Fast and accurate predictions of protein stability changes upon mutations using statistical potentials and neural networks: PoPMuSiC-2.0

Enhanced Thermal Stability/Activity of Geobacillus jurassicus Esterase by Rational Design and Application in the Synthesis of Cinnamyl Acetate

Geobacillus sp. represents an important source of thermophilic esterases, yet studies on the rational design and industrial application of these enzymes remain limited. In our previous research, we identified the esterase Gju768 from Geobacillus jurassicus DSMZ 15726. In the present study, we employed a novel computer-aided rational design approach, ACDP (AutoDock, Consurf, Discovery Studio, PoPMuSiC), to enhance the enzyme's thermal stability. Through molecular docking and conservation analysis, three hotspots were identified. Virtual saturation mutagenesis was subsequently performed, yielding two selected mutations, Q78I and Q78L, from the resulting library. Notably, mutants Q78I and Q78L exhibited significant improvements in thermal stability and enzyme activity compared to the wild type (WT). Compared to WT, mutants Q78I and Q78L exhibited a 65.27% and 38.38% increase in half-life at 65 °C, along with a 14.48% and 1.60% improvement in specific activity at their respective optimal temperatures. Furthermore, under optimized conditions for cinnamyl acetate production, mutant Q78I demonstrated a yield of 68%, compared to only 31% for WT. This study underscored the potential of protein engineering strategies to enhance enzyme performance in industrial applications, particularly for the synthesis of value-added compounds such as cinnamyl acetate.

An interpretable deep geometric learning model to predict the effects of mutations on protein-protein interactions using large-scale protein language model

Protein-protein interactions (PPIs) are central to the mechanisms of signaling pathways and immune responses, which can help us understand disease etiology. Therefore, there is a significant need for efficient and rapid automated approaches to predict changes in PPIs. In recent years, there has been a significant increase in applying deep learning techniques to predict changes in binding affinity between the original protein complex and its mutant variants. Particularly, the adoption of graph neural networks (GNNs) has gained prominence for their ability to learn representations of protein-protein complexes. However, the conventional GNNs have mainly concentrated on capturing local features, often disregarding the interactions among distant elements that hold potential important information. In this study, we have developed a transformer-based graph neural network to extract features of the mutant segment from the three-dimensional structure of protein-protein complexes. By embracing both local and global features, the approach ensures a more comprehensive understanding of the intricate relationships, thus promising more accurate predictions of binding affinity changes. To enhance the representation capability of protein features, we incorporate a large-scale pre-trained protein language model into our approach and employ the global protein feature it provides. The proposed model is shown to be able to predict the mutation changes in binding affinity with a root mean square error of 1.10 and a Pearson correlation coefficient of near 0.71, as demonstrated by performance on test and validation cases. Our experiments on all five datasets, including both single mutant and multiple mutant cases, demonstrate that our model outperforms four state-of-the-art baseline methods, and the efficacy was subjected to comprehensive experimental evaluation. Our study introduces a transformer-based graph neural network approach to accurately predict changes in protein-protein interactions (PPIs). By integrating local and global features and leveraging pretrained protein language models, our model outperforms state-of-the-art methods across diverse datasets. The results of this study can provide new views for studying immune responses and disease etiology related to protein mutations. Furthermore, this approach may contribute to other biological or biochemical studies related to PPIs.Scientific contribution Our scientific contribution lies in the development of a novel transformer-based graph neural network tailored to predict changes in protein-protein interactions (PPIs) with excellent accuracy. By seamlessly integrating both local and global features extracted from the three-dimensional structure of protein-protein complexes, and leveraging the rich representations provided by pretrained protein language models, our approach surpasses existing methods across diverse datasets. Our findings may offer novel insights for the understanding of complex disease etiology associated with protein mutations. The novel tool can be applicable to various biological and biochemical investigations involving protein mutations.

An augmented transformer model trained on protein family specific variant data leads to improved prediction of variants of uncertain significance

Variants of uncertain significance (VUS) represent variants that lack sufficient evidence to be confidently associated with a disease, thus posing a challenge in the interpretation of genetic testing results. Here we report an improved method for predicting the VUS of Arylsulfatase A (ARSA) gene as part of the Critical Assessment of Genome Interpretation challenge (CAGI6). Our method uses a transfer learning approach that leverages a pre-trained protein language model to predict the impact of mutations on the activity of the ARSA enzyme, whose deficiency is known to cause a rare genetic disorder, metachromatic leukodystrophy. Our innovative framework combines zero-shot log odds scores and embeddings from the ESM, an evolutionary scale model as features for training a supervised model on gene variants functionally related to the ARSA gene. The zero-shot log odds score feature captures the generic properties of the proteins learned due to its pre-training on millions of sequences in the UniProt data, while the ESM embeddings for the proteins in the ARSA family capture features specific to the family. We also tested our approach on another enzyme, N-acetyl-glucosaminidase (NAGLU), that belongs to the same superfamily as ARSA. Our results demonstrate that the performance of our family models (augmented ESM models) is either comparable or better than the ESM models. The ARSA model compares favorably with the majority of state-of-the-art predictors on area under precision and recall curve (AUPRC) performance metric. However, the NAGLU model outperforms all pathogenicity predictors evaluated in this study on AUPRC metric. The improved AUPRC has relevance in a diagnostic setting where variant prioritization generally entails identifying a small number of pathogenic variants from a larger number of benign variants. Our results also indicate that genes that have sparse or no experimental variant impact data, the family variant data can serve as a proxy training data for making accurate predictions. Attention analysis of active sites and binding sites in ARSA and NAGLU proteins shed light on probable mechanisms of pathogenicity for positions that are highly attended.

Decoding omicron: Genetic insight into its transmission dynamics, severity spectrum and ever-evolving strategies of immune escape in comparison with other SARS-CoV-2 variants

BACKGROUND

The coronavirus disease 2019 (COVID-19) pandemic, driven by the rapid evolution of the SARS-CoV-2 virus, has led to the emergence of multiple variants with significant impacts on global health. This study aims to analyze the evolutionary trends and mutational landscape of SARS-CoV-2 variants circulating in Pune, Maharashtra, India, from August 2022 to April 2024. Using comprehensive genomic surveillance data, we identified the predominance of variants such as BA.2.75, XBB.x, and the newly emerged subvariants JN.1, KP.1, and KP.2. These subvariants, belonging to the BA.2.86 lineage, have raised concerns owing to their potential for increased transmissibility and immune evasion.

RESULTS

Phylogenetic analysis of 84 sequenced samples from Pune revealed 18 distinct lineages, with JN.1 and KP.2 forming a novel branch compared with their ancestral lineage, BA.2. Detailed mutational analysis highlighted key mutations in the N-terminal domain (NTD) and receptor-binding domain (RBD) of the spike protein, affecting viral stability, ACE2 binding affinity, and neutralizing antibody escape. Our findings, along with the predictions of SpikePro, suggest that the combination of these mutations enhances the viral fitness of JN.1 and KP.2, contributing to their rapid emergence and spread.

