0

我有用于时间过程实验（6 个时间点）的 RNAseq 数据，涉及数万个基因。我已经使用 Tidyverse 上的 Filter 程序来查找符合某些标准的基因（qPCR 的参考基因），但我不知道如何轻松地将这些数据制作成图形。现在，我必须完全改变数据集的格式，但这需要很长时间才不切实际。

目标只是为每个基因绘制一个图表，显示每个条件下表达随时间的变化（不同的叶对和干旱/充分浇水）。我已经在 Excel 中为某些人完成了此操作，但想要一种更快的方法来完成此操作。

数据集是这样设置的：

[1] "gene.id"                    "LP1.2.02:00.WW"             "LP1.2.02:00.WW_1"           "LP1.2.02:00.WW_2"          
 [5] "LP1.2.06:00.WW"             "LP1.2.06:00.WW_1"           "LP1.2.06:00.WW_2"           "LP1.2.10:00.WW"            
 [9] "LP1.2.10:00.WW_1"           "LP1.2.10:00.WW_2"           "LP1.2.14:00.WW"             "LP1.2.14:00.WW_1"          
[13] "LP1.2.14:00.WW_2"           "LP1.2.18:00.WW"             "LP1.2.18:00.WW_1"           "LP1.2.18:00.WW_2"          
[17] "LP1.2.22:00.WW"             "LP1.2.22:00.WW_1"           "LP1.2.22:00.WW_2"           "LP3.4.5.02:00.WW"          
[21] "LP3.4.5.02:00.WW_1"         "LP3.4.5.02:00.WW_2"         "LP3.4.5.06:00.WW"           "LP3.4.5.06:00.WW_1"        
[25] "LP3.4.5.06:00.WW_2"         "LP3.4.5.10:00.WW"           "LP3.4.5.10:00.WW_1"         "LP3.4.5.10:00.WW_2"        
[29] "LP3.4.5.14:00.WW"           "LP3.4.5.14:00.WW_1"         "LP3.4.5.14:00.WW_2"         "LP3.4.5.18:00.WW"          
[33] "LP3.4.5.18:00.WW_1"         "LP3.4.5.18:00.WW_2"         "LP3.4.5.22:00.WW"           "LP3.4.5.22:00.WW_1"        
[37] "LP3.4.5.22:00.WW_2"         "LP1.2.02:00.Drought"        "LP1.2.02:00.Drought_1"      "LP1.2.02:00.Drought_2"     
[41] "LP1.2.06:00.Drought"        "LP1.2.06:00.Drought_1"      "LP1.2.06:00.Drought_2"      "LP1.2.10:00.Drought"       
[45] "LP1.2.10:00.Drought_1"      "LP1.2.10:00.Drought_2"      "LP1.2.14:00.Drought"        "LP1.2.14:00.Drought_1"     
[49] "LP1.2.14:00.Drought_2"      "LP1.2.18:00.Drought"        "LP1.2.18:00.Drought_1"      "LP1.2.18:00.Drought_2"     
[53] "LP1.2.22:00.Drought"        "LP1.2.22:00.Drought_1"      "LP1.2.22:00.Drought_2"      "LP3.4.5.02:00.Drought"     
[57] "LP3.4.5.02:00.Drought_1"    "LP3.4.5.02:00.Drought_2"    "LP3.4.5.06:00.Drought"      "LP3.4.5.06:00.Drought_1"   
[61] "LP3.4.5.06:00.Drought_2"    "LP3.4.5.10:00.Drought"      "LP3.4.5.10:00.Drought_1"    "LP3.4.5.10:00.Drought_2"   
[65] "LP3.4.5.14:00.Drought"      "LP3.4.5.14:00.Drought_1"    "LP3.4.5.14:00.Drought_2"    "LP3.4.5.18:00.Drought"     
[69] "LP3.4.5.18:00.Drought_1"    "LP3.4.5.18:00.Drought_2"    "LP3.4.5.22:00.Drought."     "LP3.4.5.22:00.Drought"     
[73] "LP3.4.5.22:00.Drought_1"    "X74"                        "LP1.2.02:00.WW.mean"        "LP1.2.06:00.WW.mean"       
[77] "LP1.2.10:00.WW.mean"        "LP1.2.14:00.WW.mean"        "LP1.2.18:00.WW.mean"        "LP1.2.22:00.WW.mean"       
[81] "LP1.2.02:00.drought.mean"   "LP1.2.06:00.drought.mean"   "LP1.2.10:00.drought.mean"   "LP1.2.14:00.drought.mean"  
[85] "LP1.2.18:00.drought.mean"   "LP1.2.22:00.drought.mean"   "LP3.4.5.02:00.WW.mean"      "LP3.4.5.06:00.WW.mean"     
[89] "LP3.4.5.10:00.WW.mean"      "LP3.4.5.14:00.WW.mean"      "LP3.4.5.18:00.WW.mean"      "LP3.4.5.22:00.WW.mean"     
[93] "LP3.4.5.02:00.drought.mean" "LP3.4.5.06:00.drought.mean" "LP3.4.5.10:00.drought.mean" "LP3.4.5.14:00.drought.mean"
[97] "LP3.4.5.18:00.drought.mean" "LP3.4.5.22:00.drought.mean"

