> exprs_mat[1:6, 1:4]
Tarca_001_P1A01 Tarca_003_P1A03 Tarca_004_P1A04 Tarca_005_P1A05
1_at 6.062215 6.125023 5.875502 6.126131
10_at 3.796484 3.805305 3.450245 3.628411
100_at 5.849338 6.191562 6.550525 6.421877
1000_at 3.567779 3.452524 3.316134 3.432451
10000_at 6.166815 5.678373 6.185059 5.633757
100009613_at 4.443027 4.773199 4.393488 4.623783
我也有该Affymetrix表达的表型(行中为RNA样品标识符,列中为样品描述):
> pheno[1:6, 1:4]
SampleID GA Batch Set
Tarca_001_P1A01 Tarca_001_P1A01 11.0 1 PRB_HTA
Tarca_013_P1B01 Tarca_013_P1B01 15.3 1 PRB_HTA
Tarca_025_P1C01 Tarca_025_P1C01 21.7 1 PRB_HTA
Tarca_037_P1D01 Tarca_037_P1D01 26.7 1 PRB_HTA
Tarca_049_P1E01 Tarca_049_P1E01 31.3 1 PRB_HTA
Tarca_061_P1F01 Tarca_061_P1F01 32.1 1 PRB_HTA
因为在phenodata中,样本标识符在行中,所以我需要找到将phenodata中的sampleID与表达式矩阵exprs_mat
中的sampleID匹配的方法。
目标:
我想通过测量每个基因与phenodata
中的目标谱数据之间的相关性来过滤表达矩阵中的基因。这是我最初的尝试,但对准确性不太确定:
更新:我在R中的实现:
我打算看看每个样本中的基因如何与注释数据中相应样本的GA值相关联。这是我在R中找到此相关性的简单函数:
getPCC <- function(expr_mat, anno_mat, verbose=FALSE){
stopifnot(class(expr_mat)=="matrix")
stopifnot(class(anno_mat)=="matrix")
stopifnot(ncol(expr_mat)==nrow(anno_mat))
final_df <- as.data.frame()
lapply(colnames(expr_mat), function(x){
lapply(x, rownames(y){
if(colnames(x) %in% rownames(anno_mat)){
cor_mat <- stats::cor(y, anno_mat$GA, method = "pearson")
ncor <- ncol(cor_mat)
cmatt <- col(cor_mat)
ord <- order(-cmat, cor_mat, decreasing = TRUE)- (ncor*cmatt - ncor)
colnames(ord) <- colnames(cor_mat)
res <- cbind(ID=c(cold(ord), ID2=c(ord)))
res <- as.data.frame(cbind(out, cor=cor_mat[res]))
final_df <- cbind(res, cor=cor_mat[out])
}
})
})
return(final_df)
}
,但是以上脚本未返回我期望的正确输出。有什么想法可以正确实现吗?有什么想法吗?
答案 0 :(得分:1)
做了这样的帮助:
library(tidyverse)
x <- data.frame(stringsAsFactors=FALSE,
Levels = c("1_at", "10_at", "100_at", "1000_at", "10000_at", "100009613_at"),
Tarca_001_P1A01 = c(6.062215, 3.796484, 5.849338, 3.567779, 6.166815,
4.443027),
Tarca_003_P1A03 = c(6.125023, 3.805305, 6.191562, 3.452524, 5.678373,
4.773199),
Tarca_004_P1A04 = c(5.875502, 3.450245, 6.550525, 3.316134, 6.185059,
4.393488),
Tarca_005_P1A05 = c(6.126131, 3.628411, 6.421877, 3.432451, 5.633757,
4.623783)
)
y <- data.frame(stringsAsFactors=FALSE,
gene = c("Tarca_001_P1A01", "Tarca_013_P1B01", "Tarca_025_P1C01",
"Tarca_037_P1D01", "Tarca_049_P1E01", "Tarca_061_P1F01"),
SampleID = c("Tarca_001_P1A01", "Tarca_013_P1B01", "Tarca_025_P1C01",
"Tarca_037_P1D01", "Tarca_049_P1E01", "Tarca_061_P1F01"),
GA = c(11, 15.3, 21.7, 26.7, 31.3, 32.1),
Batch = c(1, 1, 1, 1, 1, 1),
Set = c("PRB_HTA", "PRB_HTA", "PRB_HTA", "PRB_HTA", "PRB_HTA", "PRB_HTA")
)
x %>% gather(SampleID, value, -Levels) %>%
left_join(., y, by = "SampleID") %>%
group_by(SampleID) %>%
filter(value == max(value)) %>%
spread(SampleID, value)