A review of enzyme design in catalytic stability by artificial intelligence

Abstract

The design of enzyme catalytic stability is of great significance in medicine and industry. However, traditional methods are time-consuming and costly. Hence, a growing number of complementary computational tools have been developed, e.g. ESMFold, AlphaFold2, Rosetta, RosettaFold, FireProt, ProteinMPNN. They are proposed for algorithm-driven and data-driven enzyme design through artificial intelligence (AI) algorithms including natural language processing, machine learning, deep learning, variational autoencoder/generative adversarial network, message passing neural network (MPNN). In addition, the challenges of design of enzyme catalytic stability include insufficient structured data, large sequence search space, inaccurate quantitative prediction, low efficiency in experimental validation and a cumbersome design process. The first principle of the enzyme catalytic stability design is to treat amino acids as the basic element. By designing the sequence of an enzyme, the flexibility and stability of the structure are adjusted, thus controlling the catalytic stability of the enzyme in a specific industrial environment or in an organism. Common indicators of design goals include the change in denaturation energy (ΔΔG), melting temperature (ΔTm), optimal temperature (Topt), optimal pH (pHopt), etc. In this review, we summarized and evaluated the enzyme design in catalytic stability by AI in terms of mechanism, strategy, data, labeling, coding, prediction, testing, unit, integration and prospect.

Solvatochromic sensors detect proteome aggregation in stressed liver tissues with hepatic cancer and cirrhosis

“…Thermal shift assay is one of the standard characterization methods to evaluate the thermodynamic stability of target protein, where T m is defined as the midpoint of temperature during the protein misfolding and aggregating transition. 42,43 Thermal shift analysis emphasized that the fluorescence T m values of P1 and P2 were slightly lower than the turbidity readings at OD 330 that measures insoluble aggregates. This result indicated that the binding of P1 and P2 probes with misfolded proteins occurred earlier than the formation of insoluble aggregates measured by OD 330 (Fig.…”

In Vitro Biotransformation of High-Titer d-Glucarate by Stepwise-Added Enzyme Cocktails

“…MIOX is the most important enzyme for GA production via MI, regardless of microbial fermentation and ivBT here. , MIOX has low specific activity and low stability, resulting in a large amount of MIOX and a long reaction time, respectively. Therefore, further improvements of MIOX could focus on (1) discovery of better enzymes, (2) enzyme engineering by rational design, directed evolution, and AI-aided protein engineering, − and (3) enzyme immobilization . Further studies on the stability of MIOX and cascade process optimization are underway to further improve the performance of this process.…”

AlphaFold2 and Deep Learning for Elucidating Enzyme Conformational Flexibility and Its Application for Design

“…Some recent reviews focused on structure-based protein design with DL strategies are available, 39,40 as well as a review related to the design of more stable enzymes. 41 These available strategies for structure prediction can be classified depending on the number of input parameters used: those that require the input query sequence, MSA, and set of templates for accurate predictions and those that predict the folded structure based on the input sequence only. Similarly to AF2, the RoseTTAFold (RF) algorithm developed almost at the same time as AF2 requires an MSA and a set of initial templates to make accurate predictions of the folded structure.…”

“…In this section, we aim to provide a brief overview of the most representative techniques developed, and we put special emphasis to those strategies that are particularly relevant for enzyme design. Some recent reviews focused on structure-based protein design with DL strategies are available, , as well as a review related to the design of more stable enzymes …”