Role of APOBEC3 in genetic diversity among endogenous murine leukemia viruses

Abstract

The ability of human and murine APOBECs (specifically, APOBEC3) to inhibit infecting retroviruses and retrotransposition of some mobile elements is becoming established. Less clear is the effect that they have had on the establishment of the endogenous proviruses resident in the human and mouse genomes. We used the mouse genome sequence to study diversity and genetic traits of nonecotropic murine leukemia viruses (polytropic [Pmv], modified polytropic [Mpmv], and xenotropic [Xmv] subgroups), the best-characterized large set of recently integrated proviruses. We identified 49 proviruses. In phylogenetic analyses, Pmvs and Mpmvs were monophyletic, whereas Xmvs were divided into several clades, implying a greater number of replication cycles between the integration events. Four distinct primer binding site types (Pro, Gln1, Gln2 and Thr) were dispersed within the phylogeny, indicating frequent mispriming. We analyzed the frequency and context of G-to-A mutations for the role of mA3 in formation of these proviruses. In the Pmv and Mpmv (but not Xmv) groups, mutations attributable to mA3 constituted a large fraction of the total. A significant number of nonsense mutations suggests the absence of purifying selection following mutation. A strong bias of G-to-A relative to C-to-T changes was seen, implying a strand specificity that can only have occurred prior to integration. The optimal sequence context of G-to-A mutations, TTC, was consistent with mA3. At least in the Pmv group, a significant 5' to 3' gradient of G-to-A mutations was consistent with mA3 editing. Altogether, our results for the first time suggest mA3 editing immediately preceding the integration event that led to retroviral endogenization, contributing to inactivation of infectivity.

Figure 1. Phylogenetic Reconstruction of Nonecotropic MLV Proviruses in the C57BL/6J Genome

A maximum likelihood analysis of codon adjusted internal region ORFs (gag, pol, and env) of nonecotropic MLVs and related reference sequences is shown. Bootstrap supports >60% are shown next to branch nodes. The Pmv and Mpmv proviruses are monophyletic and group separately from each other, while the Xmv proviruses form three clades, marked A, B, and C. The ecotropic endogenous provirus Emv 2 (MLV Eco), and the exogenous virus MoMLV are also included as outgroups, as is the Xmv-like retrovirus (HuXmv) recently described in human prostate cancer [50]. tRNA primer types inferred from the PBS sequences are noted by the symbols next to sequence names.

Figure 2. Mutation Dstribution within Endogenous Nonecotropic MLV Genes

G-to-A mutation frequencies relative to total G nucleotides in the consensus sequence of each subgroup are compared to C-to-T mutations relative to total C nucleotides in the consensus sequence of each subgroup, as are frequencies of G-to-A mutations leading to synonymous and nonsynonymous changes relative to possible consensus G nucleotides, and to fractions of all G-to-A mutations that introduce stop codons in the coding region of (A) Pmv, (B) Mpmv, and (C) Xmv. (D) shows the genome totals for each group. Significance levels for the comparisons shown by brackets were calculated using the Wilcoxon matched-pairs signed-ranks test, a nonparametric alternative to the more commonly used paired Student's t-test, favored for normally distributed data.

Figure 3. Preference Sequences for G-to-A Mutations

Upper panels: (−) DNA nucleotide frequencies are plotted relative to expected frequencies for each of ten positions up- and downstream of the putative mA3 deamination targets for each group of proviruses. Lower panels: Significance (negative Log₁₀ p-value, χ² tests with 3 degrees of freedom) of the deviations from expected frequencies is plotted for each position.

Figure 4. Gradients of G-to-A Mutations in Endogenous Nonecotropic MLVs

(A) The provirus sequences between the primer sites from the BLAST alignment of each subgroup were divided into ten equal bins and fractions of observed G-to-A mutations relative to the number of G nucleotides within consensus sequences were pooled for each bin and plotted cumulatively 5′ to 3′ for (B) Pmv, (C) Mpmv, and (D) Xmv. Plots were normalized for direct comparison. The total numbers of mutations analyzed for each plot are presented next to the names in each legend. The same numbers of mutations were used in the two simulation models (equal and skewed random models) and plotted (open symbols) next to the observed data for each subgroup.

Figure 5. G and A Nucleotide Compositions of Nonecotropic Proviruses

The frequency of A is plotted against the frequency of G in the indicated proviruses. Filled symbols represent consensuses for each group. One Pmv and one Mpmv provirus, indicated with names, were “hypermutated.” Two Xmv proviruses with long branch lengths (Figure 1) that do not show G-to-A hypermutation are also marked.