Biocatalysis harnesses enzymes to make valuable products. This green technology is used in countless applications from bench scale to industrial production and allows practitioners to access complex organic molecules, often with fewer synthetic steps and reduced waste. The last decade has seen an explosion in the development of experimental and computational tools to tailor enzymatic properties, equipping enzyme engineers with the ability to create biocatalysts that perform reactions not present in nature. By using (chemo)-enzymatic synthesis routes or orchestrating intricate enzyme cascades, scientists can synthesize elaborate targets ranging from DNA and complex pharmaceuticals to starch made in vitro from CO ₂ -derived methanol. In addition, new chemistries have emerged through the combination of biocatalysis with transition metal catalysis, photocatalysis, and electrocatalysis. This review highlights recent key developments, identifies current limitations, and provides a future prospect for this rapidly developing technology.

Anthocyanins are ubiquitous plant pigments used in a variety of technological applications. Yet, after over a century of research, the penultimate biosynthetic step to anthocyanidins attributed to the action of leucoanthocyanidin dioxygenase has never been efficiently reconstituted outside plants, preventing the construction of heterologous cell factories. Through biochemical and structural analysis, here we show that anthocyanin-related glutathione transferases, currently implicated only in anthocyanin transport, catalyse an essential dehydration of the leucoanthocyanidin dioxygenase product, flavan-3,3,4-triol, to generate cyanidin. Building on this knowledge, introduction of anthocyanin-related glutathione transferases into a heterologous biosynthetic pathway in baker’s yeast results in >35-fold increased anthocyanin production. In addition to unravelling the long-elusive anthocyanin biosynthesis, our findings pave the way for the colourants’ heterologous microbial production and could impact the breeding of industrial and ornamental plants.

Late-stage functionalization of natural products offers an elegant route to create novel entities in a relevant biological target space. In this context, enzymes capable of halogenating sp³carbons with high stereo- and regiocontrol under benign conditions have attracted particular attention. Enabled by a combination of smart library design and machine learning, we engineer the iron/α-ketoglutarate dependent halogenase WelO5* for the late-stage functionalization of the complex and chemically difficult to derivatize macrolides soraphen A and C, potent anti-fungal agents. While the wild type enzyme WelO5* does not accept the macrolide substrates, our engineering strategy leads to active halogenase variants and improves upon their apparentk_catand total turnover number by more than 90-fold and 300-fold, respectively. Notably, our machine-learning guided engineering approach is capable of predicting more active variants and allows us to switch the regio-selectivity of the halogenases facilitating the targeted analysis of the derivatized macrolides’ structure-function activity in biological assays.

The field of computational drug design requires accurate scoring functions to predict binding affinities for protein–ligand interactions. However, train–test data leakage between the PDBbind database and the Comparative Assessment of Scoring Function benchmark datasets has severely inflated the performance metrics of currently available deep-learning-based binding affinity prediction models, leading to overestimation of their generalization capabilities. Here we address this issue by proposing PDBbind CleanSplit, a training dataset curated by a new structure-based filtering algorithm that eliminates train–test data leakage as well as redundancies within the training set. Retraining current top-performing models on CleanSplit caused their benchmark performance to drop substantially, indicating that the performance of existing models is largely driven by data leakage. By contrast, our graph neural network model maintains high benchmark performance when trained on CleanSplit. Leveraging a sparse graph modelling of protein–ligand interactions and transfer learning from language models, our model is able to generalize to strictly independent test datasets.