ProSpero: Active Learning for Robust Protein Design Beyond Wild-Type Neighborhoods
This addresses a data-efficient protein engineering problem for biologists and researchers, offering a robust method for exploring novel sequences while preserving biological plausibility, though it appears incremental as it builds on existing generative models and active learning techniques.
The paper tackles the challenge of designing novel and high-fitness protein sequences beyond wild-type neighborhoods, proposing ProSpero, an active learning framework that integrates fitness-relevant residue selection with biologically-constrained Sequential Monte Carlo sampling, and shows it consistently outperforms or matches existing methods across diverse protein engineering tasks.
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.