Machine Learning in Enzymology (Methods in Enzymology)

Machine Learning in Enzymology, Volume 742 surveys cutting-edge machine learning–based approaches for the study of enzyme catalysis, dynamics, and design. Sections in this new release include Inferring conformational equilibria from sparse experimental data, Gaussian Process Regression and DeepMD models for simulating solution-phase and enzyme reactions, Modern Computational Enzymology Methods for Nucleic Acid Catalysis, Capturing Transition States of Enzyme Dynamics, Deep learning approaches for identifying the reaction coordinates and mechanisms of enzyme catalysis, Methods of walking in path space as applied to chemical reactions in enzymes, and more.Additional sections cover Using large language models for enzyme kinetics data extraction, Multidimensional Mechanistic Profiling at Scale with High-Throughput Enzymology, Using CLEAN for new enzyme discovery, Using EZSpecificity to expand the substrate border, and GeoEvoBuilder-Driven Enzyme Engineering with Enhanced Activity and Thermostability.
- Discusses cutting-edge machine learning approaches for both computational and experimental studies of enzymes
- Integrates physics-based simulations with data-driven models to characterize enzymatic mechanisms
- Includes methodological frameworks for enzyme discovery and rational protein engineering