您的位置：首页 > 其它

edgeR（未完）

2015-10-14 16:00 309 查看
edgeR的安装：

source("http://bioconductor.org/biocLite.R")
biocLite("edgeR")

查看R的当前工作目录：

> getwd()
[1] "D:/My Documents"


载入包：

library(limma)
library(edgeR)


读取数据：

raw.data <- read.delim("pnas_expression_filtered.tsv")


查看数据格式：

head(raw.data)
ensembl_ID lane1 lane2 lane3 lane4 lane5 lane6 lane8
1 ENSG00000124208   478   619   628   744   483   716   240
2 ENSG00000182463    27    20    27    26    48    55    24
3 ENSG00000124201   180   218   293   275   373   301    88
4 ENSG00000124207    76    80    85    97    80    81    37
5 ENSG00000125835   132   200   200   228   280   204    52
6 ENSG00000125834    42    60    72    86   131    99    30


数据的处理一(把ensembl_ID这一列去掉)：

d <- raw.data[,2:8]
> head(d)
lane1 lane2 lane3 lane4 lane5 lane6 lane8
1   478   619   628   744   483   716   240
2    27    20    27    26    48    55    24
3   180   218   293   275   373   301    88
4    76    80    85    97    80    81    37
5   132   200   200   228   280   204    52
6    42    60    72    86   131    99    30

第一列基因标号：
rownames(d) <- raw.data[,1]
head(rownames(d))
[1] "ENSG00000124208" "ENSG00000182463" "ENSG00000124201" "ENSG00000124207"
[5] "ENSG00000125835" "ENSG00000125834"


group <- c(rep("Control",4),rep("DHT",3))
group
[1] "Control" "Control" "Control" "Control" "DHT"     "DHT"     "DHT"

d <- DGEList(counts = d, group=group)
Calculating library sizes from column totals.

d
An object of class "DGEList"
$counts
lane1 lane2 lane3 lane4 lane5 lane6 lane8
ENSG00000124208   478   619   628   744   483   716   240
ENSG00000182463    27    20    27    26    48    55    24
ENSG00000124201   180   218   293   275   373   301    88
ENSG00000124207    76    80    85    97    80    81    37
ENSG00000125835   132   200   200   228   280   204    52
16489 more rows ...

$samples
group lib.size norm.factors
lane1 Control   976847            1
lane2 Control  1154746            1
lane3 Control  1439393            1
lane4 Control  1482652            1
lane5     DHT  1820628            1
lane6     DHT  1831553            1
lane8     DHT   680798            1

dim(d)
[1] 16494     7

d <- calcNormFactors(d)
d
An object of class "DGEList"
$counts
lane1 lane2 lane3 lane4 lane5 lane6 lane8
ENSG00000124208   478   619   628   744   483   716   240
ENSG00000182463    27    20    27    26    48    55    24
ENSG00000124201   180   218   293   275   373   301    88
ENSG00000124207    76    80    85    97    80    81    37
ENSG00000125835   132   200   200   228   280   204    52
16489 more rows ...

$samples
group lib.size norm.factors
lane1 Control   976847    1.0296636
lane2 Control  1154746    1.0372521
lane3 Control  1439393    1.0362662
lane4 Control  1482652    1.0378383
lane5     DHT  1820628    0.9537095
lane6     DHT  1831553    0.9525624
lane8     DHT   680798    0.9583181

plotMDS.DGEList(d, main = "MDS Plot for Li Data", xlim = c(-1, 1),labels = c("Control1","Control2","Control3","Control4","DHT1", "DHT2", "DHT3"))


内容来自用户分享和网络整理，不保证内容的准确性，如有侵权内容，可联系管理员处理 点击这里给我发消息
标签： 
相关文章推荐
新的分享
章节导航