Protein engineering is essential for altering the substrate scope, catalytic activity and selectivity of enzymes for applications in biocatalysis. However, traditional approaches, such as directed evolution and rational design, encounter the challenge in dealing with the experimental screening process of a large protein mutation space. Machine learning methods allow the approximation of protein fitness landscapes and the identification of catalytic patterns using limited experimental data, thus providing a new avenue to guide protein engineering campaigns. In this concept article, we review machine learning models that have been developed to assess enzyme‐substrate‐catalysis performance relationships aiming to improve enzymes through data‐driven protein engineering. Furthermore, we prospect the future development of this field to provide additional strategies and tools for achieving desired activities and selectivities.

The exploration of certain microbial resources such as beneficial endophytic microorganisms is considered a promising strategy for the discovery of new antimicrobial compounds for the pharmaceutical industries and agriculture. Thirty-one endophytic bacterial strains affiliated with Bacillus, Janthinobacterium, Yokenella, Enterobacter, Pseudomonas, Serratia, and Microbacterium were previously isolated from vetiver (Chrysopogon zizanioides (L.) Roberty) roots. These endophytes showed antifungal activity against Fusarium graminearum and could be a source of antimicrobial metabolites. In this study, in particular, using high-throughput screening, we analyzed their antagonistic activities and those of their cell-free culture supernatants against three species of Fusarium plant pathogens, a bacterial strain of Escherichia coli, and a yeast strain of Saccharomyces cerevisiae, as well as their capacity to produce lipopeptides. The results showed that the culture supernatants of four strains close to B. subtilis species exhibited antimicrobial activities against Fusarium species and E. coli. Using mass spectrometry analyses, we identified two groups of lipopeptides (surfactins and plipastatins) in their culture supernatants. Whole-genome sequencing confirmed that these bacteria possess NRPS gene clusters for surfactin and plipastatin. In vitro tests confirmed the inhibitory effect of plipastatin alone or in combination with surfactin against the three Fusarium species.

Hybrid catalysis is an emerging concept that combines chemo- and biocatalysts in a wide variety of approaches. Combining the specifications and advantages of multiple disciplines, it is a very promising way to diversify tomorrow's catalysis.

From the fusion of bio- and chemocatalysts, immobilized in innovative materials, a new family of catalysts is emerging: multi-catalytic hybrid materials (MCHMs). It offers atom and energy savings and, above all, new prospects in chemical synthesis.