本期内容为[跟着NC学作图]--散点图

文章题目：

感兴趣的可以自己去看！

1. 导入数据，文章中的代码是比较复杂的，那么我自己就使用画图前的数据。

> nb_Omicron_Delta
sample  nb_Delta  nb_Omicron  ratio_Delta  ratio_Omicron  ID  proto  ext  Delta  Coinf
22PlCoInf-MIDV2xEMAGx0x100_S373  0  47  0  1  22PlCoInf-MIDV2xEMAGx0x100  MIDNIGHT V2  EMAG  0  FALSE
22PlCoInf-MIDV2xEMAGx100x0_S384  25  0  1  0  22PlCoInf-MIDV2xEMAGx100x0  MIDNIGHT V2  EMAG  100  FALSE
22PlCoInf-MIDV2xEMAGx10x90_S374  24  47  0.96  1  22PlCoInf-MIDV2xEMAGx10x90  MIDNIGHT V2  EMAG  10  TRUE
22PlCoInf-MIDV2xEMAGx20x80_S375  25  46  1  0.978723404  22PlCoInf-MIDV2xEMAGx20x80  MIDNIGHT V2  EMAG  20  TRUE
22PlCoInf-MIDV2xEMAGx30x70_S376  25  44  1  0.936170213  22PlCoInf-MIDV2xEMAGx30x70  MIDNIGHT V2  EMAG  30  TRUE
22PlCoInf-MIDV2xEMAGx40x60_S377  25  44  1  0.936170213  22PlCoInf-MIDV2xEMAGx40x60  MIDNIGHT V2  EMAG  40  TRUE

sample  nb_Delta  nb_Omicron  ratio_Delta  ratio_Omicron  ID  proto  ext  Delta  Coinf  median_Delta  IQR_Delta  median_Omicron  IQR_Omicron
22PlCoInf-MIDV2xEMAGx0x100_S373  0  47  0  1  22PlCoInf-MIDV2xEMAGx0x100  MIDNIGHT V2  EMAG  0  FALSE  0  0  99  1.5
22PlCoInf-MIDV2xEMAGx100x0_S384  25  0  1  0  22PlCoInf-MIDV2xEMAGx100x0  MIDNIGHT V2  EMAG  100  FALSE  99  0  0  0
22PlCoInf-MIDV2xEMAGx10x90_S374  24  47  0.96  1  22PlCoInf-MIDV2xEMAGx10x90  MIDNIGHT V2  EMAG  10  TRUE  33  11.5  64  10
22PlCoInf-MIDV2xEMAGx20x80_S375  25  46  1  0.978723404  22PlCoInf-MIDV2xEMAGx20x80  MIDNIGHT V2  EMAG  20  TRUE  53  12  43.5  18
22PlCoInf-MIDV2xEMAGx30x70_S376  25  44  1  0.936170213  22PlCoInf-MIDV2xEMAGx30x70  MIDNIGHT V2  EMAG  30  TRUE  67  13  29.5  13.25
22PlCoInf-MIDV2xEMAGx40x60_S377  25  44  1  0.936170213  22PlCoInf-MIDV2xEMAGx40x60  MIDNIGHT V2  EMAG  40  TRUE  70  10  26  10.5
22PlCoInf-MIDV2xEMAGx50x50_S378  25  46  1  0.978723404  22PlCoInf-MIDV2xEMAGx50x50  MIDNIGHT V2  EMAG  50  TRUE  78  5  18.5  8.75

2. Plot A

nb_Omicron_Delta$Delta = as.numeric(nb_Omicron_Delta$Delta)
p1 <- ggplot(data=nb_Omicron_Delta, aes(x=ratio_Omicron, y=ratio_Delta ,colour=Delta)) 

p1 <-  p1 +
    geom_point(aes(colour=Delta,shape=Coinf),alpha=0.9) +
    facet_grid(.~proto) + 
    ylab("Delta-specific mutations detection rate") + xlab("Omicron-specific mutations detection rate") +
    scale_color_gradient2(low = "steelblue1", mid = "cyan4", high = "tomato",
      breaks=c(0,10,20,30,40,50,60,70,80,90,100), midpoint = 50,
      name = "Delta:Omicron", labels = c("0:100","10:90","20:80", "30:70","40:60","50:50","60:40","70:30", "80:20","90:10","100:0")) +
    scale_shape(name = "Experimental\nCoinfection") +
    geom_vline(xintercept = 0.25,linetype =  "dotted", alpha = 0.5, inherit.aes = FALSE) +
    geom_hline(yintercept = 0.90,linetype =  "dotted", alpha = 0.5, inherit.aes = FALSE) +
    theme_bw() 

