【ChIP-seq分析】超级增强子系列5：用ChIPseeker进行超级增强子基因注释

# 常用距离设置
library(ChIPseeker)
library(TxDb.Hsapiens.UCSC.hg38.knownGene)
txdb <- TxDb.Hsapiens.UCSC.hg38.knownGene
# 方法1：±50kb（较保守）
peak_anno <- annotatePeak(peak_data, 
                         tssRegion = c(-50000, 50000),
                         TxDb = txdb, 
                         annoDb = "org.Hs.eg.db",
                         verbose = FALSE)
# 方法2：±100kb（常用）
peak_anno <- annotatePeak(peak_data, 
                         tssRegion = c(-100000, 100000),
                         TxDb = txdb, 
                         annoDb = "org.Hs.eg.db",
                         verbose = FALSE)
# 方法3：±500kb（较宽松）
peak_anno <- annotatePeak(peak_data, 
                         tssRegion = c(-500000, 500000),
                         TxDb = txdb, 
                         annoDb = "org.Hs.eg.db",
                         verbose = FALSE)

# 完整代码：使用多种距离进行超级增强子注释
setwd("您的文件夹路径")
bed_files <- list.files(pattern = "\\.bed$")
print(paste("找到以下BED文件:", paste(bed_files, collapse = ", ")))
# 为不同距离创建注释
distance_settings <- c(50000, 100000, 500000)  # 50kb, 100kb, 500kb
names(distance_settings) <- c("50kb", "100kb", "500kb")
# 对每个样本和每个距离进行注释
all_annotations <- list()
for (bed_file in bed_files) {
  sample_name <- gsub("\\.bed$", "", bed_file)
  peak_data <- readPeakFile(bed_file)
  cat("正在处理:", sample_name, "\n")
  # 对每个距离进行注释
  sample_annotations <- list()
  for (dist_name in names(distance_settings)) {
    distance <- distance_settings[dist_name]
    cat("  距离设置:", dist_name, "(", distance, "bp)\n")
    peak_anno <- annotatePeak(peak_data, 
                             tssRegion = c(-distance, distance),
                             TxDb = txdb, 
                             annoDb = "org.Hs.eg.db",
                             addFlankGeneInfo = TRUE,
                             flankDistance = distance,
                             verbose = FALSE)
    # 保存注释结果
    anno_df <- as.data.frame(peak_anno)
    output_file <- paste0(sample_name, "_", dist_name, "_annotated.txt")
    write.table(anno_df, file = output_file, sep = "\t", quote = FALSE, row.names = FALSE)
    sample_annotations[[dist_name]] <- peak_anno
  }
  all_annotations[[sample_name]] <- sample_annotations
}