Synthetic fungal multifunctional cellulases for enhanced biomass conversion
Synthetic multifunctional enzymes exhibit superior performance to their non-multifunctional enzyme components and exhibit novel cellulose deconstruction mechanisms.
SEARCH · Search NASA
Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.
Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.
Synthetic multifunctional enzymes exhibit superior performance to their non-multifunctional enzyme components and exhibit novel cellulose deconstruction mechanisms.
Biocatalytic C–H activation has the potential to merge enzymatic and synthetic strategies for bond formation. Fe II /αKG-dependent halogenases are particularly distinguished for their ability both to control selective C–H activation as well as to direct group transfer of a bound anion along a reaction axis separate from oxygen rebound, enabling the development of new transformations. In this context, we elucidate the basis for the selectivity of enzymes that perform selective halogenation to yield 4-Cl-lysine (BesD), 5-Cl-lysine (HalB), and 4-Cl-ornithine (HalD), allowing us to probe how site-selectivity and chain length selectivity are achieved. We now report the crystal structure of the HalB and HalD, revealing the key role of the substrate-binding lid in positioning the substrate for C 4 vs C 5 chlorination and recognition of lysine vs ornithine. Targeted engineering of the substrate-binding lid further demonstrates that these selectivities can be altered or switched, showcasing the potential to develop halogenases for biocatalytic applications.
The restoration of the native form of laccase from B. aclada from the type 2 copper-depleted form of the enzyme was investigated. Copper ions were found to be incorporated into the active site after soaking the depleted enzyme in a Cu{sup +}-containing solution. Laccases belong to the class of multicopper oxidases catalyzing the oxidation of phenols accompanied by the reduction of molecular oxygen to water without the formation of hydrogen peroxide. The activity of laccases depends on the number of Cu atoms per enzyme molecule. The structure of type 2 copper-depleted laccase from Botrytis aclada has been solved previously. With the aim of obtaining the structure of the native form of the enzyme, crystals of the depleted laccase were soaked in Cu{sup +}- and Cu{sup 2+}-containing solutions. Copper ions were found to be incorporated into the active site only when Cu{sup +} was used. A comparative analysis of the native and depleted forms of the enzymes was performed.
Summary Growth of biodiesel industries resulted in increased coproduction of crude glycerol which is therefore becoming a waste product instead of a valuable ‘coproduct’. Glycerol can be used for the production of valuable chemicals, e.g. biofuels, to reduce glycerol waste disposal. In this study, a novel bacterial strain is described which converts glycerol mainly to ethanol and hydrogen with very little amounts of acetate, formate and 1,2‐propanediol as coproducts. The bacterium offers certain advantages over previously studied glycerol‐fermenting microorganisms. Anaerobium acetethylicum during growth with glycerol produces very little side products and grows in the presence of maximum glycerol concentrations up to 1500 mM and in the complete absence of complex organic supplements such as yeast extract or tryptone. The highest observed growth rate of 0.116 h −1 is similar to that of other glycerol degraders, and the maximum concentration of ethanol that can be tolerated was found to be about 60 mM (2.8 g l −1 ) and further growth was likely inhibited due to ethanol toxicity. Proteome analysis as well as enzyme assays performed in cell‐free extracts demonstrated that glycerol is degraded via glyceraldehyde‐3‐phosphate, which is further metabolized through the lower part of glycolysis leading to formation of mainly ethanol and hydrogen. In conclusion, fermentation of glycerol to ethanol and hydrogen by this bacterium represents a remarkable option to add value to the biodiesel industries by utilization of surplus glycerol.
