Machine Learning Enables Selection of Epistatic Enzyme Mutants for Stability Against Unfolding and Detrimental Aggregation

• Published in: Chembiochem : a European journal of chemical biology Vol. 22; no. 5; pp. 904 - 914
• Main Authors: Li, Guangyue, Qin, Youcai, Fontaine, Nicolas T., Ng Fuk Chong, Matthieu, Maria‐Solano, Miguel A., Feixas, Ferran, Cadet, Xavier F., Pandjaitan, Rudy, Garcia‐Borràs, Marc, Cadet, Frederic, Reetz, Manfred T.
• Format: Journal Article
• Language: English
• Published: Germany Wiley Subscription Services, Inc 02.03.2021; John Wiley and Sons Inc
• Subjects: Agglomeration; Amino acid sequence; artificial intelligence; Deep learning; Enzymes; Epistasis; Epoxide hydrolase; Fourier transforms; innov'SAR; Learning algorithms; Limonene; Machine learning; Molecular dynamics; molecular dynamics simulations; Protein engineering; Proteins; Robustness; Signal processing; Stability; Stereoselectivity; molecular dynamics simulations; innov'SAR; epistasis; machine learning; epoxide hydrolase; artificial intelligence
• ISSN: 1439-4227; 1439-7633
• DOI: 10.1002/cbic.202000612

Machine learning (ML) has pervaded most areas of protein engineering, including stability and stereoselectivity. Using limonene epoxide hydrolase as the model enzyme and innov'SAR as the ML platform, comprising a digital signal process, we achieved high protein robustness that can resist unfolding with concomitant detrimental aggregation. Fourier transform (FT) allows us to take into account the order of the protein sequence and the nonlinear interactions between positions, and thus to grasp epistatic phenomena. The innov'SAR approach is interpolative, extrapolative and makes outside‐the‐box, predictions not found in other state‐of‐the‐art ML or deep learning approaches. Equally significant is the finding that our approach to ML in the present context, flanked by advanced molecular dynamics simulations, uncovers the connection between epistatic mutational interactions and protein robustness. A quick learner: Machine learning based on the innov'SAR algorithm leads to efficient selection of highly robust limonene epoxide hydrolase mutants with enhanced unfolding stability and resistance to aggregation by recognizing epistatic mutational interactions.