CONCLUSION

This study underscores the importance of continuous genomic surveillance and advanced computational modeling to track and predict the evolutionary trajectories of SARS-CoV-2 variants. The insights gained from this research are crucial for informing public health strategies, vaccine updates, and therapeutic interventions to mitigate the impact of current and future SARS-CoV-2 variants.

Assessing predictions on fitness effects of missense variants in HMBS in CAGI6

This paper presents an evaluation of predictions submitted for the "HMBS" challenge, a component of the sixth round of the Critical Assessment of Genome Interpretation held in 2021. The challenge required participants to predict the effects of missense variants of the human HMBS gene on yeast growth. The HMBS enzyme, critical for the biosynthesis of heme in eukaryotic cells, is highly conserved among eukaryotes. Despite the application of a variety of algorithms and methods, the performance of predictors was relatively similar, with Kendall's tau correlation coefficients between predictions and experimental scores around 0.3 for a majority of submissions. Notably, the median correlation (≥ 0.34) observed among these predictors, especially the top predictions from different groups, was greater than the correlation observed between their predictions and the actual experimental results. Most predictors were moderately successful in distinguishing between deleterious and benign variants, as evidenced by an area under the receiver operating characteristic (ROC) curve (AUC) of approximately 0.7 respectively. Compared with the recent two rounds of CAGI competitions, we noticed more predictors outperformed the baseline predictor, which is solely based on the amino acid frequencies. Nevertheless, the overall accuracy of predictions is still far short of positive control, which is derived from experimental scores, indicating the necessity for considerable improvements in the field. The most inaccurately predicted variants in this round were associated with the insertion loop, which is absent in many orthologs, suggesting the predictors still heavily rely on the information from multiple sequence alignment.

Rewiring protein sequence and structure generative models to enhance protein stability prediction

Predicting changes in protein thermostability due to amino acid substitutions is essential for understanding human diseases and engineering useful proteins for clinical and industrial applications. While recent advances in protein generative models, which learn probability distributions over amino acids conditioned on structural or evolutionary sequence contexts, have shown impressive performance in predicting various protein properties without task-specific training, their strong unsupervised prediction ability does not extend to all protein functions. In particular, their potential to improve protein stability prediction remains underexplored. In this work, we present SPURS, a novel deep learning framework that adapts and integrates two general-purpose protein generative models-a protein language model (ESM) and an inverse folding model (ProteinMPNN)-into an effective stability predictor. SPURS employs a lightweight neural network module to rewire per-residue structure representations learned by ProteinMPNN into the attention layers of ESM, thereby informing and enhancing ESM's sequence representation learning. This rewiring strategy enables SPURS to harness evolutionary patterns from both sequence and structure data, where the sequence like-lihood distribution learned by ESM is conditioned on structure priors encoded by ProteinMPNN to predict mutation effects. We steer this integrated framework to a stability prediction model through supervised training on a recently released mega-scale thermostability dataset. Evaluations across 12 benchmark datasets showed that SPURS delivers accurate, rapid, scalable, and generalizable stability predictions, consistently outperforming current state-of-the-art methods. Notably, SPURS demonstrates remarkable versatility in protein stability and function analyses: when combined with a protein language model, it accurately identifies protein functional sites in an unsupervised manner. Additionally, it enhances current low- N protein fitness prediction models by serving as a stability prior model to improve accuracy. These results highlight SPURS as a powerful tool to advance current protein stability prediction and machine learning-guided protein engineering workflows. The source code of SPURS is available at https://github.com/luo-group/SPURS .

Mutational Scanning and Binding Free Energy Computations of the SARS-CoV-2 Spike Complexes with Distinct Groups of Neutralizing Antibodies: Energetic Drivers of Convergent Evolution of Binding Affinity and Immune Escape Hotspots

The rapid evolution of SARS-CoV-2 has led to the emergence of variants with increased immune evasion capabilities, posing significant challenges to antibody-based therapeutics and vaccines. In this study, we conducted a comprehensive structural and energetic analysis of SARS-CoV-2 spike receptor-binding domain (RBD) complexes with neutralizing antibodies from four distinct groups (A-D), including group A LY-CoV016, group B AZD8895 and REGN10933, group C LY-CoV555, and group D antibodies AZD1061, REGN10987, and LY-CoV1404. Using coarse-grained simplified simulation models, rapid energy-based mutational scanning, and rigorous MM-GBSA binding free energy calculations, we elucidated the molecular mechanisms of antibody binding and escape mechanisms, identified key binding hotspots, and explored the evolutionary strategies employed by the virus to evade neutralization. The residue-based decomposition analysis revealed energetic mechanisms and thermodynamic factors underlying the effect of mutations on antibody binding. The results demonstrate excellent qualitative agreement between the predicted binding hotspots and the latest experiments on antibody escape. These findings provide valuable insights into the molecular determinants of antibody binding and viral escape, highlighting the importance of targeting conserved epitopes and leveraging combination therapies to mitigate the risk of immune evasion.

Quantitative Characterization and Prediction of the Binding Determinants and Immune Escape Hotspots for Groups of Broadly Neutralizing Antibodies Against Omicron Variants: Atomistic Modeling of the SARS-CoV-2 Spike Complexes with Antibodies

A growing body of experimental and computational studies suggests that the cross-neutralization antibody activity against Omicron variants may be driven by the balance and tradeoff between multiple energetic factors and interaction contributions of the evolving escape hotspots involved in antigenic drift and convergent evolution. However, the dynamic and energetic details quantifying the balance and contribution of these factors, particularly the balancing nature of specific interactions formed by antibodies with epitope residues, remain largely uncharacterized. In this study, we performed molecular dynamics simulations, an ensemble-based deep mutational scanning of SARS-CoV-2 spike residues, and binding free energy computations for two distinct groups of broadly neutralizing antibodies: the E1 group (BD55-3152, BD55-3546, and BD5-5840) and the F3 group (BD55-3372, BD55-4637, and BD55-5514). Using these approaches, we examined the energetic determinants by which broadly potent antibodies can largely evade immune resistance. Our analysis revealed the emergence of a small number of immune escape positions for E1 group antibodies that correspond to the R346 and K444 positions in which the strong van der Waals and interactions act synchronously, leading to the large binding contribution. According to our results, the E1 and F3 groups of Abs effectively exploit binding hotspot clusters of hydrophobic sites that are critical for spike functions along with the selective complementary targeting of positively charged sites that are important for ACE2 binding. Together with targeting conserved epitopes, these groups of antibodies can lead expand the breadth and resilience of neutralization to the antigenic shifts associated with viral evolution. The results of this study and the energetic analysis demonstrate excellent qualitative agreement between the predicted binding hotspots and critical mutations with respect to the latest experiments on average antibody escape scores. We argue that the E1 and F3 groups of antibodies targeting binding epitopes may leverage strong hydrophobic interactions with the binding epitope hotspots that are critical for the spike stability and ACE2 binding, while escape mutations tend to emerge in sites associated with synergistically strong hydrophobic and electrostatic interactions.

