Inferring evolutionary rates using serially sampled sequences from several populations

Abstract

The estimation of evolutionary rates from serially sampled sequences has recently been the focus of several studies. In this paper, we extend these analyzes to allow the estimation of a joint rate of substitution, omega, from several evolving populations from which serial samples are drawn. In the case of viruses evolving in different hosts, therapy may halt replication and therefore the accumulation of substitutions in the population. In such cases, it may be that only a proportion, p, of subjects are nonresponders who have viral populations that continue to evolve. We develop two likelihood-based procedures to jointly estimate p and omega, and empirical Bayes' tests of whether an individual should be classified as a responder or nonresponder. An example data set comprising HIV-1 partial envelope sequences from six patients on highly active antiretroviral therapy is analyzed.