散点图和直方图

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

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

sx.voiceclouds.cn