英文:
Add text to ggplot (add number of differentially expressed genes to MA plot)
问题
Sure, here's the translated code part without the code comments:
在MA图函数中，将显著表达的基因数量添加到图中。
MA图显示两组之间差异表达的基因，其中包括它们的折叠变化和平均表达。
我试图将不同ially表达的基因总数添加到图的右上角。而不是“硬编码”x和y坐标，更希望相对定位。
也许应该将数字添加到包含要绘制的数据的df中，而不是新的数据？任何建议都将不胜感激！
# 示例数据
set.seed(47)
gene_creator <- paste("gene", 1:100, sep="")
genes = sample(gene_creator, 8)
dex_A <- data.frame(
gene = genes,
group = "group_A",
logFC = sample(c(-5:5), replace=T, size=8),
adj.P.Val = sample(c(0.01, 1), replace=T, size=8),
AveExpr = sample(c(30:36), replace=T, size=8)
)
dex_B <- data.frame(
gene = genes,
group = "group_B",
logFC = sample(c(-5:5), replace=T, size=8),
adj.P.Val = sample(c(0.01, 1), replace=T, size=8),
AveExpr = sample(c(30:36), replace=T, size=8)
)
dex_df <- rbind(dex_A, dex_B)
# 解决方案（不起作用）
library('tidyverse')
library('ggrepel')
## 找到最小和最大的基因
minmax <- bind_rows(dex_df %>%
filter(adj.P.Val < 0.05) %>%
group_by(group) %>%
slice_max(logFC, n = 3) %>%
mutate(rank = "top5"),
dex_df %>%
filter(adj.P.Val < 0.05) %>%
group_by(group) %>%
slice_min(logFC, n = 3) %>%
mutate(rank = "min5"))
## 获取数字
numbers <- dex_df %>%
group_by(group) %>%
summarize(
n_up = sum(adj.P.Val <= 0.05 & logFC > 0.5),
n_down = -sum(adj.P.Val <= 0.05 & logFC < 0.5)
) %>%
pivot_longer(-group, names_to = "direction", values_to = "n")
# 颜色显著性
colors_sig <- c("#999999", "#0072B2", "#D55E00")
names(colors_sig) <- c("NA", "Up", "Down")
# 制作MA图
make_plot_MA <- function(dex_df, minmax, numbers, comp){
# 获取comp的最小和最大值
MINmax <- minmax %>% filter(group == comp)
# 不同ially的数字
numb4text <- numbers %>% filter(group == comp)
# 绘制
dex_df %>%
mutate(lab = ifelse(dex_df$gene %in% minmax$gene, as.character(dex_df$gene), NA)) %>%
mutate(col = ifelse(dex_df$adj.P.Val > 0.05, "NS", ifelse(logFC > 0, 'Up', 'Down'))) %>%
filter(group == comp) %>%
ggplot(aes(x = AveExpr, y = logFC, label = lab, color = col)) +
geom_point()+
geom_hline(yintercept = 0) +
xlab("Log2 mean expression") +
ylab("Log2 fold change") +
geom_label_repel(color = 'black', min.segment.length = 0) +
geom_point(data = . %>% filter(gene %in% minmax$gene), color = "black") +
ggtitle(comp) +
scale_color_manual(values = colors_sig) +
geom_text(data=numb4text, aes(x=34, y=6, label=n))
}
make_plot_MA(dex_df, MinMax, numbers, 'group_A')
I hope this helps! If you have any further questions or need additional assistance, please feel free to ask.
英文:
In a MA plot function, add the number of significantly expressed genes to the plot.
MA plots show differentially expressed genes between two groups with their fold-change and the average expression.
I am trying to add the total number of differentially expressed genes to the upper right side of the plot. Instead of "hard coding" the x and y coordinates, a reallative localisation would be prefered.
Maybe the numbers should be added to the df cotaing the data to be plotted instead of a new one? Any advise would me much appreciated!
