Machine Learning-Based Enzyme Engineering of PETase for Improved Efficiency in Degrading Non-Biodegradable Plastic

Globally, nearly a million plastic bottles are produced every minute (1). These non-biodegradable plastic products are composed of Polyethylene terephthalate (PET). In 2016, researchers discovered PETase, an enzyme from the bacteria Ideonella sakaiensis which breaks down PET and nonbiodegradable plastic. However, PETase has low efficiency at high temperatures. In this project, we optimized the rate of PET degradation by PETase by designing new mutant enzymes which could break down PET much faster than PETase, which is currently the gold standard. We used machine learning (ML) guided directed evolution to modify the PETase enzyme to have a higher optimal temperature (Topt), which would allow the enzyme to degrade PET more efficiently. First, we trained three machine learning models to predict Topt with high performance, including Logistic Regression, Linear Regression and Random Forest. We then used Random Forest to perform ML-guided directed evolution. Our algorithm generated hundreds of mutants of PETase and screened them using Random Forest to select mutants with the highest Topt, and then used the top mutants as the enzyme being mutated. After 1000 iterations, we produced a new mutant of PETase with Topt of 71.38℃. We also produced a new mutant enzyme after 29 iterations with Topt of 61.3℃. To ensure these mutant enzymes would remain stable, we predicted their melting temperatures using an external predictor and found the 29-iteration mutant had improved thermostability over PETase. Our research is significant because using our approach and algorithm, scientists can optimize additional enzymes for improved efficiency.

Directed evolution of the rRNA methylating enzyme Cfr reveals molecular basis of antibiotic resistance

Alteration of antibiotic binding sites through modification of ribosomal RNA (rRNA) is a common form of resistance to ribosome-targeting antibiotics. The rRNA-modifying enzyme Cfr methylates an adenosine nucleotide within the peptidyl transferase center, resulting in the C-8 methylation of A2503 (m8A2503). Acquisition of cfr results in resistance to eight classes of ribosome-targeting antibiotics. Despite the prevalence of this resistance mechanism, it is poorly understood whether and how bacteria modulate Cfr methylation to adapt to antibiotic pressure. Moreover, direct evidence for how m8A2503 alters antibiotic binding sites within the ribosome is lacking. In this study, we performed directed evolution of Cfr under antibiotic selection to generate Cfr variants that confer increased resistance by enhancing methylation of A2503 in cells. Increased rRNA methylation is achieved by improved expression and stability of Cfr through transcriptional and post-transcriptional mechanisms, which may be exploited by pathogens under antibiotic stress as suggested by natural isolates. Using a variant that achieves near-stoichiometric methylation of rRNA, we determined a 2.2 Å cryo-electron microscopy structure of the Cfr-modified ribosome. Our structure reveals the molecular basis for broad resistance to antibiotics and will inform the design of new antibiotics that overcome resistance mediated by Cfr.

Directed Evolution of a Ketone Synthase for Efficient and Highly Selective Functionalization of Internal Alkenes by Accessing Reactive Carbocation Intermediates

The direct regioselective oxidation of internal alkenes to ketones could simplify synthetic routes and solve a longstanding challenge in synthesis. This reaction is of particular importance because ketones are predominant moieties in valuable products as well as crucial intermediates in synthesis. Here we report the directed evolution of a ketone synthase that oxidizes internal alkenes directly to ketones with several thousand turnovers. The evolved ketone synthase benefits from more than a dozen crucial mutations, most of them distal to the active site. Computational analysis reveals that all these mutations collaborate to facilitate the formation of a highly reactive carbocation intermediate by generating a confined, rigid and preorganized active site through an enhanced dynamical network. The evolved ketone synthase fully exploits a catalytic cycle that has largely eluded small molecule catalysis and consequently enables various challenging functionalization reactions of internal alkenes. This includes the first catalytic, enantioselective oxidation of internal alkenes to ketones, as well as the formal asymmetric hydration and hydroamination of unactivated internal alkenes in combination with other biocatalysts.

