Predicting Protein Stability Research Articles

Modern Approaches to Protein Constructions: A Comprehensive Review of Computational Tools and Databases for De Novo Protein Design and Engineering

ABSTRACTThe field of protein engineering has witnessed transformative advancements, with computational tools and databases driving novel innovations in de novo protein design. This review consolidates and critiques a comprehensive range of modern computational resources, offering a unique focus on their applications across diverse domains, including protein stability prediction, posttranslational modification analysis, and mutation effect evaluation. Key contributions include a detailed examination of tools integrating machine learning and artificial intelligence to enhance predictive accuracy and streamline protein engineering workflows. By highlighting underexplored tools and novel methodologies, such as advanced protein–ligand interaction predictors and neural network–based stability assessment models, this study establishes itself as a unique reference for researchers aiming to develop tailored proteins for therapeutic, industrial, and biomedical applications.

DDGemb: predicting protein stability change upon single- and multi-point variations with embeddings and deep learning.

The knowledge of protein stability upon residue variation is an important step for functional protein design and for understanding how protein variants can promote disease onset. Computational methods are important to complement experimental approaches and allow a fast screening of large datasets of variations. In this work we present DDGemb, a novel method combining protein language model embeddings and transformer architectures to predict protein ΔΔG upon both single- and multi-point variations. DDGemb has been trained on a high-quality dataset derived from literature and tested on available benchmark datasets of single- and multi-point variations. DDGemb performs at the state of the art in both single- and multi-point variations. DDGemb is available as web server at https://ddgemb.biocomp.unibo.it. Datasets used in this study are available at https://ddgemb.biocomp.unibo.it/datasets.

Structure-based self-supervised learning enables ultrafast protein stability prediction upon mutation.

Predicting free energy changes (ΔΔG) is essential for enhancing our understanding of protein evolution and plays a pivotal role in protein engineering and pharmaceutical development. While traditional methods offer valuable insights, they are often constrained by computational speed and reliance on biased training datasets. These constraints become particularly evident when aiming for accurate ΔΔG predictions across a diverse array of protein sequences. Herein, we introduce Pythia, a self-supervised graph neural network specifically designed for zero-shot ΔΔG predictions. Our comparative benchmarks demonstrate that Pythia outperforms other self-supervised pretraining models and force field-based approaches while also exhibiting competitive performance with fully supervised models. Notably, Pythia shows strong correlations and achieves a remarkable increase in computational speed of up to 105-fold. We further validated Pythia's performance in predicting the thermostabilizing mutations of limonene epoxide hydrolase, leading to higher experimental success rates. This exceptional efficiency has enabled us to explore 26 million high-quality protein structures, marking a significant advancement in our ability to navigate the protein sequence space and enhance our understanding of the relationships between protein genotype and phenotype. In addition, we established a web server at https://pythia.wulab.xyz to allow users to easily perform such predictions.

Hyena architecture enables fast and efficient protein language modeling

AbstractThe emergence of self‐supervised deep language models has revolutionized natural language processing tasks and has recently extended its applications to biological sequence analysis. Traditional language models, primarily based on Transformer architectures, demonstrate substantial effectiveness in various applications. However, these models are inherently constrained by the attention mechanism's quadratic computational complexity, , which limits their efficiency and leads to high computational costs. To address these limitations, we introduce ProtHyena, a novel approach that leverages the Hyena operator in protein language modeling. This innovative methodology alternates between subquadratic long convolutions and element‐wise gating operations, which circumvents the constraints imposed by attention mechanisms and reduces computational complexity to subquadratic levels. This enables faster and more memory‐efficient modeling of protein sequences. ProtHyena can achieve state‐of‐the‐art results and comparable performance in 8 downstream tasks, including protein engineering (protein fluorescence and stability prediction), protein property prediction (neuropeptide cleavage, signal peptide, solubility, disorder, gene function prediction), protein structure prediction, with only 1.6 M parameters. The architecture of ProtHyena represents a highly efficient solution for protein language modeling, offering a promising avenue for fast and efficient analysis of protein sequences.

