Prediction Of Thermostability Research Articles

TemStaPro: protein thermostability prediction using sequence representations from protein language models.

Reliable prediction of protein thermostability from its sequence is valuable for both academic and industrial research. This prediction problem can be tackled using machine learning and by taking advantage of the recent blossoming of deep learning methods for sequence analysis. These methods can facilitate training on more data and, possibly, enable the development of more versatile thermostability predictors for multiple ranges of temperatures. We applied the principle of transfer learning to predict protein thermostability using embeddings generated by protein language models (pLMs) from an input protein sequence. We used large pLMs that were pre-trained on hundreds of millions of known sequences. The embeddings from such models allowed us to efficiently train and validate a high-performing prediction method using over one million sequences that we collected from organisms with annotated growth temperatures. Our method, TemStaPro (Temperatures of Stability for Proteins), was used to predict thermostability of CRISPR-Cas Class II effector proteins (C2EPs). Predictions indicated sharp differences among groups of C2EPs in terms of thermostability and were largely in tune with previously published and our newly obtained experimental data. TemStaPro software and the related data are freely available from https://github.com/ievapudz/TemStaPro and https://doi.org/10.5281/zenodo.7743637.

Computer-Aided Reconstruction and Application of Bacillus halodurans S7 Xylanase with Heat and Alkali Resistance.

β-1,4-Endoxylanase is the most critical hydrolase for xylan degradation during lignocellulosic biomass utilization. However, its poor stability and activity in hot and alkaline environments hinder its widespread application. In this study, BhS7Xyl from Bacillus halodurans S7 was improved using a computer-aided design through isothermal compressibility (βT) perturbation engineering and by combining three thermostability prediction algorithms (ICPE-TPA). The best variant with remarkable improvement in specific activity, heat resistance (70 °C), and alkaline resistance (both pH 9.0 and 70 °C), R69F/E137M/E145L, exhibited a 4.9-fold increase by wild-type in specific activity (1368.6 U/mg), a 39.4-fold increase in temperature half-life (458.1 min), and a 57.6-fold increase in pH half-life (383.1 min). Furthermore, R69F/E137M/E145L was applied to the hydrolysis of agricultural waste (corncob and hardwood pulp) to efficiently obtain a higher yield of high-value xylooligosaccharides. Overall, the ICPE-TPA strategy has the potential to improve the functional performance of enzymes under extreme conditions for the high-value utilization of lignocellulosic biomass.

Prediction of Thermostability of Enzymes Based on the Amino Acid Index (AAindex) Database and Machine Learning.

The combination of wet-lab experimental data on multi-site combinatorial mutations and machine learning is an innovative method in protein engineering. In this study, we used an innovative sequence-activity relationship (innov'SAR) methodology based on novel descriptors and digital signal processing (DSP) to construct a predictive model. In this paper, 21 experimental (R)-selective amine transaminases from Aspergillus terreus (AT-ATA) were used as an input to predict higher thermostability mutants than those predicted using the existing data. We successfully improved the coefficient of determination (R2) of the model from 0.66 to 0.92. In addition, root-mean-squared deviation (RMSD), root-mean-squared fluctuation (RMSF), solvent accessible surface area (SASA), hydrogen bonds, and the radius of gyration were estimated based on molecular dynamics simulations, and the differences between the predicted mutants and the wild-type (WT) were analyzed. The successful application of the innov'SAR algorithm in improving the thermostability of AT-ATA may help in directed evolutionary screening and open up new avenues for protein engineering.

A Machine Learning Study on the Thermostability Prediction of (R)-ω-Selective Amine Transaminase from Aspergillus terreus.

Artificial intelligence technologies such as machine learning have been applied to protein engineering, with unique advantages in protein structure, function prediction, catalytic activity, and other issues in recent years. Screening better mutants is still a bottleneck in protein engineering. In this paper, a new sequence-activity relationship method was analyzed for its application in improving the thermal stability of Aspergillus terreus (R)-ω-selective amine transaminase. The experimental data from 6 single-point mutated enzymes were used as a learning dataset to build models and predict the thermostability of 26 mutants. Based on digital signal processing (DSP), this method digitized the amino acid sequence of proteins by fast Fourier transform (FFT) and then established the best model applying partial least squares regression (PLSR) to screen out all possible mutants, especially those with high performance. In protein engineering, the innovative sequence activity relationship (ISAR) method can make a reasonable prediction using limited experimental data and significantly reduce the experimental cost. The half-life (T1/2) of (R)-ω-transaminase was fitted with the amino acid sequence by the ISAR algorithm, resulting in an R2 of 0.8929 and a cvRMSE of 4.89. At the same time, the mutants with higher T1/2 than the existing ones were predicted, laying the groundwork for better (R)-ω-transaminase in the later stage. The ISAR algorithm is expected to provide a new technique for protein evolution and screening.

