easylabel--为散点图/火山图添加标记！

作图丫

发布于 2022-03-29 09:55:26

9250

发布于 2022-03-29 09:55:26

文章被收录于专栏：作图丫

导语

GUIDE ╲

在R语言绘图中的一个常见问题是用大量点或标签标记散点图。

背景介绍

在我们的科研中，常常遇到需要用散点图、火山图或者曼哈顿图进行数据可视化，就会碰到一个问题，在众多的点中，哪些才是我们想要找到的呢？今天小编给大家介绍的这个R包easylabel，可以轻松标记散点图以及快速绘制火山图和 MA 图以进行基因表达分析。使用交互式shiny和绘图界面，我们可以将鼠标悬停在点上以查看特定点的位置，然后单击点以轻松标记它们。还提供了一种直接导出为 PDF 以供发表的简单方法。

R包安装

install.packages("easylabel")
library(easylabel)

可视化介绍

散点图

使用 easylabel() 打开一个shiny的应用程序并绘制和标记散点图。

data(mtcars)
easylabel(mtcars, x = 'mpg', y = 'wt',
          colScheme = 'royalblue')

调整颜色

easylabel(mtcars, x = 'mpg', y = 'wt',
          col = 'cyl')

形状

# gapminder data set
if(!require(gapminder)) {install.packages("gapminder")}
library(gapminder)
easylabel(gapminder[gapminder$year == 2007, ], x = 'gdpPercap', y = 'lifeExp',
          col = 'continent', shape = 'continent',
          size = 10,
          labs = 'country', 
          zeroline = FALSE)

大小设置

library(gapminder)
easylabel(gapminder[gapminder$year == 2007, ], x = 'gdpPercap', y = 'lifeExp',
          col = 'continent', labs = 'country', 
          size = 'pop',
          alpha = 0.6,
          zeroline = FALSE)

坐标轴设置标题

easylabel(xymatrix, x = 'x', y = 'y', col = 'col',
          colScheme = c('darkgrey', 'green3', 'gold3', 'blue'),
          xlab = expression("log"[2] ~ " fold change post-Rituximab"),
          ylab = expression("log"[2] ~ " fold change post-Tocilizumab"),
          showgrid = TRUE)

火山图

示例数据

# Example DESeq2 object
head(volc1)
##               baseMean log2FoldChange     lfcSE         stat     pvalue
## 5_8S_rRNA   0.01625099     0.02726923 2.9811510  0.009147217 0.99270168
## 5S_rRNA     3.66321881     0.05989097 0.4115732  0.145517159 0.88430257
## 7SK        12.96667458    -0.46156215 1.3668722 -0.337677614 0.73560615
## A1BG      290.75694559     0.23486554 0.3514587  0.668259368 0.50396804
## A1BG-AS1  170.77906789     0.11800652 0.2001594  0.589562618 0.55548392
## A1CF        4.56855647    -1.23495475 0.4855212 -2.543565265 0.01097276
##                padj
## 5_8S_rRNA        NA
## 5S_rRNA   0.9823854
## 7SK       0.9528927
## A1BG      0.8956205
## A1BG-AS1  0.9117136
## A1CF      0.4531638

# Example limma object
head(volc2)
##               logFC  AveExpr         t      P.Value   adj.P.Val           B
## A1BG      0.7697662 6.389039  4.692064 0.0011239293 0.008610736 -1.16895727
## A1BG-AS1  0.5298897 3.610850  4.688657 0.0011293516 0.008638889 -0.85241114
## AAAS     -0.4162720 5.349529 -5.578986 0.0003398373 0.004148831  0.17585449
## AACS     -0.2049703 3.690271 -1.465073 0.1768461859 0.299064278 -5.88763988
## AAGAB     0.2970478 5.538436  5.446618 0.0004033869 0.004553688 -0.02478892
## AAK1      0.1969886 1.861988  1.286456 0.2302992497 0.362402197 -5.74356735

#MA plots
easyMAplot(volc2, useQ = TRUE)

