GEO線上分析工具

1. GEO 資料庫搜尋介面

2. Find genes

• find gene name or symbol: 直接查詢資料集組中該基因的基因表達譜

• find genes that are up/down for this conditions: 可以根據選擇實驗的篩選條件，來找到一系列隨該篩選條件有較明顯表達差異的基因表達譜。

  
  
  

  image.png
  
  
  

  image.png

3. Compare 2 sets of samples

4. Cluster heatmaps 聚類分析圖

1. 層級聚類方法：（single-link: 最近距離、complete-link: 最遠距離、Average-link: 平均距離）
2. 分散性聚類方法：

• K - Medioids演算法 ：用類中的某個點來代表該聚類，能處理任意型別的屬性，對異常資料不夠敏感
• K - Means 演算法： 聚類中心用個各類別中所有資料的平均值表示，應用最為廣泛，收斂速度快，能擴充套件以用於大規模的資料集，傾向於識別凸形分佈、大小相近、密度相近的聚類，中心選擇和噪聲聚類對結果影響大

3. 按基因在染色體上的位置來聚類

   
   
   

   image.png
   
   
   

   image.png
   
   
   

   image.png
   
   
   

   image.png
   
   
   

   image.png

5. Experiment design value distribution (箱線圖)

6. GEO2R工具

• GEO2R 能利用開源軟體R平臺和bioconductor進行資料處理

  
  
  

  image.png
  
  
  

  image.png
  
  
  

  image.png

• 分析後的結果

  
  
  

  image.png
  
  
  

  image.png

• R 語言指令碼，可以自己下載學習修改

# Version info: R 3.2.3, Biobase 2.30.0, GEOquery 2.40.0, limma 3.26.8
# R scripts generated  Wed May 16 00:10:26 EDT 2018

################################################################
#   Differential expression analysis with limma
library(Biobase)
library(GEOquery)
library(limma)

# load series and platform data from GEO

gset <- getGEO("GSE642", GSEMatrix =TRUE, AnnotGPL=TRUE)
if (length(gset) > 1) idx <- grep("GPL81", attr(gset, "names")) else idx <- 1
gset <- gset[[idx]]

# make proper column names to match toptable 
fvarLabels(gset) <- make.names(fvarLabels(gset))

# group names for all samples
gsms <- "000000111111"
sml <- c()
for (i in 1:nchar(gsms)) { sml[i] <- substr(gsms,i,i) }

# log2 transform
ex <- exprs(gset)
qx <- as.numeric(quantile(ex, c(0., 0.25, 0.5, 0.75, 0.99, 1.0), na.rm=T))
LogC <- (qx[5] > 100) ||
          (qx[6]-qx[1] > 50 && qx[2] > 0) ||
          (qx[2] > 0 && qx[2] < 1 && qx[4] > 1 && qx[4] < 2)
if (LogC) { ex[which(ex <= 0)] <- NaN
  exprs(gset) <- log2(ex) }

# set up the data and proceed with analysis
sml <- paste("G", sml, sep="")    # set group names
fl <- as.factor(sml)
gset$description <- fl
design <- model.matrix(~ description + 0, gset)
colnames(design) <- levels(fl)
fit <- lmFit(gset, design)
cont.matrix <- makeContrasts(G1-G0, levels=design)
fit2 <- contrasts.fit(fit, cont.matrix)
fit2 <- eBayes(fit2, 0.01)
tT <- topTable(fit2, adjust="fdr", sort.by="B", number=250)

tT <- subset(tT, select=c("ID","adj.P.Val","P.Value","t","B","logFC","Gene.symbol","Gene.title"))
write.table(tT, file=stdout(), row.names=F, sep="\t")


################################################################
#   Boxplot for selected GEO samples
library(Biobase)
library(GEOquery)

# load series and platform data from GEO

gset <- getGEO("GSE642", GSEMatrix =TRUE, getGPL=FALSE)
if (length(gset) > 1) idx <- grep("GPL81", attr(gset, "names")) else idx <- 1
gset <- gset[[idx]]

# group names for all samples in a series
gsms <- "000000111111"
sml <- c()
for (i in 1:nchar(gsms)) { sml[i] <- substr(gsms,i,i) }
sml <- paste("G", sml, sep="")  set group names

# order samples by group
ex <- exprs(gset)[ , order(sml)]
sml <- sml[order(sml)]
fl <- as.factor(sml)
labels <- c("A","B")

# set parameters and draw the plot
palette(c("#dfeaf4","#f4dfdf", "#AABBCC"))
dev.new(width=4+dim(gset)[[2]]/5, height=6)
par(mar=c(2+round(max(nchar(sampleNames(gset)))/2),4,2,1))
title <- paste ("GSE642", '/', annotation(gset), " selected samples", sep ='')
boxplot(ex, boxwex=0.6, notch=T, main=title, outline=FALSE, las=2, col=fl)
legend("topleft", labels, fill=palette(), bty="n")