Missing values mean the catalog has no recorded information. They do not mean a feature is absent.
Entry typeAI Model / Software
Access modeAcademic Open Source
AI roleDe Novo Molecular Diffusion
Input dataNot recorded
Output dataNot recorded
Licence conditionsOpen Source for academic research; commercial license required for for-profit use
Commercial eligibilityCommercial licensing available through University of Washington CoMotion
Compute requirements1x NVIDIA A100 or RTX 4090 GPU (>= 24GB VRAM)
ValidationNot recorded
TypeGenerative all-atom diffusion model
Intended useNot recorded
CompatibilityNot recorded
ManufacturerInstitute for Protein Design
Biological applicationEnzyme active site design, small molecule sensor engineering, and drug receptor design
Research workflowDiffusion of protein backbone and sidechains around explicit ligand coordinates
Evidence levelPeer-reviewed research (Science 2024)
Integration evidencehttps://github.com/baker-laboratory/rf_diffusion_all_atom
Laboratory handoffDesigns validated via yeast surface display and biolayer interferometry (BLI)
AvailabilityAvailable on GitHub
Price / accessFree for academic research / Paid commercial license