#!/usr/bin/env bash
# Bulk download script for GSE155726
# Generated from Yeo Lab Publications Database
# Total files: 11

OUTDIR="GSE155726"
mkdir -p "$OUTDIR"
cd "$OUTDIR"

# --- GEO supplementary files ---
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE155nnn/GSE155726/suppl/GSE155726_RAW.tar" -O "GSE155726_RAW.tar"

# --- SRA run files ---
# Tip: use 'fasterq-dump' from SRA Toolkit for FASTQ conversion
#      with optional renaming to original submitted FASTQ names.
# Set to 1 to rename SRR outputs (e.g. SRR_1.fastq.gz -> sample_R1.fastq.gz)
RENAME_SRA_TO_ORIGINAL=1

_compress_if_exists() {
  local stem="$1"
  if [ -f "${stem}.fastq" ]; then
    gzip -f "${stem}.fastq"
    echo "${stem}.fastq.gz"
    return 0
  fi
  if [ -f "${stem}.fq" ]; then
    gzip -f "${stem}.fq"
    echo "${stem}.fq.gz"
    return 0
  fi
  return 1
}

# Option A: Download via SRA Toolkit (recommended)
fasterq-dump --split-files "SRR12391497"
gz1="$(_compress_if_exists 'SRR12391497_1' || true)"
gz2="$(_compress_if_exists 'SRR12391497_2' || true)"
gzs="$(_compress_if_exists 'SRR12391497' || true)"

fasterq-dump --split-files "SRR12391498"
gz1="$(_compress_if_exists 'SRR12391498_1' || true)"
gz2="$(_compress_if_exists 'SRR12391498_2' || true)"
gzs="$(_compress_if_exists 'SRR12391498' || true)"

fasterq-dump --split-files "SRR12391499"
gz1="$(_compress_if_exists 'SRR12391499_1' || true)"
gz2="$(_compress_if_exists 'SRR12391499_2' || true)"
gzs="$(_compress_if_exists 'SRR12391499' || true)"

fasterq-dump --split-files "SRR12391500"
gz1="$(_compress_if_exists 'SRR12391500_1' || true)"
gz2="$(_compress_if_exists 'SRR12391500_2' || true)"
gzs="$(_compress_if_exists 'SRR12391500' || true)"

fasterq-dump --split-files "SRR12391501"
gz1="$(_compress_if_exists 'SRR12391501_1' || true)"
gz2="$(_compress_if_exists 'SRR12391501_2' || true)"
gzs="$(_compress_if_exists 'SRR12391501' || true)"


# Option B: Direct download (larger .sra files)
curl -L -O -C - "https://sra-pub-src-2.s3.amazonaws.com/SRR12391497/NPC_HEK_control_STAMP_possorted_genome_bam.bam.1"
curl -L -O -C - "https://sra-pub-src-2.s3.amazonaws.com/SRR12391498/NPC_HEK_RBFOX2_STAMP_possorted_genome_bam.bam.1"
curl -L -O -C - "https://sra-pub-src-2.s3.amazonaws.com/SRR12391499/RBP_STAMP_possorted_genome_bam.bam.1"
curl -L -O -C - "https://sra-pub-src-1.s3.amazonaws.com/SRR12391500/control_STAMP_possorted_genome_bam.bam.1"
curl -L -O -C - "https://sra-pub-src-1.s3.amazonaws.com/SRR12391501/RPS2_STAMP_possorted_genome_bam.bam.1"

# --- Additional data files ---
curl -L -O -C - "https://sra-pub-src-1.s3.amazonaws.com/SRR12391500/control_STAMP_possorted_genome_bam.bam.1"
curl -L -O -C - "https://sra-pub-src-2.s3.amazonaws.com/SRR12391497/NPC_HEK_control_STAMP_possorted_genome_bam.bam.1"
curl -L -O -C - "https://sra-pub-src-2.s3.amazonaws.com/SRR12391498/NPC_HEK_RBFOX2_STAMP_possorted_genome_bam.bam.1"
curl -L -O -C - "https://sra-pub-src-2.s3.amazonaws.com/SRR12391499/RBP_STAMP_possorted_genome_bam.bam.1"
curl -L -O -C - "https://sra-pub-src-1.s3.amazonaws.com/SRR12391501/RPS2_STAMP_possorted_genome_bam.bam.1"

echo "Download complete. Files saved to $OUTDIR"