Multimodal neural network for enhanced protein stability prediction by integration of contact scores and spatial maps

The prediction of protein stability changes upon mutation remains a significant challenge in bioinformatics, with implications for understanding disease mechanisms and drug design. Despite progress through machine learning and neural network models, there is a need for more accurate predictive models. We explored Random Forest, single input 2D CNN, multi-input 2D CNN, and multimodal CNN approaches to train a model for predicting favorable and unfavorable mutations for protein stability. Our findings revealed that the multi-input 2D CNN trained on contact maps outperformed other approaches employed in this study. An accuracy of 0.679 was achieved, with a negative prediction of 0.74 and a specificity of 0.81, demonstrating promising advancements in predicting protein stability and demonstrating the utility of integrating diverse data representations. Nonetheless, further refinement is necessary to address overfitting and improve its predictive accuracy for unseen data. This work contributes to the broader effort to enhance computational models for protein stability prediction, underscoring the need for balanced complexity in model design. The dataset was modeled via AlphaFold, followed by refinement with amber relaxation to ensure that the resultant 3D models of the variants were both structurally accurate and energetically feasible. An advanced Python-based AI/ML pipeline was developed to train the models, evaluate the datasets, and predict protein stability using scikit-learn, TensorFlow, and Keras deep learning libraries.

Towards thermophilic protein stability prediction: A comprehensive study of machine learning approaches

Abstract. Thermophilic proteins are critical in biology due to their enhanced thermal stability. Different machine learning approaches have been applied to estimate protein thermal stability. Current study categorizes the previous research into classification and regression tasks and explores the impact of different data representations, including tabular, sequence, and graph data on evaluation performance. Pipelines for prediction using different representations are thoroughly described. Current challenges, such as insufficient and imbalanced datasets, are addressed with potential solutions, such as transfer learning and re-sampling methods. Additionally, model interpretability, discussing various approaches to obtain model explanations and highlighting that some explanations are inconsistent have also been included in current study. Such comprehensive overview provides insights into existing methodologies and suggests potential research directions and improvements.

Enhancing protein stability prediction with geometric learning and pre-training strategies.

Enhancing protein stability prediction with geometric learning and pre-training strategies.

Using AI-predicted protein structures as a reference to predict loss-of-function activity in tumor suppressor breast cancer genes

BackgroundThe loss-of-function (LOF) classification of most missense variants in tumor suppressor breast cancer genes BRCA1, BRCA2, PALB2, and RAD51C remains unclassified and confounds clinical actionability. Classifying these variants is challenging due to their rarity, leading clinicians to rely on in silico predictive methods. Protein stability changes are associated with function, making stability predictors valuable. Stability predictions upon missense variant perturbations require high-resolution protein structures. However, the availability of these high-resolution structures is lacking. This study explores using generative AI to predict high-resolution protein structures, which can then be analyzed with in silico protein stability prediction methods to assess LOF activity in ordered regions of the protein. This study also determines the appropriate in silico protein stability and dedicated in silico missense prediction methods in dbNSFP v4.7 database to predict LOF activity in ordered regions of these four genes. Functional classifications from homology recombination DNA repair (HDR) assays and variant classifications from the ClinVar database provide a reliable dataset for evaluating the performance of these in silico prediction methods. ResultsComplex AlphaFold2 structures of the BRCA1-C terminal (BRCT) domain and the DNA-binding (DB) domain of BRCA2, analyzed using protein stability tool FoldX predicts LOF activity from missense variants significantly better than experimentally-derived structures in ordered regions. The BRCT domain achieved an Area Under the Curve (AUC)= 0.861 (95 % CI:0.858–0.863) and AUC= 0.842 (95 % CI:0.840–0.845), while the DB domain achieved an AUC= 0.836 (95 % CI:0.8322–0.841), compared to AUC= 0.847 (95 % CI:0.844–0.850) and AUC= 0.835 (95 % CI:0.832–0.837) from the BRCT domain, and AUC= 0.830 (95 % CI:0.821–0.8320) from the DB domain from experimentally-derived structures. Protein stability does not predict LOF activity from missense variants better than dedicated in silico missense predictors. Overall, we find that AlphaMissense ranks highly, with an average AUC= 0.890 (95 % CI 0.886–0.895) from ordered regions across these four cancer genes, compared to all other in silico missense predictors present in the dbNSFP database. ConclusionsThe study reveals that generative AI protein predicted structures can outperform experimentally-derived structures in evaluating LOF activity from predicted protein stability in ordered regions of genes BRCA1, BRCA2, PALB2 and RAD51C. The study also highlights the predictive performance of AlphaMissense as the premier in silico missense prediction method to predict LOF activity from missense variants in these four tumor suppressor breast cancer genes. The code for this study can be downloaded for free on GitHub (https://github.com/rohandavidg/CarePred)

