Machine Learning-Guided Protein Engineering
Top Cited Papers
Open Access
- 13 October 2023
- journal article
- research article
- Published by American Chemical Society (ACS) in ACS Catalysis
- Vol. 13 (21) , 13863-13895
Abstract
Recent progress in engineering highly promising biocatalysts has increasingly involved machine learning methods. These methods leverage existing experimental and simulation data to aid in the discovery and annotation of promising enzymes, as well as in suggesting beneficial mutations for improving known targets. The field of machine learning for protein engineering is gathering steam, driven by recent success stories and notable progress in other areas. It already encompasses ambitious tasks such as understanding and predicting protein structure and function, catalytic efficiency, enantioselectivity, protein dynamics, stability, solubility, aggregation, and more. Nonetheless, the field is still evolving, with many challenges to overcome and questions to address. In this Perspective, we provide an overview of ongoing trends in this domain, highlight recent case studies, and examine the current limitations of machine learning-based methods. We emphasize the crucial importance of thorough experimental validation of emerging models before their use for rational protein design. We present our opinions on the fundamental problems and outline the potential directions for future research.Keywords
Funding Information
- Technology Agency of the Czech Republic (TN02000122, TN02000122/001N)
- European Regional Development Fund (CZ.02.1.01/0.0/0.0/15_003/0000468)
- Ministerstvo Školství, Mládeže a Tělovýchovy (CZ.02.1.01/0.0/0.0/17_043/0009632, LM2023055, LX22NPO5102, RI LM2023069)
- Grantová Agentura České Republiky (21-11563M)
- HORIZON EUROPE Marie Sklodowska-Curie Actions (891397)
- European Cooperation in Science and Technology (CA21162)
- Horizon 2020 Framework Programme (857560)
This publication has 341 references indexed in Scilit:
- MetaNetX.org: a website and repository for accessing, analysing and manipulating metabolic networksBioinformatics, 2013
- EnzML: multi-label prediction of enzyme classes using InterPro signaturesBMC Bioinformatics, 2012
- Rhea—a manually curated resource of biochemical reactionsNucleic Acids Research, 2011
- Structural space of protein–protein interfaces is degenerate, close to complete, and highly connectedProceedings of the National Academy of Sciences, 2010
- Synonymous codon usage influences the local protein structure observedNucleic Acids Research, 2010
- The Influence of Protein Dynamics on the Success of Computational Enzyme DesignJournal of the American Chemical Society, 2009
- Global distribution of conformational states derived from redundant models in the PDB points to non-uniqueness of the protein structureProceedings of the National Academy of Sciences, 2009
- PDB_REDO: automated re-refinement of X-ray structure models in the PDBJournal of Applied Crystallography, 2009
- AAindex: amino acid index database, progress report 2008Nucleic Acids Research, 2007
- The Protein Data BankNucleic Acids Research, 2000