Non-LTR retrotransposons encode noncanonical RRM domains in their first open reading frame

Abstract

Non-LTR retrotransposons (NLRs) are a unique class of mobile genetic elements that have significant impact on the evolution of eukaryotic genomes. However, the molecular details and functions of their encoded proteins, in particular of the accessory ORF1p proteins, are poorly understood. Here, we identify noncanonical RNA-recognition-motifs (RRMs) in several phylogenetically unrelated NLR ORF1p proteins. This provides an explanation for their RNA-binding properties and clearly shows that they are not related to the retroviral nucleocapsid protein Gag, despite the frequent presence of CCHC zinc knuckles. In particular, we characterize the ORF1p protein of the human long interspersed nuclear element 1 (LINE-1 or L1). We show that L1ORF1p is a multidomain protein, consisting of a coiled coil (cc), RRM, and C-terminal domain (CTD). Most importantly, we solved the crystal structure of the RRM domain, which is characterized by extended loops stabilized by unique salt bridges. Furthermore, we demonstrate that L1ORF1p trimerizes via its N-terminal cc domain, and we suggest that this property is functionally important for all homologues. The formation of distinct complexes with single-stranded nucleic acids requires the presence of the RRM and CTD domains on the same polypeptide chain as well as their close cooperation. Finally, the phylogenetic analysis of mammalian L1ORF1p shows an ancient origin of the RRM domain and supports a modular evolution of NLRs.

Fig. 1.

Identification and organization of RRM domains in phylogenetically unrelated NLR-ORF1p proteins. Type I ORF1p is widespread and contains Gag-like CCHC zinc-knuckles. Type II ORF1p is found in the human L1 element and trimerizes via a coiled coil (cc). Other types are described in the main text (see also Tables S1 and S2). CTD, C-terminal domain; PHD, plant homeodomain; ES, esterase domain. Some domains may not always be present (dotted outlines).

Fig. 2.

Phylogenetic conservation of mammalian-type L1 ORF1p. Structure-based sequence alignments of the RRM (L1O1-RRM, top) and CTD (L1O1-CTD, bottom) domains show highly conserved residues boxed in red. Surface residues only conserved in placental mammals (group I) or only outside of placental mammals (group II) are boxed separately. Residues forming the conserved salt bridges are shaded in blue. Residues providing aromatic, RNA-binding side-chains in canonical RRMs are shaded in yellow. Triangles mark residues mutated in this study with a strong (red), moderate (orange) or negligible (green) effect on RNA-binding. Additional motifs mutated in a previous study (14) are shaded in gray. The C-terminal sequences of Sp and Nv cannot be confidently aligned to the mammalian-type CTD domain. Gene identifiers: Hs, Homo sapiens (gi:307098); Mm, Mus musculus (gi:198644); Cf, Canis familiaris (gi:116175029); Bt, Bos taurus (gi:66734172); Ss, Sus scrofa (gi:148645275); Me, Macropus eugenii (gi:151302550); Xt, Xenopus tropicalis (gi:85740540); Ol, Oryzias latipes (gi:3746501), Sp, Strongylocentrotus purpuratus (gi:111740418); Nv, Nematostella vectensis (gi:149338150).

Fig. 3.

Domain structure and trimerization of human L1 ORF1p. (A) Schematic organization of the monomer into the coiled-coil (cc), RRM (M) and CTD (C) domains. Heptad repeats in the cc-domain are indicated. The unconserved part of the protein is in gray, the positions of the trimerization motifs are indicated red. (B) Trimeric state of the full-length protein analyzed by size-exclusion chromatography (r_H ≈ 75 Å) and MALLS (M_r = 120 kDa). (Inset) Schematic representation of the trimer adapted from (22).

Fig. 4.

Nucleic acid-binding properties of human L1 ORF1p. Size exclusion chromatography was done with various nucleic acid substrates (red lines) in the absence (dashed lines) or in the presence (solid lines) of protein (blue solid lines). Elution volumes of the complexes and of the free components are indicated by arrows and dashed gray lines, while apparent concentrations are calculated from the relative absorption properties of the components. M, hL1ORF1p-M; C, hL1ORF1p-C; MC, hL1ORF1p-MC; AluRNA, SA86 (46).

Fig. 5.

Crystal structure of the RRM domain of human L1 ORF1p. (A) Ribbons representation with α-helices in yellow and β-strands in green. The side chains forming the conserved salt-bridges are shown as sticks (blue). (B) Localization of mutated side-chains. The RRM (Left) and CTD (Right) domains are shown as ribbons with selected side chains as sticks (for colors see triangles in Fig. 2; asterisks: aromatic side chain in canonical RRMs; murine CTD (PDB-ID 2jrb (24)) shown with human amino acid numbers). (C) Electrostatic potential mapped on the molecular surface of the RRM domain (pI = 10.6). Potentials are contoured from −10 kT/e (red) to + 10 kT/e (blue). (Left) View as in A, onto the surface of the β-sheet and the adjacent loop L(β2-β3). (Right) Backside view, 180° from (A). (D) Surface colored by sequence conservation. Sequence similarity among placental mammals (Fig. 2, group I) is color-ramped : white (50% or less) to orange (100%). All three-dimensional representations are done with PyMOL (http://www.pymol.org).