用几何特征提升RNA序列设计精度，实现端到端逆折叠。
Deep Learning Framework for RNA Inverse Folding with Geometric Structure Potentials
- 结合GVP与Transformer，捕捉三维结构中的几何信息。
- 在标准测试中序列恢复率0.481，TM-score达0.332，领先现有方法。
- 对未见家族泛化能力强，适合生物设计与结构预测研究者。
RNA的多种生物学功能源于其结构多样性，但根据三维构象准确设计RNA序列（逆折叠）仍具挑战。本文提出一种深度学习框架，融合几何向量感知器（GVP）层与Transformer架构，实现端到端RNA序列设计。构建了基于实验解析的RNA三维结构数据集，从BGSU RNA列表中筛选并去重，并使用序列恢复率和TM-score分别评估序列与结构保真度。在标准基准与RNA-Puzzles测试中，模型表现达到当前最优水平，序列恢复率为0.481，TM-score为0.332，优于多种不同家族与长度尺度的现有方法。采用Rfam注释进行掩码家族级验证，证实模型具备强泛化能力。此外，逆折叠生成的序列经AlphaFold3重构后，与原始结构高度相似，凸显了GVP层对几何特征的有效捕捉在增强基于Transformer的RNA设计中的关键作用。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。