在 R 的一个文件夹中的多个.txt 文件上运行循环

Question

我有一个脚本，可以计算拷贝数变异并将数据保存到基于第一列信息的名为“genesforcomp1”的现有文件中。 输入文件名为 BRCA1.txt、BRCA2.txt、BRCA3.txt.......BRCA4376.txt。 另一个输入文件“genes.txt”在每个循环中都相同，用于注释，而“genesforcomp1”用于更新output。 由于文件较多，想知道能否通过R中的循环function来实现。 这是我的脚本

setwd("/home/sumit/Test/1_Lung/AllCNV/0a0bd4cc-3da8-44ff-ba08-a7e86b95f2f6/aa")
library(GenomicRanges)
library(dplyr)
library("scales")
require(tidyverse)
#Create annotation or refrence table
genes <- read.table("/home/sumit/Test/1_Lung/AllCNV/0a0bd4cc-3da8-44ff-ba08-a7e86b95f2f6/genes.txt", sep="\t", stringsAsFactors=FALSE, header=TRUE)
genes$chromosome_name <- gsub('X', '23', genes$chromosome_name)
genes$chromosome_name <- gsub('Y', '24', genes$chromosome_name)
colnames(genes) <- c("GeneSymbol","Chr","Start","End")
genes_GR <- makeGRangesFromDataFrame(genes,keep.extra.columns = TRUE)
#File need to be analyzed (3 step: preprocessing, comparison with reference or annotation and post-porcessing)
df<- read.table("BRCA1.txt", sep="\t", stringsAsFactors=FALSE, header=TRUE)
df$Chromosome <- gsub('X', '23', df$Chromosome)
df$Chromosome <- gsub('Y', '24', df$Chromosome)
colnames(df) <- c("Barcode", "Chr", "Start", "End", "extra1", "extra2")
cnv <-  makeGRangesFromDataFrame(df, keep.extra.columns = TRUE)
hits <- findOverlaps(genes_GR, cnv, type="within")
df_ann <- cbind(df[subjectHits(hits),],genes[queryHits(hits),])
df_ann <- unique(df_ann)
df_ann <- df_ann[ , c("GeneSymbol", "Chr", "extra2")]
colnames(df_ann) <- c("Ensembl_ID","Chr","Seg_value")
df_ann$Seg_value2 <- abs(df_ann$Seg_value)
df_ann$Seg_value2 = 2^df_ann$Seg_value2
df_ann$Seg_value2 = df_ann[, 4] - 1
df_ann$Seg_value2 = df_ann[, 4] * 2
df_ann$Seg_value2 <- with(df_ann, sign(Seg_value) * Seg_value2)
df_ann <- df_ann[ , c("Ensembl_ID", "Seg_value")]
df_ann$Seg_value <- rescale(df_ann$Seg_value, to = c(-1, 1))
df_ann1 <- read.table("/home/sumit/Academic/DHR/TCGA/Gene List/Final1/genesbase.txt", sep="\t", stringsAsFactors=FALSE, header=TRUE)
df <- rbind.data.frame(df_ann, df_ann1)
df <- df[!duplicated(df$Ensembl_ID),]
#saving the results into existing file based on first column values
df1 <- read.delim("genesforcomp1", check.names=FALSE, stringsAsFactors=FALSE)
lst <- list(data.frame(df1), data.frame(df))
df2 <- reduce(lst, full_join, by = "Ensembl_ID") %>% replace(., is.na(.), 0);
write.table(df2, file="genesforcomp1", quote = F, sep = "\t", row.names = F)

任何关于如何循环脚本的建议或想法将不胜感激。 提前致谢！

Answer 1

由于您的文件名遵循一个很好的模式，您可以执行从 1 到 4376 的循环，并将代码中的"BRCA1.txt"替换为paste0("BRCA", i, ".txt") 。 可能有一些方法可以在不对模式进行硬编码的情况下进行循环，但在您的情况下，您似乎不需要它。

setwd("/home/sumit/Test/1_Lung/AllCNV/0a0bd4cc-3da8-44ff-ba08-a7e86b95f2f6/aa")
library(GenomicRanges)
library(dplyr)
library("scales")
require(tidyverse)
#Create annotation or refrence table
genes <- read.table("/home/sumit/Test/1_Lung/AllCNV/0a0bd4cc-3da8-44ff-ba08-a7e86b95f2f6/genes.txt", sep="\t", stringsAsFactors=FALSE, header=TRUE)
genes$chromosome_name <- gsub('X', '23', genes$chromosome_name)
genes$chromosome_name <- gsub('Y', '24', genes$chromosome_name)
colnames(genes) <- c("GeneSymbol","Chr","Start","End")
genes_GR <- makeGRangesFromDataFrame(genes,keep.extra.columns = TRUE)
#File need to be analyzed (3 step: preprocessing, comparison with reference or annotation and post-porcessing)
for(i in 1:4376){
  df<- read.table(paste0("BRCA", i, ".txt"), sep="\t", stringsAsFactors=FALSE, header=TRUE)
  df$Chromosome <- gsub('X', '23', df$Chromosome)
  df$Chromosome <- gsub('Y', '24', df$Chromosome)
  colnames(df) <- c("Barcode", "Chr", "Start", "End", "extra1", "extra2")
  cnv <-  makeGRangesFromDataFrame(df, keep.extra.columns = TRUE)
  hits <- findOverlaps(genes_GR, cnv, type="within")
  df_ann <- cbind(df[subjectHits(hits),],genes[queryHits(hits),])
  df_ann <- unique(df_ann)
  df_ann <- df_ann[ , c("GeneSymbol", "Chr", "extra2")]
  colnames(df_ann) <- c("Ensembl_ID","Chr","Seg_value")
  df_ann$Seg_value2 <- abs(df_ann$Seg_value)
  df_ann$Seg_value2 = 2^df_ann$Seg_value2
  df_ann$Seg_value2 = df_ann[, 4] - 1
  df_ann$Seg_value2 = df_ann[, 4] * 2
  df_ann$Seg_value2 <- with(df_ann, sign(Seg_value) * Seg_value2)
  df_ann <- df_ann[ , c("Ensembl_ID", "Seg_value")]
  df_ann$Seg_value <- rescale(df_ann$Seg_value, to = c(-1, 1))
  df_ann1 <- read.table("/home/sumit/Academic/DHR/TCGA/Gene List/Final1/genesbase.txt", sep="\t", stringsAsFactors=FALSE, header=TRUE)
  df <- rbind.data.frame(df_ann, df_ann1)
  df <- df[!duplicated(df$Ensembl_ID),]
  #saving the results into existing file based on first column values
  df1 <- read.delim("genesforcomp1", check.names=FALSE, stringsAsFactors=FALSE)
  lst <- list(data.frame(df1), data.frame(df))
  df2 <- reduce(lst, full_join, by = "Ensembl_ID") %>% replace(., is.na(.), 0);
  write.table(df2, file="genesforcomp1", quote = F, sep = "\t", row.names = F)
}