Metraipolis › archive › dc_89eafc09f70b
Linear Fitness Subspace in Protein Language Models Enables Sample-Efficient Directed Evolution — arXiv:2610.07607
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.07607
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:20:55.886Z
- SHA-256 of the archived text
8760616165b625f8f56c06322f2d602db6fa34a8ad3a9d26825b01f1c78bdf05- Stable URL of this page
https://metraipolis.com/documento/dc_89eafc09f70b
How to cite
Linear Fitness Subspace in Protein Language Models Enables Sample-Efficient Directed Evolution — arXiv:2610.07607 — arXiv (en), https://arxiv.org/abs/2610.07607 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_89eafc09f70b (Metraipolis archive dc_89eafc09f70b, sha256 8760616165b625f8f56c06322f2d602db6fa34a8ad3a9d26825b01f1c78bdf05)
BibTeX
@misc{dc89eafc09f70b,
title = {Linear Fitness Subspace in Protein Language Models Enables Sample-Efficient Directed Evolution — arXiv:2610.07607},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.07607},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_89eafc09f70b; sha256 8760616165b625f8f56c06322f2d602db6fa34a8ad3a9d26825b01f1c78bdf05},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07607. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Model-guided directed evolution seeks to identify high-fitness protein variants under limited oracle budgets. Protein language models (PLMs) provide rich representations for this task, but task-agnostic zero-shot scores can be misaligned with a target assay, while supervised search in high-dimensional embedding spaces can make surrogate modeling and uncertainty estimation sample-inefficient. We propose the Linear Fitness Subspace (LFS) hypothesis: within mutation-induced residue-level representation changes, a compact, assay-specific set of directions makes fitness variation linearly accessible from few labeled variants. This is a local, supervision-recoverable statement rather than a claim that protein fitness landscapes or global PLM geometry are universally linear. Building on this observation, we introduce Subspace-Guided Evolutionary Search (SGES), which estimates an LFS from a small initial sample and performs surrogate modeling, uncertainty estimation, and acquisition in the learned subspace. Across 10 core ProteinGym assays, 87 extended static-validation assays, and an 18-assay budgeted-search evaluation, SGES improves fitness prediction and search efficiency over zero-shot PLMs and recent ML-guided protein optimization baselines. Controlled comparisons with PCA, random projections, label-shuffled PLS, classical mutation features, and acquisition ablations further isolate the benefit of a fitness-aligned site-delta coordinate. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Quantitative Methods (q-bio.QM) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.07607 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T11:15:24.740Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).