-2

我正在学习处理 VCF（变体调用文件）以生成图表和报告。这是 R 代码，由于我未知的原因而崩溃。请告知如何修复它并告诉适当的教程。

library(VariantAnnotation)  
library(SNPRelate)

vcf<-readVcf("test.vcf","hg19") # load your VCF file from a set dir

snpgdsVCF2GDS("test.vcf", "my.gds")

snpgdsSummary("my.gds")

genofile <- openfn.gds("my.gds")

#dendogram

dissMatrix  <-  snpgdsDiss(genofile , sample.id=NULL, snp.id=NULL,
autosome.only=TRUE,remove.monosnp=TRUE, maf=NaN, missing.rate=NaN,
num.thread=10, verbose=TRUE)

snpHCluster <-  snpgdsHCluster(dist, sample.id=NULL, need.mat=TRUE,
hang=0.25)

cutTree <- snpgdsCutTree(snpHCluster, z.threshold=15, outlier.n=5,
n.perm = 5000, samp.group=NULL,col.outlier="red", col.list=NULL,
pch.outlier=4, pch.list=NULL,label.H=FALSE, label.Z=TRUE,
verbose=TRUE)

#pca

sample.id <- read.gdsn(index.gdsn(genofile, "sample.id"))

pop_code <- read.gdsn(index.gdsn(genofile, "sample.id")

pca <- snpgdsPCA(genofile)

tab <- data.framesample.id = pca$sample.id,pop =
factor(pop_code)[match(pca$sample.id, sample.id)],EV1 =
pca$eigenvect[,1],EV2 = pca$eigenvect[,2],stringsAsFactors = FALSE)

plot(tab$EV2, tab$EV1, col=as.integer(tab$pop),xlab="eigenvector 2",
ylab="eigenvector 1") legend("topleft", legend=levels(tab$pop),
pch="o", col=1:nlevels(tab$pop))
4

1 回答 1

1

您的代码有几个问题：

-snpgdsHCluster 步骤应该在 dissMatrix 上运行，而不是 dist：

snpHCluster <-  snpgdsHCluster(dissMatrix, sample.id=NULL, need.mat=TRUE,
    hang=0.25)

- 在选项卡行中的数据框之后需要一个括号：

tab <- data.frame(sample.id = pca$sample.id,pop =
   factor(pop_code)[match(pca$sample.id, sample.id)],EV1 =
   pca$eigenvect[,1],EV2 = pca$eigenvect[,2],stringsAsFactors = FALSE)

-legend 是独立于 plot 的命令：

plot(tab$EV2, tab$EV1, col=as.integer(tab$pop),xlab="eigenvector 2",
    ylab="eigenvector 1") 

legend("topleft", legend=levels(tab$pop),
    pch="o", col=1:nlevels(tab$pop))

我认为否则它应该对你有用。

于 2015-02-03T13:45:26.420 回答