Computational approach for identification, characterization, three-dimensional structure modelling and machine learning-based thermostability prediction of xylanases from the genome of Aspergillus fumigatus

Identification of thermostable and alkaline xylanases from different fungal and bacterial species have gained an interest for the researchers because of its biotechnological relevance in many industries, such as pulp, paper, and bioethanol. In this study, we have identified and characterized xylanases from the genome of the thermophilic fungus of Aspergillus fumigatus by in silico analysis. Genome data mining revealed that the A fumigatus genome has six xylanase genes that belong to GH10, GH11, GH43 glycoside hydrolase families. In general, most of the bacterial and fungal GH11 xylanases are alkaline, and GH10 xylanases are acidic; however, we found that one identified xylanase from A fumigatus that belongs to the GH10 family is alkaline while the rest are acidic. Moreover, physicochemical properties also stated that most of the xylanases identified have lower molecular weight except one that belongs to the GH43 family. Structure prediction by homology modelling gave optimized structures of the xylanases. It suggests that GH10 family structure models adapt (β∕α) 8 barrel type, GH11 homology models adapt β-jelly type, and the GH43 family has a fivefold β-propeller type structure. Molecular docking of identified xylanases with xylan revealed that GH11 xylanases have strong interaction (-9.6 kcal/mol) with xylan than the GH10 (-8.5 and -9.3 kcal/mol) and GH43 (-8.8 kcal/mol). We used the machine learning approach based TAXyl server to predict the thermostability of the xylanases. It revealed that two GH10 xylanases and one GH11 xylanase are thermo-active up to 75ᵒC. We have explored the physiochemical properties responsible for maintaining thermostability for bacterial and fungal GH10 and GH11 xylanases by comparing crystal structures. All the analyzed parameters specified that GH10 xylanases from both the fungi and bacteria are more thermostable due to higher hydrogen bonds, salt bridges, and helical content.

Evaluating Protein Engineering Thermostability Prediction Tools Using an Independently Generated Dataset.

Engineering proteins to enhance thermal stability is a widely utilized approach for creating industrially relevant biocatalysts. The development of new experimental datasets and computational tools to guide these engineering efforts remains an active area of research. Thus, to complement the previously reported measures of T50 and kinetic constants, we are reporting an expansion of our previously published dataset of mutants for β-glucosidase to include both measures of TM and ΔΔG. For a set of 51 mutants, we found that T50 and TM are moderately correlated, with a Pearson correlation coefficient and Spearman’s rank coefficient of 0.58 and 0.47, respectively, indicating that the two methods capture different physical features. The performance of predicted stability using nine computational tools was also evaluated on the dataset of 51 mutants, none of which are found to be strong predictors of the observed changes in T50, TM, or ΔΔG. Furthermore, the ability of the nine algorithms to predict the production of isolatable soluble protein was examined, which revealed that Rosetta ΔΔG, FoldX, DeepDDG, PoPMuSiC, and SDM were capable of predicting if a mutant could be produced and isolated as a soluble protein. These results further highlight the need for new algorithms for predicting modest, yet important, changes in thermal stability as well as a new utility for current algorithms for prescreening designs for the production of mutants that maintain fold and soluble production properties.

An Overview of the Protein Thermostability Prediction: Databases and Tools

Thermophilic proteins are characterized as high thermal stability proteins while mesophilic proteins are stable at lower temperatures. These types of proteins have numerous applications regarding protein engineering, drug design and industrial processes. Studies showedthatthermal stability is strongly related to structuraland sequential properties in thermophilic proteins. Some computational studies were being taken to identify the mentioned properties in heat resistant proteins. This paper reviews the studies of protein thermostability prediction and gives an introduction to the thermal stability related tools and databases.

Rapid Computational Prediction of Thermostabilizing Mutations for G Protein-Coupled Receptors.

G protein-coupled receptors (GPCRs) are highly dynamic and often denature when extracted in detergents. Deriving thermostable mutants has been a successful strategy to stabilize GPCRs in detergents, but this process is experimentally tedious. We have developed a computational method to predict the position of the thermostabilizing mutations for a given GPCR sequence. We have validated the method against experimentally measured thermostability data for single mutants of the β1-adrenergic receptor (β1AR), adenosine A2A receptor (A2AR) and neurotensin receptor 1 (NTSR1). To make these predictions we started from homology models of these receptors of varying accuracies and generated an ensemble of conformations by sampling the rigid body degrees of freedom of transmembrane helices. Then, an all-atom force field function was used to calculate the enthalpy gain, known as the “stability score” upon mutation of every residue, in these receptor structures, to alanine. For all three receptors, β1AR, A2AR, and NTSR1, we observed that mutations of hydrophobic residues in the transmembrane domain to alanine that have high stability scores correlate with high experimental thermostability. The prediction using the stability score improves when using an ensemble of receptor conformations compared to a single structure, showing that receptor flexibility is important. We also find that our previously developed LITiCon method for generating conformation ensembles is similar in performance to predictions using ensembles obtained from microseconds of molecular dynamics simulations (which is computationally hundred times slower than LITiCon). We improved the thermostability prediction by including other properties such as residue-based stress and the extent of allosteric communication by each residue in the stability score. Our method is the first step toward a computational method for rapid prediction of thermostable mutants of GPCRs.

