BUSCOv4.sh

#!/bin/bash

# This script will run BUSCO version 4.0.6 to assess genome assembly completeness

###############
###  SETUP  ###
###############

###  Conda  ###
echo "Setting up conda environment"
source /home/sejoslin/.bashrc
conda activate busco4
#export AUGUSTUS_CONFIG_PATH="/home/sejoslin/config/augustus-3.2.3/config"


###  Variables  ###
echo "Setting up variables"

THREADS=${SLURM_NTASKS}

# external variables
PREFIX=$1		# Prefix of all fastq files (and output)
ASSEMBLY=$2		# Assembly file
OUT_DIR=$3		# Path to outputt directory
LINEAGE=$4		# Lineage will to be downloaded and used (figure it out with `busco --list-datasets`

# internal variables
busco_dir="${OUT_DIR}/BUSCO"

echo "  Assembly : ${ASSEMBLY}"
echo "  Lineage File : ${LINEAGE}"
echo "  BUSCO Directory : ${busco_dir}"
echo "  Threads : ${THREADS}"
echo ""



###################
###  RUN BUSCO  ###
###################

mkdir -p ${busco_dir}
cd ${busco_dir}

BUSCO_call="busco -m genome \
    -i ${ASSEMBLY} \
    -l ${LINEAGE} \
    -o BUSCO_${PREFIX} \
    --out_path ${busco_dir} \
    -c $((THREADS - 1))"
echo ${BUSCO_call}
eval ${BUSCO_call}



## BUSCO README ##
cat << readme >> BUSCO_${PREFIX}/README.md
This directory contains output for the reports generated by $(busco --version) for the assembly of Hypomesus transpacificus.
Files & Directories:
    --run_lineage_name/         == Main results folder.
    --short_summary_*.txt   	== Contains a plain text summary of the results in BUSCO notation and give brief breakdown of metrics.
    --full_table_.tsvi  		== Contains the complete results in a tabular format with scores and lengths of BUSCO matches, and coordinates.
    --missing_buscos_list_*.tsv	== Contains a list of missing BUSCOs.
    --hmmer_output/	        	== Directory containing HMMER output of searches with BUSCO HMMs
    --blast_output/ 		    == tBLASTn results
    --logs/                     == Detailed busco.log with debug info and stderr & stdout of all 3rd party software
    --augustus_output		    == Augustus-predicted genes
    --predicted_genes           == Augustus raw gene output.
    --extracted_proteins        == Augustus protein FASTA output.
    --retraining_parameters     == BUSCO retraining. Specific to species.
    --gb                        == GenBank format complete BUSCOs before retraining.
    --gff                       == General Feature Format complete BUSCOs before retraining.
    --training_set.db           == Genes used for Augustus retraining.
    --blast_output/             == Results of the tBLASTn alignment tool, for the eukaryotic genome runs.
    --tblastn.tsv               == tabular tBLASTn results
    --coordinates.tsv           == locations of BUSCO matches (eukaryotic genome)
    --tblastn_missing_and_frag_rerun.tsv  == tabular tBLASTn results during the 2nd phase (eukaryotic genome)
    --coordinates_missing_and_frag_rerun.tsv  == locations of BUSCO matches during the 2nd phase (eukaryotic genome)
    --db/                       == Blast database
    --sequences                 == Sequences having blast results.
    --single_copy_busco_seq 	== FASTA format file for each complete single-copy BUSCO identified.
readme