RiboFlow: Conditional De Novo RNA Co-Design via Synergistic Flow Matching

Jiahua Rao (Sun Yat-Sen University) · Shuangjia Zheng (Shanghai Jiaotong University) · Runze Ma (Shanghai Jiao Tong University) · Zhongyue Zhang (Shanghai Jiaotong University) · Zichen Wang (University of Illinois at Urbana-Champaign) · Chenqing Hua (Mila-Quebec AI Institute, I work on protein design) · Zhuomin Zhou (Shanghai Jiaotong University)

binding affinity conformational flexibilitycontrollable capabilitiesdata scarcitydata-efficient generationflow matching model generative modelsribobindriboflowrna backbone framesrna designrna-molecule interactionssequence-structure consistencystructural validitystructure-aware generationtorsion angles

Ribonucleic acid (RNA) binds to molecules to achieve specific biological functions. While generative models are advancing biomolecule design, existing methods for designing RNA that target specific ligands face limitations in capturing RNA’s conformational flexibility, ensuring structural validity, and overcoming data scarcity. To address these challenges, we introduce RiboFlow, a synergistic flow matching model to co-design RNA structures and sequences based on target molecules. By integrating RNA backbone frames, torsion angles, and sequence features in an unified architecture, RiboFlow explicitly models RNA’s dynamic conformations while enforcing sequence-structure consistency to improve validity. Additionally, we curate RiboBind, a large-scale dataset of RNA-molecule interactions, to resolve the scarcity of high-quality structural data. Extensive experiments reveal that RiboFlow not only outperforms state-of-the-art RNA design methods by a large margin but also showcases controllable capabilities for achieving high binding affinity to target ligands. Our work bridges critical gaps in controllable RNA design, offering a framework for structure-aware, data-efficient generation.