Background selection theory overestimates effective population size for high mutation rates

Abstract

Background selection describes the reduction in neutral diversity caused by selection against deleterious alleles at other loci. It is typically assumed that the purging of deleterious alleles affects linked neutral variants, and indeed simulations typically only treat a genomic window. However, background selection at unlinked loci also depresses neutral diversity. In agreement with previous analytical approximations, in our simulations of a human-like genome with a realistically high genome-wide deleterious mutation rate, the effects of unlinked background selection exceed those of linked background selection. Background selection reduces neutral genetic diversity by a factor that is independent of census population size. Outside of genic regions, the strength of background selection increases with the mean selection coefficient, contradicting the linked theory but in agreement with the unlinked theory. Neutral diversity within genic regions is fairly independent of the strength of selection. Deleterious genetic load among haploid individuals is underdispersed, indicating non-independent evolution of deleterious mutations. Empirical evidence for underdispersion was previously interpreted as evidence for global epistasis, but we recover it from a non-epistatic model. SIGNIFICANCEAs individuals bearing deleterious alleles are removed from a population, other alleles are removed with them, some that are tightly linked near the deleterious allele on a chromosome and some that arent linked at all. When the deleterious mutation rate is realistically high, unlinked pairs of loci are a more important influence on the removal of genetic variation. Simulations that assume independent evolution cannot capture removal just by using a lower "effective population size", because the probabilities of having deleterious alleles on different chromosomes are negatively correlated rather than independent.