前言：
写这篇文章的目的是为了梳理一下学习思路，按部就班地仿生信菜鸟团和：Y大宽
教程大纲，做归纳整理，即便再次运行，仍然遇到代码出错或者软件使用等诸多问题，是以为之记。
MA plot
详细关于Bland-Altman图具体含义，请移步至
- R语言：Bland-Altman分析
- 连续变量的一致性评价
> plotMA(res,ylim=c(-2,2))
> topGene <- rownames(res)[which.min(res$padj)]
> with(res[topGene, ], {
+ points(baseMean, log2FoldChange, col="dodgerblue", cex=6, lwd=2)
+ text(baseMean, log2FoldChange, topGene, pos=2, col="dodgerblue")
+ })
结果如下：
Rplot01.png
经过lfcShrink 收缩log2 fold change
> res_order<-res[order(row.names(res)),]
> res = res_order
> res.shrink <- lfcShrink(dds, contrast = c("condition","treat","control"), res=res)
> plotMA(res.shrink, ylim = c(-5,5))
> topGene <- rownames(res)[which.min(res$padj)]
> with(res[topGene, ], {
+ points(baseMean, log2FoldChange, col="dodgerblue", cex=2, lwd=2)
+ text(baseMean, log2FoldChange, topGene, pos=2, col="dodgerblue")
+ })
> plotMA(res.shrink, ylim = c(-5,5))
> topGene <- rownames(res)[which.min(res$padj)]
> with(res[topGene, ], {
+ points(baseMean, log2FoldChange, col="dodgerblue", cex=2, lwd=2)
+ text(baseMean, log2FoldChange, topGene, pos=2, col="dodgerblue")
+ })
结果如下：
Rplot02.png
2. Plot counts
# 不画图，只显示数据
plotCounts(dds, gene=which.min(res$padj), intgroup="condition", returnData=TRUE)
#只画图，不显示数据
plotCounts(dds, gene="ENSG00000002586", intgroup="condition", returnData=FAULSE)
下面用ggplot2来画CD99的box图和point图
- boxplot
# Plot it
> plotCounts(dds, gene="ENSG00000002586", intgroup="condition", returnData=TRUE) %>%
+ ggplot(aes(condition, count)) + geom_boxplot(aes(fill=condition)) + scale_y_log10() + ggtitle("CD99")
Rplot03.png
- point plot
> d <- plotCounts(dds, gene="ENSG00000002586", intgroup="condition", returnData=TRUE)
> ggplot(d, aes(x=condition, y=count)) +
+ geom_point(aes(color= condition),size= 4, position=position_jitter(w=0.5,h=0)) +
+ scale_y_log10(breaks=c(25,100,400))+ ggtitle("CD99")
Rplot04.png
3. PCA(principal components analysis)
> vsdata <- vst(dds, blind=FALSE)
> plotPCA(vsdata, intgroup="condition")
Rplot05.png
4. 热图：两部分
4.1 count matrix 热图
> library("pheatmap")
> select<-order(rowMeans(counts(dds, normalized = TRUE)),
+ decreasing = TRUE)[1:20]
> df <- as.data.frame(colData(dds)[,c("condition","sizeFactor")])
# this gives log2(n + 1)
> ntd <- normTransform(dds)
> pheatmap(assay(ntd)[select,], cluster_rows=FALSE, show_rownames=FALSE,
+ cluster_cols=FALSE, annotation_col=df)
Rplot06.png
4.2 sample-to-sample distances热图
> sampleDists <- dist(t(assay(vsdata)))
> library("RColorBrewer")
> sampleDistMatrix <- as.matrix(sampleDists)
> rownames(sampleDistMatrix) <- paste(vsdata$condition, vsdata$type, sep="-")
> colnames(sampleDistMatrix) <- NULL
> colors <- colorRampPalette( rev(brewer.pal(9, "Blues")) )(255)
> pheatmap(sampleDistMatrix,
+ clustering_distance_rows=sampleDists,
+ clustering_distance_cols=sampleDists,
+ col=colors)
Rplot07.png
5. 基因集(gene set)富集分析
# enrichment analysis using clusterprofiler package created by yuguangchuang
> library(clusterProfiler)
> library(DOSE)
> library(org.Hs.eg.db)
> sig.gene <- read.csv(file="readcount_all.csv")# 我用DEG_treat_vs_control.csv后续分析没有富集到，所以换用这个
> head(sig.gene)
> gene <- sig.gene[,1] #注意是ID所在的列
> head(gene)
> gene.df <- bitr(gene, fromType = "ENSEMBL",
toType = c("SYMBOL","ENTREZID"),
OrgDb = org.Hs.eg.db)
> head(gene.df)
5.1 GO富集分析：
#Go classification
#Go enrichment
> library("stringr") #后面出图的参数str_wrap需要这个包
ego_cc <- enrichGO(gene = gene.df$ENSEMBL,
OrgDb = org.Hs.eg.db,
keyType = 'ENSEMBL',
ont = "CC",
pAdjustMethod = "BH",
pvalueCutoff = 0.01,
qvalueCutoff = 0.05)
ego_bp <- enrichGO(gene = gene.df$ENSEMBL,
OrgDb = org.Hs.eg.db,
keyType = 'ENSEMBL',
ont = "BP",
pAdjustMethod = "BH",
pvalueCutoff = 0.01,
qvalueCutoff = 0.05)
> barplot(ego_cc,showCategory = 18,title="The GO_CC enrichment analysis of all DEGs ")+
+ scale_size(range=c(2, 12))+
+ scale_x_discrete(labels=function(ego_cc) str_wrap(ego_cc,width = 25))
> barplot(ego_bp,showCategory = 18,title="The GO_BP enrichment analysis of all DEGs ")+
+ scale_size(range=c(2, 12))+
+ scale_x_discrete(labels=function(ego_bp) str_wrap(ego_bp,width = 25))
Rplot10.png
Rplot11.png
5.2 KEGG enrichment
> install.packages("stringr")
> library(stringr)
> kk<-enrichKEGG(gene =gene.df$ENTREZID,
organism = 'hsa',
pvalueCutoff = 0.05)
> kk[1:30]
> barplot(kk,showCategory = 25, title="The KEGG enrichment analysis of all DEGs")+
scale_size(range=c(2, 12))+
scale_x_discrete(labels=function(kk) str_wrap(kk,width = 25))
> dotplot(kk,showCategory = 25, title="The KEGG enrichment analysis of all DEGs")+
scale_size(range=c(2, 12))+
scale_x_discrete(labels=function(kk) str_wrap(kk,width = 25))
Rplot12.png
Rplot13.png
6. Gene Set Enrichment Analysis（GSEA）
我用的数据库这部分没有找到差异的，所以只是罗列操作步骤，待以后有数据再做处理
# 获取按照log2FC大小来排序的基因列表
> sig.gene <- read.csv(file="DEG_treat_vs_control.csv")
> genelist <- sig.gene$log2FoldChange
> names(genelist) <- sig.gene[,1]
> genelist <- sort(genelist, decreasing = TRUE)
# GSEA分析
> gsemf <- gseGO(genelist,
OrgDb = org.Hs.eg.db,
keyType = "ENSEMBL",
ont="BP"
)
# 查看信息
head(gsemf)
# 画出GSEA图
gseaplot(gsemf, geneSetID="GO:0001819")