ABSTRACT Spatial organization of pathway enzymes has emerged as a promising tool to address several challenges in metabolic engineering, such as flux imbalances and off-target product formation. Bacterial microcompartments (MCPs) are a spatial organization strategy used natively by many bacteria to encapsulate metabolic pathways that produce toxic, volatile intermediates. Several recent studies have focused on engineering MCPs to encapsulate heterologous pathways of interest, but how this engineering affects MCP assembly and function is poorly understood. In this study, we investigated the role of signal sequences, short domains that target proteins to the MCP core, in the assembly of 1,2-propanediol utilization (Pdu) MCPs. We characterized two novel Pdu signal sequences on the structural proteins PduM and PduB, which constitute the first report of metabolosome signal sequences on structural proteins rather than enzymes. We then explored the role of enzymatic and structural Pdu signal sequences on MCP assembly by deleting their encoding sequences from the genome alone and in combination. Deleting enzymatic signal sequences decreased the MCP formation, but this defect could be recovered in some cases by overexpressing genes encoding the knocked-out signal sequence fused to a heterologous protein. By contrast, deleting structural signal sequences caused similar defects to knocking out the genes encoding the full-length PduM and PduB proteins. Our results contribute to a growing understanding of how MCPs form and function in bacteria and provide strategies to mitigate assembly disruption when encapsulating heterologous pathways in MCPs. IMPORTANCE Spatially organizing biosynthetic pathway enzymes is a promising strategy to increase pathway throughput and yield. Bacterial microcompartments (MCPs) are proteinaceous organelles that many bacteria natively use as a spatial organization strategy to encapsulate niche metabolic pathways, providing significant metabolic benefits. Encapsulating heterologous pathways of interest in MCPs could confer these benefits to industrially relevant pathways. Here, we investigate the role of signal sequences, short domains that target proteins for encapsulation in MCPs, in the assembly of 1,2-propanediol utilization (Pdu) MCPs. We characterize two novel signal sequences on structural proteins, constituting the first Pdu signal sequences found on structural proteins rather than enzymes, and perform knockout studies to compare the impacts of enzymatic and structural signal sequences on MCP assembly. Our results demonstrate that enzymatic and structural signal sequences play critical but distinct roles in Pdu MCP assembly and provide design rules for engineering MCPs while minimizing disruption to MCP assembly.
As part of the Cyclotron Road program, Aralez Inc. investigated methods for producing chemicals sustainably, with a particular focus on engineering enzymes to make novel chemical products or accept new substrates that aren’t found in nature. We used directed evolution and other protein engineering techniques to create enzymes that perform abiological chemistry or make chemical products through a non-natural synthetic route. This work was an important step towards increasing the scope of compounds that can be manufactured in a sustainable fashion, which in turn will alleviate the high energy consumption, costly emissions, and waste that are hallmarks of current methods in chemical manufacturing.
There is keen interest to develop new technologies to recycle the plastic poly(ethylene terephthalate) (PET). To this end, the use of PET-hydrolyzing enzymes has shown promise for PET deconstruction to its monomers, terephthalate (TPA) and ethylene glycol (EG). Here, we compare the Ideonella sakaiensis PETase wild-type enzyme to a previously reported improved variant (W159H/S238F). We compare the thermostability of each enzyme and describe a 1.45 Å resolution structure of the mutant, highlighting changes in the substrate binding cleft compared to the wild-type enzyme. Subsequently, the performance of the wild-type and variant enzyme was compared as a function of temperature, substrate morphology, and reaction mixture composition. These studies show that reaction temperature has the strongest influence on performance between the two enzymes. We also show that both enzymes achieve higher levels of PET conversion for substrates with moderate crystallinity relative to amorphous substrates. Finally, we assess the impact of product accumulation on reaction progress for the hydrolysis of both PET and bis(2-hydroxyethyl) terephthalate (BHET). Each enzyme displays different inhibition profiles to mono(2-hydroxyethyl) terephthalate (MHET) and TPA, while both are sensitive to inhibition by EG. Overall, this work highlights the importance of reaction conditions, substrate selection, and product accumulation for catalytic performance of PET-hydrolyzing enzymes, which have implications for enzyme screening in the development of enzyme-based polyester recycling.