Accurate Characterization of the Allosteric Energy Landscapes, Binding Hotspots and Long-Range Communications for KRAS Complexes with Effector Proteins : Integrative Approach Using Microsecond Molecular Dynamics, Deep Mutational Scanning of Binding Energetics and Allosteric Network Modeling

KRAS is a pivotal oncoprotein that regulates cell proliferation and survival through interactions with downstream effectors such as RAF1. Oncogenic mutations in KRAS, including G12V, G13D, and Q61R, drive constitutive activation and hyperactivation of signaling pathways, contributing to cancer progression. Despite significant advances in understanding KRAS biology, the structural and dynamic mechanisms of KRAS binding and allostery by which oncogenic mutations enhance KRAS-RAF1 binding and signaling remain incompletely understood. In this study, we employ microsecond molecular dynamics simulations, Markov State Modeling, mutational scanning and binding free energy calculations together with dynamic network modeling to elucidate the effect of KRAS mutations and characterize the thermodynamic and allosteric drivers and hotspots of KRAS binding and oncogenic activation. Our simulations revealed that oncogenic mutations stabilize the open active conformation of KRAS by differentially modulating the flexibility of the switch I and switch II regions, thereby enhancing RAF1 binding affinity. The G12V mutation rigidifies both switch I and switch II, locking KRAS in a stable, active state. In contrast, the G13D mutation moderately reduces switch I flexibility while increasing switch II dynamics, restoring a balance between stability and flexibility. The Q61R mutation induces a more complex conformational landscape, characterized by the increased switch II flexibility and expansion of functional macrostates, which promotes prolonged RAF1 binding and signaling. Mutational scanning of KRAS-RAF1 complexes identified key binding affinity hotspots, including Y40, E37, D38, and D33, and together with the MM-GBSA analysis revealed the hotspots leverage synergistic electrostatic and hydrophobic binding interactions in stabilizing the KRAS-RAF1 complexes. Network-based analysis of allosteric communication identifies critical KRAS residues (e.g., L6, E37, D57, R97) that mediate long-range interactions between the KRAS core and the RAF1 binding interface. The central β-sheet of KRAS emerges as a hub for transmitting conformational changes, linking distant functional sites and facilitating allosteric regulation. Strikingly, the predicted allosteric hotspots align with experimentally identified allosteric binding hotspots that define the energy landscape of KRAS allostery. This study highlights the power of integrating computational modeling with experimental data to unravel the complex dynamics of KRAS and its mutants. The identification of binding hotspots and allosteric communication routes offers new opportunities for developing targeted therapies to disrupt KRAS-RAF1 interactions and inhibit oncogenic signaling. Our results underscore the potential of computational approaches to guide the design of allosteric inhibitors and mutant-specific therapies for KRAS-driven cancers.

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.

Quantitative Characterization and Prediction of the Binding Determinants and Immune Escape Hotspots for Groups of Broadly Neutralizing Antibodies Against Omicron Variants: Atomistic Modeling of the SARS-CoV-2 Spike Complexes with Antibodies

The growing body of experimental and computational studies suggested that the cross-neutralization antibody activity against Omicron variants may be driven by balance and tradeoff of multiple energetic factors and interaction contributions of the evolving escape hotspots involved in antigenic drift and convergent evolution. However, the dynamic and energetic details quantifying the balance and contribution of these factors, particularly the balancing nature of specific interactions formed by antibodies with the epitope residues remain scarcely characterized. In this study, we performed molecular dynamics simulations, ensemble-based deep mutational scanning of SARS-CoV-2 spike residues and binding free energy computations for two distinct groups of broadly neutralizing antibodies : E1 group (BD55-3152, BD55-3546 and BD5-5840) and F3 group (BD55-3372, BD55-4637 and BD55-5514). Using these approaches, we examine the energetic determinants by which broadly potent antibodies can largely evade immune resistance. Our analysis revealed the emergence of a small number of immune escape positions for E1 group antibodies that correspond to R346 and K444 positions in which the strong van der Waals and interactions act synchronously leading to the large binding contribution. According to our results, E1 and F3 groups of Abs effectively exploit binding hotspot clusters of hydrophobic sites critical for spike functions along with selective complementary targeting of positively charged sites that are important for ACE2 binding. Together with targeting conserved epitopes, these groups of antibodies can lead to the expanded neutralization breadth and resilience to antigenic shift associated with viral evolution. The results of this study and the energetic analysis demonstrate excellent qualitative agreement between the predicted binding hotspots and critical mutations with respect to the latest experiments on average antibody escape scores. We argue that E1 and F3 groups of antibodies targeting binding epitopes may leverage strong hydrophobic interactions with the binding epitope hotspots critical for the spike stability and ACE2 binding, while escape mutations tend to emerge in sites associated with synergistically strong hydrophobic and electrostatic interactions.

Dioxygen reductase heterogeneity is crucial for robust aerobic growth physiology of Escherichia coli

The development of a system to leverage molecular oxygen for energy-efficient pathways required several molecular adaptations. The enzymatic reduction of dioxygen to water is one such prominent evolutionary molecular trait. Microbes evolved several enzymes capable of reducing dioxygen and, interestingly, retained multiples of them in their genomes. While their structure and biochemical functions are well-studied, understanding their degeneracy and co-operativity in the system remains elusive. We used genetic engineering and evolutionary repair approaches to examine the impact of the high oxygen affinity cytochrome bd oxidase deficiency in Escherichia coli aerobic growth. We found a crucial role of cytochrome bd oxidases in the robustness of aerobic physiology. Evolutionary repair experiments alleviated growth defects in bd oxidase-deficient strains by ArcAB system dysregulation at the cost of impaired stress response pathways. Energy generation pathways are potential antimicrobial targets, and understanding collateral phenotypes is crucial in designing therapeutic approaches that reduce antimicrobial resistance development.

Bioinformatic approach to identifying causative missense polymorphisms in animal genomes

BACKGROUND

Trends in the development of genetic markers for the purposes of genomic and marker-assisted selection primarily focus on identifying causative polymorphisms. Using these polymorphisms as markers enables a more accurate association between genotype and phenotype. Bioinformatic analysis allows calculating the impact of missense polymorphisms on the structural and functional characteristics of proteins, which makes it promising for identifying causative polymorphisms. In this study, a bioinformatic approach is applied to evaluate and differentiate polymorphisms based on their causality in genes that affect the production traits of pigs and cows, which are two important livestock species.

