關于RNA-seq中的reads count標準化處理的方法匯總，請先看看這篇：
當我們在說RNA-seq reads count標準化時，其實在說什么？
本文集中討論常用的edgeR包中三種標準化方法TMM\UQ\RLE的比較
英文原貼Normalisation methods implemented in edgeR
1.首先創建一個數據集
包含四個樣品c1,c2是正常組，p1,p2是病人。共有50個轉錄本，每個樣品內轉錄本counts的總數都是500個，前25個轉錄本在四個樣品里都有表達，其中病人轉錄本的數目(20)是對照組(10)的兩倍, 后25個轉錄本只在正常組中檢測到。
#prepare example
control_1 <- rep(10, 50)
control_2 <- rep(10, 50)
patient_1 <- c(rep(20, 25),rep(0,25))
patient_2 <- c(rep(20, 25),rep(0,25))
df <- data.frame(c1=control_1,
c2=control_2,
p1=patient_1,
p2=patient_2)
head(df)
c1 c2 p1 p2
1 10 10 20 20
2 10 10 20 20
3 10 10 20 20
4 10 10 20 20
5 10 10 20 20
6 10 10 20 20
tail(df)
c1 c2 p1 p2
45 10 10 0 0
46 10 10 0 0
47 10 10 0 0
48 10 10 0 0
49 10 10 0 0
50 10 10 0 0
#equal depth
colSums(df)
c1 c2 p1 p2
500 500 500 500
數據集信息詳見Robinson and Oshlack http://genomebiology.com/2010/11/3/R25
2.如果不做標準化處理
#load library
library(edgeR)
#create group vector
group <- c('control','control','patient','patient')
#create DGEList object
d <- DGEList(counts=df, group=group)
#check out the DGEList object
d
An object of class "DGEList"
$counts
c1 c2 p1 p2
1 10 10 20 20
2 10 10 20 20
3 10 10 20 20
4 10 10 20 20
5 10 10 20 20
45 more rows ...
$samples
group lib.size norm.factors
c1 control 500 1
c2 control 500 1
p1 patient 500 1
p2 patient 500 1
d <- DGEList(counts=df, group=group)
d <- estimateCommonDisp(d)
#perform the DE test
de <- exactTest(d)
#how many differentially expressed transcripts?
table(p.adjust(de$table$PValue, method="BH")<0.05)
TRUE
50
可以看到：檢測出共50個轉錄本有差異，即每個轉錄本都是差異表達的，假陽性很高。
3.TMM normalisation
TMM <- calcNormFactors(d, method="TMM")
TMM
An object of class "DGEList"
$counts
c1 c2 p1 p2
1 10 10 20 20
2 10 10 20 20
3 10 10 20 20
4 10 10 20 20
5 10 10 20 20
45 more rows ...
$samples
group lib.size norm.factors
c1 control 500 0.7071068
c2 control 500 0.7071068
p1 patient 500 1.4142136
p2 patient 500 1.4142136
我們看到對前25個轉錄本而言，正常組和病人之間沒有差異 (10/0.7071068 (~14.14) 等于 20/1.4142136 (~14.14))。因此檢測出有25個轉錄本存在差異（后25個轉錄本）
TMM <- estimateCommonDisp(TMM)
TMM <- exactTest(TMM)
table(p.adjust(TMM$table$PValue, method="BH")<0.05)
FALSE TRUE
25 25
4.RLE normalisation
RLE
An object of class "DGEList"
$counts
c1 c2 p1 p2
1 10 10 20 20
2 10 10 20 20
3 10 10 20 20
4 10 10 20 20
5 10 10 20 20
45 more rows ...
$samples
group lib.size norm.factors
c1 control 500 0.7071068
c2 control 500 0.7071068
p1 patient 500 1.4142136
p2 patient 500 1.4142136
RLE <- estimateCommonDisp(RLE)
RLE <- exactTest(RLE)
table(p.adjust(RLE$table$PValue, method="BH")<0.05)
FALSE TRUE
25 25
5.UQ normalisation
uq
An object of class "DGEList"
$counts
c1 c2 p1 p2
1 10 10 20 20
2 10 10 20 20
3 10 10 20 20
4 10 10 20 20
5 10 10 20 20
45 more rows ...
$samples
group lib.size norm.factors
c1 control 500 0.7071068
c2 control 500 0.7071068
p1 patient 500 1.4142136
p2 patient 500 1.4142136
uq <- estimateCommonDisp(uq)
uq <- exactTest(uq)
table(p.adjust(uq$table$PValue, method="BH")<0.05)
FALSE TRUE
25 25
因為數據比較簡單，這里三種標準化方法得到的結果一致，那么真實測序數據的情況又如何呢？
6.測試一套真實數據
my_url <-"[https://davetang.org/file/pnas_expression.txt](https://davetang.org/file/pnas_expression.txt)"
data <-read.table(my_url, header=TRUE, sep="\t")
dim(data)
[1] 37435 9
ensembl_ID lane1 lane2 lane3 lane4 lane5 lane6 lane8 len
1 ENSG00000215696 0 0 0 0 0 0 0 330
2 ENSG00000215700 0 0 0 0 0 0 0 2370
3 ENSG00000215699 0 0 0 0 0 0 0 1842
4 ENSG00000215784 0 0 0 0 0 0 0 2393
5 ENSG00000212914 0 0 0 0 0 0 0 384
6 ENSG00000212042 0 0 0 0 0 0 0 92
準備DGEList
rownames(d) <- data[,1]
group <- c(rep("Control",4),rep("DHT",3))
d <- DGEList(counts = d, group=group)
An object of class "DGEList"
$counts
lane1 lane2 lane3 lane4 lane5 lane6 lane8
ENSG00000215696 0 0 0 0 0 0 0
ENSG00000215700 0 0 0 0 0 0 0
ENSG00000215699 0 0 0 0 0 0 0
ENSG00000215784 0 0 0 0 0 0 0
ENSG00000212914 0 0 0 0 0 0 0
37430 more rows ...