配色方案

easyVolcano(volc2,
            useQ = TRUE,
            fccut = 0,
            main = "Volcano title")

添加左右注释

easyVolcano(volc1,
            useQ = TRUE, fullGeneNames = TRUE,
            Ltitle = expression(symbol("\254") ~ "Non-responder"),
            Rtitle = expression("Responder" ~ symbol("\256")),
            LRtitle_side = 1,
            cex.lab = 0.9, cex.axis = 0.8,
            fccut = c(1, 2), fdrcutoff = 0.2,
            ylim = c(0, 6), xlim = c(-5, 5),
            colScheme = c('darkgrey', 'blue', 'orange', 'red'))

添加标签框

# Simple outlines
easyVolcano(volc2, useQ = TRUE, fccut = 0,
            rectangles = TRUE)

# Red outlined labels, rounded ends
easyVolcano(volc2, useQ = TRUE, fullGeneNames = TRUE,
            rectangles = TRUE,
            padding = 5,
            border_radius = 10,
            line_col = 'red',
            border_col = 'red',
            text_col = 'red')

# Transparent grey rectangles, rounded ends
easyMAplot(volc2, fdrcut = c(0.05, 0.01, 0.001), size = 6, useQ = TRUE,
           alpha = 0.75, outline_col = NA,
           fullGeneNames = TRUE,
           colScheme = c('darkgrey', brewer.pal(9, 'RdYlBu')[c(7:9, 3:1)]),
           rectangles = TRUE,
           border_col = NA,
           padding = 5,
           rect_col = adjustcolor('grey', alpha.f = 0.6),
           border_radius = 20)

# White text on black background, no rounding
easyVolcano(volc2, useQ = TRUE, fullGeneNames = TRUE,
            fccut = 0,
            rectangles = TRUE,
            padding = 4,
            border_radius = 0,
            rect_col = 'black',
            text_col = 'white',
            border_col = NA)

曼哈顿图

可以使用函数 easyManhattan() 标记曼哈顿图。

# https://www.ebi.ac.uk/gwas/studies/GCST003156
library(data.table)
SLE_gwas <- fread('../bentham_2015_26502338_sle_efo0002690_1_gwas.sumstats.tsv')
# Simple Manhattan plot
easyManhattan(SLE_gwas)
# 4 colours for chromosomes
easyManhattan(SLE_gwas, chromCols = RColorBrewer::brewer.pal(4, 'Paired'))

Locus plots

# Create a locus plot over one chromosomal region
library(plotly)
p1 = easyManhattan(SLE_gwas[SLE_gwas$chrom == 6 & 
                              SLE_gwas$pos >= 28e6 & 
                              SLE_gwas$pos <= 34e6, ], 
                   output_shiny = FALSE, labs = "rsid", 
                   startLabels=c("rs115466242", "rs2853999"), 
                   npeaks = 3)
# To annotate genes in that region
source("https://raw.githubusercontent.com/KatrionaGoldmann/BioOutputs/master/R/bio_gene_locations.R")
library(ggbio)
library(gginnards)
library(ggrepel)
if (! "EnsDb.Hsapiens.v75" %in% rownames(installed.packages()))
  BiocManager::install("EnsDb.Hsapiens.v75")

p2 = bio_gene_locations(6, c(28e6, 34e6),  
                        subset_genes = c('HLA-F', 'HLA-G', 'HLA-A', 'HLA-E', 
                                         'HLA-C', 'HLA-B', 'HLA-DRA', 
                                         'HLA-DRB5', 'HLA-DRB1', 'HLA-DQA1', 
                                         'HLA-DQB1', 'HLA-DQA2', 'HLA-DQB2', 
                                         'HLA-DOB', 'HLA-DMB', 'HLA-DMA', 
                                         'HLA-DOA', 'HLA-DPA1', 'HLA-DPB1')) 

plotly::subplot(p1, p2$plotly_location %>% layout(yaxis=list(range=c(0.25, 2))), 
                shareY = T, titleX = T, margin=0.05,
                nrows=2, heights=c(0.7, 0.3))