Structurama: bayesian inference of population structure

Abstract

Structurama is a program for inferring population structure. Specifically, the program calculates the posterior probability of assigning individuals to different populations. The program takes as input a file containing the allelic information at some number of loci sampled from a collection of individuals. After reading a data file into computer memory, Structurama uses a Gibbs algorithm to sample assignments of individuals to populations. The program implements four different models: The number of populations can be considered fixed or a random variable with a Dirichlet process prior; moreover, the genotypes of the individuals in the analysis can be considered to come from a single population (no admixture) or as coming from several different populations (admixture). The output is a file of partitions of individuals to populations that were sampled by the Markov chain Monte Carlo algorithm. The partitions are sampled in proportion to their posterior probabilities. The program implements a number of ways to summarize the sampled partitions, including calculation of the 'mean' partition-a partition of the individuals to populations that minimizes the squared distance to the sampled partitions.

Keywords: Bayesian estimaion; Dirichlet Process Prior; Markov chain Monte Carlo; population structure.