Cerium oxide nanoparticles (CNPs) have shown tremendous potential in various applications such as water gas shift catalysis, chemical mechanical planarization (CMP), solid oxide fuel cells (SOFC), solar cells4 and high temperature oxidation protection coatings1. Recently, CNPs have been demonstrated to protect biological tissues against radiation induced damage, scavenging of superoxide anions, prevention of laser induced retinal damage, reduction of spinal injury in a tissue culture model, prevention of cardiovascular myopathy, pH dependent antioxidant properties, as a tool for immunoassays as well as other inflammatory diseases2. In most biomedical applications it is speculated that nanoceria is a regenerative radical scavenger with the ability to regenerate its active 3+ oxidation state for radical scavenging. Thus far there are no reports to control the regeneration of Ce3+ oxidation state which is the most important parameter in the application of CNPs as a reliable and regenerative radical scavenger. Thus, there is an imminent need to increase the potency of CNPs to achieve higher degree of protection against reactive oxygen species (ROS), to increase the residence time of CNPs in body and to control the regeneration of 3+ oxidation state. PEG has been reported to increase the residence time of nanoparticles and proteins inside cells and provide biocompatibility3. PEGylated counterparts of the SOD enzymes have shown improved performance over non-PEGylated enzymes. Herein, we report our efforts to synthesize CNPs directly in polyethylene glycol (mol wt 600) solution and determine the effect of increasing concentration of PEG (PEG vol % as 5, 10, 20, 40, 60 and 80) on the SOD mimetic properties exhibited by nanoceria. We also report how the active Ce3+ oxidation state can be regenerated or further tuned to regenerate at faster rate. We further demonstrate the role of PEG on the redox chemistry of CNPs catalyzed by hydrogen peroxide. Several complexes of PEGs with lanthanides have been reported and characterized4. To evaluate the effect of PEG concentration on the complexation of cerium, UV-Vis spectra of the precursor salt of cerium (cerium nitrate hexahydrate) in different solutions of PEG were obtained (SI-1). It was observed that all PEG solutions showed an increase in absorption relative to the water based solution of cerium nitrate but the observed non specific trend cannot be ascribed to a systematic decrease in the solvent polarity or dielectric constant. This observation is in contrast to Uekawa et al5 who reported a red shift upon addition of cerium nitrate in PEG however, they ruled out the charge transfer between Ce4+ and oxygen. The above observation confirms the complexation of PEG with cerium ions. The CNPs were then synthesized as described in the experimental details (SI-2). High resolution transmission electron micrograph (Figure 1a) demonstrates that PEG coats as an amorphous layer on CNPs as observed from an amorphous background behind the crystalline core. To confirm further CNPs synthesized in PEG were dialyzed using a 3500 MWCO cellulose membrane and the FTIR spectrum was collected from the isolated powder. Figure 1b confirms the presence of PEG on the nanoceria particles. To facilitate the explanation, only representative spectrum from 20% PEG solution is shown.
The overall goal of this DOE Phase 2 project was to further develop and conduct pilot-scale and field testing of a biomimetic in-duct scrubbing system for the capture of gaseous CO 2 coupled with sequestration of captured carbon by carbonation of alkaline industrial wastes. The Phase 2 project, reported on here, combined efforts in enzyme development, scrubber optimization, and sequestrant evaluations to perform an economic feasibility study of technology deployment. The optimization of carbonic anhydrase (CA) enzyme reactivity and stability are critical steps in deployment of this technology. A variety of CA enzyme variants were evaluated for reactivity and stability in both bench scale and in laboratory pilot scale testing to determine current limits in enzyme performance. Optimization of scrubber design allowed for improved process economics while maintaining desired capture efficiencies. A range of configurations, materials, and operating conditions were examined at the Alcoa Technical Center on a pilot scale scrubber. This work indicated that a cross current flow utilizing a specialized gas-liquid contactor offered the lowest system operating energy. Various industrial waste materials were evaluated as sources of alkalinity for the scrubber feed solution and as sources of calcium for precipitation of carbonate. Solids were mixed with a simulated sodium bicarbonate scrubber blowdown to comparatively examine reactivity. Supernatant solutions and post-test solids were analyzed to quantify and model the sequestration reactions. The best performing solids were found to sequester between 2.3 and 2.9 moles of CO 2 per kg of dry solid in 1-4 hours of reaction time. These best performing solids were cement kiln dust, circulating dry scrubber ash, and spray dryer absorber ash. A techno-economic analysis was performed to evaluate the commercial viability of the proposed carbon capture and sequestration process in full-scale at an aluminum smelter and a refinery location. For both cases the in-duct scrubber technology was compared to traditional amine- based capture. Incorporation of the laboratory results showed that for the application at the aluminum smelter, the in-duct scrubber system is more economical than traditional methods. However, the reverse is true for the refinery case, where the bauxite residue is not effective enough as a sequestrant, combined with challenges related to contaminants in the bauxite residue accumulating in and fouling the scrubber absorbent. Sensitivity analyses showed that the critical variables by which process economics could be improved are enzyme concentration, efficiency, and half-life. At the end of the first part of the Phase 2 project, a gate review (DOE Decision Zero Gate Point) was conducted to decide on the next stages of the project. The original plan was to follow the pre-testing phase with a detailed design for the field testing. Unfavorable process economics, however, resulted in a decision to conclude the project before moving to field testing. It is noted that CO 2 Solutions proposed an initial solution to reduce process costs through more advanced enzyme management, however, DOE program requirements restricting any technology development extending beyond 2014 as commercial deployment timeline did not allow this solution to be undertaken.
