Question

尊敬的堆栈溢出社区：

我在使用DeSEQ2进行RNA序列分析时遇到一个问题。我有4个小组，每个小组3个样本，并使用以下代码设置小组：

(condition <- factor(c(rep("ctl", 3), rep("A", 3), rep("B", 3), rep("C", 3))))

谁能告诉我DeSEQ2中的比较是如何完成的？我不确定默认输出中的p值和log2FC是什么意思。假设它应该在默认输出中输出ctl vsA。但是，当我只有ctl和A作为输入（2个组）时，数据不同。另外，有没有一种方法可以指定程序如何执行比较？我读了一些以前的主题，但是答案不是很清楚。任何帮助将不胜感激！

最佳，

文汉

    `enter code here` 
    countdata <- read.table("B6_B6MHV_B6MHVWY.txt", header=TRUE, row.names=1)
countdata <- countdata[ ,6:ncol(countdata)]
colnames(countdata) <- gsub("\\.[sb]am$", "", colnames(countdata))
countdata <- as.matrix(countdata)
head(countdata)
(condition <- factor(c(rep("ctl", 3), rep("A", 3), rep("B", 3), rep("C", 3))))
library(DESeq2)
(coldata <- data.frame(row.names=colnames(countdata), condition))
dds <- DESeqDataSetFromMatrix(countData=countdata, colData=coldata, design=~condition)
dds
dds <- DESeq(dds)
# Plot
dispersions
png("qc-dispersions.png", 2000, 2000, pointsize=20)
plotDispEsts(dds, main="Dispersion plot")
dev.off()

# Regularized log transformation for clustering/heatmaps, etc
rld <- rlogTransformation(dds)
head(assay(rld))
hist(assay(rld))

# Colors for plots below
## Ugly:
## (mycols <- 1:length(unique(condition)))
## Use RColorBrewer, better
library(RColorBrewer)
(mycols <- brewer.pal(8, "Dark2")[1:length(unique(condition))])

# Sample distance heatmap
sampleDists <- as.matrix(dist(t(assay(rld))))
library(gplots)
png("qc-heatmap-samples.png", w=1500, h=2500, pointsize=1500)
heatmap.2(as.matrix(sampleDists), key=F, trace="none",
col=colorpanel(100, "black", "white"),
ColSideColors=mycols[condition], RowSideColors=mycols[condition],
margin=c(10, 10), main="Sample Distance Matrix")
dev.off()

# Principal components analysis
## Could do with built-in DESeq2 function:
## DESeq2:lotPCA(rld, intgroup="condition")
## I like mine better:
rld_pca <- function (rld, intgroup = "condition", ntop = 500, colors=NULL, legendpos="bottomleft", main="PCA Biplot", textcx=1, ...) {
require(genefilter)
require(calibrate)
require(RColorBrewer)
rv = rowVars(assay(rld))
select = order(rv, decreasing = TRUE)[seq_len(min(ntop, length(rv)))]
pca = prcomp(t(assay(rld)[select, ]))
fac = factor(apply(as.data.frame(colData(rld)[, intgroup, drop = FALSE]), 1, paste, collapse = " : "))
if (is.null(colors)) {
if (nlevels(fac) >= 3) {
colors = brewer.pal(nlevels(fac), "Paired")
} else {
colors = c("black", "red")
}
}
pc1var <- round(summary(pca)$importance[2,1]*100, digits=1)
pc2var <- round(summary(pca)$importance[2,2]*100, digits=1)
pc1lab <- paste0("PC1 (",as.character(pc1var),"%)")
pc2lab <- paste0("PC1 (",as.character(pc2var),"%)")
plot(PC2~PC1, data=as.data.frame(pca$x), bg=colors[fac], pch=21, xlab=pc1lab, ylab=pc2lab, main=main, ...)
with(as.data.frame(pca$x), textxy(PC1, PC2, labs=rownames(as.data.frame(pca$x)), cex=textcx))
legend(legendpos, legend=levels(fac), col=colors, pch=20)
# rldyplot(PC2 ~ PC1, groups = fac, data = as.data.frame(pca$rld),
# pch = 16, cerld = 2, aspect = "iso", col = colours, main = draw.key(key = list(rect = list(col = colours),
# terldt = list(levels(fac)), rep = FALSE)))
}
png("qc-pca.png", 1500, 1500, pointsize=25)
rld_pca(rld, colors=mycols, intgroup="condition", xlim=c(-75, 35))
dev.off()


# Get differential expression results
res <- results(dds)
table(res$padj<0.05)
## Order by adjusted p-value
res <- res[order(res$padj), ]
## Merge with normalized count data
resdata <- merge(as.data.frame(res), as.data.frame(counts(dds, normalized=TRUE)), by="row.names", sort=FALSE)
names(resdata)[1] <- "Gene"
head(resdata)
## Write results
write.csv(resdata, file="diffexpr-results.csv")

Deseq2多组比较

0 个答案: