Discrimination of psychrophilic enzymes using machine learning algorithms with amino acid composition descriptor

Abstract

IntroductionPsychrophilic enzymes are a class of macromolecules with high catalytic activity at low temperatures. Cold-active enzymes possessing eco-friendly and cost-effective properties, are of huge potential application in detergent, textiles, environmental remediation, pharmaceutical as well as food industry. Compared with the time-consuming and labor-intensive experiments, computational modeling especially the machine learning (ML) algorithm is a high-throughput screening tool to identify psychrophilic enzymes efficiently.MethodsIn this study, the influence of 4 ML methods (support vector machines, K-nearest neighbor, random forest, and naïve Bayes), and three descriptors, i.e., amino acid composition (AAC), dipeptide combinations (DPC), and AAC + DPC on the model performance were systematically analyzed.Results and discussionAmong the 4 ML methods, the support vector machine model based on the AAC descriptor using 5-fold cross-validation achieved the best prediction accuracy with 80.6%. The AAC outperformed than the DPC and AAC + DPC descriptors regardless of the ML methods used. In addition, amino acid frequencies between psychrophilic and non-psychrophilic proteins revealed that higher frequencies of Ala, Gly, Ser, and Thr, and lower frequencies of Glu, Lys, Arg, Ile,Val, and Leu could be related to the protein psychrophilicity. Further, ternary models were also developed that could classify psychrophilic, mesophilic, and thermophilic proteins effectively. The predictive accuracy of the ternary classification model using AAC descriptor via the support vector machine algorithm was 75.8%. These findings would enhance our insight into the cold-adaption mechanisms of psychrophilic proteins and aid in the design of engineered cold-active enzymes. Moreover, the proposed model could be used as a screening tool to identify novel cold-adapted proteins.

Exploring the molecular mechanism of cold‐adaption of an alkaline protease mutant by molecular dynamics simulations and residue interaction network

“…Previous studies have also reported that cold‐adapted serine hydroxymethyl transferase enhanced the interaction with solvents to improve their conformational flexibility, which resulted in high catalytic activity at low temperatures (Zhang, Xia, et al, 2021). In addition, statistical analyses of amino acids of the psychrophilic and mesophilic proteins showed that there are more Ser and Thr amino acids in the psychrophilic proteins, which lead to the formation of more interactions between the proteins and water molecules, thus increasing the flexibility of protein structure (Huang et al, 2023; Nath & Subbiah, 2014).…”

Comprehensive insights on environmental adaptation strategies in Antarctic bacteria and biotechnological applications of cold adapted molecules

“…Furthermore, studies based on machine learning have been reported on thermophilic and mesophilic bacterial proteins, however little is known about the application of ML approach in psychrophilic enzymes. Recent study on psychrophilic amino acid composition (AAC) using machine learning (ML) algorithm showed that psychrophiles proteins contains high frequency of Ala, Gly, Ser, and Thr, compared to Glu, Lys, Arg, Ile, Val, and Leu amino acids (Huang et al, 2023a). The support vector machine learning model (SVM) in combination with molecular dynamics (MD) is employed to study the thermostability of psychrophilic alpha-amylase (Figure 3) (exhibited high activity at low temperature) isolated from Pseudoalteromonas haloplanktis (Li et al, 2020).…”

Psychrophilic enzymes: strategies for cold-adaptation

“…It was shown that proteins adapted to different temperatures are highly similar, that no alterations in the reaction mechanism are involved, that all catalytic residues are highly conserved (see Figure 4 for an example), and that the structural changes necessary for cold-adaptation are discrete and enzyme-specific [58]. As compared to enzymes adapted to higher temperatures, cold-adapted enzymes frequently display a reduction in strength and/or number of stabilizing interactions, and/or an introduction of specific protein flexibility-enhancing modifications [32,[59][60][61][62]. These alterations may be localized, commonly near the active site, or global.…”