ProSpero：超越野生型邻域的鲁棒蛋白质设计的主动学习
ProSpero: Active Learning for Robust Protein Design Beyond Wild-Type Neighborhoods
AI总结：
ProSpero提出主动学习框架，结合代理模型与生物约束采样，实现高适应度且新颖的蛋白质序列设计，超越野生型邻域并保持合理性。
摘要：
在数据高效的蛋白质工程中，设计兼具高适应度和新颖性的蛋白质序列是一项具有挑战性的任务。在野生型邻域之外的探索往往会导致生物学上不合理的序列，或者依赖于在新颖区域中失去保真度的代理模型。在此，我们提出了ProSpero，一种主动学习框架，其中冻结的预训练生成模型由从预言机反馈更新的代理模型引导。通过将适应度相关的残基选择与生物学约束的顺序蒙特卡洛采样相结合，我们的方法能够在保持生物学合理性的同时，实现超越野生型邻域的探索。我们表明，即使代理模型被错误设定，我们的框架仍然有效。ProSpero在各种蛋白质工程任务中持续优于或匹配现有方法，检索出兼具高适应度和新颖性的序列。
英文摘要：
Designing protein sequences of both high fitness and novelty is a challenging task in data-efficient protein engineering. Exploration beyond wild-type neighborhoods often leads to biologically implausible sequences or relies on surrogate models that lose fidelity in novel regions. Here, we propose ProSpero, an active learning framework in which a frozen pre-trained generative model is guided by a surrogate updated from oracle feedback. By integrating fitness-relevant residue selection with biologically-constrained Sequential Monte Carlo sampling, our approach enables exploration beyond wild-type neighborhoods while preserving biological plausibility. We show that our framework remains effective even when the surrogate is misspecified. ProSpero consistently outperforms or matches existing methods across diverse protein engineering tasks, retrieving sequences of both high fitness and novelty.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