Prediction of mutation-induced protein stability changes based on the geometric representations learned by a self-supervised method

BackgroundThermostability is a fundamental property of proteins to maintain their biological functions. Predicting protein stability changes upon mutation is important for our understanding protein structure–function relationship, and is also of great interest in protein engineering and pharmaceutical design.ResultsHere we present mutDDG-SSM, a deep learning-based framework that uses the geometric representations encoded in protein structure to predict the mutation-induced protein stability changes. mutDDG-SSM consists of two parts: a graph attention network-based protein structural feature extractor that is trained with a self-supervised learning scheme using large-scale high-resolution protein structures, and an eXtreme Gradient Boosting model-based stability change predictor with an advantage of alleviating overfitting problem. The performance of mutDDG-SSM was tested on several widely-used independent datasets. Then, myoglobin and p53 were used as case studies to illustrate the effectiveness of the model in predicting protein stability changes upon mutations. Our results show that mutDDG-SSM achieved high performance in estimating the effects of mutations on protein stability. In addition, mutDDG-SSM exhibited good unbiasedness, where the prediction accuracy on the inverse mutations is as well as that on the direct mutations.ConclusionMeaningful features can be extracted from our pre-trained model to build downstream tasks and our model may serve as a valuable tool for protein engineering and drug design.

A computational workflow for analysis of missense mutations in precision oncology

Every year, more than 19 million cancer cases are diagnosed, and this number continues to increase annually. Since standard treatment options have varying success rates for different types of cancer, understanding the biology of an individual's tumour becomes crucial, especially for cases that are difficult to treat. Personalised high-throughput profiling, using next-generation sequencing, allows for a comprehensive examination of biopsy specimens. Furthermore, the widespread use of this technology has generated a wealth of information on cancer-specific gene alterations. However, there exists a significant gap between identified alterations and their proven impact on protein function. Here, we present a bioinformatics pipeline that enables fast analysis of a missense mutation’s effect on stability and function in known oncogenic proteins. This pipeline is coupled with a predictor that summarises the outputs of different tools used throughout the pipeline, providing a single probability score, achieving a balanced accuracy above 86%. The pipeline incorporates a virtual screening method to suggest potential FDA/EMA-approved drugs to be considered for treatment. We showcase three case studies to demonstrate the timely utility of this pipeline. To facilitate access and analysis of cancer-related mutations, we have packaged the pipeline as a web server, which is freely available at https://loschmidt.chemi.muni.cz/predictonco/.Scientific contributionThis work presents a novel bioinformatics pipeline that integrates multiple computational tools to predict the effects of missense mutations on proteins of oncological interest. The pipeline uniquely combines fast protein modelling, stability prediction, and evolutionary analysis with virtual drug screening, while offering actionable insights for precision oncology. This comprehensive approach surpasses existing tools by automating the interpretation of mutations and suggesting potential treatments, thereby striving to bridge the gap between sequencing data and clinical application.

Protein stability prediction by fine-tuning a protein language model on a mega-scale dataset.

