Machine Learning-Assisted Engineering of Light, Oxygen, Voltage Photoreceptor Adduct Lifetime

Abstract

Naturally occurring and engineered flavin-binding, blue-light-sensing, light, oxygen, voltage (LOV) photoreceptor domains have been used widely to design fluorescent reporters, optogenetic tools, and photosensitizers for the visualization and control of biological processes. In addition, natural LOV photoreceptors with engineered properties were recently employed for optimizing plant biomass production in the framework of a plant-based bioeconomy. Here, the understanding and fine-tuning of LOV photoreceptor (kinetic) properties is instrumental for application. In response to blue-light illumination, LOV domains undergo a cascade of photophysical and photochemical events that yield a transient covalent FMN-cysteine adduct, allowing for signaling. The rate-limiting step of the LOV photocycle is the dark-recovery process, which involves adduct scission and can take between seconds and days. Rational engineering of LOV domains with fine-tuned dark recovery has been challenging due to the lack of a mechanistic model, the long time scale of the process, which hampers atomistic simulations, and a gigantic protein sequence space covering known mutations (combinatorial challenge). To address these issues, we used machine learning (ML) trained on scarce literature data and iteratively generated and implemented experimental data to design LOV variants with faster and slower dark recovery. Over the three prediction–validation cycles, LOV domain variants were successfully predicted, whose adduct-state lifetimes spanned 7 orders of magnitude, yielding optimized tools for synthetic (opto)biology. In summary, our results demonstrate ML as a viable method to guide the design of proteins even with limited experimental data and when no mechanistic model of the underlying physical principles is available.

Interpretable and explainable predictive machine learning models for data-driven protein engineering

“…ML methods have found invaluable applications in diverse biotechnology areas, including drug discovery (Rickerby et al, 2020), assessing various aspects of protein fitness such as thermostability (Csicsery-Ronay et al, 2022), stereoselectivity (Moon et al, 2021;Li et al, 2021), fluorescence properties (Somermeyer et al, 2022), predicting affinity in protein complex interactions (Medina-Ortiz et al, 2023;Liu et al, 2021), functional classification based on Enzyme Commission numbers (Shi et al, 2022;Fernández et al, 2023), recognition of biological activities in peptide sequences (Quiroz et al, 2021), photoreceptor adduct lifetime (Hemmer et al, 2023), and assessing DNA-binding proteins (Qu et al, 2019). The versatility of ML methods has resulted in their integration with traditional experimental techniques, such as DE and RD (Yang et al, 2019;Wittmann et al, 2021).…”