RESULTS

The influence of both known causative and candidate missense polymorphisms in the MC4R, NR6A1, PRKAG3, RYR1, and SYNGR2 genes of pigs, as well as the ABCG2, DGAT1, GHR, and MSTN genes of cows, was assessed. The study included an evaluation of the effect of polymorphisms on protein functions, considering the evolutionary and physicochemical characteristics of amino acids at polymorphic sites. Additionally, it examined the impact of polymorphisms on the stability of tertiary protein structures, including changes in folding, binding of protein monomers, and interaction with ligands.

CONCLUSIONS

The comprehensive bioinformatic analysis used in this study enables the differentiation of polymorphisms into neutral, where both amino acids in the polymorphic site do not significantly affect the structure and function of the protein, and causative, where one of the amino acids significantly impacts the protein's properties. This approach can be employed in future research to screen extensive sets of polymorphisms in animal genomes, identifying the most promising polymorphisms for further investigation in association studies.

ESM-scan-A tool to guide amino acid substitutions

Protein structure prediction and (re)design have gone through a revolution in the last 3 years. The tremendous progress in these fields has been almost exclusively driven by readily available machine learning algorithms applied to protein folding and sequence design problems. Despite these advancements, predicting site-specific mutational effects on protein stability and function remains an unsolved problem. This is a persistent challenge, mainly because the free energy of large systems is very difficult to compute with absolute accuracy and subtle changes to protein structures are hard to capture with computational models. Here, we describe the implementation and use of ESM-Scan, which uses the ESM zero-shot predictor to scan entire protein sequences for preferential amino acid changes, thus enabling in silico deep mutational scanning experiments. We benchmark ESM-Scan on its predictive capabilities for stability and functionality of sequence changes using three publicly available datasets and proceed by experimentally testing the tool's performance on a challenging test case of a blue-light-activated diguanylate cyclase from Methylotenera species (MsLadC), where it accurately predicted the importance of a highly conserved residue in a region involved in allosteric product inhibition. Our experimental results show that the ESM-zero shot model is capable of inferring the effects of a set of amino acid substitutions in their correlation between predicted fitness and experimental results. ESM-Scan is publicly available at https://huggingface.co/spaces/thaidaev/zsp.

Integrative Bioinformatics Analysis: Unraveling Variant Signatures and Single-Nucleotide Polymorphism Markers Associated with 5-FU-Based Chemotherapy Resistance in Colorectal Cancer Patients

BACKGROUND

Drug resistance in colorectal cancer (CRC) is modulated by multiple molecular factors, which can be ascertained through genetic investigation. Single nucleotide polymorphisms (SNPs) within key genes have the potential to impair the efficacy of chemotherapeutic agents such as 5-fluorouracil (5-FU). Therefore, the identification of SNPs linked to drug resistance can significantly contribute to the advancement of tailored therapeutic approaches and the enhancement of treatment outcomes in patients with CRC.

MATERIAL AND METHOD

To identify dysregulated genes in 5-FU-based chemotherapy responder or non-responder CRC patients, a meta-analysis was performed. Next, the protein-protein interaction (PPI) network of the identified genes was analyzed using the STRING database. The most significant module was chosen for further analysis. In addition, a literature review was conducted to identify drug resistance-related genes. Enrichment analysis was conducted to validate the main module genes and the genes identified from the literature review. The associations between SNPs and drug resistance were investigated, and the consequences of missense variants were assessed using in silico tools.

RESULT

The meta-analysis identified 796 dysregulated genes. Then, to conduct PPI analysis and enrichment analysis, we were able to discover 23 genes that are intricately involved in the cell cycle pathway. Consequently, these 23 genes were chosen for SNP analysis. By using the dbSNP database and ANNOVAR, we successfully detected and labeled SNPs in these specific genes. Additionally, after careful exclusion of SNPs with allele frequencies below 0.01, we evaluated 6 SNPs from the HDAC1, MCM2, CDK1, BUB1B, CDC14B, and CCNE1 genes using 8 bioinformatics tools. Therefore, these SNPs were identified as potentially harmful by multiple computational tools. Specifically, rs199958833 in CDK1 (Val124Gly) was predicted to be damaging by all tools used. Our analysis strongly indicates that this specific SNP could negatively affect the stability and functionality of the CDK1 protein.

CONCLUSION

Based on our current understanding, the evaluation of CDK1 polymorphisms in the context of drug resistance in CRC has yet to be undertaken. In this investigation, we showed that rs199958833 variant in the CDK1 gene may favor resistance to 5-FU-based chemotherapy. However, these findings need validation in an independent cohort of patients.

Variation and evolution analysis of SARS-CoV-2 using self-game sequence optimization

Introduction

The evolution of SARS-CoV-2 has precipitated the emergence of new mutant strains, some exhibiting enhanced transmissibility and immune evasion capabilities, thus escalating the infection risk and diminishing vaccine efficacy. Given the continuous impact of SARS-CoV-2 mutations on global public health, the economy, and society, a profound comprehension of potential variations is crucial to effectively mitigate the impact of viral evolution. Yet, this task still faces considerable challenges.

Methods

This study introduces DARSEP, a method based on Deep learning Associates with Reinforcement learning for SARS-CoV-2 Evolution Prediction, combined with self-game sequence optimization and RetNet-based model.

Results

DARSEP accurately predicts evolutionary sequences and investigates the virus's evolutionary trajectory. It filters spike protein sequences with optimal fitness values from an extensive mutation space, selectively identifies those with a higher likelihood of evading immune detection, and devises a superior evolutionary analysis model for SARS-CoV-2 spike protein sequences. Comprehensive downstream task evaluations corroborate the model's efficacy in predicting potential mutation sites, elucidating SARS-CoV-2's evolutionary direction, and analyzing the development trends of Omicron variant strains through semantic changes.

Conclusion

Overall, DARSEP enriches our understanding of the dynamic evolution of SARS-CoV-2 and provides robust support for addressing present and future epidemic challenges.

Improving the prediction of protein stability changes upon mutations by geometric learning and a pre-training strategy

Accurate prediction of protein mutation effects is of great importance in protein engineering and design. Here we propose GeoStab-suite, a suite of three geometric learning-based models-GeoFitness, GeoDDG and GeoDTm-for the prediction of fitness score, ΔΔG and ΔTm of a protein upon mutations, respectively. GeoFitness engages a specialized loss function to allow supervised training of a unified model using the large amount of multi-labeled fitness data in the deep mutational scanning database. To further improve the downstream tasks of ΔΔG and ΔTm prediction, the encoder of GeoFitness is reutilized as a pre-trained module in GeoDDG and GeoDTm to overcome the challenge of lacking sufficient labeled data. This pre-training strategy, in combination with data expansion, markedly improves model performance and generalizability. In the benchmark test, GeoDDG and GeoDTm outperform the other state-of-the-art methods by at least 30% and 70%, respectively, in terms of the Spearman correlation coefficient.