它有很多标题，从标题中可以看出，它们包含时间、叶子对和条件。所以，我不确定如何将其转换为 x~y 图。

我有几个想法，包括尝试将条件划分为不同的子集（LP1.2. WW/LP.1.2.D/LP3.4.5.WW/LP.3.4.5.D）并为时间制作一个子集（02： 00、06:00 等）并尝试为此制作图表。

#make subset for the time points 
    Time <- c("02:00", "06:00", "10:00", "14:00", "18:00", "22:00")


#make subsets for each condition (LP1.2. WW/ LP.1.2.D/LP3.4.5.WW/LP.3.4.5.D)
    LP1.2.WW.mean <- as.matrix(KG_graph_data[c( "LP1.2.02:00.WW.mean",
                      "LP1.2.06:00.WW.mean",
                      "LP1.2.10:00.WW.mean", 
                      "LP1.2.14:00.WW.mean", 
                      "LP1.2.18:00.WW.mean",
                      "LP1.2.22:00.WW.mean",
                      "gene.id")])
    LP.1.2.D.mean <- 
    as.matrix(KG_graph_data[c("LP1.2.02:00.drought.mean",
                                       "LP1.2.06:00.drought.mean",
                                       "LP1.2.10:00.drought.mean",
                                       "LP1.2.14:00.drought.mean",
                                       "LP1.2.18:00.drought.mean",
                                       "LP1.2.22:00.drought.mean",
                                       "gene.id")])
    LP345.WW.mean <- as.matrix((KG_graph_data[c("LP3.4.5.02:00.WW.mean",
                                        "LP3.4.5.06:00.WW.mean",
                                        "LP3.4.5.10:00.WW.mean",
                                        "LP3.4.5.14:00.WW.mean",
                                        "LP3.4.5.18:00.WW.mean",
                                        "LP3.4.5.22:00.WW.mean",
                                        "gene.id")]))
    LP345.D.mean <- 
   as.matrix(KG_graph_data[c("LP3.4.5.02:00.drought.mean",
                                      "LP3.4.5.06:00.drought.mean",
                                      "LP3.4.5.10:00.drought.mean",
                                      "LP3.4.5.14:00.drought.mean",
                                      "LP3.4.5.18:00.drought.mean",
                                      "LP3.4.5.22:00.drought.mean",
                                      "gene.id")])

我尝试从每个矩阵中提取一个特定的基因，然后可能从中绘制一个图表，但它仅在它来自一个矩阵时才有效，即使那样，该表也不包含数据。

Total_KgGene007565 <- subset(LP1.2.WW.mean, "gene.id"=="KgGene007565",
                         LP.1.2.D.mean, "gene.id"=="KgGene007565",
                         LP345.WW.mean, "gene.id"=="KgGene007565",
                         LP345.D.mean, "gene.id"="KgGene007565")

我不确定如何从这里开始，或者这是否是解决此问题的错误方法。

4

0 回答 0