作者：白介素2
相關(guān)閱讀：
ggpubr-專為學(xué)術(shù)繪圖而生（二）
ggstatsplot-專為學(xué)術(shù)繪圖而生(一)
R語(yǔ)言生存分析-02-ggforest
R語(yǔ)言生存分析-01
生存曲線
R語(yǔ)言GEO數(shù)據(jù)挖掘01-數(shù)據(jù)下載及提取表達(dá)矩陣
R語(yǔ)言GEO數(shù)據(jù)挖掘02-解決GEO數(shù)據(jù)中的多個(gè)探針對(duì)應(yīng)一個(gè)基因
R語(yǔ)言GEO數(shù)據(jù)挖掘03-limma分析差異基因
R語(yǔ)言GEO數(shù)據(jù)挖掘04-功能富集分析
如果沒有時(shí)間精力學(xué)習(xí)代碼，推薦了解：零代碼數(shù)據(jù)挖掘課程
ggpubr-專為學(xué)術(shù)繪圖而生(二)
由Hadley Wickham創(chuàng)建的ggplot2非常好用的可視化包了，但是由ggplot2繪制的圖形通常不能直接用于發(fā)表，還需要經(jīng)過一定程度的編輯，對(duì)于不少那么會(huì)編程的研究人員而言可能并不是特別友好。
因此，ggpubr應(yīng)運(yùn)而生，它提供了簡(jiǎn)單易用的函數(shù)，用于繪制定制的高質(zhì)量圖，可以直接用于發(fā)表。
以下演示官方教程：
Sys.setlocale('LC_ALL','C')
library(ggpubr)
set.seed(1234)
wdata = data.frame(
sex = factor(rep(c("F", "M"), each=200)),
weight = c(rnorm(200, 55), rnorm(200, 58)))
dim(wdata)
head(wdata, 4)
#> sex weight
#> 1 F 53.79293
#> 2 F 55.27743
#> 3 F 56.08444
#> 4 F 52.65430
density plot-ggdensity
color設(shè)置輪廓顏色,fill填充顏色設(shè)置
palette 顏色設(shè)置
ggdensity(wdata, x = "weight",
add = "mean", rug = TRUE,
color = "sex",fill = "sex",
palette = c("#00AFBB", "#E7B800"))
頻數(shù)分布圖
gghistogram
gghistogram(wdata, x = "weight",
add = "mean", rug = TRUE,
color = "sex", fill = "sex",
palette = c("#00AFBB", "#E7B800"))
箱線圖與小提琴圖
# Load data
data("ToothGrowth")
df <- ToothGrowth
head(df, 4)
#> len supp dose
#> 1 4.2 VC 0.5
#> 2 11.5 VC 0.5
#> 3 7.3 VC 0.5
#> 4 5.8 VC 0.5
p <- ggboxplot(df, x = "dose", y = "len",
color = "dose", palette =c("#00AFBB", "#E7B800", "#FC4E07"),
add = "jitter", shape = "dose")
p
my_comparisons：指定比較方式和Pvaue
stat_compare_means增加global pvalue
# Add p-values comparing groups
# Specify the comparisons you want
my_comparisons <- list( c("0.5", "1"), c("1", "2"), c("0.5", "2") )
p + stat_compare_means(comparisons = my_comparisons)+ # Add pairwise comparisons p-value
stat_compare_means(label.y = 50)
含有boxplot的小提琴圖-ggviolin
label="p.signif"以星號(hào)展示pvalue
add="boxplot"在小提琴中增加箱線圖
ggviolin(df, x = "dose", y = "len", fill = "dose",
palette = c("#00AFBB", "#E7B800", "#FC4E07"),
add = "boxplot", add.params = list(fill = "white"))+
stat_compare_means(comparisons = my_comparisons, label = "p.signif")+ # Add significance levels
stat_compare_means(label.y = 50)
柱狀圖
data("mtcars")
dfm <- mtcars
# 將cyl轉(zhuǎn)換為因子
dfm$cyl <- as.factor(dfm$cyl)
# Add the name colums
dfm$name <- rownames(dfm)
# Inspect the data
head(dfm[, c("name", "wt", "mpg", "cyl")])
#> name wt mpg cyl
#> Mazda RX4 Mazda RX4 2.620 21.0 6
