Tracking marsupial evolution using archaic genomic retroposon insertions

Abstract

The Australasian and South American marsupial mammals, such as kangaroos and opossums, are the closest living relatives to placental mammals, having shared a common ancestor around 130 million years ago. The evolutionary relationships among the seven marsupial orders have, however, so far eluded resolution. In particular, the relationships between the four Australasian and three South American marsupial orders have been intensively debated since the South American order Microbiotheria was taxonomically moved into the group Australidelphia. Australidelphia is significantly supported by both molecular and morphological data and comprises the four Australasian marsupial orders and the South American order Microbiotheria, indicating a complex, ancient, biogeographic history of marsupials. However, the exact phylogenetic position of Microbiotheria within Australidelphia has yet to be resolved using either sequence or morphological data analysis. Here, we provide evidence from newly established and virtually homoplasy-free retroposon insertion markers for the basal relationships among marsupial orders. Fifty-three phylogenetically informative markers were retrieved after in silico and experimental screening of approximately 217,000 retroposon-containing loci from opossum and kangaroo. The four Australasian orders share a single origin with Microbiotheria as their closest sister group, supporting a clear divergence between South American and Australasian marsupials. In addition, the new data place the South American opossums (Didelphimorphia) as the first branch of the marsupial tree. The exhaustive computational and experimental evidence provides important insight into the evolution of retroposable elements in the marsupial genome. Placing the retroposon insertion pattern in a paleobiogeographic context indicates a single marsupial migration from South America to Australia. The now firmly established phylogeny can be used to determine the direction of genomic changes and morphological transitions within marsupials.

Figure 1. Transposition in transposition (TinT) pattern of selected marsupial SINEs.

In genomes there is an intricate association between SINE elements and the much longer long interspersed elements (LINEs), as the replication of SINEs ultimately depends on the enzymatic machinery of LINEs. Using the TinT method in marsupial genomes, we detected independent SINE-LINE associations that overlapped in time. The L1 system dominates SINE retropositions in Didelphimorphia (SINE1_Mdo, SINE1a_Mdo). The retroposon-like transposable element (RTE) system predominates in the lineage leading to the kangaroo (WALLSI1-4), and LINE2- (MIR, MdoRep1, THER1_MD) and LINE3- (MIR3) mobilized SINE systems are present in both lineages and were active over long periods of marsupial evolution. Experimental screening revealed the activities of two, sometimes three, SINE-LINE associations at some deep nodes. For instance, at least three SINE-LINE associations were active in the common ancestor of the four Australasian orders (RTE-WALLSI1a/L1-WSINE1/L2-MIR_Mars) (Figure S1). In most other mammalian genomes, only one SINE-LINE group was active at a time; thus, the discovery of multiple groups may indicate a long branch and/or overlapping activity. As several different SINE-LINE systems were also active at the Australidelphia node (RTE-Mar1a,b,c_Mdo/L1-WSINE1/RTE-WALLSI3), we favor overlapping, extended activity of retroposition systems in marsupials. The extended presence of diverse SINE transposition systems found in marsupial genomes is unique in mammals. Twenty-four SINE subfamilies were extracted from genomic data of M. domestica and M. eugenii to screen for nested insertions, revealing information about their relative activity periods. Elements shown in black denote L3-, those in blue L2-, those in green RTE-, and those in red L1-mobilized SINEs. Ovals represent the 50% probability of the activity distribution and horizontal lines indicate the 90% probability of the activity distribution. Relative time axes are given at the bottom.

Figure 2. Phylogenetic tree of marsupials derived from retroposon data.

The tree topology is based on a presence/absence retroposon matrix (Table 1) implemented in a heuristic parsimony analysis (Figure S3). The names of the seven marsupial orders are shown in red, and the icons are representative of each of the orders: Didelphimorphia, Virginia opossum; Paucituberculata, shrew opossum; Microbiotheria, monito del monte; Notoryctemorphia, marsupial mole; Dasyuromorphia, Tasmanian devil; Peramelemorphia, bilby; Diprotodontia, kangaroo. Phylogenetically informative retroposon insertions are shown as circles. Gray lines denote South American species distribution, and black lines Australasian marsupials. The cohort Australidelphia is indicated as well as the new name proposed for the four “true” Australasian orders (Euaustralidelphia).