Hook loop dynamics engineering transcended the barrier of activity-stability trade-off and boosted the thermostability of enzymes

The improvement of enzyme thermostability often accompanies the decreased activity due to the loss of the key regions' flexibility. As a representative structure, unlocking the potential of loop dynamics will not only provide new ideas for stabilization strategies, but also help to deepen the understanding of the relationship between enzyme structural dynamics and function. In this study, a creative "hook loop dynamics engineering" (HLoD) strategy was successfully proposed for simultaneously improving the thermostability and maintaining activity of the model enzyme, Candida Antarctica lipase B. A small and smart mutant library involving five key residues located at the "hook loop" was meticulously identified and systematically investigated and thus yielded a five-point multiple mutant M1 (L147S/T244P/S250P/T256D/N292D), demonstrating a remarkable 7.0-fold increase in thermostability at 60 °C compared to the wild-type (WT). Furthermore, the activity of M1 remained comparable to that of WT, effectively transcending the barrier of activity-stability trade-off. Molecular dynamics simulations revealed that the precise regulation of hook loop dynamics via intermolecular interactions, such as salt bridges and hydrogen bonding, curbed the excessive flexibility of the pivotal regions α5 and α10 at high temperatures, thus driving the substantial enhancement of the thermostability of M1. Refining the dynamics of the flexible region via HLoD, which transcended the barrier of activity-stability trade-off, exhibited to be a robust and potentially universal strategy for designing enzymes with outstanding thermostability and activity.

AlphaFold2 Modeling and Molecular Dynamics Simulations of the Conformational Ensembles for the SARS-CoV-2 Spike Omicron JN.1, KP.2 and KP.3 Variants: Mutational Profiling of Binding Energetics Reveals Epistatic Drivers of the ACE2 Affinity and Escape Hotspots of Antibody Resistance

The most recent wave of SARS-CoV-2 Omicron variants descending from BA.2 and BA.2.86 exhibited improved viral growth and fitness due to convergent evolution of functional hotspots. These hotspots operate in tandem to optimize both receptor binding for effective infection and immune evasion efficiency, thereby maintaining overall viral fitness. The lack of molecular details on structure, dynamics and binding energetics of the latest FLiRT and FLuQE variants with the ACE2 receptor and antibodies provides a considerable challenge that is explored in this study. We combined AlphaFold2-based atomistic predictions of structures and conformational ensembles of the SARS-CoV-2 spike complexes with the host receptor ACE2 for the most dominant Omicron variants JN.1, KP.1, KP.2 and KP.3 to examine the mechanisms underlying the role of convergent evolution hotspots in balancing ACE2 binding and antibody evasion. Using the ensemble-based mutational scanning of the spike protein residues and computations of binding affinities, we identified binding energy hotspots and characterized the molecular basis underlying epistatic couplings between convergent mutational hotspots. The results suggested the existence of epistatic interactions between convergent mutational sites at L455, F456, Q493 positions that protect and restore ACE2-binding affinity while conferring beneficial immune escape. To examine immune escape mechanisms, we performed structure-based mutational profiling of the spike protein binding with several classes of antibodies that displayed impaired neutralization against BA.2.86, JN.1, KP.2 and KP.3. The results confirmed the experimental data that JN.1, KP.2 and KP.3 harboring the L455S and F456L mutations can significantly impair the neutralizing activity of class 1 monoclonal antibodies, while the epistatic effects mediated by F456L can facilitate the subsequent convergence of Q493E changes to rescue ACE2 binding. Structural and energetic analysis provided a rationale to the experimental results showing that BD55-5840 and BD55-5514 antibodies that bind to different binding epitopes can retain neutralizing efficacy against all examined variants BA.2.86, JN.1, KP.2 and KP.3. The results support the notion that evolution of Omicron variants may favor emergence of lineages with beneficial combinations of mutations involving mediators of epistatic couplings that control balance of high ACE2 affinity and immune evasion.

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

BACKGROUND

Thermostability 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.

RESULTS

Here 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.

CONCLUSION

Meaningful 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.

Atomistic Prediction of Structures, Conformational Ensembles and Binding Energetics for the SARS-CoV-2 Spike JN.1, KP.2 and KP.3 Variants Using AlphaFold2 and Molecular Dynamics Simulations: Mutational Profiling and Binding Free Energy Analysis Reveal Epistatic Hotspots of the ACE2 Affinity and Immune Escape

The most recent wave of SARS-CoV-2 Omicron variants descending from BA.2 and BA.2.86 exhibited improved viral growth and fitness due to convergent evolution of functional hotspots. These hotspots operate in tandem to optimize both receptor binding for effective infection and immune evasion efficiency, thereby maintaining overall viral fitness. The lack of molecular details on structure, dynamics and binding energetics of the latest FLiRT and FLuQE variants with the ACE2 receptor and antibodies provides a considerable challenge that is explored in this study. We combined AlphaFold2-based atomistic predictions of structures and conformational ensembles of the SARS-CoV-2 Spike complexes with the host receptor ACE2 for the most dominant Omicron variants JN.1, KP.1, KP.2 and KP.3 to examine the mechanisms underlying the role of convergent evolution hotspots in balancing ACE2 binding and antibody evasion. Using the ensemble-based mutational scanning of the spike protein residues and computations of binding affinities, we identified binding energy hotspots and characterized molecular basis underlying epistatic couplings between convergent mutational hotspots. The results suggested that the existence of epistatic interactions between convergent mutational sites at L455, F456, Q493 positions that enable to protect and restore ACE2 binding affinity while conferring beneficial immune escape. To examine immune escape mechanisms, we performed structure-based mutational profiling of the spike protein binding with several classes of antibodies that displayed impaired neutralization against BA.2.86, JN.1, KP.2 and KP.3. The results confirmed the experimental data that JN.1, KP.2 and KP.3 harboring the L455S and F456L mutations can significantly impair the neutralizing activity of class-1 monoclonal antibodies, while the epistatic effects mediated by F456L can facilitate the subsequent convergence of Q493E changes to rescue ACE2 binding. Structural and energetic analysis provided a rationale to the experimental results showing that BD55-5840 and BD55-5514 antibodies that bind to different binding epitopes can retain neutralizing efficacy against all examined variants BA.2.86, JN.1, KP.2 and KP.3. The results support the notion that evolution of Omicron variants may favor emergence of lineages with beneficial combinations of mutations involving mediators of epistatic couplings that control balance of high ACE2 affinity and immune evasion.