$samples
group lib.size norm.factors
lane1 Control 978576 1
lane2 Control 1156844 1
lane3 Control 1442169 1
lane4 Control 1485604 1
lane5 DHT 1823460 1
lane6 DHT 1834335 1
lane8 DHT 681743 1
還是先不做標準化處理
no_norm <- exactTest(no_norm)
table(p.adjust(no_norm$table$PValue, method="BH")<0.05)
FALSE TRUE
33404 4031
TMM normalisation
TMM <- calcNormFactors(d, method="TMM")
TMM
An object of class "DGEList"
$counts
lane1 lane2 lane3 lane4 lane5 lane6 lane8
ENSG00000215696 0 0 0 0 0 0 0
ENSG00000215700 0 0 0 0 0 0 0
ENSG00000215699 0 0 0 0 0 0 0
ENSG00000215784 0 0 0 0 0 0 0
ENSG00000212914 0 0 0 0 0 0 0
37430 more rows ...
$samples
group lib.size norm.factors
lane1 Control 978576 1.0350786
lane2 Control 1156844 1.0379515
lane3 Control 1442169 1.0287815
lane4 Control 1485604 1.0222095
lane5 DHT 1823460 0.9446243
lane6 DHT 1834335 0.9412769
lane8 DHT 681743 0.9954283
TMM <- estimateCommonDisp(TMM)
TMM <- exactTest(TMM)
table(p.adjust(TMM$table$PValue, method="BH")<0.05)
FALSE TRUE
33519 3916
RLE
RLE <- calcNormFactors(d, method="RLE")
RLE
An object of class "DGEList"
$counts
lane1 lane2 lane3 lane4 lane5 lane6 lane8
ENSG00000215696 0 0 0 0 0 0 0
ENSG00000215700 0 0 0 0 0 0 0
ENSG00000215699 0 0 0 0 0 0 0
ENSG00000215784 0 0 0 0 0 0 0
ENSG00000212914 0 0 0 0 0 0 0
37430 more rows ...
$samples
group lib.size norm.factors
lane1 Control 978576 1.0150010
lane2 Control 1156844 1.0236675
lane3 Control 1442169 1.0345426
lane4 Control 1485604 1.0399724
lane5 DHT 1823460 0.9706692
lane6 DHT 1834335 0.9734955
lane8 DHT 681743 0.9466713
RLE <- estimateCommonDisp(RLE)
RLE <- exactTest(RLE)
table(p.adjust(RLE$table$PValue, method="BH")<0.05)
FALSE TRUE
33465 3970
the upper quartile method
uq <- calcNormFactors(d, method="upperquartile")
uq
An object of class "DGEList"
$counts
lane1 lane2 lane3 lane4 lane5 lane6 lane8
ENSG00000215696 0 0 0 0 0 0 0
ENSG00000215700 0 0 0 0 0 0 0
ENSG00000215699 0 0 0 0 0 0 0
ENSG00000215784 0 0 0 0 0 0 0
ENSG00000212914 0 0 0 0 0 0 0
37430 more rows ...
$samples
group lib.size norm.factors
lane1 Control 978576 1.0272514
lane2 Control 1156844 1.0222982
lane3 Control 1442169 1.0250528
lane4 Control 1485604 1.0348864
lane5 DHT 1823460 0.9728534
lane6 DHT 1834335 0.9670858
lane8 DHT 681743 0.9541011
uq <- estimateCommonDisp(uq)
uq <- exactTest(uq)
table(p.adjust(uq$table$PValue, method="BH")<0.05)
FALSE TRUE
33466 3969
以上四種處理方法找到的差異基因取交集，可以看出不做標準化處理會得到405個假陽性和342個假陰性的轉錄本
library(gplots)
get_de <- function(x, pvalue){
my_i <- p.adjust(x$PValue, method="BH") < pvalue
row.names(x)[my_i]
}
my_de_no_norm <- get_de(no_norm$table, 0.05)
my_de_tmm <- get_de(TMM$table, 0.05)
my_de_rle <- get_de(RLE$table, 0.05)
my_de_uq <- get_de(uq$table, 0.05)
gplots::venn(list(no_norm = my_de_no_norm, TMM = my_de_tmm, RLE = my_de_rle, UQ = my_de_uq))
不做標準化會得到405個假陽性和342個假陰性的轉錄本
三種標準化方法找到的差異基因大部分是一致的
gplots::venn(list(TMM = my_de_tmm, RLE = my_de_rle, UQ = my_de_uq))
1.png
小結
三種標準化方法效果類似，處理結果都比不做標準化要好
The normalisation factors were quite similar between all normalisation methods, which is why the results of the differential expression were quite concordant. Most methods down sized the DHT samples with a normalisation factor of less than one to account for the larger library sizes of these samples.
