Low-N Protein Activity Optimization with FolDE

TL;DR

FolDE is a novel active learning method for protein optimization that uses naturalness-based warm-starting and a constant-liar batch selector to improve the discovery of top-performing mutants, outperforming existing methods.

Contribution

The paper introduces FolDE, an active learning approach that enhances protein activity prediction and mutant discovery using naturalness-based warm-starting and a new batch selection strategy.

Findings

FolDE discovers 23% more top 10% mutants than baseline methods.

FolDE is 55% more likely to find top 1% mutants.

The workflow is available as open-source software.

Abstract

Proteins are traditionally optimized through the costly construction and measurement of many mutants. Active Learning-assisted Directed Evolution (ALDE) alleviates that cost by predicting the best improvements and iteratively testing mutants to inform predictions. However, existing ALDE methods face a critical limitation: selecting the highest-predicted mutants in each round yields homogeneous training data insufficient for accurate prediction models in subsequent rounds. Here we present FolDE, an ALDE method designed to maximize end-of-campaign success. In simulations across 20 protein targets, FolDE discovers 23% more top 10% mutants than the best baseline ALDE method (p=0.005) and is 55% more likely to find top 1% mutants. FolDE achieves this primarily through naturalness-based warm-starting, which augments limited activity measurements with protein language model outputs to improve activity prediction. We also introduce a constant-liar batch selector, which improves batch diversity; this is important in multi-mutation campaigns but had limited effect in our benchmarks. The complete workflow is freely available as open-source software, making efficient protein optimization accessible to any laboratory.