Research map / Probabilistic and scientific modeling / Molecules and proteins
Non-identifiability and the Blessings of Misspecification in Models of Molecular Fitness
Eli N Weinstein, Alan Nawzad Amin, Jonathan Frazer, Debora Susan Marks
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 |
|---|---|---|---|
| relax parametric AR model toward nonparametric BEAR (higher h) (ablation) | Autoregressive fitness model · Fitness estimation (Spearman) vs density estimation | fitness estimation vs likelihood | Mixed |
| use misspecified parametric fitness models instead of true data density | SWI, EVE, Wavenet · Functional assays (37) | Spearman correlation vs assay: 35/37 (95%) SWI, 35/37 (95%) EVE, 36/37 (97%) Wavenet beat data density | Improved |
| use misspecified parametric models instead of true data density | SWI, EVE · Pathogenicity prediction (97 genes) | AUROC: 31/97 (32%) SWI, 46/97 (47%) EVE beat data density | Mixed |
| nonparametric BEAR instead of Wavenet for density estimation | Density estimation · Functional assays (37) | held-out predictive performance: better on 27/37 assays (73%) | Improved |
Closest papers by meaning
- Contrastive losses as generalized models of global epistasis (NeurIPS 2024 · similarity 0.88)
- Steering Generative Models with Experimental Data for Protein Fitness Optimization (NeurIPS 2025 · similarity 0.87)
- Augmenting Biological Fitness Prediction Benchmarks with Landscapes Features from GraphFLA (NeurIPS 2025 · similarity 0.86)
- DePLM: Denoising Protein Language Models for Property Optimization (NeurIPS 2024 · similarity 0.86)
- Improving protein optimization with smoothed fitness landscapes (ICLR 2024 · similarity 0.86)
- Robust Model-Based Optimization for Challenging Fitness Landscapes (ICLR 2024 · similarity 0.85)
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.
