biostudies-literatureUnknownButcher JNIA NIH HHSNIAID NIH HHSGates FoundationNIGMS NIH HHSDeep 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 <i>in silico</i> benchmarks with one tenth the computational cost. Finally, we demonstrate the broad applicability of RFD3 by designing and experimenbioRxiv : the preprint server for biology2025.09.18.676967https://www.ebi.ac.uk/biostudies/studies/S-EPMC12458353biostudies-literature&lt;i&gt;De novo&lt;/i&gt; Design of All-atom Biomolecular Interactions with RFdiffusion3.PMC12458353INV-010680U19 AI181881R01 AG063845R01 GM123089Kim PTFunk JEisenach HButcher JCorley NChen JPolitanska YZhang OSehgal EBaker DBrent RIDiMaio FMathis SMuraishi ALi YKazman MQiang BDidi KKrishna RThompson TRCoventry BSalike SMitra Rfalse&lt;i&gt;De novo&lt;/i&gt; Design of All-atom Biomolecular Interactions with RFdiffusion3.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 <i>in silico</i> benchmarks with one tenth the computational cost. Finally, we demonstrate the broad applicability of RFD3 by designing and experimen2025-01-01T00:00:00Z2025 Nov2026-06-02T03:13:57.306Z2026-06-02T03:09:19.844ZS-EPMC124583534100097610.1101/2025.09.18.676967