sample sheet
bactopia prepare -p ${reads} > fastqs.txt

#Run Bactopia
bactopia -profile docker --datasets ${datasets} --samples ./fastqs.txt --outdir ./results