Double-edged sword: The evolutionary consequences of the epigenetic silencing of transposable elements

Abstract

Transposable elements (TEs) are genomic parasites that selfishly replicate at the expense of host fitness. Fifty years of evolutionary studies of TEs have concentrated on the deleterious genetic effects of TEs, such as their effects on disrupting genes and regulatory sequences. However, a flurry of recent work suggests that there is another important source of TEs' harmful effects-epigenetic silencing. Host genomes typically silence TEs by the deposition of repressive epigenetic marks. While this silencing reduces the selfish replication of TEs and should benefit hosts, a picture is emerging that the epigenetic silencing of TEs triggers inadvertent spreading of repressive marks to otherwise expressed neighboring genes, ultimately jeopardizing host fitness. In this Review, we provide a long-overdue overview of the recent genome-wide evidence for the presence and prevalence of TEs' epigenetic effects, highlighting both the similarities and differences across mammals, insects, and plants. We lay out the current understanding of the functional and fitness consequences of TEs' epigenetic effects, and propose possible influences of such effects on the evolution of both hosts and TEs themselves. These unique evolutionary consequences indicate that TEs' epigenetic effect is not only a crucial component of TE biology but could also be a significant contributor to genome function and evolution.

Fig 1. Mechanisms for the epigenetic silencing of TEs in animals and plants.

To portray the similarities of the mechanism underlying TE epigenetic silencing between species, this figure only shows core proteins involved in the processes for four representative eukaryotic species. Detailed mechanisms and involved proteins could be found at other detailed reviews (e.g., [,–136]). In mammals, piRNAs are loaded onto MIWI2, which promotes a chromosomal environment that ultimately recruits the mammalian DNMT3 to methylate TE sequences [137,138]. Complementarily, KAP1, also called TRIM28, recognizes retroviral TE sequences by binding to a conserved primer binding site [139] and recruits H3K9 methyltransferase SETDB1 and HP1 to form a repressive heterochromatic environment at TE sequences [–142]. Drosophila lacks DNA methylation, but TEs can still be epigenetically silenced through histone modifications. Nascent TE transcripts are targeted by piRNA loaded PIWI, which complexes with Asterix (Arx, also known as Gtsf1) and Panoramix (Panx, also called Silencio) [–146]. This complex recruits Su(var)3-9, a key H3K9 methyltransferase, to lay down repressive H3K9me2/3 at TE sequences [147]. A similar mechanism is also observed in Schizosaccharomyces pombe, where RITSC binds to nascent TE transcripts through base-pairing with siRNAs and recruits histone methyltransferase complex to methylate H3K9 histone tails [148]. In plants, euchromatic TEs are silenced through the RdDM pathway [168]. AGO4 or AGO6 are guided by siRNA [149,150] and targeted to siRNA-matching regions through scaffolding RNA that were transcribed by Pol V [–153]. This double-stranded RNA further recruits methyltransferases DRM1 and DRM2 (homolog to the mammalian methyltransferase DNMT3 [154]), resulting in methylation of TE sequences [155,156]. AGO4, argonaute 4; DNMT3, DNA methyltransferase 3; DRM,1, domains rearranged methylase 1; KAP1,; KRAB-associated protein 1 KRAB, Krüppel-associated box; MIWI2, mouse piwi 2; pRNA, PWI-interacting RNA; RdDM, siRNA-directed DNA methylation; RITSC, RNA-induced transcriptional silencing complex; siRNA, small interfering RNA; TE, transposable element.

Fig 2. Phenotypic variation hints TEs’ epigenetic effects.

(A) In mice, an IAP retrotransposon inserted upstream of agouti locus results in ectopic transcription of the gene that was initiated within the IAP, leading to yellow fur [157]. Curiously, isogenic mice with this IAP insertion were observed to display a wide spectrum of coat color, from yellow, mixture of yellow and agouti, to agouti, which was attributed to the varying epigenetic states of the IAP element [24]. Similar observations are also abundant in plants. (B) Variegated methylation of the promoter of Dfr-B, a flower color gene, results in color streaks in morning glory, and this is associated with the presence of a nearby MuLE DNA element [25]. (C) A LINE element in the 3’ noncoding regions causes the hypermethylation of bonsai gene, which silencing the gene and leading to bonsai-like A. thaliana [26]. (D) In muskmelon (Cucumis melo), the sex determination of flowers is associated with an insertion of GynohAT DNA element in the proximity to WIP1, which encodes a transcription factor that promotes male flower development. The presence of the TE leads to hypermethylation of WIP1 and thus female flowers [27]. IAP, intracisternal A-particle; LINE, long interspersed nuclear elements; TE, transposable element.

Fig 3. Impacts of the epistatic interactions among TEs’ deleterious effects on TEs’ population dynamics.

(A) Three possible models for the interactions among TEs’ deleterious effects: additive (green), multiplicative (blue), and synergistic (orange) models (reviewed in [54]). (B) The per-generation change in TE copy number (Δn) under these models when the transposition rate of TEs holds constant. Theories predict that Δn is determined by the rate of TE replication (increases copy number) and the rate of changes in host fitness (decreases copy number by selection against TEs’ deleterious effects) [69]. Additive model: When the deleterious effects of TEs are independent, host fitness is determined by summing the effects of individual TE in the host genome. In this case, host fitness declines linearly with respect to TE copy number (green in A), and the rate of fitness change with every additional TE holds constant (the slope of green line in A). Unless the rate of fitness change is exactly the same as the rate of increase in TE copy number through transposition, no equilibrium could be reached (B left panel). On the contrary, with epistatic interactions among TEs’ deleterious effects (multiplicative or synergistic), the relationship between host fitness and TE copy number is nonlinear, and equilibrium in TE copy number is possible. Multiplicative model: The deleterious effects of TEs weaken with each additional TE in a host genome (blue in A), and the rate of fitness change decreases with increased TE copy number (slope of blue line in A). While TE copy number could reach equilibrium (i.e., when Δn = 0, B middle panel), this equilibrium is unstable. A slight decrease in TE copy number leads to an even faster decline in TE copy number (arrow [1]) while a slight increase has the opposite effects (arrow [2], B middle panel). Synergistic model: Each additional TE imposes a larger fitness cost than the last TE, and the rate of fitness change escalates with more TEs in a host genome (slope of orange line in A), which accelerates the removal of TEs from the population. A stable equilibrium is possible because slight perturbations always lead back to the equilibrium (arrow [3] and [4], B right panel). TE, transposable element.