我的维恩图不相交 - missing/wrong 与我的代码有什么关系

My venn diagrams dont intersect - what's missing/wrong with my code

我有两个基因列表,我想在维恩图中表示列表之间的重叠。有人可以建议我在下面的代码中缺少什么吗?我正在使用 VennDiagram 包,我得到的结果是两个不相交的圆圈。我还使用 Venny https://bioinfogp.cnb.csic.es/tools/venny/index2.0.2.html 绘制维恩并确认存在重叠。

library(VennDiagram)

#select the data
dataset1 <- data.frame(as.character(v7$HGNC_Symbol)) #567 genes
dataset2 <- data.frame(as.character(test$toupper.v13.HGNC_Symbol.)) #476 genes

#rename the columns so I know the source
names(dataset1)[1] <- "Progenesis"
names(dataset2)[1] <- "BiomaRt"

#sort the dataframes alphabetically 
dataset1 <- dataset1 %>% arrange(Progenesis)
dataset2 <- dataset2 %>% arrange(BiomaRt)

#create a list of numbers and join it to dataframe1
mylist <- c(1:592)
dataset1 <- data.frame(mylist, dataset1)

#create a list of numbers and join it to dataframe2
mylist <- c(1:494)
dataset2 <- data.frame(mylist, dataset2)

#join the two dataframes
v <- plyr::join(dataset1, dataset2, type='full')

#draw the Venn Diagram

Dataset1 <- as.vector(v$Progenesis)
Dataset2 <- as.vector(v$BiomaRt)
Dataset2 <- na.omit(Dataset2)

    #first 20 rows of each dataset 
    dput(Dataset1)
        c("AACS ", "AARS ", "ABCF1 ", "ACAD11 ", "ACIN1 ", "ACO1 ", "ACOX3 ", 
        "ACP1 ", "ACSL3 ", "ACY1A ", "ACYP1 ", "ADA ", "ADI1 ", "ADK ", 
        "ADSL ", "ADSS ", "AGPAT3 ", "AHSA2 ", "AK4 ", "AKAP1 ")
        dput(Dataset2)
        structure(c("AACS", "AARS", "AARS", "ABCF1", "ACAD11", "ACIN1", 
        "ACO1", "ACOX3", "ACSL3", "ACYP1", "ADA", "ADI1", "ADK", "ADSL", 
        "AGPAT3", "AHSA2", "AKAP1", "AKAP12", "AKR1A1", "AKR1A1"),
        na.action = structure(495:592, class = "omit"))

venn.diagram(
  x = list(Dataset1, Dataset2),
  category.names = c("Set1" , "Set2"),
  filename = 'venn_diagram.png',
  output=TRUE
  )

欢迎所有建议。

谢谢

The result of my code is this

What I want is here

我对你的数据有几点意见:

dput(Dataset1)
        c("AACS ", "AARS ", "ABCF1 ", "ACAD11 ", "ACIN1 ", "ACO1 ", "ACOX3 ", 
        "ACP1 ", "ACSL3 ", "ACY1A ", "ACYP1 ", "ADA ", "ADI1 ", "ADK ", 
        "ADSL ", "ADSS ", "AGPAT3 ", "AHSA2 ", "AK4 ", "AKAP1 ")
dput(Dataset2)
        structure(c("AACS", "AARS", "AARS", "ABCF1", "ACAD11", "ACIN1", 
        "ACO1", "ACOX3", "ACSL3", "ACYP1", "ADA", "ADI1", "ADK", "ADSL", 
        "AGPAT3", "AHSA2", "AKAP1", "AKAP12", "AKR1A1", "AKR1A1"),
        na.action = structure(495:592, class = "omit"))

您的 Dataset1 包含以 空格 结尾的字符串。它们不等于 Dataset2 中的那些,例如 "AACS " 不等于 "AACS"。尝试将您的数据集转换为

Dataset1 <- c("AACS","AARS","ABCF1","ACAD11","ACIN1","ACO1","ACOX3", 
              "ACP1","ACSL3","ACY1A","ACYP1","ADA","ADI1","ADK", 
              "ADSL","ADSS","AGPAT3","AHSA2","AK4","AKAP1")

在这种情况下,您的输出应如下所示: 您的输出文件类型是 .png,因此您应该使用参数 imagetype='png'.