Deep-Learning Predictions of Biomolecular Structures: Persistent Limitations and New Horizons Extended by Explicit Ion Addition
Year: 2026
Type: article
Abstract: The advent of deep-learning-driven tools such as AlphaFold has revolutionized the prediction of biomolecular structures, offering unprecedented accuracy and accessibility for proteins, RNA, and their complexes. While these tools have demonstrated remarkable success in benchmarking competitions and enabled experimentalists to generate models with ease, their widespread use has also highlighted persistent challenges. These include difficulties in assessing model confidence, limitations in predicting transmembrane domains, nucleic acids, conformational diversity, and interactions with ions or ligands, as well as the tendency to misfold intrinsically disordered regions (IDRs). In this perspective, we critically evaluate the strengths and limitations of current AI-based structure prediction tools through illustrative examples with a particular emphasis on the impact of explicit ion modeling. We notably report that the explicit addition of a few potassium cations to the prediction of IDRs or G-quadruplexes can substantially shift AF3’s predicted conformation compared to “dry” predictions. On this basis, we suggest modeling sequences both “dry” and in the presence of explicit potassium cations as a simple, practical way to sample alternative conformations and to expose disordered regions that current predictors tend to overfold. We discuss the importance of reporting confidence metrics in publications to avoid overinterpretation. Furthermore, we address the unique challenges of RNA structure prediction, where data scarcity and structural complexity limit the performance of both classical and deep learning methods. Our analysis underscores the need for continued methodological advancements, integration of complementary computational tools, and expansion of high-quality experimental data sets.
Institutions: Centre National de la Recherche Scientifique, Université Paris Cité, Institut de Biologie Physico-Chimique, Inserm, Université Paris Sciences et Lettres, Université Paris-Saclay, Chimie et Modélisation pour la Biologie du Cancer, Institut Curie, Laboratoire Analyse et Modélisation pour la Biologie et l'Environnement, CY Cergy Paris Université
Language: English
Subfield: Molecular Biology
Domain: Life Sciences
Open Access status: green
Funder: Agence Nationale de la Recherche
Awards: Interactive Pharmacophore using Augmented Reality, Superoxide Production by Transmembrane Electron Transfer, Combining Magnetic Resonance strategies and computational modelling to decipher the dynamics of the disordered microtubule-associated protein Tau, Structure, Assembly and Biophysical Properties of Mitofusins, Divide&Connect: Building up cell-cell continuity during plant cell division, Centre d'analyse de systèmes complexes dans les environnements complexes, Dynamique des membranes transductrices d'énergie : biogénèse et organisation supramoléculaire.
OpenAlex ID: W7171448118
