Opportunities and Challenges for Machine Learning-Assisted Enzyme Engineering

Abstract

Enzymes can be engineered at the level of their amino acid sequences to optimize key properties such as expression, stability, substrate range, and catalytic efficiencyor even to unlock new catalytic activities not found in nature. Because the search space of possible proteins is vast, enzyme engineering usually involves discovering an enzyme starting point that has some level of the desired activity followed by directed evolution to improve its “fitness” for a desired application. Recently, machine learning (ML) has emerged as a powerful tool to complement this empirical process. ML models can contribute to (1) starting point discovery by functional annotation of known protein sequences or generating novel protein sequences with desired functions and (2) navigating protein fitness landscapes for fitness optimization by learning mappings between protein sequences and their associated fitness values. In this Outlook, we explain how ML complements enzyme engineering and discuss its future potential to unlock improved engineering outcomes.

Computational stabilization of a non-heme iron enzyme enables efficient evolution of new function

“…User-friendly deep learning tools like ProteinMPNN and related tools like MutCompute are rapidly emerging, 22,29,30 and our work suggests that these tools should be routinely incorporated into enzyme engineering workflows to efficiently optimize catalytic fitness for new biocatalysts. 31…”

“…Recent applications of deep learning to protein design have provided new and relatively straightforward methods to stabilize protein scaffolds, 22,29,30 and there is broad interest in applying these approaches to directed evolution. 31 Here we demonstrate that the deep learning tool ProteinMPNN 29,30 enables more efficient optimization of a synthetically-relevant, non-native C-H hydroxylation reaction in an Fe(II)/αKG family member. A critical step was restricting the redesign from modifying active site and adjacent residues, which would otherwise be readily mutated to stabilize the enzyme.…”

The Development and Opportunities of Predictive Biotechnology

“…The effective and sustainable utilization of data through methods like machine learning and deep learning still needs to be explored. [4,9,16,42,[63][64][65] This endeavor holds immense potential for reinterpreting and integrating stored data into new value chains. To make this possible, collaborative efforts are required to establish central databases, standardize data, develop universally linkable user interfaces, and clarify IP rights and usage costs.…”

Protein Representations: Encoding Biological Information for Machine Learning in Biocatalysis

“…Finally, ML has been combined with DE in the aptly termed "machine learningassisted" directed evolution (MLDE), where it has significantly improved the exploration of the sequence-function landscape in the search for enhanced variants (Bruce J. Wu et al, 2019;Xu et al, 2020;Yang et al, 2024Yang et al, , 2019. Traditionally, the focus within ML research has often been to refine the algorithms, whereas data representation is treated as a secondary concern.…”