BindCraft
EPFL / MIT (Pacesa, Ovchinnikov, Correia)
One-shot automated pipeline for de novo protein binder design. Backpropagates through AlphaFold2 to hallucinate binders. 10-100% experimental success rates.
Best For
De novo protein binder design for challenging targets (non-antibody scaffolds)
License
Open Source (MIT)
Strengths
- +10-100% experimental success rates
- +No high-throughput screening needed
- +MIT license
Limitations
- −Not antibody-specific
- −Computationally intensive
- −Target-dependent success
R&D Pipeline Coverage
Related Tools
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.
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.
More in Antibody Design
DiffAb
Luo et al. (NeurIPS 2022)
Diffusion-based generative model that jointly designs antibody CDR sequences and 3D structures conditioned on antigen structure.
RFantibody
Baker Lab / IPD (University of Washington)
RFdiffusion fine-tuned for de novo antibody design. Generates VHHs, scFvs, and full antibodies targeting user-specified epitopes. Experimentally validated with cryo-EM.
AntiFold
OPIG (Oxford)
Antibody-specific inverse folding model fine-tuned from ESM-IF1. Designs sequences predicted to maintain structural fold given an antibody backbone.
Stay updated on BindCraft
Weekly newsletter covering AI tool releases, benchmarks, and what practitioners actually use.