只需2步！用ChatGPT打造CNS级精美图表

用户11203141

发布于 2025-03-06 10:50:46

6600

代码可运行

文章被收录于专栏：天意云&天意科研云&天意生信云天意云&天意科研云&天意生信云

运行总次数：0

代码可运行

各位科研小伙伴，是不是经常遇到这样的情况：看到论文里一个超级赞的图，结果作者既没有标明图的类型，也没提供相应的代码？只能干瞪眼，到处求源代码

接下来，小编就要教你一招绝活。利用ChatGPT的识图编程能力，轻松写出图表代码，并且直接绘制出精美的科研数据图表。

从此科研绘图不求人！

参考文献图表

我们以这篇发表近期在ScienceDirect的文献为例

源文献地址:https://doi.org/10.1016/j.jare.2024.06.027

识图-代码生成

我们来复现这篇文献中的图A

对ChatGPT输入指令：

请用随机数据复现该图，包括微生物群落的系统发育树，对应序列的KO功能注释

ChatGPT开始分析输出代码....

ChatGPT输出代码

# 安装并加载必要的包
if (!requireNamespace("ggtree", quietly = TRUE)) install.packages("ggtree")
if (!requireNamespace("ape", quietly = TRUE)) install.packages("ape")
if (!requireNamespace("dplyr", quietly = TRUE)) install.packages("dplyr")
if (!requireNamespace("tidyr", quietly = TRUE)) install.packages("tidyr")
if (!requireNamespace("ggplot2", quietly = TRUE)) install.packages("ggplot2")

library(ggtree)
library(ape)
library(dplyr)
library(tidyr)
library(ggplot2)

# 随机生成系统发育树
set.seed(42)
tree <- rtree(100)  # 生成包含100个分支的随机树

# 随机生成KO功能注释
KO_annotations <- data.frame(
  label = tree$tip.label,
  ko_K00706 = sample(0:4, 100, replace = TRUE),
  ko_K01442 = sample(0:4, 100, replace = TRUE),
  ko_K07007 = sample(0:4, 100, replace = TRUE),
  ko_K15868 = sample(0:4, 100, replace = TRUE)
)

# 将KO功能注释转换为长格式
KO_long <- KO_annotations %>%
  pivot_longer(cols = starts_with("ko"), names_to = "KO", values_to = "Count")

# 绘制环状系统发育树
p_tree <- ggtree(tree, layout = "circular") +
  geom_tiplab(size = 2, aes(angle = angle))

# 绘制KO功能注释柱状图
p_bar <- ggplot(KO_long, aes(x = label, y = Count, fill = KO)) +
  geom_bar(stat = "identity", position = "dodge") +
  theme_minimal() +
  theme(axis.text.x = element_blank(), 
        axis.ticks.x = element_blank(), 
        panel.grid = element_blank()) +
  scale_fill_brewer(palette = "Set3") +
  coord_polar(theta = "x")

# 将环状树和柱状图组合在一起
library(cowplot)
plot_grid(p_tree, p_bar, ncol = 1, align = "v", rel_heights = c(2, 1))

运行结果

跟我们预期不太一致，ChatGPT分开了2张图。我们输入优化指令

代码优化

根据输出情况优化指令

添加的柱状图需要分布在环状发育树外围

ChatGPT开始优化代码....

# 安装并加载必要的包
if (!requireNamespace("ggtree", quietly = TRUE)) install.packages("ggtree")
if (!requireNamespace("ape", quietly = TRUE)) install.packages("ape")
if (!requireNamespace("dplyr", quietly = TRUE)) install.packages("dplyr")
if (!requireNamespace("tidyr", quietly = TRUE)) install.packages("tidyr")
if (!requireNamespace("ggplot2", quietly = TRUE)) install.packages("ggplot2")
if (!requireNamespace("RColorBrewer", quietly = TRUE)) install.packages("RColorBrewer")
if (!requireNamespace("patchwork", quietly = TRUE)) install.packages("patchwork")

library(ggtree)
library(ape)
library(dplyr)
library(tidyr)
library(ggplot2)
library(RColorBrewer)
library(patchwork)

# 随机生成系统发育树
set.seed(42)
tree <- rtree(100)  # 生成包含100个分支的随机树

# 随机生成KO功能注释
KO_annotations <- data.frame(
  label = tree$tip.label,
  ko_K00706 = sample(0:4, 100, replace = TRUE),
  ko_K01442 = sample(0:4, 100, replace = TRUE),
  ko_K07007 = sample(0:4, 100, replace = TRUE),
  ko_K15868 = sample(0:4, 100, replace = TRUE)
)

# 将KO功能注释转换为长格式
KO_long <- KO_annotations %>%
  pivot_longer(cols = starts_with("ko"), names_to = "KO", values_to = "Count")

# 绘制环状系统发育树
p_tree <- ggtree(tree, layout = "circular") +
  geom_tiplab(size = 2, aes(angle = angle))

# 获取树枝角度数据
angle_data <- p_tree$data %>%
  filter(isTip) %>%
  select(label, angle)

# 将角度数据加入KO注释数据中
KO_long <- KO_long %>%
  left_join(angle_data, by = "label")

# 绘制环状系统发育树
p_tree <- ggtree(tree, layout = "circular") +
  geom_tiplab(size = 2, aes(angle = angle))

# 添加KO功能注释柱状图到环状树的外围
p_bar <- ggplot(KO_long, aes(x = factor(label, levels = tree$tip.label), y = Count, fill = KO)) +
  geom_bar(stat = 'identity', position = position_dodge(width = 0.7)) +
  scale_fill_brewer(palette = "Set3") +
  coord_polar(theta = "x", start = 0) +
  theme_void() +
  theme(legend.position = "right")

# 将环状树和柱状图组合在一起
p_combined <- p_tree + inset_element(p_bar, 0, 0, 1, 1)

# 打印绘图结果
print(p_combined)

tips：ChatGPT生成代码，如果报错，直接将报错原因复制，发给ChatGPT即可，ChatGPT会重新优化代码！