ESM3
EvolutionaryScale
Multimodal protein language model that simultaneously reasons over sequence, structure, and function. Can generate novel proteins by prompting with partial information.
Best For
Function-driven protein generation; exploring remote evolutionary analogs
License
API (free academic tier); largest model non-commercial
Strengths
- +Multimodal (sequence + structure + function)
- +98B parameter model
Limitations
- −Largest model requires significant compute
- −Generation quality varies with prompting
R&D Pipeline Coverage
Related Tools
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.
Chroma
Generate:Biomedicines
Programmable generative model for protein and protein complex design using diffusion with conditioning on geometry, symmetry, and functional annotations.
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 ESM3
Weekly newsletter covering AI tool releases, benchmarks, and what practitioners actually use.