Deep Learning Framework for RNA Inverse Folding with Geometric Structure Potentials
This work addresses the problem of accurately designing RNA sequences for given 3D conformations, which is crucial for biological applications, representing a strong specific gain rather than a broad paradigm shift.
The paper tackles the challenge of RNA inverse folding by introducing a deep learning framework that integrates Geometric Vector Perceptron layers with a Transformer architecture, achieving state-of-the-art performance with recovery and TM-scores of 0.481 and 0.332 on benchmarks and RNA-Puzzles.
RNA's diverse biological functions stem from its structural versatility, yet accurately predicting and designing RNA sequences given a 3D conformation (inverse folding) remains a challenge. Here, I introduce a deep learning framework that integrates Geometric Vector Perceptron (GVP) layers with a Transformer architecture to enable end-to-end RNA design. I construct a dataset consisting of experimentally solved RNA 3D structures, filtered and deduplicated from the BGSU RNA list, and evaluate performance using both sequence recovery rate and TM-score to assess sequence and structural fidelity, respectively. On standard benchmarks and RNA-Puzzles, my model achieves state-of-the-art performance, with recovery and TM-scores of 0.481 and 0.332, surpassing existing methods across diverse RNA families and length scales. Masked family-level validation using Rfam annotations confirms strong generalization beyond seen families. Furthermore, inverse-folded sequences, when refolded using AlphaFold3, closely resemble native structures, highlighting the critical role of geometric features captured by GVP layers in enhancing Transformer-based RNA design.