LIMBER: A Hybrid RNA Foundation Model for Predicting and Understanding RNA Structure and Function
Preprint
Abstract
RNA foundation models offer a promising route to decoding the relationships between RNA sequence, structure and function, yet how model architecture shapes the acquisition and organization of biological information remains poorly understood. Here we introduce Layer-Interleaved Mamba-Bidirectional Encoder for RNA (LIMBER), a hybrid foundation model integrating bidirectional self-attention with selective state-space modeling, pre-trained on 40.5 million non-coding RNA sequences. With task-specific fine-tuning, LIMBER achieves leading performance on secondary-structure prediction and non-coding RNA classification benchmarks, while demonstrating strong transferability to translation-related tasks and RNA–small-molecule interaction prediction. Beyond model development, we establish a unified, task-agnostic framework to systematically evaluate and interpret the biological knowledge intrinsically acquired by RNA foundation models. This framework validates LIMBER’s strong capabilities in recovering RNA structures and predicting mutational effects, while uncovering a hierarchical, task-dependent organization of biological information across model layers. In addition, we demonstrate distinct scaling behaviors across structural, evolutionary, and functional capabilities by training and evaluating a broad panel of model variants spanning model capacity, training duration, and dataset size. Taken together, these findings establish LIMBER as a versatile RNA foundation model and provide insight into how architectural design, internal representations and scaling shape the learning of RNA sequence-structure-function relationships.Keywords
Funding Information
- startup funds provided by the University of Notre Dame
- NSF award (2607564)
This publication has 71 references indexed in Scilit:
- Machine Learning for RNA-Targeting Drug DesignJournal of Chemical Information and Modeling, 2026
- Small-Molecule Drug Discovery Targeting RNAs: Hope or Hype?Journal of Medicinal Chemistry, 2026
- Computer-aided design of RNA-targeted small molecules: A growing need in drug discoveryChem, 2021
- How to benchmark RNA secondary structure prediction accuracyMethods, 2019
- IRESfinder: Identifying RNA internal ribosome entry site in eukaryotic cell using framed k-mer featuresJournal of Genetics and Genomics, 2018
- Mutation effects predicted from sequence co-variationNature Biotechnology, 2017
- 3D RNA and Functional Interactions from Evolutionary CouplingsCell, 2016
- Understanding the transcriptome through RNA structureNature Reviews Genetics, 2011
- RNA structural motifs: building blocks of a modular biomoleculeQuarterly Reviews of Biophysics, 2005
- In a nutshellNature, 1991