#> Mazda RX4 Wag Mazda RX4 Wag 2.875 21.0 6
#> Datsun 710 Datsun 710 2.320 22.8 4
#> Hornet 4 Drive Hornet 4 Drive 3.215 21.4 6
#> Hornet Sportabout Hornet Sportabout 3.440 18.7 8
#> Valiant Valiant 3.460 18.1 6
對(duì)barplot排序
按顏色填充時(shí),并不會(huì)按分組來排序，只會(huì)進(jìn)行整體排序
ggbarplot(dfm, x = "name", y = "mpg",
fill = "cyl", # 按cyl填充顏色
color = "white", # 柱子的邊界顏色設(shè)置
palette = "jco", # jco雜志的顏色板
sort.val = "desc", # 降序排列
sort.by.groups = FALSE, # 不按分組排序
x.text.angle = 90 # x軸字體旋轉(zhuǎn)90度
)
按分組降序排列
sort.by.groups=TRUE 參數(shù)
這個(gè)比較適用于繪制GO的富集情況
ggbarplot(dfm, x = "name", y = "mpg",
fill = "cyl", # change fill color by cyl
color = "white", # Set bar border colors to white
palette = "jco", # jco journal color palett. see ?ggpar
sort.val = "asc", # Sort the value in dscending order
sort.by.groups = TRUE, # 按分組內(nèi)進(jìn)行排序
x.text.angle = 90 # Rotate vertically x axis texts
)
偏差圖-deviation plot
deviation plot會(huì)展示定量數(shù)值偏差一個(gè)參考值的，相當(dāng)于對(duì)數(shù)據(jù)進(jìn)行中心化的處理
以下繪制mpg的z-score，這個(gè)過程比較簡(jiǎn)單，換上自己的數(shù)據(jù)計(jì)算即可
#計(jì)算mpg的zscore
dfm$mpg_z <- (dfm$mpg -mean(dfm$mpg))/sd(dfm$mpg)
#按zscore分為high, low兩組
dfm$mpg_grp <- factor(ifelse(dfm$mpg_z < 0, "low", "high"),
levels = c("low", "high"))
# Inspect the data
head(dfm[, c("name", "wt", "mpg", "mpg_z", "mpg_grp", "cyl")])
#> name wt mpg mpg_z mpg_grp cyl
#> Mazda RX4 Mazda RX4 2.620 21.0 0.1508848 high 6
#> Mazda RX4 Wag Mazda RX4 Wag 2.875 21.0 0.1508848 high 6
#> Datsun 710 Datsun 710 2.320 22.8 0.4495434 high 4
#> Hornet 4 Drive Hornet 4 Drive 3.215 21.4 0.2172534 high 6
#> Hornet Sportabout Hornet Sportabout 3.440 18.7 -0.2307345 low 8
#> Valiant Valiant 3.460 18.1 -0.3302874 low 6
創(chuàng)建一個(gè)根據(jù)mpg的值排序的barplot
ggbarplot(dfm, x = "name", y = "mpg_z",
fill = "mpg_grp", # 根據(jù)mpg值的高低填充
color = "white", # Set bar border colors to white
palette = "jco", # jco journal color palett. see ?ggpar
sort.val = "asc", # 升序排列
sort.by.groups = FALSE, # Don't sort inside each group
x.text.angle = 90, # Rotate vertically x axis texts
ylab = "MPG z-score", # y軸名稱
xlab = FALSE, #x軸名稱
legend.title = "MPG Group" # 圖注名稱
)
旋轉(zhuǎn)圖形
ggtheme參數(shù)設(shè)置主題
rotate=TRUE參數(shù)設(shè)置圖形旋轉(zhuǎn)
ggbarplot(dfm, x = "name", y = "mpg_z",
fill = "mpg_grp", # change fill color by mpg_level
color = "white", # Set bar border colors to white
palette = "jco", # jco journal color palett. see ?ggpar