Example data
set.seed(47)
gene_creator <- paste("gene",1:100,sep="")
genes = sample(gene_creator,8)
dex_A <- data.frame(
gene = genes,
group = "group_A",
logFC = sample(c(-5:5), replace=T, size=8),
adj.P.Val = sample(c(0.01,1), replace=T, size=8),
AveExpr = sample(c(30:36), replace=T, size=8)
)
dex_B <- data.frame(
gene = genes,
group = "group_B",
logFC = sample(c(-5:5), replace=T, size=8),
adj.P.Val = sample(c(0.01,1), replace=T, size=8),
AveExpr = sample(c(30:36), replace=T, size=8)
)
dex_df <- rbind(dex_A, dex_B)
Solution (not working)
library('tidyverse')
library('ggrepel')
## find min max genes
minmax <- bind_rows(dex_df %>%
filter(adj.P.Val < 0.05) %>%
group_by(group) %>%
slice_max(logFC, n = 3) %>%
mutate(rank = "top5"),
dex_df %>%
filter(adj.P.Val < 0.05) %>%
group_by(group) %>%
slice_min(logFC, n = 3) %>%
mutate(rank = "min5"))
## get numbers
numbers <- dex_df %>%
group_by(group) %>%
summarize(
n_up = sum(adj.P.Val <= 0.05 & logFC > 0.5),
n_down = -sum(adj.P.Val <= 0.05 & logFC < 0.5)
) %>%
pivot_longer(-group, names_to = "direction", values_to = "n")
# colors significance
colors_sig <- c("#999999", "#0072B2", "#D55E00")
names(colors_sig) <- c("NA", "Up", "Down")
# make MA plot
make_plot_MA <- function(dex_df, minmax, numbers, comp){
# get Min Max for comp
MINmax <- minmax %>% filter(group == comp)
# numbers of difEx
numb4text <- numbers %>% filter(group == comp)
# plot
dex_df %>%
mutate(lab = ifelse(dex_df$gene %in% minmax$gene, as.character(dex_df$gene), NA)) %>%
mutate(col = ifelse(dex_df$adj.P.Val > 0.05, "NS", ifelse(logFC > 0, 'Up', 'Down'))) %>%
filter(group == comp) %>%
#filter(adj.P.Val < 0.05) %>%
ggplot(aes(x = AveExpr, y = logFC, label = lab, color = col)) +
geom_point()+
geom_hline(yintercept = 0) +
xlab ("Log2 mean expression") +
ylab ("Log2 fold change") +
geom_label_repel(color = 'black', min.segment.length = 0) +
geom_point(data = . %>% filter(gene %in% minmax$gene), color = "black") +
ggtitle(comp) +
scale_color_manual(values = colors_sig) +
geom_text(data=numb4text, aes(x=34, y=6, label=n))
}
make_plot_MA(dex_df, MinMax, numbers, 'group_A')
答案1
得分: 1
Here is the translated code:
make_plot_MA <- function(dex_df, minmax, numbers, comp){
# 获取comp的最小值和最大值
MINmax <- minmax %>% filter(group == comp)
# difEx的数字
numb4text <- numbers %>% filter(group == comp)
label.up=paste("up:", numb4text$n[1])
label.down=paste("down:", numb4text$n[2])
# 画图
dex_df %>%
mutate(lab = ifelse(dex_df$gene %in% minmax$gene, as.character(dex_df$gene), NA)) %>%
mutate(col = ifelse(dex_df$adj.P.Val > 0.05, "NS", ifelse(logFC > 0, 'Up', 'Down'))) %>%
filter(group == comp) %>%
ggplot(aes(x = AveExpr, y = logFC, label = lab, color = col)) +
geom_point()+
geom_hline(yintercept = 0) +
xlab ("Log2 mean expression") +
ylab ("Log2 fold change") +
geom_label_repel(color = 'black', min.segment.length = 0) +
geom_point(data = . %>% filter(gene %in% minmax$gene), color = "black") +
ggtitle(comp) +
scale_color_manual(values = colors_sig) +
geom_text(inherit.aes = F,aes(x=max(dex_df$AveExpr), y=max(dex_df$logFC), label=label.up))+
geom_text(inherit.aes = F,aes(x=max(dex_df$AveExpr), y=max(dex_df$logFC)-1, label=label.down))
}
make_plot_MA(dex_df, minmax, numbers, 'group_A')
I've translated the code for you.
<details>
<summary>英文:</summary>
make_plot_MA <- function(dex_df, minmax, numbers, comp){
get Min Max for comp
MINmax <- minmax %>% filter(group == comp)
numbers of difEx
numb4text <- numbers %>% filter(group == comp)
label.up=paste("up:", numb4text$n1)
label.down=paste("down:", numb4text$n[2])
plot
dex_df %>%
mutate(lab = ifelse(dex_df$gene %in% minmax$gene, as.character(dex_df$gene), NA)) %>%
mutate(col = ifelse(dex_df$adj.P.Val > 0.05, "NS", ifelse(logFC > 0, 'Up', 'Down'))) %>%
filter(group == comp) %>%
#filter(adj.P.Val < 0.05) %>%
ggplot(aes(x = AveExpr, y = logFC, label = lab, color = col)) +
geom_point()+
geom_hline(yintercept = 0) +
xlab ("Log2 mean expression") +
ylab ("Log2 fold change") +
geom_label_repel(color = 'black', min.segment.length = 0) +
geom_point(data = . %>% filter(gene %in% minmax$gene), color = "black") +
ggtitle(comp) +
scale_color_manual(values = colors_sig) +
geom_text(inherit.aes = F,aes(x=max(dex_df$AveExpr), y=max(dex_df$logFC), label=label.up))+
geom_text(inherit.aes = F,aes(x=max(dex_df$AveExpr), y=max(dex_df$logFC)-1, label=label.down))
}
make_plot_MA(dex_df, minmax, numbers, 'group_A')
[![plot with labels][1]][1]
[1]: https://i.stack.imgur.com/2AsiY.png
</details>
通过集体智慧和协作来改善编程学习和解决问题的方式。致力于成为全球开发者共同参与的知识库，让每个人都能够通过互相帮助和分享经验来进步。
评论