RFDpoly, a generalized diffusion framework extending RFdiffusion to nucleic acids, enables de novo design of complex RNA tertiary structures and protein-nucleic acid assemblies with atomic-level accuracy, as validated by cryo-EM reconstruction of novel RNA pseudocycles and X-ray crystallography of designed protein-DNA complexes, demonstrating that structure-based computational design principles can be successfully applied beyond proteins to create diverse, experimentally validated nucleic acid architectures.

Nucleic acids fold into sequence-dependent tertiary structures and carry out diverse biological functions, much like proteins. However, while considerable advances have been made in the de novo design of protein structure and function, the same has not yet been achieved for RNA tertiary structures of similar intricacy. Here, we describe a generative diffusion framework, RFDpoly, for generalized de novo biopolymer (RNA, DNA and protein) design, and use it to create diverse and designable RNA structures. We design RNA structures with novel folds and experimentally validate them using a combination of chemical footprinting (SHAPE-seq) and electron microscopy. We further use this approach to design protein-nucleic acid assemblies; the crystal structure of one such design is nearly identical to the design model. This work demonstrates that the principles of structure-based de novo protein design can be extended to nucleic acids, opening the door to creating a wide range of new RNA structures and protein-nucleic acid complexes.