Research map / Image generation / Fast diffusion sampling
Protein Design with Guided Discrete Diffusion
Nate Gruver, Samuel Don Stanton, Nathan C. Frey, Tim G. J. Rudner, Isidro Hotzel, Julien Lafrance-Vanasse, Arvind Rajpal, Kyunghyun Cho, Andrew Gordon Wilson
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use sequence-only discrete diffusion instead of structure-based models for CDR infilling | antibody CDR infilling · OAS CDR infilling | sequence recovery | Improved |
| use NOS gradient guidance instead of PPLM or DiGress | discrete diffusion antibody models · beta sheet / SASA objectives | objective vs likelihood trade-off | Improved |
| use LaMBO-2 instead of AdaLead or PEX genetic algorithms | hu4D5 optimization · hu4D5 HER2 in silico | feasible acquisition value: feasible to 16 steps vs 2 (AdaLead) and 4 (PEX) | Improved |
| choose edit positions by saliency instead of uniformly at random (ablation) | LaMBO-2 · hu4D5 HER2, small edit budget | acquisition value | Improved |
| add NOS gradient guidance (step size > 0) to unguided edits (ablation) | LaMBO-2 · hu4D5 HER2, small edit budget | acquisition value | Improved |
| iterative refinement diffusion sampling instead of autoregressive-style sampling (ablation) | NOS-D · beta sheets objective | objective value | Improved |
| set KL penalty lambda too small | LaMBO-2 in vitro round 2 · antibody expression | expression rate | Hurt |
Closest papers by meaning
- Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design (ICLR 2025 · similarity 0.90)
- Retrieval Augmented Diffusion Model for Structure-informed Antibody Design and Optimization (ICLR 2025 · similarity 0.90)
- Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction (ICLR 2025 · similarity 0.89)
- Protein Discovery with Discrete Walk-Jump Sampling (ICLR 2024 · similarity 0.89)
- Reward-Guided Iterative Refinement in Diffusion Models at Test-Time with Applications to Protein and DNA Design (ICML 2025 · similarity 0.89)
- Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-based Decoding (NeurIPS 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
