Basic functions for marker informativeness

Humberto Reyes Valdés

Copy and paste the following script in an R console.

#Polymorfism information content

#x is a vector of allele frequencies

pic<-function(x){1-sum(x^2)-sum(x^2)^2+sum(x^4)}

#Maximum PIC for a alleles

mPIC<-function(a){(a-1)^2*(a+1)/a^3}

#Heterozygosity

#x is a vector of allele frequencies

het<-function(x){1-sum(x^2)}

#Unbiased estimation of heterozygosity

#x is a vector of allele frequencies and n is the number of sampled alleles

het.unbiased<-function(x,n){het(x)*n/(n-1)}

###############################

#Functions to calculate entropy

MyLog2p<-function(x){if(x==0) 0 else x*log(x,2)} #Defining x logx

entropy<-function(x){-sum(sapply(x,MyLog2p))} #x is a vector of probabilities