Specificity and nonspecificity in RNA-protein interactions

Abstract

To fully understand the regulation of gene expression, it is critical to quantitatively define whether and how RNA-binding proteins (RBPs) discriminate between alternative binding sites in RNAs. Here, we describe new methods that measure protein binding to large numbers of RNA variants, and ways to analyse and interpret data obtained by these approaches, including affinity distributions and free energy landscapes. We discuss how the new methodologies and the associated concepts enable the development of inclusive, quantitative models for RNA-protein interactions that transcend the traditional binary classification of RBPs as either specific or nonspecific.

Figure 1. The major classes of eukaryotic RNAs

For each class of RNA, the approximate length, number of different species and abundance are indicated. For more detailed information see REF. . (i) The length of mRNAs reflects mature, processed mRNAs; the number of mRNA species refers to putative mRNA coding genes. (ii) long non coding RNAs (lncRNA) include all RNAs that do not explicitly belong to another RNA class, and exceed 200 nt in length. (iii) 7SLRNA refers to the RNA component of the signal recognition particle (SRP). (iv) piRNAs are expressed only at specific stages of germ cell development, and are not included in calculations of cellular RNA abundances.

Figure 2. RBP affinity distributions

(a) Ranked affinities for an RBP with a binding site of 6 nucleotides (C5 from E. coli) to all RNA variants . The numbers on the left indicate the nucleotide position in the binding site. (b) Histogram of relative affinities (log scale) for the sequence variants shown in panel (a). Relative affinities are calculated in relation to a standard variant, which can be chosen freely . “Specific” RNA variants are marked by the asterisk and cluster in the high affinity region of the distribution and produce a binding consensus sequence (motif), shown as a logo underneath the plot. The remainder of the distribution consists of “non-specific” RNA variants, which do not produce a consensus motif.

Figure 3. RBP binding models

(a) Position Weight Matrix (PWM). The structure denotes a hypothetical RNA binding site with six nucleotides. The plot (colored dots) depicts the score (linear coefficient) for each base at each position. The score is calculated from affinity distribution such as this shown in Figure 2(b). The score for each base corresponds to the contribution of the indicated nucleotide at each position to the overall binding free energy. (b) Binding model considering interactions between two bases (Pairwise Interaction Matrix - PIM, or Dinucleotide Weight Matrix - DWM). The structure denotes a hypothetical RNA binding site with six nucleotides, lines show the possible pairwise (energetic) couplings between two nucleotides. Colored fields correspond to the score for each of the 16 pairwise nucleotide permutation at each two positions. Scores are calculated from affinity distribution such as this shown in Figure 2(b). A yellow field (denoting a high score) indicates that a given nucleotide combination promotes binding (that is, increases the overall PWM score). A blue field (low score) indicates inhibition of binding by a given nucleotide combination. A black field indicates no significant contribution either way.

Figure 4. Strategies to increase or decrease intrinsic specificity of RBPs

(a) Change in binding site size with additive contributions by added nucleotides to binding energy. For a hypothetical RBP, additional nucleotides in a binding site would shift the affinity distribution towards higher affinities, but would not necessarily broaden the affinity distribution and thus not increase inherent specificity. (b) Change in binding site size with contributions of pairwise energetic couplings by added nucleotides. For a hypothetical RBP, hypothetical pairwise couplings by additional nucleotides in the binding site could strongly favor a small number of nucleotide combinations, thereby broaden the affinity distribution and thus greatly increase inherent specificity. (c) Increase or decrease in intrinsic specificity through multiple RBDs. Multiple RBDs (RBD1 and RBD2) can be part of the same protein or of separate proteins (left). The panels on the right show ranked affinity distributions (according to the same sequences for both RBDs) for each RDB. The panels in row three show the ranked affinity distribution upon combination of both RBDs, and the corresponding histogram of this ranked affinity distribution, color coded as indicated. Inherent protein specificity can be increased by additive specificities of the RBDs or decreased by compensatory specificities. Intrinsic specificities for individual RBDs can vary. Note, however, that binding preferences of individual RBDs do not need to be strictly additive, but can be synergistic, either through interactions between the RBDs or through cooperative binding of multiple several proteins.