EnginZyme AB is a Swedish synthetic biology company that, through the use of its proprietary enzyme immobilisation technology, is transforming the chemical industry and enabling the development of scalable, efficient continuous enzymatic processes. One of the primary cost drivers for continuous, immobilised enzyme reactors for fine chemicals is the expected enzyme lifetime. This places an emphasis on stability that is not common to other areas such as the production of APIs. To address this problem, the enzyme engineering group at EnginZyme has developed a state of the art in silico tool named ‘ThunderDome’ that enables the design and selection of highly stable enzymes from a single pass. Unlike other engineering strategies, we screen just a few 10s of enzymes to identify suitably robust and high performing candidates. In this presentation we will highlight some of our experiences in applying computational methods to producing industrial grade enzymes. Our process combines biological, classical in silico and state of the art machine learning methods to predict outstanding performance in enzymes.
Martin Engqvist is a Group Lead of Computational Enzyme Design at EnginZyme, a company focusing on sustainable chemicals production using biological catalysts. Martin specializes in applying machine learning to enzyme design, improving their stability and activity. His academic journey includes a Ph.D. in Botany/Plant Biology from the University of Cologne, postdoctoral research in directed evolution at Caltech, bioinformatics research at Gothenburg University, and a tenure as Assistant Professor at Chalmers University of Technology.
