ProTEUS:透過閉環蛋白質演化的突變解析世界模型
ProTEUS: A mutation-resolved world model for closed-loop protein evolution
ProTEUS 結合序列、演化與結構表示、快速全原子預測及閉環實驗回饋,引導蛋白質演化並提升突變體活性。其全原子預測器速度比 AlphaFold3 快逾 10 倍,並在零樣本及監督式微調突變預測任務中超越既有模型。兩項針對醛脱氫酶和左聚糖蔗糖酶的閉環工程實驗,均獲得活性高於野生型逾 10 倍的變體。
Published on Nov 9
·
on Nov 11
Authors:
,
,
,
,
,
,
Abstract
ProTEUS is a mutation-resolved world model that combines sequence, evolutionary, and structural representations with fast all-atom prediction and closed-loop feedback to guide protein evolution and improve mutant activity.
Protein engineering requires navigating rugged fitness landscapes, where small sequence changes can produce large functional differences, but experimental screening can only sample a small fraction of sequence space. Thus, a central challenge is to efficiently traverse the large combinatorial space of mutations in silico. We introduce ProTEUS, a mutation-resolved world model for closed-loop protein evolution. Pretrained on deep mutational scanning assays, ProTEUS learns a joint representation of sequence, evolutionary, and structural information using MutationFormer, a mutation-biased attention architecture. Variants are represented as states in this joint latent space, and mutations define actions whose functional consequences are predicted. To support exploration of many mutants, we developed a fast, physics-constrained all-atom predictor that utilizes explicit geometric constraint enforcement to achieve >10 fold increase in speed than AlphaFold3 with guaranteed physical validity. Lastly, ProTEUS refines its prediction and understanding of protein activity through closed loop experimental feedback to guide evolution toward a desired phenotype. ProTEUS surpasses established models in both zero-shot and supervised fine-tuning mutation prediction tasks. We experimentally demonstrate its utility in two closed-loop multi-objective engineering campaigns on aldehyde dehydrogenase and levansucrase, yielding variants with >10 fold higher activity than wild type. ProTEUS provides a world-model framework that connects virtual evaluation of mutational outcomes with experimental learning for efficient protein evolution.
View arXiv page View PDF Project page GitHub 1 Add to collection
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2611.13348 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2611.13348 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2611.13348 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co