Madrigal Harrison, I. | Search bioRxiv

bioRxiv2026

Design and characterization of peptide-responsive biosensors

Gram-positive bacteria use secreted peptides and peptide-responsive transcription factors for quorum sensing. Here, we demonstrate that intracellular expression of these peptide effectors with their cognate transcription factors leads to regulation of gene expression in both in vitro and in vivo systems. Because both effector and regulatory parts can be readily expressed, complex circuits, including auto-activation schemes, can be developed, with switch-like behaviors. Moreover, the peptide effectors can be fused to proteins, enabling a direct intracellular readout of translation and potentially allowing any protein to encode regulatory interactions in cells. Our results support a foundation for regulatory circuits that extend beyond canonical components such as LacI and TetR.

bioengineering↗

bioRxiv2026

Combining Machine Learning and Directed Evolution for Optimization of a Monooxygenase

L-3,4-dihydroxyphenylalanine (L-Dopa) is an important pharmaceutical for the treatment of Parkinsons disease and a precursor to numerous catechol-containing compounds. The flavin-dependent monooxygenase HpaBC is a promising biocatalyst for microbial L-Dopa production but exhibits limited native activity toward L-tyrosine. Although structure-based machine learning (ML) models have become increasingly popular for protein engineering, relatively few studies have systematically compared their performance or evaluated their integration into iterative engineering workflows. Here, we benchmarked multiple ML models for their ability to predict activity enhancing mutations in HpaBC. Experimentally validated single mutants were used to seed combinatorial design with EVOLVEpro, generating progressively improved higher-order variants. We next evaluated how expanding the EVOLVEpro training set with directed evolution derived variants influenced combinatorial predictions and finally explored an expanded sequence space by allowing combinations of both machine learning derived and directed evolution derived mutations. This workflow produced HpaBC variants with substantially improved activity. Although incorporating directed evolution data substantially altered EVOLVEpros predicted mutational trajectories, both training strategies converged on variants with comparable activities, demonstrating that distinct regions of sequence space can yield similarly optimized enzymes. Together, these results provide a systematic comparison of zero-shot ML models and establish an iterative framework for integrating machine learning with directed evolution to accelerate enzyme engineering.

biochemistry↗