The key regulatory step in the biosynthesis of abscisic acid (ABA), a hormone central to the regulation of several important processes in plants, is the oxidative cleavage of the 11,12 double bond of a 9-cis-epoxycarotenoid. The enzyme viviparous14 (VP14) performs this cleavage in maize (Zea mays), making it a target for the rational design of novel chemical agents and genetic modifications that improve plant behavior through the modulation of ABA levels. The structure of VP14, determined to 3.2-{angstrom} resolution, provides both insight into the determinants of regio- and stereospecificity of this enzyme and suggests a possible mechanism for oxidative cleavage. Furthermore, mutagenesis of the distantly related CCD1 of maize shows how the VP14 structure represents a template for all plant carotenoid cleavage dioxygenases (CCDs). In addition, the structure suggests how VP14 associates with the membrane as a way of gaining access to its membrane soluble substrate.
This project focused on developing cell-free systems to directly express multi-enzyme catalysts and perform CO2 bioconversions for industrial chemical production. The use of cell-free expression (CFE) systems derived from bacterial lysates is emerging as a promising approach for biomanufacturing. CFEs are genetically programmable, permit the expression of toxic enzymes, and allow for rapid prototyping of metabolic pathways. Research Contributions: 1. Understanding the Area Investigated: This research advances the understanding of cell-free systems by demonstrating their capability to perform complex multi-enzyme reactions. By directly expressing multi-gene systems, CFEs avoid the high costs and inefficiencies associated with producing and purifying enzymes for multi-step pathways. 2. Technical Effectiveness and Economic Feasibility: The project successfully engineered a CFE-based multienzyme biocatalyst for the de novo synthesis of serine and glycine from CO2 equivalents (formate and bicarbonate) and ammonia. This method achieved a 30% conversion rate of formate into these industrially important amino acids. Additionally, an 8-gene CFE biocatalyst was developed to produce malate, conserving 43% of carbon that would otherwise be lost as CO2. This approach has the potential to reach higher carbon efficiency than microbial production. 3. Public Benefit: The cell-free production of chemicals like serine, glycine, and malate using electrochemically generated formate could significantly reduce CO2 emissions. For example, satisfying the global malate market with this method could avoid approximately 400,000 tons of CO2 emissions annually. This work demonstrates the potential of CFE systems to produce platform chemicals, contributing to environmental sustainability and reducing reliance on petrochemicals. Future Prospects: The CFE-based biocatalyst process could be extended to produce a variety of chemicals, including other industrial di-acids, aromatics, terpenes, alcohols, and polymers. This project showcases the capabilities of cell-free expression systems for prototyping carbon-conserving pathways and sustainably bioproducing platform chemicals, marking a significant step towards economically-viable industrial processes.
The fastest synthetic molecular catalysts for production and oxidation of H2 emulate components of the active site of natural hydrogenases. The role of controlled structural dynamics is recognized as a critical component in the catalytic performance of many enzymes, including hydrogenases, but is largely neglected in the design of synthetic molecular cata-lysts. In this work, the impact of controlling structural dynamics on the rate of production of H2 was studied for a series of [Ni(PPh2NC6H4-R2)2]2+ catalysts including R = n-hexyl, n-decyl, n-tetradecyl, n-octadecyl, phenyl, or cyclohexyl. A strong correlation was observed between the ligand structural dynamics and the rates of electrocatalytic hydrogen production in acetonitrile, acetonitrile-water, and protic ionic liquid-water mixtures. Specifically, the turnover frequencies correlate inversely with the rates of ring inversion of the amine-containing ligand, as this dynamic process dictates the positioning of the proton relay in the second coordination sphere and therefore governs protonation at either catalytically productive or non-productive sites. This study demonstrates that the dynamic processes involved in proton delivery can be controlled through modifications of the outer coordination sphere of the catalyst, similar to the role of the protein architecture in many enzymes. The present work provides new mechanistic insight into the large rate enhancements observed in aqueous protic ionic liquid media for the [Ni(PPh2NR2)]2+ family of catalysts. The incorporation of controlled structural dynamics as a design parameter to modulate proton delivery in molecular catalysts has enabled H2 production rates that are up to three orders of magnitude faster than the [Ni(PPh2NPh2)]2+complex. The observed turnover frequencies are up to 106 s-1 in acetonitrile-water, and over 107 s-1 in protic ionic liquid-water mixtures, with a minimal increase in overpotential. This material is based upon work supported as part of the Center for Molecular Electrocatalysis, an Energy Frontier Research Center funded by the U.S. Department of Energy, Office of Science, Office of Basic Energy Sciences, and was performed in part using the Molecular Science Computing Facility (MSCF) in the William R. Wiley Environmental Molecular Sciences Laboratory, a DOE national scientific user facility located at Pacific Northwest National Laboratory (PNNL). PNNL is operated by Battelle for DOE.
