如何在R中绘制Z分数

Question

我有一张表格，其中有不同样本的归一化分数。我计算了z值和需要创建的情节如下图所示：

我的表如下所示：

Gene_name E_2401_ctrl_1 E_2401_ctrl_2 E_2401_ctrl_3 E_2401_drt_1 E_2401_drt_2 LOC_Os01g01312 1.601736731 0.310548148 1.238589942 -0.899941148 -0.980640435 LOC_Os01g01360 -0.850254449 -0.420792594 0.083358279 0.86759297 0.102030534 LOC_Os01g01390 0.40382069 -0.377555928 -0.009849284 -0.285629267 0.219967368 LOC_Os01g01610 -1.102507436 -0.90329537 -0.458899223 1.042853272 0.904937227 LOC_Os01g01620 -0.806239145 -1.190898502 -0.229250108 0.812535653 1.004865332

我有近3000个基因和50个样本。因此，在Excel中绘图不是一种选择。

Answer 1

从数据创建数据帧：

df <- data.frame(Gene_name = c("E_2401_ctrl_1", "E_2401_ctrl_2", "E_2401_ctrl_3", "E_2401_drt_1", "E_2401_drt_2"), 
       LOC_Os01g01312 = c(1.601736731, 0.310548148, 1.238589942, -0.899941148, -0.980640435), 
       LOC_Os01g01360 = c(-0.850254449, -0.420792594, 0.083358279, 0.86759297, 0.102030534), 
       LOC_Os01g01390 = c(0.40382069 , -0.377555928, -0.009849284, -0.285629267, 0.219967368), 
       LOC_Os01g01610 = c(-1.102507436, -0.90329537, -0.458899223, 1.042853272, 0.904937227), 
       LOC_Os01g01620 = c(-0.806239145, -1.190898502, -0.229250108, 0.812535653, 1.004865332)) 

library(ggplot2) 
library(reshape2) 

为ggplot重塑长格式是个好主意

df_melt <- reshape2::melt(df, id.vars = "Gene_name") 

检查数据现在看起来如何

head(df_melt, 10) 

基因名称在一列中，并且相应的z分数在另一列中

ggplot(data = df_melt)+ 
     geom_line(aes(x = variable, y = value, group = Gene_name))+ 
     theme(axis.text.x = element_text(angle = 45, hjust = 1))+ 
     xlab("gene")+ 
     ylab("") 

如何读取：

ggplot(data = df_melt) 

既然你想连接值的行指定，从中可以得出的情节

geom_line(aes(x = variable, y = value, group = Gene_name)) 

geom_line数据。在ggplot中，所有变量都在aes（）内部。

theme(axis.text.x = element_text(angle = 45, hjust = 1))+ 
    xlab("")+ 
    ylab("z-score") 

剩下的只是化妆

，如果你想刻面图，添加一个变量，通过它会突间

df_melt <- data.frame(rbind(df_melt, df_melt), 
    letters=rep(c("A", "B"), each = nrow(df_melt))) 

在这里，我只是重复数据帧两次，

rbind(df_melt, df_melt) 

以及第一个标有“A”和第二个标有“B”的行。

letters=rep(c("A", "B"), each = nrow(df_melt)) 
df_melt 

现在你可以用“字母”变小面

ggplot(data = df_melt)+ 
    geom_line(aes(x = variable, y = value, group = Gene_name))+ 
    theme(axis.text.x = element_text(angle = 45, hjust = 1))+ 
    xlab("gene")+ 
    ylab("z-score")+ 
    facet_wrap(~letters, ncol = 1) 

编辑：类群标签可以通过添加颜色=变量参数的AES（着色），您需要彩色的GEOM内调用。我会从一开始启动：

df <- data.frame(Gene_name = c("E_2401_ctrl_1", "E_2401_ctrl_2", "E_2401_ctrl_3", "E_2401_drt_1", "E_2401_drt_2"), 
       LOC_Os01g01312 = c(1.601736731, 0.310548148, 1.238589942, -0.899941148, -0.980640435), 
       LOC_Os01g01360 = c(-0.850254449, -0.420792594, 0.083358279, 0.86759297, 0.102030534), 
       LOC_Os01g01390 = c(0.40382069 , -0.377555928, -0.009849284, -0.285629267, 0.219967368), 
       LOC_Os01g01610 = c(-1.102507436, -0.90329537, -0.458899223, 1.042853272, 0.904937227), 
       LOC_Os01g01620 = c(-0.806239145, -1.190898502, -0.229250108, 0.812535653, 1.004865332)) 

df_melt <- reshape2::melt(df, id.vars = "Gene_name") 

#the ifelse() part makes another column called "lett" where if it is a "crtl" gene will be "A" and "B" if not 

df_melt <- data.frame(rbind(df_melt, df_melt), 
         lett = ifelse(grepl("ctrl", df_melt$Gene_name), "A", "B")) 


ggplot(data = df_melt)+ 
    geom_line(aes(x = variable, y = value,group = Gene_name, color=lett))+ 
    theme(axis.text.x = element_text(angle = 45, hjust = 1))+ 
    xlab("gene")+ 
    ylab("z-score")+ 
    scale_color_manual(values=c("A" = "red", "B" = "blue")) 

更多的控制颜色：

http://ggplot2.tidyverse.org/reference/scale_manual.html http://ggplot2.tidyverse.org/reference/scale_brewer.html