1 曼哈顿图

https://r-graph-gallery.com/101_Manhattan_plot.html

1.1 基本

# Load the library
library(qqman)

gwasResults %>% head()

# Make the Manhattan plot on the gwasResults dataset
manhattan(gwasResults, chr="CHR", bp="BP", snp="SNP", p="P" )

snpsOfInterest
manhattan(gwasResults, highlight = snpsOfInterest)

# 注释
manhattan(gwasResults, annotatePval = 0.01)

qq(gwasResults$P)

1.2 使用 ggplot2 高度可定制

don <- gwasResults %>% 
  
  # Compute chromosome size
  group_by(CHR) %>% 
  summarise(chr_len=max(BP)) %>% 
  
  # Calculate cumulative position of each chromosome
  mutate(tot=cumsum(chr_len)-chr_len) %>%
  select(-chr_len) %>%
  
  # Add this info to the initial dataset
  left_join(gwasResults, ., by=c("CHR"="CHR")) %>%
  
  # Add a cumulative position of each SNP
  arrange(CHR, BP) %>%
  mutate( BPcum=BP+tot)

axisdf = don %>%
  group_by(CHR) %>%
  summarize(center=( max(BPcum) + min(BPcum) ) / 2 )

ggplot(don, aes(x=BPcum, y=-log10(P))) +
    
    # Show all points
    geom_point( aes(color=as.factor(CHR)), alpha=0.8, size=1.3) +
    scale_color_manual(values = rep(c("grey", "skyblue"), 22 )) +
    
    # custom X axis:
    scale_x_continuous( label = axisdf$CHR, breaks= axisdf$center ) +
    scale_y_continuous(expand = c(0, 0) ) +     # remove space between plot area and x axis
  
    # Custom the theme:
    theme_bw() +
    theme( 
      legend.position="none",
      panel.border = element_blank(),
      panel.grid.major.x = element_blank(),
      panel.grid.minor.x = element_blank()
    )

# List of SNPs to highlight are in the snpsOfInterest object
# We will use ggrepel for the annotation
library(ggrepel)

# Prepare the dataset
don <- gwasResults %>% 
  
  # Compute chromosome size
  group_by(CHR) %>% 
  summarise(chr_len=max(BP)) %>% 
  
  # Calculate cumulative position of each chromosome
  mutate(tot=cumsum(chr_len)-chr_len) %>%
  select(-chr_len) %>%
  
  # Add this info to the initial dataset
  left_join(gwasResults, ., by=c("CHR"="CHR")) %>%
  
  # Add a cumulative position of each SNP
  arrange(CHR, BP) %>%
  mutate( BPcum=BP+tot) %>%

  # Add highlight and annotation information
  mutate( is_highlight=ifelse(SNP %in% snpsOfInterest, "yes", "no")) %>%
  mutate( is_annotate=ifelse(-log10(P)>4, "yes", "no")) 

# Prepare X axis
axisdf <- don %>% group_by(CHR) %>% summarize(center=( max(BPcum) + min(BPcum) ) / 2 )

# Make the plot
ggplot(don, aes(x=BPcum, y=-log10(P))) +
    
    # Show all points
    geom_point( aes(color=as.factor(CHR)), alpha=0.8, size=1.3) +
    scale_color_manual(values = rep(c("grey", "skyblue"), 22 )) +
    
    # custom X axis:
    scale_x_continuous( label = axisdf$CHR, breaks= axisdf$center ) +
    scale_y_continuous(expand = c(0, 0) ) +     # remove space between plot area and x axis

    # Add highlighted points
    geom_point(data=subset(don, is_highlight=="yes"), color="orange", size=2) +
  
    # Add label using ggrepel to avoid overlapping
    geom_label_repel( data=subset(don, is_annotate=="yes"), aes(label=SNP), size=2) +

    # Custom the theme:
    theme_bw() +
    theme( 
      legend.position="none",
      panel.border = element_blank(),
      panel.grid.major.x = element_blank(),
      panel.grid.minor.x = element_blank()
    )

1.3 切换到带有 plotly 的交互式版本

gwasResults %>% 
  filter(-log10(P)>1) %>% head()

library(plotly)

# Prepare the dataset
don <- gwasResults %>% 
  
  # Compute chromosome size
  group_by(CHR) %>% 
  summarise(chr_len=max(BP)) %>% 
  
  # Calculate cumulative position of each chromosome
  mutate(tot=cumsum(chr_len)-chr_len) %>%
  select(-chr_len) %>%
  
  # Add this info to the initial dataset
  left_join(gwasResults, ., by=c("CHR"="CHR")) %>%
  
  # Add a cumulative position of each SNP
  arrange(CHR, BP) %>%
  mutate( BPcum=BP+tot) %>%

  # Add highlight and annotation information
  mutate( is_highlight=ifelse(SNP %in% snpsOfInterest, "yes", "no")) %>%

  # Filter SNP to make the plot lighter
  filter(-log10(P)>0.5)
  
# Prepare X axis
axisdf <- don %>% group_by(CHR) %>% summarize(center=( max(BPcum) + min(BPcum) ) / 2 )

# Prepare text description for each SNP:
don$text <- paste("SNP: ", don$SNP, "\nPosition: ", don$BP, "\nChromosome: ", don$CHR, "\nLOD score:", -log10(don$P) %>% round(2), "\nWhat else do you wanna know", sep="")

# Make the plot
p <- ggplot(don, aes(x=BPcum, y=-log10(P), text=text)) +
    
    # Show all points
    geom_point( aes(color=as.factor(CHR)), alpha=0.8, size=1.3) +
    scale_color_manual(values = rep(c("grey", "skyblue"), 22 )) +
    
    # custom X axis:
    scale_x_continuous( label = axisdf$CHR, breaks= axisdf$center ) +
    scale_y_continuous(expand = c(0, 0) ) +     # remove space between plot area and x axis
    ylim(0,9) +

    # Add highlighted points
    geom_point(data=subset(don, is_highlight=="yes"), color="orange", size=2) +
  
    # Custom the theme:
    theme_bw() +
    theme( 
      legend.position="none",
      panel.border = element_blank(),
      panel.grid.major.x = element_blank(),
      panel.grid.minor.x = element_blank()
    )
p = ggplotly(p, tooltip="text")
p

1.4 环形曼哈顿图

# library(CMplot)