Plastic use is ubiquitous in the modern world, and polyethylene terephthalate (PET) is one of the most abundantly produced plastics (and the most highly produced polyester), with ~65 million metric tons manufactured annually. To the consumer, PET is likely most recognizable as the plastic used to make beverage bottles. Like many plastics, traditional mechanical or chemical means of PET deconstruction and upcycling are costly and inefficient. Because of these challenges, recycled plastic is generally of lower quality and is more expensive to produce than virgin plastic derived from petroleum. Ultimately, this results in most plastic ending up as waste. We view plastic waste as an underutilized resource which, with the development of more efficient and high-quality recycling processes, could (1) generate significant economic value while (2) decreasing petroleum usage and greenhouse gas emissions, as well as (3) minimizing its negative environmental and health impacts. Biocatalytic recycling, or biomanufacturing the basic building blocks of new plastic from plastic waste, is a promising approach to plastic reuse that complements existing recycling technologies. Recently, biological enzymes capable of breaking down PET have garnered significant attention as an attractive means of dealing with the plastic problem. These enzymes are currently undergoing pilot studies for implementation in industrial-scale enzyme-based recycling. However, there are significant limitations to current enzymes, including the need to perform costly pre-processing of the plastic waste before the enzymes are able to work. Further optimization of these enzymes is necessary to make these technologies competitive, and ultimately incentivise industry-wide adoption of this biology-based green recycling technology. n this work we demonstrate a means to design and generate performant biological enzymes, capable of efficiently deconstructing plastic waste. Specifically, we applied recent advances in artificial intelligence, machine learning, and statistical analysis to design new versions and discover natural enzymes capable of breaking down PET. We focused on optimizing key properties that are important for industrial-scale enzymatic recycling such as pH and thermotolerance. Normal testing of enzymatic plastic-deconstruction is extremely labor intensive and so through this work we also developed a robotic-assisted experimental pipeline capable of characterizing thousands of candidate enzymes. The results of this iterative, AI-guided, multi-discipline approach have led to increases in enzymatic breakdown of over 150X over starting enzymes. This work supports the rapidly developing and transformative field of biocatalytic solutions to environmental problems beyond the discovery and predictive understanding of enzymes for polymer recycling, and has wide implications for tackling numerous energy problems such as carbon capture and fixation (e.g., engineering carbon monoxide dehydrogenase and the rubisco-pathway), biomining (e.g., design of lanthanide-binding proteins) and biomanufacturing (e.g., lignin-deconstruction enzymes).
The reduction of CO 2 into useful products, including hydrocarbon fuels, is an ongoing area of especial interest due to efforts to mitigate buildup of this greenhouse gas. While the industrial Fischer–Tropsch process can facilitate the hydrogenation of CO 2 with H 2 to form short-chain hydrocarbon products under high temperatures and pressures, a desire to perform these reactions under ambient conditions has inspired the use of biological approaches. Particularly, enzymes offer insight into how to activate and reduce CO 2 , but only one enzyme, nitrogenase, can perform the multielectron, multiproton reduction of CO 2 into hydrocarbons. The vanadium-containing variant, V-nitrogenase, displays especial reactivity towards the hydrogenation of CO and CO 2 . This Focus Review discusses recent progress towards the activation and reduction of CO 2 with three primary V-nitrogenase systems. These systems span both ATP-dependent and ATP-independent processes and utilize approaches with whole cells, isolated proteins, and extracted cofactors.