Deep mutational scanning reveals sequence to function constraints for SWEET family transporters

Protein science is entering a transformative phase enabled by deep mutational scans that provide an unbiased view of the residue level interactions that mediate function. However, it has yet to be extensively used to characterize the mutational and evolutionary landscapes of plant proteins. Here, we apply the method to explore sequence-function relationships within the sugar transporter AtSWEET13. DMS results describe how mutational interrogation throughout different regions of the protein affects AtSWEET13 abundance and transport function. Our results identify novel transport-enhancing mutations that are validated using the FRET sensor assays. Extending DMS results to phylogenetic analyses reveal the role of transmembrane helix 4 (TM4) which makes the SWEET family transporters distinct from prokaryotic SemiSWEETs. We show that transmembrane helix 4 is intolerant to motif swapping with other clade-specific SWEET TM4 compositions, despite accommodating single point-mutations towards aromatic and charged polar amino acids. We further show that the transfer learning approaches based on physics and ML based In silico variant prediction tools have limited utility for engineering plant proteins as they were unable to reproduce our experimental results. We conclude that DMS can produce datasets which, when combined with the right predictive computational frameworks, can direct plant engineering efforts through derivative phenotype selection and evolutionary insights.

Identification, Characterization, and Computer-Aided Rational Design of a Novel Thermophilic Esterase from Geobacillus subterraneus, and Application in the Synthesis of Cinnamyl Acetate

Investigation of a novel thermophilic esterase gene from Geobacillus subterraneus DSMZ 13552 indicated a high amino acid sequence similarity of 25.9% to a reported esterase from Geobacillus sp. A strategy that integrated computer-aided rational design tools was developed to select mutation sites. Six mutants were selected from four criteria based on the simulated saturation mutation (including 19 amino acid residues) results. Of these, the mutants Q78Y and G119A were found to retain 87% and 27% activity after incubation at 70 °C for 20 min, compared with the 19% activity for the wild type. Subsequently, a double-point mutant (Q78Y/G119A) was obtained and identified with optimal temperature increase from 65 to 70 °C and a 41.51% decrease in Km. The obtained T1/2 values of 42.2 min (70 °C) and 16.9 min (75 °C) for Q78Y/G119A showed increases of 340% and 412% compared with that in the wild type. Q78Y/G119A was then employed as a biocatalyst to synthesize cinnamyl acetate, for which the conversion rate reached 99.40% with 0.3 M cinnamyl alcohol at 60 °C. The results validated the enhanced enzymatic properties of the mutant and indicated better prospects for industrial application as compared to that in the wild type. This study reported a method by which an enzyme could evolve to achieve enhanced thermostability, thereby increasing its potential for industrial applications, which could also be expanded to other esterases.

AlphaFold2 Predictions of Conformational Ensembles and Atomistic Simulations of the SARS-CoV-2 Spike XBB Lineages Reveal Epistatic Couplings between Convergent Mutational Hotspots that Control ACE2 Affinity

In this study, we combined AlphaFold-based atomistic structural modeling, microsecond molecular simulations, mutational profiling, and network analysis to characterize binding mechanisms of the SARS-CoV-2 spike protein with the host receptor ACE2 for a series of Omicron XBB variants including XBB.1.5, XBB.1.5+L455F, XBB.1.5+F456L, and XBB.1.5+L455F+F456L. AlphaFold-based structural and dynamic modeling of SARS-CoV-2 Spike XBB lineages can accurately predict the experimental structures and characterize conformational ensembles of the spike protein complexes with the ACE2. Microsecond molecular dynamics simulations identified important differences in the conformational landscapes and equilibrium ensembles of the XBB variants, suggesting that combining AlphaFold predictions of multiple conformations with molecular dynamics simulations can provide a complementary approach for the characterization of functional protein states and binding mechanisms. Using the ensemble-based mutational profiling of protein residues and physics-based rigorous calculations of binding affinities, we identified binding energy hotspots and characterized the molecular basis underlying epistatic couplings between convergent mutational hotspots. Consistent with the experiments, the results revealed the mediating role of the Q493 hotspot in the synchronization of epistatic couplings between L455F and F456L mutations, providing a quantitative insight into the energetic determinants underlying binding differences between XBB lineages. We also proposed a network-based perturbation approach for mutational profiling of allosteric communications and uncovered the important relationships between allosteric centers mediating long-range communication and binding hotspots of epistatic couplings. The results of this study support a mechanism in which the binding mechanisms of the XBB variants may be determined by epistatic effects between convergent evolutionary hotspots that control ACE2 binding.

Application of an alchemical free energy method for the prediction of thermostable DuraPETase variants

Non-equilibrium (NEQ) alchemical free energy calculations are an emerging tool for accurately predicting changes in protein folding free energy resulting from amino acid mutations. In this study, this method in combination with the Rosetta ddg monomer tool was applied to predict more thermostable variants of the polyethylene terephthalate (PET) degrading enzyme DuraPETase. The Rosetta ddg monomer tool efficiently enriched promising mutations prior to more accurate prediction by NEQ alchemical free energy calculations. The relative change in folding free energy of 96 single amino acid mutations was calculated by NEQ alchemical free energy calculation. Experimental validation of ten of the highest scoring variants identified two mutations (DuraPETaseS61M and DuraPETaseS223Y) that increased the melting temperature (Tm) of the enzyme by up to 1 °C. The calculated relative change in folding free energy showed an excellent correlation with experimentally determined Tm resulting in a Pearson's correlation coefficient of r =  - 0.84. Limitations in the prediction of strongly stabilizing mutations were, however, encountered and are discussed. Despite these challenges, this study demonstrates the practical applicability of NEQ alchemical free energy calculations in prospective enzyme engineering projects. KEY POINTS: • Rosetta ddg monomer enriches stabilizing mutations in a library of DuraPETase variants • NEQ free energy calculations accurately predict changes in Tm of DuraPETase • The DuraPETase variants S223Y, S42M, and S61M have increased Tm.

FiTMuSiC: leveraging structural and (co)evolutionary data for protein fitness prediction

Systematically predicting the effects of mutations on protein fitness is essential for the understanding of genetic diseases. Indeed, predictions complement experimental efforts in analyzing how variants lead to dysfunctional proteins that in turn can cause diseases. Here we present our new fitness predictor, FiTMuSiC, which leverages structural, evolutionary and coevolutionary information. We show that FiTMuSiC predicts fitness with high accuracy despite the simplicity of its underlying model: it was among the top predictors on the hydroxymethylbilane synthase (HMBS) target of the sixth round of the Critical Assessment of Genome Interpretation challenge (CAGI6) and performs as well as much more complex deep learning models such as AlphaMissense. To further demonstrate FiTMuSiC's robustness, we compared its predictions with in vitro activity data on HMBS, variant fitness data on human glucokinase (GCK), and variant deleteriousness data on HMBS and GCK. These analyses further confirm FiTMuSiC's qualities and accuracy, which compare favorably with those of other predictors. Additionally, FiTMuSiC returns two scores that separately describe the functional and structural effects of the variant, thus providing mechanistic insight into why the variant leads to fitness loss or gain. We also provide an easy-to-use webserver at https://babylone.ulb.ac.be/FiTMuSiC , which is freely available for academic use and does not require any bioinformatics expertise, which simplifies the accessibility of our tool for the entire scientific community.