Directed evolution of angiotensin-converting enzyme 2 (ACE2) variants with enhanced peptidase activity profiles for novel therapeutic applications

Mutants of the Angiotensin Converting-Enzyme 2 (ACE2) carboxypeptidase possessing enhanced hydrolytic activity and specificity hold potential to beneficially modulate the Angiotensin receptor (ATR) therapeutic axis with increased efficacy and reduced potential side effects relative to wild type ACE2. In pursuing this goal, we established a yeast display-based liquid chromatography screen that enabled use of directed evolution to identify ACE2 mutants with improved target peptide substrate, Angiotensin-II (Ang-II), activity and specificity relative to Apelin-13, an off-target peptide substrate. Screening yeast-displayed ACE2 active site residue saturation mutant libraries revealed three substitution-tolerant positions that can be mutated to enhance ACE2's activity profile. Double mutant libraries combining substitutions at these positions, M360, T371 and Y510, yielded candidate improved ACE2 mutants that were recombinantly expressed and purified at 1 mg/L yield and > 90% homogeneity. Relative to wild type, the leading mutant, T371L/Y510Ile, has seven-fold increased kcat toward Ang-II and six-fold decreased kcat/Km for Apelin-13 hydrolysis. In single substrate hydrolysis assays featuring physiologically relevant substrate concentrations T371L/Y510Ile hydrolyzes more Ang-II than wild type with concomitant Ang-II:Apelin-13 specificity improvements reaching 30-fold. Additionally, T371L/Y510Ile hydrolyzed Ang-II at rates greater than wild type, with Apelin-13 hydrolysis reductions of up to 80 percent, in multiplex assays containing a mixture of peptides relevant to the ATR therapeutic axis. Our efforts have delivered ATR axis-acting therapeutic candidates with relevance to established and unexplored ACE2 therapeutic applications and demonstrate the feasibility of developing ACE2 variants for use in biomedical contexts unrelated to the ATR axis such as localized activation of peptide-based prodrugs.

Directed Evolution of The PobR Allosteric Transcription Factor To Generate A Biosensor For 4-Hydroxymandelic Acid

4-Hydroxymandelic acid (HMA) is widely applied in pharmaceuticals, food and cosmetics. In this study, we aimed to develop an allosteric transcription factors (aTFs) based biosensor for HMA. PobR, an aTF for HMA analog 4-hydroxybenzoic acid, was used to alter its selectivity and create novel aTFs responsive to HMA by directed evolution. We established a PobR mutant library with a capacity of 550,000 mutants using error-prone PCR and Megawhop PCR. Through our screening, two mutants were obtained with responsiveness to HMA. Analysis of each missense mutation indicating residues 122-126 were involved in its PobR ligand specificity. These results showed the effectiveness of directed evolution in switching the ligand specificity of a biosensor and improving HMA production.

Directed Evolution of an Efficient and Thermostable PET Depolymerase

The recent discovery of a hydrolytic enzyme, IsPETase, that can deconstruct poly(ethylene) terephthalate (PET), has sparked great interest in biocatalytic approaches to recycle plastics. Realisation of commercial utility will require the development of robust engineered enzymes that meet the demands of industrial processes. Although rationally engineered variants of PETases have been reported, enzymes that have been experimentally optimised through iterative rounds of directed evolution - the go-to method for engineering industrially useful biocatalysts – have not yet been described. Here, we report the development and implementation of an automated, high-throughput directed evolution platform for engineering polymer degrading enzymes. Evaluation of >13,000 IsPETase variants, applying catalytic activity at elevated temperatures as a primary selection pressure, afforded a HotPETase variant with 21 mutations that has a melting temperature of 82.5C and can therefore operate near or above the glass transition temperature of PET (60-70C). HotPETase can depolymerise semi-crystalline PET more rapidly than previously reported PETases and can selectively deconstruct the PET component of a laminated packaging multi-material. Structural characterisation of HotPETase reveals several interesting features that have emerged during evolution to improve thermotolerance and catalytic performance. Our study establishes laboratory evolution as a platform to engineer useful plastic degrading enzymes to underpin biocatalytic plastic recycling processes.