Research map / Probabilistic and scientific modeling / Molecules and proteins
A One-shot Framework for Directed Evolution of Antibodies
Sai Pooja Mahajan, Natasa Tagasovska, Stefania Vasilaki, Arian Rokkum Jamasb, Andrew Martin Watkins, Rajesh Ranganath
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 |
|---|---|---|---|
| add data matching (ablation) | AFFINITYENHANCER · Mean over 4 held-out seeds | mean improved rate: 4.29 % -> 8.46 % | Improved |
| add data matching (ablation) | AFFINITYENHANCER · Mean over 4 held-out seeds | binder rate: 6.61 % -> 50.10 % | Improved |
| add GearNet embedder and pOAS decoder (ablation) | AFFINITYENHANCER · Mean over 4 held-out seeds | mean improved rate: 1.32 % -> 8.46 % | Improved |
| add GearNet embedder and pOAS decoder (ablation) | AFFINITYENHANCER · Mean over 4 held-out seeds | binder rate: 27.02 % -> 50.10 % | Improved |
| use Graph Transformer instead of CNN (ablation) | AFFINITYENHANCER · Mean over 4 held-out seeds | mean improved rate: 0.63 % -> 8.46 % | Improved |
| use Graph Transformer instead of CNN (ablation) | AFFINITYENHANCER · Mean over 4 held-out seeds | binder rate: 16.07 % -> 50.10 % | Improved |
| add adjacency matrix to Graph Transformer (ablation) | AFFINITYENHANCER · Mean over 4 held-out seeds | binder rate: 35.04 % -> 50.10 % | Improved |
| add adjacency matrix to Graph Transformer (ablation) | AFFINITYENHANCER · Mean over 4 held-out seeds | mean improved rate: 9.98 % -> 8.46 % | Hurt |
| add adjacency matrix to Graph Transformer (ablation) | AFFINITYENHANCER · Trastuzumab | improved rate: 39.02 % -> 31.50 % | Hurt |
| add structure-aware matched training (vs sequence-only PropEn) | PropEn · Mean over 4 held-out seeds | mean improved rate: 0.00 % -> 8.46 % | Improved |
| add data matching (ablation) | AFFINITYENHANCER · Seed 2 | improved rate: 13.92 % -> 2.26 % | Hurt |
| replace MLDE with AffinityEnhancer | MLDE · Seed 1 (low ED) | binder rate: 34.7% -> 36.4% | Improved |
Closest papers by meaning
- AffinityFlow: Guided Flows for Antibody Affinity Maturation (ICML 2025 · similarity 0.92)
- Antibody Design Using a Score-based Diffusion Model Guided by Evolutionary, Physical and Geometric Constraints (ICML 2024 · similarity 0.90)
- Retrieval Augmented Diffusion Model for Structure-informed Antibody Design and Optimization (ICLR 2025 · similarity 0.89)
- Bayesian Optimization of Antibodies Informed by a Generative Model of Evolving Sequences (ICLR 2025 · similarity 0.88)
- Antigen-Specific Antibody Design via Direct Energy-based Preference Optimization (NeurIPS 2024 · similarity 0.88)
- Cross-Gate MLP with Protein Complex Invariant Embedding Is a One-Shot Antibody Designer (AAAI 2024 · similarity 0.88)
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.