sort.val = "desc", # Sort the value in descending order
sort.by.groups = FALSE, # Don't sort inside each group
x.text.angle = 90, # Rotate vertically x axis texts
ylab = "MPG z-score",
legend.title = "MPG Group",
rotate = TRUE,
ggtheme = theme_minimal()
)
點(diǎn)圖
Lollipop chart-棒棒糖圖
棒棒糖圖比較適用于有大量值需要可視化的情況
ggdotchart函數(shù)
add="segments"增加從0到點(diǎn)的棒子
ggdotchart(dfm, x = "name", y = "mpg",
color = "cyl", # Color by groups
palette = c("#00AFBB", "#E7B800", "#FC4E07"), # Custom color palette
sorting = "ascending", # 升序排列
add = "segments", # 增加棒棒
ggtheme = theme_pubr() # ggplot2 theme
)
1.降序 sorting = “descending”.
2.垂直旋轉(zhuǎn) rotate = TRUE.
3.按分組排序 group = “cyl”.
4.改變點(diǎn)的大小，dot.soze=6.
- mpg值作為標(biāo)簽 label = “mpg” or label = round(dfm$mpg).
ggdotchart(dfm, x = "name", y = "mpg",
color = "cyl", # 按分組改變顏色
palette = c("#00AFBB", "#E7B800", "#FC4E07"), # 顏色
sorting = "descending", # 降序
add = "segments", # 增加棒棒
rotate = TRUE, # 旋轉(zhuǎn)
group = "cyl", # 按分組排序
dot.size = 6, # 調(diào)整點(diǎn)大小
label = round(dfm$mpg), # 增加值作為標(biāo)簽
font.label = list(color = "white", size = 9,
vjust = 0.5), # 調(diào)整標(biāo)簽
ggtheme = theme_pubr() # 主題
)
Deviation graph
Use y = “mpg_z” 計(jì)算zscore
改變棒棒的顏色和大小 add.params = list(color = “l(fā)ightgray”, size = 2)
ggdotchart(dfm, x = "name", y = "mpg_z",
color = "cyl", # Color by groups
palette = c("#00AFBB", "#E7B800", "#FC4E07"), # Custom color palette
sorting = "descending", # Sort value in descending order
add = "segments", # Add segments from y = 0 to dots
add.params = list(color = "lightgray", size = 2), # Change segment color and size
group = "cyl", # Order by groups
dot.size = 6, # Large dot size
label = round(dfm$mpg_z,1), # Add mpg values as dot labels
font.label = list(color = "white", size = 9,
vjust = 0.5), # Adjust label parameters
ggtheme = theme_pubr() # ggplot2 theme
)+
geom_hline(yintercept = 0, linetype = 2, color = "lightgray")
Cleveland 點(diǎn)圖
文字顏色也按分組調(diào)整 y.text.col=TRUE
ggdotchart(dfm, x = "name", y = "mpg",
color = "cyl", # Color by groups
palette = c("#00AFBB", "#E7B800", "#FC4E07"), # Custom color palette
sorting = "descending", # Sort value in descending order
rotate = TRUE, # Rotate vertically
dot.size = 2, # Large dot size
y.text.col = TRUE, # y軸文字的顏色
ggtheme = theme_pubr() # ggplot2 theme
)+
theme_cleveland()
用簡(jiǎn)單的函數(shù)即可對(duì)圖形進(jìn)行高度的定制，熟悉這些參數(shù)，然后調(diào)整自己的數(shù)據(jù)格式，繪制各種高級(jí)的圖，R真是包羅萬(wàn)象
參考資料
本期內(nèi)容就到這里，我是白介素2，下期再見
