探针转换与基因去重

rm(list = ls())
#打破下载时间的限制,改前60秒，改后10w秒
options(timeout = 100000) 
options(scipen = 20)#不要以科学计数法表示

library(dplyr)
library(tibble)
exprSet <- exprSet %>% 
  rownames_to_column(var="probeset") %>% 
  #合并探针的信息
  inner_join(probe2symbol,by="probeset") %>% 
  #去掉多余信息
  select(-probeset) %>% 
  #重新排列
  select(symbol,everything()) %>% 
  #求出平均数(这边的点号代表上一步产出的数据)
  mutate(rowMean =rowMeans(.[grep("GSM", names(.))])) %>% 
  #去除symbol中的NA
  filter(symbol != "NA") %>% 
  #把表达量的平均值按从大到小排序
  arrange(desc(rowMean)) %>% 
  # symbol留下第一个
  distinct(symbol,.keep_all = T) %>% 
  #反向选择去除rowMean这一列
  select(-rowMean) %>% 
  # 列名变成行名
  column_to_rownames(var = "symbol")
#> Error: object 'exprSet' not found

#方法有三种：1.随机去重 2.取行平均值最大的探针 3.取多个探针的平均值.此处为"方法2".

#方法1：去除symbol中的NA
  filter(symbol != "NA") 
#> Error: object 'symbol' not found

#方法2：去除symbol中的空格
id4 = soft[,c("ID","GENE_SYMBOL")]
#> Error: object 'soft' not found
  k = id4$GENE_SYMBOL=="";table(k)
#> Error: object 'id4' not found
  id4 = id4[!k,]
#> Error: object 'id4' not found
  id4 = soft[, c("ID", "GENE_SYMBOL")]
#> Error: object 'soft' not found

#方法3：去除GENE_SYMBOL 列中内容为空字符串 "" 或者包含 "///" 的行
k = id4$GENE_SYMBOL == "" | grepl("///", id4$GENE_SYMBOL)
#> Error: object 'id4' not found

# 统计 k 中 TRUE 和 FALSE 的数量
table(k)
#> Error: object 'k' not found

# 去除这些行
id4 = id4[!k, ]
#> Error: object 'id4' not found

knitr::knit("a.Rmd")
#> Error in parse_block(g[-1], g[1], params.src, markdown_mode): Duplicate chunk label 'setup', which has been used for the chunk:
#> knitr::opts_chunk$set(
#>   collapse = TRUE,
#>   comment = "#>"
#> )
#> knitr::opts_chunk$set(fig.width = 10,fig.height = 7,collapse = TRUE)
#> knitr::opts_chunk$set(message = FALSE,warning = FALSE)