在R中用盒状图表示

我有一个数据集，我想通过箱线图比较任意两个基因的表达值，如何接近这一点，这是我的数据集样本：

structure(list(gene_id = structure(6:11, .Label = c("__alignment_not_unique", 
"__ambiguous", "__no_feature", "__not_aligned", "__too_low_aQual", 
"ENSG00000000005", "ENSG00000000419", "ENSG00000000457", "ENSG00000000460", 
"ENSG00000000938", "ENSG00000000971", "ENSG00000001036", "ENSG00000001084", 
"ENSG00000001167", "ENSG00000001460", "ENSG00000001461", "ENSG00000001497", 
"ENSG00000001561", "ENSG00000001617", "ENSG00000001626", "ENSG00000001629", 
"ENSG00000001630", "ENSG00000001631", "ENSG00000002016", "ENSG00000002079", 
"ENSG00000002330", "ENSG00000002549", "ENSG00000002586", "ENSG00000002587", 
"ENSG00000002726", "ENSG00000002745", "ENSG00000002746", "ENSG00000002822", 
"ENSG00000002834", "ENSG00000002919", "ENSG00000002933", "ENSG00000003056", 
"ENSG00000003096", "ENSG00000003137", "ENSG00000003147", "ENSG00000003249", 
"ENSG00000003393", "ENSG00000003400", "ENSG00000003402", "ENSG00000003436", 
"ENSG00000003509", "ENSG00000003756", "ENSG00000003987", "ENSG00000003989", 
"ENSG00000004059", "ENSG00000004139", "ENSG00000004142", "ENSG00000004399", 
"ENSG00000285989", "ENSG00000285990", "ENSG00000285991", "ENSG00000285992", 
"ENSG00000285993", "ENSG00000285994"), class = "factor"), expr = c(6L, 
754L, 447L, 426L, 5L, 1L)), row.names = c(NA, 6L), class = "data.frame")

        gene_id         expr
           <fct>       <int>
1   ENSG00000000005     6
2   ENSG00000000419     754
3   ENSG00000000457     447
4   ENSG00000000460     426
5   ENSG00000000938     5
6   ENSG00000000971     1

数据集的标题：

structure(list(gene_id = structure(6:11, .Label = c("__alignment_not_unique", 
"__ambiguous", "__no_feature", "__not_aligned", "__too_low_aQual", 
"ENSG00000000005", "ENSG00000000419", "ENSG00000000457", "ENSG00000000460", 
"ENSG00000000938", "ENSG00000000971", "ENSG00000001036", "ENSG00000001084", 
"ENSG00000001167", "ENSG00000001460", "ENSG00000001461", "ENSG00000001497", 
"ENSG00000001561", "ENSG00000001617", "ENSG00000001626", "ENSG00000001629", 
"ENSG00000001630", "ENSG00000001631", "ENSG00000002016", "ENSG00000002079", 
"ENSG00000002330", "ENSG00000002549", "ENSG00000002586", "ENSG00000002587", 
"ENSG00000002726", "ENSG00000002745", "ENSG00000002746", "ENSG00000002822", 
"ENSG00000002834", "ENSG00000002919", "ENSG00000002933", "ENSG00000003056", 
"ENSG00000003096", "ENSG00000003137", "ENSG00000003147", "ENSG00000003249", 
"ENSG00000003393", "ENSG00000003400", "ENSG00000003402", "ENSG00000003436", 
"ENSG00000003509", "ENSG00000003756", "ENSG00000003987", "ENSG00000003989", 
"ENSG00000004059", "ENSG00000004139", "ENSG00000004142", "ENSG00000004399", 
"ENSG00000285989", "ENSG00000285990", "ENSG00000285991", "ENSG00000285992", 
"ENSG00000285993", "ENSG00000285994"), class = "factor"), expr = c(6L, 
754L, 447L, 426L, 5L, 1L)), row.names = c(NA, 6L), class = "data.frame")

        gene_id         expr
           <fct>       <int>
1   ENSG00000000005     6
2   ENSG00000000419     754
3   ENSG00000000457     447
4   ENSG00000000460     426
5   ENSG00000000938     5
6   ENSG00000000971     1

我明白了：

第二次审判：

dat$family <- substr(as.character(dat$gene_id), 1, nchar(as.character(dat$gene_id))-2)
boxplot(expr ~ family, data = dat, horizontal = TRUE, las = 2)

dat$family
dat%
htmltools:：browsable（）


您可以对此进行更多配置，但这只是一个开始。我建议您阅读
kableExtra
的小插曲，尤其是（或），因为它们展示了一些较新的闪影功能。
对不起@r2evans，我正在阅读您关于编辑的评论，我正在尝试修复它，我很抱歉，我正在尝试及时回复。不用担心，只是指出它，很抱歉，如果它被认为是恼火的或不愉快的，我感谢你的支持，如果你仍然想编辑这个问题，请继续，我不会更改它。我尝试了这个@r2evans
par（mar=c（5,12,2,2））条形图（df1$expr，names.arg=df1$gene_id，horiz=TRUE，las=1）
我用你的代码和我得到的图更新了这个问题。这些是针对两个基因的吗？我只想尝试两种基因。我还在学习。我能不能用ID的最后一个数字来制作“假家庭”，并根据其中任何一个数字创建两个方框图，即xxx419 xxx457 xxx460-->将全部归为“400”家庭，依此类推？我更新了问题@r2evans，这是我的错误，我剪切了数据的顶部和底部并粘贴了它们，谢谢你的提示，关于你的答案，我是新来的，我怎么知道我只比较了两个基因？数据有58734行，包括冗余，我试图删除冗余，但运气不好，冗余以双下划线“\uuuuu”开头