3. Plot B

p2 <- ggplot(data=table_MAF, aes(x=Delta, y=median_Delta)) 

p2 <-  p2 +
    geom_smooth(color="grey", fill="grey", linetype="blank") +
    geom_point(aes(colour=Delta,shape=Coinf)) +
    facet_grid(.~proto) + 
    ylab("Measured Frequency (%)") + xlab("Expected Frequency (%)") +
    geom_abline(intercept = 0, slope = 1,linetype =  "dotted", alpha = 0.5, inherit.aes = FALSE) +
    scale_color_gradient2(low = "steelblue1", mid = "cyan4", high = "tomato",
      breaks=c(0,10,20,30,40,50,60,70,80,90,100), midpoint = 50,
      name = "Delta:Omicron", labels = c("0:100","10:90","20:80", "30:70","40:60","50:50","60:40","70:30", "80:20","90:10","100:0")) +
    scale_shape(name = "Experimental\nCoinfection") +
    theme_bw()

4. Plot C

plot_AF_fig1C <- function(vcf_file,annot_file, ncol=11) {
  require(data.table)
  library(ggplot2)

  annot=annot_file

  ##########################
  ### annotate vcf
  ##########################
  vcf=vcf_file
  
  vcf$VOC <- sapply(vcf$nt_mut, function(x) ifelse(is.element(x,annot$nt_mut),annot$var[x==annot$nt_mut],NA)) ## For each variant, determine whether it is Delta- or OMICRON-specific

  vcf$proto = sapply(vcf$ID , function(x) strsplit(x,"x")[[1]][1])
  vcf$proto = gsub("MID","MIDNIGHT ",vcf$proto)
  vcf$proto = gsub("V4","ARTIC V4",vcf$proto)
  vcf$proto = gsub("V41","V4.1",vcf$proto)
  vcf$proto = gsub("MIDNIGHT $","MIDNIGHT V1",vcf$proto)
  vcf$proto = factor(vcf$proto,levels=c("MIDNIGHT V1","MIDNIGHT V2","ARTIC V4","ARTIC V4.1"))

  ########## plot AF bars of DELTA-specific and/or OMICRON-specific mutations
  vcfDO = vcf[!is.na(vcf$VOC),]

  # Plot
  p <- ggplot(data=vcfDO, aes(x=nt_pos, y=af, group = sample )) 

  p <- p +
    geom_bar(aes(fill = VOC), stat="identity") + 
    geom_point(data=vcfDO[vcfDO$af>50,], aes(x=nt_pos, y=af, group = sample,color = VOC),size=1,alpha=0.8)+
    facet_wrap(.~proto, ncol=ncol) + 
    ylab("Mutation frequency (%)") + xlab("Nucleotide position") +
    scale_color_manual(values=c("tomato","darkgrey","steelblue1"),name = "Mutations in\nconsensus", labels = c("Delta-specific", "shared", "Omicron-specific")) +
    scale_fill_manual(values=c("tomato","darkgrey","steelblue1"),name = "Mutations", labels = c("Delta-specific", "shared", "Omicron-specific")) +
    geom_hline(yintercept = 50,linetype =  "dotted", alpha = 0.5, inherit.aes = FALSE) +
    theme_bw() + theme( axis.text.x  = element_text(angle=45, size=8,hjust =1, vjust=1)) +
    theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank())

  return(p)
  
}

5. 合并图

plot_grid(p1, p2,p3, ncol = 1,labels = c("A","B","C"), align = 'v',axis = "rl",rel_heights=c(1,1,1.1))
ggsave("Fig1.pdf",width = 10 ,height=9 )
ggsave("Fig1.png",width = 10 ,height=9)

往期文章（总汇）
01-[R语言可视化-精美图形绘制系列]--精美火山图
02-R语言可视化-精美图形绘制系列--柱状图
03-R语言可视化-精美图形绘制系列--功能富集分析
04-R语言可视化-精美图形绘制系列—多组GO富集可视化
05-[R语言可视化-精美图形绘制系列--堆积图]
06-[R语言可视化-精美图形绘制系列--组间相关性分析]
07-[R语言可视化-精美图形绘制系列]--Mental分析
08-[R语言可视化-精美图形绘制系列--复杂热图+两图渐变连线]-【转载】
09-[R语言可视化-精美图形绘制系列--桑基图（Sankey）]
10-[R语言可视化-精美图形绘制系列--柱状图误差线标记]
11-跟着NC学作图 | 柱状图与相关性图
12-[R语言可视化-精美图形绘制系列--GO、KEGG富集通路关联图]
13-[跟着“基迪奥生物学”作图]--截断图
14-[R语言可视化-精美图形绘制系列]--显著性箱线图
14-2[R语言可视化]--箱线图不同的画法及参数设置 | 学习笔记
15-[R语言可视化-精美图形绘制系列]--组内相关性分析
16-[R语言可视化-精美图形绘制系列]--主成分分析（PCA）
017-[跟着NC学作图]--箱线图（一个函数获得Mean、SD、P值）
019-[跟着NC学作图]--生存分析（Survival analysis）