Protein stability plays a crucial role in a variety of applications, such as food processing, therapeutics, and the identification of pathogenic mutations. Engineering campaigns commonly seek to improve protein stability, and there is a strong interest in streamlining these processes to enable rapid optimization of highly stabilized proteins with fewer iterations. In this work, we explore utilizing a mega-scale dataset to develop a protein language model optimized for stability prediction. ESMtherm is trained on the folding stability of 528k natural and de novo sequences derived from 461 protein domains and can accommodate deletions, insertions, and multiple-point mutations. We show that a protein language model can be fine-tuned to predict folding stability. ESMtherm performs reasonably on small protein domains and generalizes to sequences distal from the training set. Lastly, we discuss our model's limitations compared to other state-of-the-art methods in generalizing to larger protein scaffolds. Our results highlight the need for large-scale stability measurements on a diverse dataset that mirrors the distribution of sequence lengths commonly observed in nature.

Review of predicting protein stability changes upon variations.

Forecasting alterations in protein stability caused by variations holds immense importance. Improving the thermal stability of proteins is important for biomedical and industrial applications. This review discusses the latest methods for predicting the effects of mutations on protein stability, databases containing protein mutations and thermodynamic parameters, and experimental techniques for efficiently assessing protein stability in high-throughput settings. Various publicly available databases for protein stability prediction are introduced. Furthermore, state-of-the-art computational approaches for anticipating protein stability changes due to variants are reviewed. Each method's types of features, base algorithm, and prediction results are also detailed. Additionally, some experimental approaches for verifying the prediction results of computational methods are introduced. Finally, the review summarizes the progress and challenges of protein stability prediction and discusses potential models for future research directions.

Clinical and genetic analyses of APMR4 syndrome caused by novel biallelic LSS variants.

Alopecia intellectual disability syndromes 4 (APMR4) caused by Lanosterol synthase (LSS) gene variants is a very rare autosomal recessive neuroectodermal syndrome. It is characterized by congenital alopecia and variable degrees of intellectual disability (ID), frequently associated with developmental delay (DD) and epilepsy. Currently, only three studies regarding LSS-related APMR4 have been reported, the pathogenesis of APMR4 is poorly understood. We studied one patient with LSS-related APMR4 who presented with severe intellectual disability, alopecia, early-onset epilepsy and developmental delay. She is absence of hair on the eyebrows, eyelashes, and scalp. Two novel LSS variants (c.401 T > G and c.369C > G) were detected with whole-exome sequencing (WES). Analysis via WB experiment indicated that c.369 > G reduced the protein expression level of LSS. Analysis of protein stability prediction showed a destabilizing for LSS caused by the variant c.401 T > G. This study is the first study in Asia to date. These findings expanded the variantal spectrum of LSS-related APMR4 and revealed the potential pathogenic mechanism of LSS gene variants.

Functional and in silico analysis of ATP8A2 and other P4-ATPase variants associated with human genetic diseases.

P4-ATPases flip lipids from the exoplasmic to cytoplasmic leaflet of cell membranes, a property crucial for many biological processes. Mutations in P4-ATPases are associated with severe inherited and complex human disorders. We determined the expression, localization and ATPase activity of four variants of ATP8A2, the P4-ATPase associated with the neurodevelopmental disorder known as cerebellar ataxia, impaired intellectual development and disequilibrium syndrome 4 (CAMRQ4). Two variants, G447R and A772P, harboring mutations in catalytic domains, expressed at low levels and mislocalized in cells. In contrast, the E459Q variant in a flexible loop displayed wild-type expression levels, Golgi-endosome localization and ATPase activity. The R1147W variant expressed at 50% of wild-type levels but showed normal localization and activity. These results indicate that the G447R and A772P mutations cause CAMRQ4 through protein misfolding. The E459Q mutation is unlikely to be causative, whereas the R1147W may display a milder disease phenotype. Using various programs that predict protein stability, we show that there is a good correlation between the experimental expression of the variants and in silico stability assessments, suggesting that such analysis is useful in identifying protein misfolding disease-associated variants.

