Research map / Probabilistic and scientific modeling / Molecules and proteins
Conditionally Site-Independent Neural Evolution of Antibody Sequences
Stephen Zhewen Lu, Aakarsh Vermani, Kohei Sanno, Jiarui Lu, Frederick A Matsen, Milind Jagota, Yun S. Song
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 |
|---|---|---|---|
| subtract Thrifty SHM likelihood to form a selection score instead of raw log-likelihood (ablation) | CoSiNE · FLAb2 DMS assays (7 datasets) | Spearman correlation: e.g. Koenig expression heavy 0.53 -> 0.61 | Improved |
| input only the heavy or light chain instead of the paired antibody (ablation) | CoSiNE selection score · FLAb2 DMS assays | Spearman correlation | Hurt |
| vary branch length t from 0.1 to 0.4 in the selection score (ablation) | CoSiNE · FLAb2 DMS assays | Spearman correlation: delta rho <= 0.045 | No clear effect |
| train from scratch without the ESM2 backbone (ablation) | CoSiNE · FLAb2 DMS assays | Spearman correlation: -0.041 on average | Hurt |
| condition rates on sequence context (CoSiNE) instead of a WAG-style context-independent matrix (ablation) | CoSiNE · antibody test transitions | per-token NLL | Improved |
| use CoSiNE instead of DASM+Thrifty for transition likelihood | CoSiNE · Rodriguez et al. test transitions | per-site likelihood: better in 62.3% of cases | Improved |
| use CoSiNE instead of ProGen2-Small on Koenig light-chain expression | CoSiNE · FLAb2 Koenig expression (light chain) | Spearman correlation: 0.508 vs 0.513 | Hurt |
| use CoSiNE instead of best baselines on Adams (mouse wildtype) | CoSiNE · FLAb2 Adams expression | Spearman correlation: 0.297 -> 0.464 | Improved |
| add classifier guidance (Guided Gillespie) with gamma from 1 to 15 (ablation) | CoSiNE sampling · CoV-AbDab SARS-CoV-1 affinity maturation | predicted affinity gain | Improved |
| set guidance strength gamma >= 10 (ablation) | Guided Gillespie · CoV-AbDab SARS-CoV-1 affinity maturation | predicted affinity gain | Mixed |
| add guidance (gamma = 5) to sampling (ablation) | CoSiNE · AbodyBuilder3 pLDDT and OASis | structural plausibility and humanness | No clear effect |
| use Taylor-approximated guidance instead of exact oracle guidance (ablation) | Guided Gillespie · antibody guidance | speed and fitness improvement: 500-fold speedup, no significant fitness difference | Improved |
Closest papers by meaning
- Bayesian Optimization of Antibodies Informed by a Generative Model of Evolving Sequences (ICLR 2025 · similarity 0.89)
- Pareto-Optimal Energy Alignment for Designing Nature-Like Antibodies (NeurIPS 2025 · similarity 0.88)
- Antibody Design Using a Score-based Diffusion Model Guided by Evolutionary, Physical and Geometric Constraints (ICML 2024 · similarity 0.88)
- Antigen-Specific Antibody Design via Direct Energy-based Preference Optimization (NeurIPS 2024 · similarity 0.87)
- Retrieval Augmented Diffusion Model for Structure-informed Antibody Design and Optimization (ICLR 2025 · similarity 0.87)
- AffinityFlow: Guided Flows for Antibody Affinity Maturation (ICML 2025 · similarity 0.87)
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.
