Deep learning has accelerated protein design, but most existing methods are restricted to generating protein backbone coordinates and often neglect interactions with other biomolecules. We present RFdiffusion3 (RFD3), a diffusion model that generates protein structures in the context of ligands, nucleic acids and other non-protein constellations of atoms. Because all polymer atoms are modeled explicitly, conditioning the model on complex sets of atom-level constraints for enzyme design and other challenges is both simpler and more effective than previous approaches. RFD3 achieves improved performance compared to prior approaches on a range of in silico benchmarks with one tenth the computational cost. Finally, we demonstrate the broad applicability of RFD3 by designing and experimentally characterizing DNA binding proteins and cysteine hydrolases. The ability to rapidly generate protein structures guided by complex sets of atom-level constraints in the context of arbitrary non-protein atoms should further expand the range of functions attainable through protein design.

Premature stop codon–containing mRNAs can produce truncated and dominantly acting proteins that harm cells. Eukaryotic cells protect themselves by degrading such mRNAs via the nonsense-mediated mRNA decay (NMD) pathway. The precise reactions by which cells attack NMD-target mRNAs remain obscure, precluding a biochemical understanding of NMD and hampering therapeutic efforts to control NMD. Here, we modify and deploy single-molecule nanopore mRNA sequencing to clarify the route by which NMD targets are attacked in an animal. We obtain single-molecule measures of splicing isoform, cleavage state, and poly(A) tail length. We observe robust endonucleolytic cleavage of NMD targets in vivo that depends on the nuclease SMG-6. We show that NMD-target mRNAs experience deadenylation and decapping, similar to that of normal mRNAs. Furthermore, we show that a factor (SMG-5) that historically was ascribed a function in deadenylation and decapping is in fact required for SMG-6-mediated cleavage. Our results support a model in which NMD factors act in concert to degrade NMD targets in animals via an endonucleolytic cleavage near the stop codon, and we suggest that deadenylation and decapping are normal parts of mRNA (and NMD target) maturation and decay rather than unique facets of NMD.

De novo protein design has advanced rapidly in recent years, yet the programmable recognition of specific DNA sequences remains a longstanding challenge. Here we describe a deep learning based approach for designing sequence selective DNA binding proteins. Our method combines structure generation using RFdiffusion3 with explicit screening against off-target interactions using AlphaFold3. We test this approach by generating 96 designs for each of 15 diverse DNA targets and identify specific binders for 7 targets, representing a ~100-fold improvement in success rates over previous approaches. We further characterize the binding landscape using variant competition assays and randomized library screening, revealing robust sequence discrimination across diverse targets. Together, these results represent a significant step forward in de novo sequence specific DNA binder design.

The catalytic and other sophisticated functions of biomolecules arise from the placement of many atoms in three-dimensional space. Here, we describe a generative artificial intelligence method for biopolymers, RFdiffusion3 (RFD3), which employs free atom diffusion to satisfy complex sets of atomic constraints more rapidly and accurately than previous methods across several challenges from enzyme design to RNA structure design. We demonstrate experimentally the power of the RFD3 pipeline for enzyme design by designing de novo phosphotriesterases with a complex active site architecture incorporating a carbamylated lysine coordinating two metal ions and zinc proteases specific for the transthyretin protein involved in amyloid diseases; in both cases we obtain active catalysts in zero shot 96 construct design campaigns.

Caenorhabditis elegansis an important model organism for human health and disease, with foundational contributions to the understanding of gene expression and tissue patterning in animals. An invaluable tool in modern gene expression research is the presence of a high-resolution ribosome structure, though no such structure exists forC. elegans. Here, we present a high-resolution single-particle cryogenic electron microscopy (cryo-EM) reconstruction and molecular model of aC. elegansribosome, revealing a significantly streamlined animal ribosome. Many facets of ribosome structure are conserved inC. elegans, including overall ribosomal architecture and the mechanism of cycloheximide, whereas other facets, such as expansion segments and eL28, are rapidly evolving. We identify uL5 and uL23 as two instances of tissue-specific ribosomal protein paralog expression conserved inCaenorhabditis, suggesting thatC. elegansribosomes vary across tissues. TheC. elegansribosome structure will provide a basis for future structural, biochemical, and genetic studies of translation in this important animal system.

EMPIAR, the Electron Microscopy Public Image Archive centered at EMBL-EBI, is a public resource for raw electron microscopy images related to EMDB, contains micrographs, particle sets and tilt-series.