DiffSBDD
Schneuing et al. (Cambridge / Microsoft / VantAI)
Equivariant diffusion model for structure-based drug design that generates novel 3D molecules directly inside protein binding pockets. Published in Nature Computational Science 2024.
Best For
3D-aware de novo molecule generation conditioned on protein pocket geometry
License
Open Source (check repo)
Strengths
- +3D pocket-conditioned generation
- +Equivariant architecture
- +Nature Comp Sci publication
- +Generates drug-like molecules
Limitations
- −Generated molecules may need synthetic feasibility filtering
- −Limited to single binding pocket
- −Requires pocket definition
R&D Pipeline Coverage
Related Tools
PocketFlow
PocketFlow Team
Flow-based generative model that creates novel small molecule ligands for a target binding pocket. Generates hundreds of candidates in minutes.
Lingo3DMol
StoneWise AI Drug Design
Pocket-based 3D molecule generation combining language model token prediction with geometric deep learning for 3D coordinate generation. Published in Nature Machine Intelligence 2024.
DiffDock / DiffDock-L
MIT CSAIL (Corso et al.)
Diffusion-based generative model that treats docking as a generative problem over ligand poses. No pre-specified binding pocket needed.
More in Generative Design
RFdiffusion
Baker Lab / IPD (University of Washington)
Diffusion-based generative model for de novo protein backbone design. Generates novel protein structures conditioned on binding targets, symmetry, or functional sites.
RFdiffusion2
Baker Lab / IPD (University of Washington)
Successor to RFdiffusion using flow matching. Designs enzymes directly from active site geometry (theozyme) specifications.
ProteinMPNN
Baker Lab / IPD (University of Washington)
Inverse folding model: generates amino acid sequences predicted to fold into a target 3D backbone structure. Standard component of all modern protein design pipelines.
Stay updated on DiffSBDD
Weekly newsletter covering AI tool releases, benchmarks, and what practitioners actually use.