RNAlyzer--novel approach for quality analysis of RNA structural models

Abstract

The continuously increasing amount of RNA sequence and experimentally determined 3D structure data drives the development of computational methods supporting exploration of these data. Contemporary functional analysis of RNA molecules, such as ribozymes or riboswitches, covers various issues, among which tertiary structure modeling becomes more and more important. A growing number of tools to model and predict RNA structure calls for an evaluation of these tools and the quality of outcomes their produce. Thus, the development of reliable methods designed to meet this need is relevant in the context of RNA tertiary structure analysis and can highly influence the quality and usefulness of RNA tertiary structure prediction in the nearest future. Here, we present RNAlyzer-a computational method for comparison of RNA 3D models with the reference structure and for discrimination between the correct and incorrect models. Our approach is based on the idea of local neighborhood, defined as a set of atoms included in the sphere centered around a user-defined atom. A unique feature of the RNAlyzer is the simultaneous visualization of the model-reference structure distance at different levels of detail, from the individual residues to the entire molecules.

Figure 1.

(a) Input data defined by the user: the reference structure (green), the model (red), the center atom of the sphere, vector of radii, level of accuracy—positions of all atoms or only the selected atom type of a particular nucleotide will be considered. (b) The sphere is built based on a selected atom of every residue from the reference structure; the radius can be set by the user (e.g. 6 Å—left, 18 Å—right picture). (c) The reference structure atoms for the selected sphere are recognized, corresponding atoms from the model are identified, both sets are superimposed, and RMSD is calculated. (d) Spheres are built based on a selected type of atom for every nucleotide in the reference structure, and the process from (c) is repeated (reference structure: RNA Puzzles Problem 3, model: Dokholyan_model_2 (23)).

Figure 2.

Secondary and tertiary structure of a reference molecule for Problem_3 from the RNAPuzzles challenge (23).

Figure 3.

Multi-model plot for Problem_3; each plot (A–E) represents results for a different sphere radius (3, 8, 20, 38 and 300 Å). X-axis represents the order of nucleotides in the sequence, Y-axis represents the RMSD.

Figure 4.

RMSD averaged plot; X-axis represents the sphere radius, Y-axis represents averaged RMSD for all spheres with fixed radius (different colors correspond to different models).

Figure 5.

2D map plot—each map corresponds to exactly one of the analyzed models (left—Chen_model_1, center—Major_model_2 and right—Das_model_3); X-axis represents the sequential order of nucleotides; Y-axis represents the sphere radius; color of the cell represents the RMSD value, following the scale presented at the bottom (blue—low RMSD and high prediction quality, red—high RMSD and low prediction quality).

Figure 6.

3D plot—analysis of three models (left—Chen_model_1, center—Major_model_2 and right—Das_model_3); X-axis represents the sequential order of nucleotides; Y-axis represents sphere radius; Z-axis represents RMSD.

Figure 7.

Cutoff plot presents a percentage of the atoms sets included in spheres with fixed radius for each considered model, which are below a selected cutoff threshold. Every curve corresponds to single model. X-axis represents sphere radius; Y-axis corresponds to percentage value. On the picture above we observe see plots for different precision values (from left to the right: 4 Å, 7 Å and 10 Å) for radius of the sphere equal to 24 Å (each predicted model is represented by a different color).

Figure 8.

Visualization of structural fragments where the prediction model is inconsistent with the reference structure (from the top: Chen_model_1, Major_model_2 and Das_model_3). From left to right: multiple model 1D plot, 3D structure (reference structure is presented in green; model is presented in red).

Figure 9.

Problem 1—Multi-model plot (left)—prediction errors for all models are indicated in two regions. RMSD averaged plot (center)—for low sphere radius Bujnicki_model_1 is the best; different colors correspond to different models. Cutoff (right) plot shows impressive local accuracy of Das_model_3 (precision 4 Å, sphere radius 6 Å); different colors correspond to different models.

Figure 10.

3D plot of Santalucia_model_1 (right) and Das_model_3 (left).

Figure 11.

Superposition of Das_model_4 and Dokholyan_model_1 (left) with the reference structure; Multi-model plot (right) corresponds to discussed regions (green color—reference structure, red color—globally less accurate model (Dokholyan_model_1), blue color—globally more accurate model (Das_model_4)).

Figure 12.

Problem 2—Multiple 1D plot (left)—prediction errors for all groups are indicated in several parts of the structure. RMSD averaged plot (center)—the Dokholyan_model_1 is the best for low sphere radius; different colors correspond to different models. Cutoff (right) plot shows impressive local prediction of Das_model_1 (precision 3 Å, sphere radius 7 Å); different colors correspond to different models.

Figure 13.

3D plots of Bujnicki_model_1 (left), Das_model_1 (center) and Dokholyan_model_1 (right).

Figure 14.

Superposition of Bujnicki_model_2 and Santalucia_model_1 (left) with reference structure; Multi-model plot (right) corresponds to discussed regions (green color—reference structure, red color—globally less accurate model (Santalucia_model_1), blue color—globally more accurate model (Bujnicki_model_2)).

Figure 15.

Problem_3—Multi-model plot (left)—prediction errors for all groups are indicated in several regions. RMSD averaged plot (right)—for low sphere radius values, Chen_model_1 is the best; different colors correspond to different models.

Figure 16.

Cutoff plot illustrates outstanding local prediction of Chen_model_1 (precision 4 Å, sphere radius 6 Å); different colors correspond to different models.

Figure 17.

3D plot of Chen_model_1 (left) and Das_model_1 (right).

Figure 18.

Superposition of Bujnicki_model_1 and Das_model_4 (left) with reference structure; Multi-model plot (right) corresponds to discussed regions (green color—reference structure, red color—globally less accurate model (Das_model_4), blue color—globally more accurate model (Bujnicki_model_1)).