Summary
Antibody-specific fine-tuning of RFdiffusion improves preservation of input frameworks and epitope targeting (1). The framework/hotspot ablation covers both VHHs and scFvs.
Figures
Ref (1)
See also
- Framework region
- Heavy-chain templates and self-distillation improve nanobody structure prediction — a different training intervention for structure prediction.
- Protein backbone diffusion models undersample loop-rich and alpha-beta domains and functional motifs
1.
Bennett NR, Watson JL, Ragotte RJ, Borst AJ, See DL, Weidle C, et al. Atomically accurate de novo design of antibodies with RFdiffusion. Nature. 2025;649(8095):183–93. Available from: https://doi.org/10.1038/s41586-025-09721-5