Prediction of Thermostability from Amino Acid Attributes by Combination of Clustering with Attribute Weighting: A New Vista in Engineering Enzymes

The engineering of thermostable enzymes is receiving increased attention. The paper, detergent, and biofuel industries, in particular, seek to use environmentally friendly enzymes instead of toxic chlorine chemicals. Enzymes typically function at temperatures below 60°C and denature if exposed to higher temperatures. In contrast, a small portion of enzymes can withstand higher temperatures as a result of various structural adaptations. Understanding the protein attributes that are involved in this adaptation is the first step toward engineering thermostable enzymes. We employed various supervised and unsupervised machine learning algorithms as well as attribute weighting approaches to find amino acid composition attributes that contribute to enzyme thermostability. Specifically, we compared two groups of enzymes: mesostable and thermostable enzymes. Furthermore, a combination of attribute weighting with supervised and unsupervised clustering algorithms was used for prediction and modelling of protein thermostability from amino acid composition properties. Mining a large number of protein sequences (2090) through a variety of machine learning algorithms, which were based on the analysis of more than 800 amino acid attributes, increased the accuracy of this study. Moreover, these models were successful in predicting thermostability from the primary structure of proteins. The results showed that expectation maximization clustering in combination with uncertainly and correlation attribute weighting algorithms can effectively (100%) classify thermostable and mesostable proteins. Seventy per cent of the weighting methods selected Gln content and frequency of hydrophilic residues as the most important protein attributes. On the dipeptide level, the frequency of Asn-Glu was the key factor in distinguishing mesostable from thermostable enzymes. This study demonstrates the feasibility of predicting thermostability irrespective of sequence similarity and will serve as a basis for engineering thermostable enzymes in the laboratory.

Ferrocene derivatives thermostability prediction using neural networks and genetic algorithms

A database containing the thermal stability of 100 new liquid crystalline ferrocene derivatives and similar phenyl compounds is reported. The experimental determination of the thermal stability was undertaken in inert atmosphere using a Mettler Toledo derivatograph. Both initial temperature when the thermal decomposition starts ( T i ) and the temperature at which the decomposition rate is maximum ( T m ) were considered as thermal stability criteria. The thermostability was predicted using models of multilayer feed forward neural networks, having one or two hidden layers with four up to 36 neurons. The input parameters taken into consideration were: the molecular mass, molecular polarization, number of aromatic units, number of ferrocenyl units, number of cholesteryl units, number of C O bonds in the molecule, number of N C bonds, number of N N bonds, and melting temperature. These parameters were selected by establishing a hierarchy for the available molecular descriptors using genetic algorithms. During the validation stage of the models, the average percentage errors were smaller than 12%. These neuronal models were included into optimization procedures based on genetic algorithms with the goal to find ideal molecular structures with the highest thermal stability ( T i = 420, 430, 440 °C and T m = 460, 470, 480 °C).

An expert system to predict protein thermostability using decision tree

Protein thermostability information is closely linked to commercial production of many biomaterials. Recent developments have shown that amino acid composition, special sequence patterns and hydrogen bonds, disulfide bonds, salt bridges and so on are of considerable importance to thermostability. In this study, we present a system to integrate these various factors that predict protein thermostability. In this study, the features of proteins in the PGTdb are analyzed. We consider both structure and sequence features and correlation coefficients are incorporated into the feature selection algorithm. Machine learning algorithms are then used to develop identification systems and performances between the different algorithms are compared. In this research, two features, (E + F + M + R)/residue and charged/non-charged, are found to be critical to the thermostability of proteins. Although the sequence and structural models achieve a higher accuracy, sequence-only models provides sufficient accuracy for sequence-only thermostability prediction.

An improved method of potential of mean force for protein-protein interactions

In this work, the traditional method of potential of mean force (PMF) is improved for describing the protein-protein interactions. This method is developed at atomic level and is distance-dependent. Compared with the traditional method, our model can reasonably consider the effects of the environmental factors. With this modification, we can obtain more reasonable and accurate pair potentials, which are the pre-requisite for precisely describing the protein-protein interactions and can help us to recognize the interaction rules of residues in protein systems. Our method can also be applied to other fields of protein science, e.g., protein fold recognition, structure prediction and prediction of thermostability.

Robust Determinants of Thermostability Highlighted by a Codon Frequency Index Capable of Discriminating Thermophilic from Mesophilic Genomes

Can genome analysis tell us about the lifestyle of an organism? We ask this question considering a thorough cross comparison of thermophilic and mesophilic genomes, since presently the number of available genomes is enough to ensure statistical significance of the results. We analyze, by means of principal component analysis (PCA), the codon composition of a database comprising 116 genomes, selected so as to include one species for each genus and show that a cross genomic approach can allow the extraction of common determinants of thermostability at the genome level. The results of our analysis indicate that all the known features of thermostability can be found in the 64 component loadings of the second principal axis of PCA. By this, we develop an index of thermostability whose discriminative power between mesophiles and thermophiles scores with 98% accuracy at the genome level and with 95% accuracy at the protein sequence level. We also prove that these results are not due to phylogenetic differences between archaea and bacteria.