Critical assessment of RNA and DNA structure predictions via Artificial Intelligence: the imitation game

Published

March 30, 2025

Author(s)

Christina Bergonzo, Alexander Grishaev

Abstract

Computational predictions of biomolecular structure via artificial intelligence (AI) based approaches, as exemplified by AlphaFold software, have the potential to model of all life's biomolecules. We performed oligonucleotide structure prediction and gauged the accuracy of the AI-generated models via their agreement with experimental solution-state observables. We find parts of these models in good agreement with experimental data, and others falling short of the ground truth. The latter include internal or capping loops, non-canonical base pairings, and regions involving conformational flexibility, all essential for RNA folding, interactions, and function. We estimate root-mean-square (r.m.s.) errors in predicted nucleotide bond vector orientations ranging between 7 ⁰ and 30 ⁰, with higher accuracies for simpler architectures of individual canonically-paired helical stems. These mixed results highlight the necessity of experimental validation of AI-based oligonucleotide model predictions and their current tendency to mimic the training dataset rather than reproduce the underlying reality.

Citation

Journal of Chemical Information and Modeling

Pub Type

Journals

Download Paper

https://doi.org/10.1021/acs.jcim.5c00245

Local Download

Keywords

RNA structure, AlphaFold, artificial intelligence, AI, NMR, RDC

Citation

Bergonzo, C. and Grishaev, A. (2025), Critical assessment of RNA and DNA structure predictions via Artificial Intelligence: the imitation game, Journal of Chemical Information and Modeling, [online], https://doi.org/10.1021/acs.jcim.5c00245, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=958615 (Accessed April 19, 2025)