散点图和直方图

生信喵

一、散点图

1. m <- read.table("prok_representative.csv",sep = ",",header = T);  
   
2. x <- m[,2]
   
3. y <- m[,4]  
   
4. plot(x,y,pch=16,xlab="Genome Size",ylab="Genes");  
   
5. fit <- lm(y~x);  
   
6. abline( fit,col="blue",lwd=1.8 );  
   
7. rr <- round( summary(fit)$adj.r.squared,2);  
   
8. intercept <- round( summary(fit)$coefficients[1],2);  
   
9. slope <- round( summary(fit)$coefficients[2],2);  
   
10. eq <- bquote( atop( "y = " * .(slope) * " x + " * .(intercept), R^2 == .(rr) ) );  
    
11. text(12,6e3,eq);

复制代码

基因组大小与基因数目相关性散点图

二、基因长度分布直方图

1. #基因长度分布图
   
2. x <- read.table("H37Rv.gff",sep = "\t",header = F,skip = 7,quote = "")  
   
3. x <- x[x$V3=="gene",]  
   
4. # x <- x %>% dplyr::filter(V3 == 'gene')
   
5. x <- abs(x$V5-x$V4)+1  
   
6. # x <- x %>% dplyr::mutate(gene_len=abs(V5-V4)+1)
   
7. # head(x$gene_len)
   
8. length(x)  
   
9. range(x)  
   
10. hist(x)  
    
11. hist(x,breaks = 80)  
    
12. ?hist
    
13. hist(x,breaks = 'Sturges')
    
14. hist(x,breaks = c(0,500,1000,1500,2000,2500,15000))  
    
15. hist(x,breaks = 80,freq = F)  
    
16. hist(x,breaks = 80,density = T)  
    
17. hist(rivers,density = T,breaks = 10)  
    
18. ?hist  
    
19. pdf(file = 'hist.pdf')
    
20. h <- hist(x,nclass=80,col="pink",xlab="Gene Length (bp)",main="Histogram of Gene Length");  
    
21. rug(x);
    
22. xfit<-seq(min(x),max(x),length=100);
    
23. yfit<-dnorm(xfit,mean=mean(x),sd=sd(x));
    
24. yfit <- yfit*diff(h$mids[1:2])*length(x);
    
25. lines(xfit, yfit, col="blue", lwd=2);
    
26. dev.off()

复制代码

基因长度分布直方图