Differentiating stable and unstable protein using convolution neural network and molecular dynamics simulations

Protein stability is a critical aspect of molecular biology and biochemistry, hinges on an intricate balance of thermodynamic and structural factors. Determining protein stability is crucial for understanding and manipulating biological machineries, as it directly correlated with the protein function. Thus, this study delves into the intricacies of protein stability, highlighting its dependence on various factors, including thermodynamics, thermal conditions, and structural properties. Moreover, a notable focus is placed on the free energy change of unfolding (ΔGunfolding), change in heat capacity (ΔCp) with protein structural transition, melting temperature (Tm) and number of disulfide bonds, which are critical parameters in understanding protein stability. In this study, a machine learning (ML) predictive model was developed to estimate these four parameters using the primary sequence of the protein. The shortfall of available tools for protein stability prediction based on multiple parameters propelled the completion of this study. Convolutional Neural Network (CNN) with multiple layers was adopted to develop a more reliable ML model. Individual predictive models were prepared for each property, and all the prepared models showed results with high accuracy. The R2 (coefficient of determination) of these models were 0.79, 0.78, 0.92 and 0.92, respectively, for ΔG, ΔCp, Tm and disulfide bonds. A case study on stability analysis of two homologous proteins was presented to validate the results predicted through the developed model. The case study included in silico analysis of protein stability using molecular docking and molecular dynamic simulations. This validation study assured the accuracy of each model in predicting the stability associated properties. The alignment of physics-based principles with ML models has provided an opportunity to develop a fast machine learning solution to replace the computationally demanding physics-based calculations used to determine protein stability. Furthermore, this work provided valuable insights into the impact of mutation on protein stability, which has implications for the field of protein engineering. The source codes are available at https://github.com/Growdeatechnology.

PMSPcnn: Predicting protein stability changes upon single point mutations with convolutional neural network

Protein missense mutations and resulting protein stability changes are important causes for many human genetic diseases. However, the accurate prediction of stability changes due to mutations remains a challenging problem. To address this problem, we have developed an unbiased effective model: PMSPcnn that is based on a convolutional neural network. We have included an anti-symmetry property to build a balanced training dataset, which improves the prediction, in particular for stabilizing mutations. Persistent homology, which is an effective approach for characterizing protein structures, is used to obtain topological features. Additionally, a regression stratification cross-validation scheme has been proposed to improve the prediction for mutations with extreme ΔΔG. For three test datasets: Ssym, p53, and myoglobin, PMSPcnn achieves a better performance than currently existing predictors. PMSPcnn also outperforms currently available methods for membrane proteins. Overall, PMSPcnn is a promising method for the prediction of protein stability changes caused by single point mutations.

ABO*A2.08 Subtype Allele Identification and Protein Structure Analysis in Newborns

To study the serological characteristics of ABO*A2.08 subtype and explore its genetic molecular mechanism. ABO blood group identification was performed on proband and her family members by routine serological methods. ABO genotyping and sequence analysis were performed by polymerase chain reaction-sequence specific primer (PCR-SSP), and direct sequencing of PCR products from exons 6 and 7 of ABO gene were directly sequenced and analyzed. The effect of gene mutation in A2.08 subtype on structural stability of GTA protein was investigated by homologous protein conserved analysis, 3D molecular modeling and protein stability prediction. The proband's serological test results showed subtype Ax, and ABO genotyping confirmed that the proband's genotype was ABO*A207/08. Gene sequencing of the proband's father confirmed the characteristic variation of c.539G>C in the 7th exon of ABO gene, leading to the replacement of polypeptide chain p.Arg180Pro (R180P). 3D protein molecular modeling and analysis suggested that the number of hydrogen bonds of local amino acids in the protein structure was changed after the mutation, and protein stability prediction showed that the mutation had a great influence on the protein structure stability. The mutation of the 7th exon c.539G>C of ABO gene leads to the substitution of polypeptide chain amino acid, which affects the structural stability of GTA protein and leads to the change of enzyme activity, resulting in the A2.08 phenotype. The mutated gene can be stably inherited.

