菌株基因组信息下载

#!/bin/bash#SBATCH -J download_ncbi_genomes#SBATCH -p common#SBATCH -N 1#SBATCH -c 2#SBATCH --mem=5G#SBATCH -t 4:00:00#SBATCH -o /xxx/xxxx/xxx/genes/log/download.%j.out#SBATCH -e /xxx/xxxx/xxx/genes/log/download.%j.errset -uo pipefail# 基础目录BASE_DIR="/xxx/xxxx/xxx/genes"LOG_DIR="$BASE_DIR/log"OUT_DIR="$BASE_DIR/single_downloads"ACC_FILE="$BASE_DIR/accessions.txt"FAILED_FILE="$BASE_DIR/failed_accessions.txt"# datasets 工具路径DATASETS="/xxx/xxxx/xxx/conda/envs/ncbi/bin/datasets"# 自动创建目录mkdir -p "$BASE_DIR" "$LOG_DIR" "$OUT_DIR"# 自动写入 accession 列表（*需要下载多少个，将“身份证号”进行对应替换*）cat > "$ACC_FILE" << 'EOF'GCA_xxxxxxxxx.1GCA_xxxxxxxxx.2 GCA_xxxxxxxxx.3GCA_xxxxxxxxx.4 GCA_xxxxxxxxx.5GCA_xxxxxxxxx.6GCA_xxxxxxxxx.7GCA_xxxxxxxxx.8  #微生物基因组的身份证信息EOF# 清空失败记录: > "$FAILED_FILE"# 检查 datasets 是否存在if [[ ! -x "$DATASETS" ]]; then    echo "Error: datasets not found or not executable: $DATASETS" >&2    exit 1fiecho "=== datasets path ==="echo "$DATASETS"echo "=== datasets version ===""$DATASETS" versioncd "$OUT_DIR"echo "=== 开始逐个下载基因组 ==="datesuccess_count=0fail_count=0while read -r acc; do    [[ -z "$acc" ]] && continue    echo "=== downloading $acc ==="    rm -f "${acc}.zip"    if "$DATASETS" download genome accession "$acc" \        --include genome,gff3,protein \        --filename "${acc}.zip"; then        echo "=== finished $acc ==="        success_count=$((success_count + 1))    else        echo "=== failed $acc ===" >&2        echo "$acc" >> "$FAILED_FILE"        rm -f "${acc}.zip"        fail_count=$((fail_count + 1))    fidone < "$ACC_FILE"echo "=== 下载结束 ==="echo "success: $success_count"echo "failed : $fail_count"echo "failed list:"cat "$FAILED_FILE" || truedate