AlphaFold2-Enabled Atomistic Modeling of Structure, Conformational Ensembles, and Binding Energetics of the SARS-CoV-2 Omicron BA.2.86 Spike Protein with ACE2 Host Receptor and Antibodies: Compensatory Functional Effects of Binding Hotspots in Modulating Mechanisms of Receptor Binding and Immune Escape

The latest wave of SARS-CoV-2 Omicron variants displayed a growth advantage and increased viral fitness through convergent evolution of functional hotspots that work synchronously to balance fitness requirements for productive receptor binding and efficient immune evasion. In this study, we combined AlphaFold2-based structural modeling approaches with atomistic simulations and mutational profiling of binding energetics and stability for prediction and comprehensive analysis of the structure, dynamics, and binding of the SARS-CoV-2 Omicron BA.2.86 spike variant with ACE2 host receptor and distinct classes of antibodies. We adapted several AlphaFold2 approaches to predict both the structure and conformational ensembles of the Omicron BA.2.86 spike protein in the complex with the host receptor. The results showed that the AlphaFold2-predicted structural ensemble of the BA.2.86 spike protein complex with ACE2 can accurately capture the main conformational states of the Omicron variant. Complementary to AlphaFold2 structural predictions, microsecond molecular dynamics simulations reveal the details of the conformational landscape and produced equilibrium ensembles of the BA.2.86 structures that are used to perform mutational scanning of spike residues and characterize structural stability and binding energy hotspots. The ensemble-based mutational profiling of the receptor binding domain residues in the BA.2 and BA.2.86 spike complexes with ACE2 revealed a group of conserved hydrophobic hotspots and critical variant-specific contributions of the BA.2.86 convergent mutational hotspots R403K, F486P, and R493Q. To examine the immune evasion properties of BA.2.86 in atomistic detail, we performed structure-based mutational profiling of the spike protein binding interfaces with distinct classes of antibodies that displayed significantly reduced neutralization against the BA.2.86 variant. The results revealed the molecular basis of compensatory functional effects of the binding hotspots, showing that BA.2.86 lineage may have evolved to outcompete other Omicron subvariants by improving immune evasion while preserving binding affinity with ACE2 via through a compensatory effect of R493Q and F486P convergent mutational hotspots. This study demonstrated that an integrative approach combining AlphaFold2 predictions with complementary atomistic molecular dynamics simulations and robust ensemble-based mutational profiling of spike residues can enable accurate and comprehensive characterization of structure, dynamics, and binding mechanisms of newly emerging Omicron variants.

Quantum biochemical analysis of the binding interactions between a potential inhibitory drug and the Ebola viral glycoprotein

Ebola virus disease (EVD) causes outbreaks and epidemics in West Africa that persist until today. The envelope glycoprotein of Ebola virus (GP) consists of two subunits, GP1 and GP2, and plays a key role in anchoring or fusing the virus to the host cell in its active form on the virion surface. Toremifene (TOR) is a ligand that mainly acts as an estrogen receptor antagonist; however, a recent study showed a strong and efficient interaction with GP. In this context, we aimed to evaluate the energetic affinity features involved in the interaction between GP and toremifene by computer simulation techniques using the Molecular Fractionation Method with Conjugate Caps (MFCC) scheme and quantum-mechanical (QM) calculations, as well as missense mutations to assess protein stability. We identified ASP522, GLU100, TYR517, THR519, LEU186, LEU515 as the most attractive residues in the EBOV glycoprotein structure that form the binding pocket. We divided toremifene into three regions and evaluated that region i was more important than region iii and region ii for the formation of the TOR-GP1/GP2 complex, which might control the molecular remodeling process of TOR. The mutations that caused more destabilization were ARG134, LEU515, TYR517 and ARG559, while those that caused stabilization were GLU523 and ASP522. TYR517 is a critical residue for the binding of TOR, and is highly conserved among EBOV species. Our results may help to elucidate the mechanism of drug action on the GP protein of the Ebola virus and subsequently develop new pharmacological approaches against EVD.Communicated by Ramaswamy H. Sarma.

Assessing computational tools for predicting protein stability changes upon missense mutations using a new dataset

Insight into how mutations affect protein stability is crucial for protein engineering, understanding genetic diseases, and exploring protein evolution. Numerous computational methods have been developed to predict the impact of amino acid substitutions on protein stability. Nevertheless, comparing these methods poses challenges due to variations in their training data. Moreover, it is observed that they tend to perform better at predicting destabilizing mutations than stabilizing ones. Here, we meticulously compiled a new dataset from three recently published databases: ThermoMutDB, FireProtDB, and ProThermDB. This dataset, which does not overlap with the well-established S2648 dataset, consists of 4038 single-point mutations, including over 1000 stabilizing mutations. We assessed these mutations using 27 computational methods, including the latest ones utilizing mega-scale stability datasets and transfer learning. We excluded entries with overlap or similarity to training datasets to ensure fairness. Pearson correlation coefficients for the tested tools ranged from 0.20 to 0.53 on unseen data, and none of the methods could accurately predict stabilizing mutations, even those performing well in anti-symmetric property analysis. While most methods present consistent trends for predicting destabilizing mutations across various properties such as solvent exposure and secondary conformation, stabilizing mutations do not exhibit a clear pattern. Our study also suggests that solely addressing training dataset bias may not significantly enhance accuracy of predicting stabilizing mutations. These findings emphasize the importance of developing precise predictive methods for stabilizing mutations.

AlphaFold2-Enabled Atomistic Modeling of Epistatic Binding Mechanisms for the SARS-CoV-2 Spike Omicron XBB.1.5, EG.5 and FLip Variants: Convergent Evolution Hotspots Cooperate to Control Stability and Conformational Adaptability in Balancing ACE2 Binding and Antibody Resistance

In this study, we combined AI-based atomistic structural modeling and microsecond molecular simulations of the SARS-CoV-2 Spike complexes with the host receptor ACE2 for XBB.1.5+L455F, XBB.1.5+F456L(EG.5) and XBB.1.5+L455F/F456L (FLip) lineages to examine the mechanisms underlying the role of convergent evolution hotspots in balancing ACE2 binding and antibody evasion. Using the ensemble-based mutational scanning of the spike protein residues and physics-based rigorous computations of binding affinities, we identified binding energy hotspots and characterized molecular basis underlying epistatic couplings between convergent mutational hotspots. Consistent with the experiments, the results revealed the mediating role of Q493 hotspot in synchronization of epistatic couplings between L455F and F456L mutations providing a quantitative insight into the mechanism underlying differences between XBB lineages. Mutational profiling is combined with network-based model of epistatic couplings showing that the Q493, L455 and F456 sites mediate stable communities at the binding interface with ACE2 and can serve as stable mediators of non-additive couplings. Structure-based mutational analysis of Spike protein binding with the class 1 antibodies quantified the critical role of F456L and F486P mutations in eliciting strong immune evasion response. The results of this analysis support a mechanism in which the emergence of EG.5 and FLip variants may have been dictated by leveraging strong epistatic effects between several convergent revolutionary hotspots that provide synergy between the improved ACE2 binding and broad neutralization resistance. This interpretation is consistent with the notion that functionally balanced substitutions which simultaneously optimize immune evasion and high ACE2 affinity may continue to emerge through lineages with beneficial pair or triplet combinations of RBD mutations involving mediators of epistatic couplings and sites in highly adaptable RBD regions.

