环境还是m6a的
conda activate m6a
cd /home/data/t210424/ac4c
call了peak结果不是很理想暂时没管
IGV图是用bam转bw，归一化方法都是RPGC（Reads Per Genomic Content）
RPGC 会将 bigWig 信号归一化为每百万 reads / 每个碱基覆盖的基因组大小
公式类似于：
RPGC=每个位点覆盖的 reads 数×106总 reads 数×基因组长度 (bp)\text{RPGC} = \frac{\text{每个位点覆盖的 reads 数} \times 10^6}{\text{总 reads 数} \times \text{基因组长度 (bp)}}RPGC=总 reads 数×基因组长度 (bp)每个位点覆盖的 reads 数×106
这样可以消除测序深度和基因组大小差异的影响
IP组用的脚本是bam2bw.sh
#!/bin/bash
# ================================================
# acRIP-seq BAM → bigWig 完整 pipeline
# 生成：
# 1. 单样本 RPGC-normalized bigWig
# 2. IP-Input 差值 bigWig
# ================================================
# ---------- 配置 ----------
bam_dir=~/ac4c/bam
bw_dir=~/ac4c/bigwig
mkdir -p $bw_dir
genome_size=2652783500 # mm10 小鼠基因组有效大小
bin_size=10 # bin 大小 bp，可调整 10~25bp
# ---------- 定义组与对应 Input ----------
declare -A inputs
inputs=( ["Sham"]="Sham_Input.bam" ["SNI"]="SNI_Input.bam" )
# ---------- Step 1: 生成单样本 RPGC-normalized bigWig ----------
echo "Step 1: Generating single-sample RPGC-normalized bigWig..."
for bam in $bam_dir/*_IP.bam
do
sample=$(basename "$bam" .bam)
echo "Processing $sample..."
bamCoverage \
-b "$bam" \
-o "$bw_dir/${sample}.bw" \
--binSize $bin_size \
--normalizeUsing RPGC \
--effectiveGenomeSize $genome_size \
--ignoreDuplicates \
--extendReads
done
echo "All done. BigWig files saved in $bw_dir"
input组
#!/bin/bash
# ========= 配置 =========
bam_dir=~/ac4c/bam
bw_dir=~/ac4c/bigwig_input
mkdir -p $bw_dir
genome_size=2652783500 # mm10
bin_size=10 # bin 大小，可以改成 25 或 50 提高速度
# ========= 输入BAM列表 =========
inputs=("Sham_Input.bam" "SNI_Input.bam")
# ========= BAM → bigWig =========
echo "Generating normalized bigWig for input BAMs..."
for bam in "${inputs[@]}"
do
sample=$(basename "$bam" .bam)
echo "Processing $sample ..."
bamCoverage \
-b "$bam_dir/$bam" \
-o "$bw_dir/${sample}.bw" \
--binSize $bin_size \
--normalizeUsing RPGC \
--effectiveGenomeSize $genome_size \
--ignoreDuplicates \
--extendReads
done
echo "All done. Input bigWigs saved in $bw_dir"
然后导入IGV做divide
感觉分辨率太低所以换成1bp只生成chr6
#!/bin/bash
# ========= 配置 =========
bam_dir=~/ac4c/bam
bw_dir=~/ac4c/bigwig_chr6_1bp
mkdir -p $bw_dir
genome_size=2652783500 # mm10
bin_size=1 # 1bp 分辨率
# ========= BAM → bigWig =========
echo "Generating high-resolution (1bp) bigWig for chr6..."
for bam in "$bam_dir"/*.bam
do
sample=$(basename "$bam" .bam) # 保留原文件名前缀
echo "Processing $sample ..."
bamCoverage \
-b "$bam" \
-o "$bw_dir/${sample}_chr6_1bp.bw" \
--binSize $bin_size \
--normalizeUsing RPGC \
--effectiveGenomeSize $genome_size \
--ignoreDuplicates \
--extendReads \
--region chr6
done
echo "All done. chr6 high-resolution bigWigs saved in $bw_dir"
