13 December 2019 in ACS Catalysis
13 October 2023 in ACS Catalysis
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.
9 November 2020 in Nucleic Acids Research
The majority of naturally occurring proteins have evolved to function under mild conditions inside the living organisms. One of the critical obstacles for the use of proteins in biotechnological applications is their insufficient stability at elevated temperatures or in the presence of salts. Since experimental screening for stabilizing mutations is typically laborious and expensive, in silico predictors are often used for narrowing down the mutational landscape. The recent advances in machine learning and artificial intelligence further facilitate the development of such computational tools. However, the accuracy of these predictors strongly depends on the quality and amount of data used for training and testing, which have often been reported as the current bottleneck of the approach. To address this problem, we present a novel database of experimental thermostability data for single-point mutants FireProtDB. The database combines the published datasets, data extracted manually from the recent literature, and the data collected in our laboratory. Its user interface is designed to facilitate both types of the expected use: (i) the interactive explorations of individual entries on the level of a protein or mutation and (ii) the construction of highly customized and machine learning-friendly datasets using advanced searching and filtering. The database is freely available at https://loschmidt.chemi.muni.cz/fireprotdb.
24 January 2018 in Biotechnology and Bioengineering
23 October 2023 in Applied Catalysis B: Environment and Energy
24 November 2017 in Scientific Reports
Studies of protein unfolding mechanisms are critical for understanding protein functions inside cells, de novo protein design as well as defining the role of protein misfolding in neurodegenerative disorders. Calorimetry has proven indispensable in this regard for recording full energetic profiles of protein unfolding and permitting data fitting based on unfolding pathway models. While both kinetic and thermodynamic protein stability are analysed by varying scan rates and reheating, the latter is rarely used in curve-fitting, leading to a significant loss of information from experiments. To extract this information, we propose fitting both first and second scans simultaneously. Four most common single-peak transition models are considered: (i) fully reversible, (ii) fully irreversible, (iii) partially reversible transitions, and (iv) general three-state models. The method is validated using calorimetry data for chicken egg lysozyme, mutated Protein A, three wild-types of haloalkane dehalogenases, and a mutant stabilized by protein engineering. We show that modelling of reheating increases the precision of determination of unfolding mechanisms, free energies, temperatures, and heat capacity differences. Moreover, this modelling indicates whether alternative refolding pathways might occur upon cooling. The Matlab-based data fitting software tool and its user guide are provided as a supplement.