The BioEnergy Science Center (BESC) developed a high-throughput screening method to rapidly identify low-recalcitrance biomass variants. Because the customary separation and analysis of liquid and solids between pretreatment and enzymatic hydrolysis used in conventional analyses is slow, labor-intensive and very difficult to automate, a streamlined approach we term ‘co-hydrolysis’ was developed. In this method, the solids and liquid in the pretreated biomass slurry are not separated, but instead hydrolysis is performed by adding enzymes to the whole pretreated slurry. The effects of pretreatment method, severity and solids loading on co-hydrolysis performance were investigated. For hydrothermal pretreatment at solids concentrations of 0.5 to 2%, high enzyme protein loadings of about 100 mg/g of substrate (glucan plus xylan) in the original poplar wood achieved glucose and xylose yields for co-hydrolysis that were comparable with those for washed solids. In addition, although poplar wood sugar yields from co-hydrolysis at 2% solids concentrations fell short of those from hydrolysis of washed solids after dilute sulfuric acid pretreatment even at high enzyme loadings, pretreatment at 0.5% solids concentrations resulted in similar yields for all but the lowest enzyme loading. Overall, the influence of severity on susceptibility of pretreated substrates to enzymatic hydrolysis was clearly discernable, showing co-hydrolysis to be a viable approach for identifying plant-pretreatment-enzyme combinations with substantial advantages for sugar production.
Circular permutation of the NADPH-dependent oxidoreductase Old Yellow Enzyme from Saccharomyces pastorianus (OYE1) can significantly enhance the enzyme’s catalytic performance. Termini relocation into four regions of the protein (sectors I–IV) near the active site has proven effective in altering enzyme function. To better understand the structural consequences and rationalize the observed functional gains in these OYE1 variants, we selected representatives from sectors I–III for further characterization by biophysical methods and X-ray crystallography. These investigations not only show trends in enzyme stability and quaternary structure as a function of termini location but also provide a possible explanation for the catalytic gains in our top-performing OYE variant (new N-terminus at residue 303; sector III). Crystallographic analysis indicates that termini relocation into sector III affects the loop β6 region (amino acid positions: 290–310) of OYE1, which forms a lid over the active site. Peptide backbone cleavage greatly enhances local flexibility, effectively converting the loop into a tether and consequently increasing the environmental exposure of the active site. Interestingly, such an active site remodeling does not negatively impact the enzyme’s activity and stereoselectivity; neither does it perturb the conformation of other key active site residues with the exception of Y375. These observations were confirmed in truncation experiments, deleting all residues of the loop β6 region in our OYE variant. Intrigued by the finding that circular permutation leaves most of the key catalytic residues unchanged, we also tested OYE permutants for possible additive or synergistic effects of amino acid substitutions. Distinct functional changes in these OYE variants were detected upon mutations at W116, known in native OYE1 to cause inversion of diastereoselectivity for (S)-carvone reduction. In conclusion, our findings demonstrate the contribution of loop β6 toward determining the stereoselectivity of OYE1, an important insight for future OYE engineering efforts.
Abstract Expressing plant metabolic pathways in microbial platforms is an efficient, cost‐effective solution for producing many desired plant compounds. As eukaryotic organisms, yeasts are often the preferred platform. However, expression of plant enzymes in a yeast frequently leads to failure because the enzymes are poorly adapted to the foreign yeast cellular environment. Here, we first summarize the current engineering approaches for optimizing performance of plant enzymes in yeast. A critical limitation of these approaches is that they are labour‐intensive and must be customized for each individual enzyme, which significantly hinders the establishment of plant pathways in cellular factories. In response to this challenge, we propose the development of a cost‐effective computational pipeline to redesign plant enzymes for better adaptation to the yeast cellular milieu. This proposition is underpinned by compelling evidence that plant and yeast enzymes exhibit distinct sequence features that are generalizable across enzyme families. Consequently, we introduce a data‐driven machine learning framework designed to extract ‘yeastizing’ rules from natural protein sequence variations, which can be broadly applied to all enzymes. Additionally, we discuss the potential to integrate the machine learning model into a full design‐build‐test cycle.