A computational exploration of global and temporal dynamics of selection pressure on HIV-1 Vif polymorphism

Virion infectivity factor (Vif), an accessory protein of HIV-1 (human immunodeficiency virus type 1), antagonizes host APOBEC3 protein (apolipoprotein B mRNA editing enzyme, catalytic polypeptide 3) or A3 via proteasomal degradation, facilitating viral replication. HLA (Human leukocyte antigens) alleles, host restriction factors, and error-prone reverse transcription contribute to the global polymorphic dynamics of HIV, impacting effective vaccine design. Our computational analysis of over 50,000 HIV-1 M vif sequences from the Los Alamos National Laboratory (LANL) database (1998–2021) revealed positive selection pressure on the vif gene (nonsynonymous to synonymous ratio, dn/ds=1.58) and an average entropy score of 0.372 in protein level. Interestingly, over the years (1998–2021), a decreasing trend of dn/ds (1.68 to 1.47) and an increasing trend of entropy (0.309 to 0.399) was observed. The predicted mutational frequency against Vif consensus sequence decreased over time (slope = -0.00024, p < 0.0001). Sequence conservation was observed in Vif functional motifs F1, F2, F3, G, BC box, and CBF β binding region, while variability was observed mainly in N- and C- terminal and Zinc finger region, which were dominantly under immune pressure by host HLA-I-restricted CD8+ T cell. Computational analysis of ∆∆Gstability through protein stability prediction tools suggested that missense mutation may affect Vif stability, especially in the Vif-A3 binding interface. Notably, mutations R17K and Y44F in F1 and G box were predicted to destabilize the Vif-A3 binding interface by altering bond formations with adjacent amino acids. Therefore, our analysis demonstrates Vif adaptation with host physiology by maintaining sequence conservation, especially in A3 interacting functional motifs, highlighting important therapeutic candidate regions of Vif against HIV-1 infections.

Predicting protein thermal stability changes upon single and multi-point mutations via restricted attention subgraph neural network

Accurate prediction of protein stability changes due to mutations is instrumental for understanding mechanisms of disease and drug failure, as well as for engineering tailored protein-based materials. In recent years, computational tools using machine learning have been developed to predict stability changes and thereby supplement available experimental methods that may be time consuming and costly for bulk mutational analysis. Existing tools are limited, however, to predicting single point mutations and showing antisymmetric bias in direct/reverse mutations. Here, we develop structure and sequence-based models to predict protein stability changes via Gibbs free energy change upon single or multi-point mutations via two parallel augmented gated attention graph neural networks integrated with global attention blocks receiving subgraphs. These subgraphs are related to mutation sites and constructed through predicted protein contact maps to capture spatial structural information. We train our model on direct and reverse mutations obtained from the S5294 dataset and test on one independent test set and eight most commonly used test sets, including S350, P53, Ssym, S669, S1925, S250, and myoglobin. Our approach shows considerable improvement in estimating the impacts of stabilizing mutations, and consistently outperforms other methods by at least a 5.2% improvement in root mean square error. This approach can be employed for finding functionally important protein variants, helping to design new proteins with vast untapped potential for broad pharmaceutical applications.

ProSTAGE: Predicting Effects of Mutations on Protein Stability by Using Protein Embeddings and Graph Convolutional Networks.

Protein thermodynamic stability is essential to clarify the relationships among structure, function, and interaction. Therefore, developing a faster and more accurate method to predict the impact of the mutations on protein stability is helpful for protein design and understanding the phenotypic variation. Recent studies have shown that protein embedding will be particularly powerful at modeling sequence information with context dependence, such as subcellular localization, variant effect, and secondary structure prediction. Herein, we introduce a novel method, ProSTAGE, which is a deep learning method that fuses structure and sequence embedding to predict protein stability changes upon single point mutations. Our model combines graph-based techniques and language models to predict stability changes. Moreover, ProSTAGE is trained on a larger data set, which is almost twice as large as the most used S2648 data set. It consistently outperforms all existing state-of-the-art methods on mutation-affected problems as benchmarked on several independent data sets. The protein embedding as the prediction input achieves better results than the previous results, which shows the potential of protein language models in predicting the effect of mutations on proteins. ProSTAGE is implemented as a user-friendly web server.