Directed protein evolution applies repeated rounds of genetic mutagenesis and phenotypic screening and is often limited by experimental throughput. Through in silico prioritization of mutant sequences, machine learning has been applied to reduce wet lab burden to a level practical for human researchers. On the other hand, robotics permits large batches and rapid iterations for protein engineering cycles, but such capacities have not been well exploited in existing machine learning-assisted directed evolution approaches. Here, we report a scalable and batched method, Bayesian Optimization-guided EVOlutionary (BO-EVO) algorithm, to guide multiple rounds of robotic experiments to explore protein fitness landscapes of combinatorial mutagenesis libraries. We first examined various design specifications based on an empirical landscape of protein G domain B1. Then, BO-EVO was successfully generalized to another empirical landscape of an Escherichia coli kinase PhoQ, as well as simulated NK landscapes with up to moderate epistasis. This approach was then applied to guide robotic library creation and screening to engineer enzyme specificity of RhlA, a key biosynthetic enzyme for rhamnolipid biosurfactants. A 4.8-fold improvement in producing a target rhamnolipid congener was achieved after examining less than 1% of all possible mutants after four iterations. Overall, BO-EVO proves to be an efficient and general approach to guide combinatorial protein engineering without prior knowledge.

Oxygen-independent, flavin mononucleotide-based fluorescent proteins (FbFPs) are promising alternatives to green fluorescent protein in anaerobic contexts. Deep mutational scanning performs systematic profiling of protein sequence-function relationships but has not been applied to FbFPs. Focusing on CreiLOV from Chlamydomonas reinhardtii, we created and analyzed two comprehensive mutant collections: (1) single-residue, site-saturation mutagenesis libraries covering all 118 residues; and (2) a full combinatorial metagenesis library among 20 mutations at 15 residues, where mutation and residue selection was based on single-site mutagenesis results. Notably, the second type of library is indispensable to study higher-order epistasis but underrepresented in the literature. Using optimized FACS-seq assays, 2,185 (>92.5%) out of 2,360 possible single-site mutants and 165,428 (>89.7%) out of 184,320 possible combinatorial mutants were reliably assigned with fitness values. We constructed statistical and machine-learning models to analyze the CreiLOV data set, enabling accurate fitness prediction of higher-order mutants using lower-order mutagenesis data. In addition, we successfully isolated CreiLOV variants with improved fluorescence quantum yield and thermostability. This work provides new empirical data and design rules to engineer combinatorial protein variants.

Underwater radiated noise (URN) has a negative impact on the marine acoustic environment where it can disrupt marine creature's basic living functions such as navigation and communication. To control the ambient ocean noise levels due to human activities, international governing bodies such as the International Maritime Organization (IMO) have issued non-mandatory guidelines to address this issue. Under such framework, the hydroacoustic performance of marine vehicles has become a critical factor to be evaluated and controlled throughout the vehicles' service life in order to mitigate the URN level and the role humankind plays in the ocean. This study aims to apply leading-edge (LE) tubercles of the humpback whales' pectoral fins to a benchmark ducted propeller to investigate its potential in noise mitigation. This was conducted using CFD, where the high-fidelity improved delayed detached eddy simulations (IDDES) in combination with the porous Ffowcs-Williams Hawkings (FW-H) acoustic analogy was used to solve the hydrodynamic flow field and propagate the generated noise to the far-field. It has been found that the LE tubercles have shown promising noise mitigation capabilities in the far-field, where the OASPL at J = 0.1 was reduced to a maximum of 3.4 dB with a maximum of 11 dB reduction in certain frequency ranges at other operating conditions. Based on detailed flow analysis researching the fundamental vortex dynamics, this noise reduction is shown to be due to the disruption of the coherent turbulent wake structure in the propeller slipstream causing the acceleration in the dissipation of turbulence and vorticity-induced noise.