autocycler.sh

autocycler.sh

# Create and activate a conda environment with the required tools
# mamba create -n autocycler -c bioconda autocycler flye raven-assembler miniasm any2fasta minipolish
# mamba activate autocycler

# Set some environment variables
threads="8"
genome_size="242000"

# Subsample reads
autocycler subsample --reads reads.fastq.gz --out_dir subsampled_reads --genome_size "$genome_size"

# Run a few assemblers. You'll need the helper scripts from the autocycler repository.
# flye: 4m15
# miniasm: 2m45
# raven: 42s
# total: 7m43s
mkdir -p assemblies
time for assembler in flye miniasm raven; do
    echo "Running $assembler"
    time for i in 01 02 03 04; do
        "./$assembler".sh subsampled_reads/sample_"$i".fastq assemblies/"$assembler"_"$i" "$threads" "$genome_size"
    done
    echo "Done running $assembler"
done

# Build a compacted De Bruijn graph
autocycler compress -i assemblies -a autocycler_out

# Group contigs into clusters
autocycler cluster -a autocycler_out

# Trim excess sequence and resolve ambiguities
for c in autocycler_out/clustering/qc_pass/cluster_*; do
    autocycler trim -c "$c"
    autocycler resolve -c "$c"
done

# Combine resolved sequences for each cluster into a single assembly
autocycler combine -a autocycler_out -i autocycler_out/clustering/qc_pass/cluster_*/5_final.gfa