General Strategies for RNA X-ray Crystallography

Abstract

An extremely small proportion of the X-ray crystal structures deposited in the Protein Data Bank are of RNA or RNA-protein complexes. This is due to three main obstacles to the successful determination of RNA structure: (1) low yields of pure, properly folded RNA; (2) difficulty creating crystal contacts due to low sequence diversity; and (3) limited methods for phasing. Various approaches have been developed to address these obstacles, such as native RNA purification, engineered crystallization modules, and incorporation of proteins to assist in phasing. In this review, we will discuss these strategies and provide examples of how they are used in practice.

Keywords: RNA; X-ray crystallography; ribozyme; structural biology; structure.

Figure 1

Ribozymes for homogenous RNA end production: (A) Secondary structure of two hammerhead ribozymes connected by an RNA crystallization target. Conserved nucleotides necessary for catalysis (blue); short complements (magenta) to the 5′ and 3′ ends of the target RNA (red) must be engineered into the ribozyme sequence. Canonical base pairs in helical stems are denoted by dashes. R = G or A; H = A, U, C; N = A, U, C, G. (B) Tertiary structure of the minimal hammerhead ribozyme (PDB:300D). Color scheme matches Figure 1A. Inset shows the ribozyme active site turned upward, with catalytic residues, participating substrate residues, and metal ions labeled. (C) Secondary structure for a glmS ribozyme consisting of the target RNA (purple) and ribozyme strand (black). The G33 (blue) residue interacts with Glc6P and is required for catalysis. (D) Tertiary structure of the Bacillus anthracis glmS ribozyme (PDB:3L3C) bound to Glc6P (shown as sticks) before cleavage. Color scheme matches Figure 1C. Inset shows the ribozyme active site, with catalytic residues and participating substrate residues (shown as sticks) labeled. Hydrogen bonds between catalytic residues, substrate, and Glc6P indicated by black dashes; cleavage site indicated by arrow. Conserved G33 residue colored blue; bound Mg²⁺ shown as green spheres.

Figure 2

Tetraloop–tetraloop receptor crystallization module: (A) Phylogenetic covariation in group IIC introns. Stems and loops in red are variable regions and are amenable areas to engineer crystallization modules. (B) Interaction between the GAAA tetraloop (orange) and the 11 nt tetraloop receptor (yellow) in the O.i. group II intron (PDB:3IGI); hydrogen bonding shown by black dashes. (C) Crystal symmetry present in one unit cell from the O.i. group II intron crystal structure (PDB:3IGI). Three RNA molecules pack into one unit cell, each one colored a different color. GAAA tetraloops are colored yellow to show where they form crystal contacts between RNA molecules.

Figure 3

Protein-assisted crystallization modules: (A) Interaction between U1A (green) and a 21-nucleotide (nt) hairpin (orange) (PDB:1URN). Several residues form hydrogen bonds (black dashes) with 7 nucleotides of the 12 nt stem-loop U1A binding site in the RNA hairpin. The interaction is further stabilized by base stacking between adjacent nucleotides in the stem-loop. Participating amino acid residues are colored yellow. The hairpin sequence for engineering is also shown with interacting nucleotides (orange). (B) Interaction between ribosomal protein L7Ae and a kink-turn (PDB:4BW0). The NC helix (blue) and C helix (magenta) are shown. The bulge (orange) forms hydrophobic interactions with several residues in L7Ae (green; hydrophobic interacting gray). The consensus sequence for engineering is also shown. (C) Interaction between the Fab BL3 antibody (purple) and the GAAACAC stem-loop binding site (orange) in an in vitro evolved RNA ligase (PDB:3IVK). Several base stacking interactions and hydrogen bonds (black dashes) form between nucleotides of the stem-loop and amino acids from the Fab. Base stacking between nucleotides of the stem-loop also occurs. Participating amino acid residues are colored yellow. No engineering sequence is shown, as antibody–RNA interactions are unique for each target obtained from the phage display pool.