Advancing NanoLuc Luciferase Stability beyond Directed Evolution and Rational Design through Expert-Guided Deep Learning.

Engineered luciferases have transformed biological imaging and sensing, yet optimizing NanoLuc luciferase (NLuc) remains challenging due to the inherent stability-activity trade-off and its limited sequence homology with characterized proteins. We report a hybrid approach that synergistically integrates deep learning with structure-guided rational design to develop enhanced NLuc variants that improve thermostability and thereby activity at elevated temperatures. By systematically analyzing libraries of engineered variants, we established that modifications to termini and loops distal from the catalytic center, combined with preservation of allosterically coupled networks, effectively increase thermal resilience while maintaining enzymatic function. Our optimized variantsnotably B.07 and B.09exhibit substantial thermostability enhancements (increased melting temperatures of 7.2 and 5.1 °C, respectively), leading to the sustained activity of a high-activity mutant at elevated temperatures. Molecular dynamics simulations and protein folding studies elucidate how these mutations favorably modulate conformational landscapes without perturbing the substrate binding architecture. Beyond providing a thermostabilized tool for bioluminescence applications, our integrated methodology presents a framework for engineering enzymes when traditional homology-based approaches fail and stability-activity constraints present formidable barriers to improvement.