Assessment of three-dimensional RNA structure prediction in CASP15

By Rhiju Das, Rachael Kretsch, Adam J. Simpkin, Thomas Mulvaney, Phillip Pham, R. Rangan, Fan Bu, Ronan M. Keegan, Maya Topf, Daniel J. Rigden and 2 more. 2023

146 citations recorded by the source corpus.

The prediction of RNA three-dimensional structures remains an unsolved problem. Here, we report assessments of RNA structure predictions in CASP15, the first CASP exercise that involved RNA structure modeling. Forty two predictor groups submitted models for at least one of twelve RNA-containing targets. These models were evaluated by the RNA-Puzzles organizers and, separately, by a CASP-recruited team using metrics (GDT, lDDT) and approaches (Z-score rankings) initially developed for assessment of proteins and generalized here for RNA assessment. The two assessments independently ranked the same predictor groups as first (AIchemy_RNA2), second (Chen), and third (RNAPolis and GeneSilico, tied); predictions from deep learning approaches were significantly worse than these top ranked groups, which did not use deep learning. Further analyses based on direct comparison of predicted models to cryogenic electron microscopy (cryo-EM) maps and X-ray diffraction data support these rankings. With the exception of two RNA-protein complexes, models submitted by CASP15 groups correctly predicted the global fold of the RNA targets. Comparisons of CASP15 submissions to designed RNA nanostructures as well as molecular replacement trials highlight the potential utility of current RNA modeling approaches for RNA nanotechnology and structural biology, respectively. Nevertheless, challenges remain in modeling fine details such as non- canonical pairs, in ranking among submitted models, and in prediction of multiple structures resolved by cryo-EM or crystallography.

Subfields: Molecular Biology, Evaluation & Benchmarks, Computational Biology & Bioinformatics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Molecular Biology

In Evaluation & Benchmarks

In Computational Biology & Bioinformatics

Citations in the corpus

Accurate structure prediction of biomolecular interactions with AlphaFold 3 (2024, methodology): “A wide range of predictors for various specific interaction types has been developed 16–28 , as well as one generalist method developed concurrently with the present work 29 , but the accuracy of such deep-learning attempts has been mixed and often below that of physics-inspired methods 30,31 .”
Accurate RNA 3D structure prediction using a language model-based deep learning approach (2022, neutral): “35,36).”
RNA target highlights in CASP15: Evaluation of predicted models by structure providers (2023, background): “12,13 2 | RESULTS 2.1 | Human and chimpanzee cytoplasmic polyadenylation element-binding protein 3 ribozymes (CASP: R1107 and R1108, PDB: 7QR4 and 7QR3) provided by Benoît Masquida Cytoplasmic polyadenylation element-binding protein 3 (CPEB3 protein) binds CPEs of messenger (m)RNAs to regulate…”
New prediction categories in CASP15 (2023, background): “In 5 – 8 The main goal of this paper is to address technical issues of introducing the new categories in CASP and serve as a point of reference for format specifications and details on how the experiment was conducted.”
CASP15 cryo-EM protein and RNA targets: refinement and analysis using experimental maps (2023, unknown): “8,37 Despite the overall quality of predictions, some reorientation of domains and secondary structure elements was often required, particularly for RNA models.”
Boltz-1 Democratizing Biomolecular Interaction Modeling (2024, unknown): “…on two benchmarks: the diverse test set of recent PDB structures that we cured as discussed in Section 2.2, and CASP15, the last community-wide protein structure prediction competition where for the first time RNA and ligand structures were also evaluated [Das et al., 2023, Robin et al., 2023].”
Integrating end-to-end learning with deep geometrical potentials for ab initio RNA structure prediction (2022, unknown): “Although utilizing domain expert knowledge with these methods could lead to somewhat better performance in RNA-Puzzles and CASP 9,10 , their performance is often suboptimal in automated benchmark test runs, suggesting that automatic prediction of regular RNA structures remains a challenging task to…”