Eric Coissac
26026288de
Restructure the benchmark pipeline to direct all simulated data, indices, statistics, and query outputs into a unified `run/` directory. Update Makefile targets, shell scripts, and Python utilities to resolve paths relative to this new base. Adjust documentation and dependency tracking to match the revised layout, and remove outdated temporary artifacts.
52 lines
989 B
Bash
Executable File
52 lines
989 B
Bash
Executable File
#!/usr/bin/env bash
|
|
|
|
set -euo pipefail
|
|
|
|
assemblies=(
|
|
GCF_000005845.2
|
|
GCF_000010245.2
|
|
GCF_000007445.1
|
|
GCF_000006665.1
|
|
|
|
GCF_000006945.2
|
|
GCF_000195995.1
|
|
GCF_000009505.1
|
|
GCF_000026565.1
|
|
|
|
GCF_000016305.1
|
|
GCF_000019965.1
|
|
GCF_000240185.1
|
|
GCF_000742135.1
|
|
|
|
GCF_000069965.1
|
|
GCF_000022565.1
|
|
GCF_000306885.1
|
|
GCF_003013715.1
|
|
|
|
GCF_000009045.1
|
|
GCF_000009825.1
|
|
GCF_000022445.1
|
|
GCF_000834255.1
|
|
)
|
|
|
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
|
GENOMES_DIR="${SCRIPT_DIR}/run/genomes"
|
|
|
|
mkdir -p "${GENOMES_DIR}"
|
|
|
|
for acc in "${assemblies[@]}"; do
|
|
echo "Downloading ${acc}"
|
|
|
|
datasets download genome accession "${acc}" \
|
|
--include genome \
|
|
--filename "${acc}.zip"
|
|
|
|
unzip -q "${acc}.zip" -d "${acc}"
|
|
find "${acc}" -name "*.fna" |
|
|
while read file; do
|
|
obiconvert -Z ${file} >"${GENOMES_DIR}/$(basename ${file}).gz"
|
|
done
|
|
|
|
rm -rf "${acc}" "${acc}.zip"
|
|
done
|