ProS-GNN: Predicting effects of mutations on protein stability using graph neural networks

Predicting protein stability change upon variation through a computational approach is a valuable tool to unveil the mechanisms of mutation-induced drug failure and develop immunotherapy strategies. Some previous machine learning-based techniques exhibit anti-symmetric bias toward destabilizing situations, whereas others struggle with generalization to unseen examples. To address these issues, we propose a gated graph neural network-based approach to predict changes in protein stability upon mutation. The model uses message passing to encode the links between the molecular structure and property after eliminating the non-mutant structure and creating input feature vectors. While doing so, it also incorporates the coordinates of the raw atoms to provide spatial insights into the chemical systems. We test the model on the Ssym, Myoglobin, Broom, and p53 datasets to demonstrate the generalization performance. Compared to existing approaches, our proposed method achieves improved linearity with symmetry in less time. The code for this study is available at: https://github.com/HongzhouTang/Pros-GNN.

Quantification of biases in predictions of protein-protein binding affinity changes upon mutations

Understanding the impact of mutations on protein-protein binding affinity is a key objective for a wide range of biotechnological applications and for shedding light on disease-causing mutations, which are often located at protein-protein interfaces. Over the past decade, many computational methods using physics-based and/or machine learning approaches have been developed to predict how protein binding affinity changes upon mutations. They all claim to achieve astonishing accuracy on both training and test sets, with performances on standard benchmarks such as SKEMPI 2.0 that seem overly optimistic. Here we benchmarked eight well-known and well-used predictors and identified their biases and dataset dependencies, using not only SKEMPI 2.0 as a test set but also deep mutagenesis data on the severe acute respiratory syndrome coronavirus 2 spike protein in complex with the human angiotensin-converting enzyme 2. We showed that, even though most of the tested methods reach a significant degree of robustness and accuracy, they suffer from limited generalizability properties and struggle to predict unseen mutations. Interestingly, the generalizability problems are more severe for pure machine learning approaches, while physics-based methods are less affected by this issue. Moreover, undesirable prediction biases toward specific mutation properties, the most marked being toward destabilizing mutations, are also observed and should be carefully considered by method developers. We conclude from our analyses that there is room for improvement in the prediction models and suggest ways to check, assess and improve their generalizability and robustness.

Accurate Characterization of Conformational Ensembles and Binding Mechanisms of the SARS-CoV-2 Omicron BA.2 and BA.2.86 Spike Protein with the Host Receptor and Distinct Classes of Antibodies Using AlphaFold2-Augmented Integrative Computational Modeling

The latest wave SARS-CoV-2 Omicron variants displayed a growth advantage and the increased viral fitness through convergent evolution of functional hotspots that work synchronously to balance fitness requirements for productive receptor binding and efficient immune evasion. In this study, we combined AlphaFold2-based structural modeling approaches with all-atom MD simulations and mutational profiling of binding energetics and stability for prediction and comprehensive analysis of the structure, dynamics, and binding of the SARS-CoV-2 Omicron BA.2.86 spike variant with ACE2 host receptor and distinct classes of antibodies. We adapted several AlphaFold2 approaches to predict both structure and conformational ensembles of the Omicron BA.2.86 spike protein in the complex with the host receptor. The results showed that AlphaFold2-predicted conformational ensemble of the BA.2.86 spike protein complex can accurately capture the main dynamics signatures obtained from microscond molecular dynamics simulations. The ensemble-based dynamic mutational scanning of the receptor binding domain residues in the BA.2 and BA.2.86 spike complexes with ACE2 dissected the role of the BA.2 and BA.2.86 backgrounds in modulating binding free energy changes revealing a group of conserved hydrophobic hotspots and critical variant-specific contributions of the BA.2.86 mutational sites R403K, F486P and R493Q. To examine immune evasion properties of BA.2.86 in atomistic detail, we performed large scale structure-based mutational profiling of the S protein binding interfaces with distinct classes of antibodies that displayed significantly reduced neutralization against BA.2.86 variant. The results quantified specific function of the BA.2.86 mutations to ensure broad resistance against different classes of RBD antibodies. This study revealed the molecular basis of compensatory functional effects of the binding hotspots, showing that BA.2.86 lineage may have primarily evolved to improve immune escape while modulating binding affinity with ACE2 through cooperative effect of R403K, F486P and R493Q mutations. The study supports a hypothesis that the impact of the increased ACE2 binding affinity on viral fitness is more universal and is mediated through cross-talk between convergent mutational hotspots, while the effect of immune evasion could be more variant-dependent.

CLICK-chemoproteomics and molecular dynamics simulation reveals pregnenolone targets and their binding conformations in Th2 cells

Pregnenolone (P5) is synthesized as the first bioactive steroid in the mitochondria from cholesterol. Clusters of differentiation 4 (CD4+) and Clusters of differentiation 8 (CD8+) immune cells synthesize P5 de novo; P5, in turn, play important role in immune homeostasis and regulation. However, P5's biochemical mode of action in immune cells is still emerging. We envisage that revealing the complete spectrum of P5 target proteins in immune cells would have multifold applications, not only in basic understanding of steroids biochemistry in immune cells but also in developing new therapeutic applications. We employed a CLICK-enabled probe to capture P5-binding proteins in live T helper cell type 2 (Th2) cells. Subsequently, using high-throughput quantitative proteomics, we identified the P5 interactome in CD4+ Th2 cells. Our study revealed P5's mode of action in CD4+ immune cells. We identified novel proteins from mitochondrial and endoplasmic reticulum membranes to be the primary mediators of P5's biochemistry in CD4+ and to concur with our earlier finding in CD8+ immune cells. Applying advanced computational algorithms and molecular simulations, we were able to generate near-native maps of P5-protein key molecular interactions. We showed bonds and interactions between key amino acids and P5, which revealed the importance of ionic bond, hydrophobic interactions, and water channels. We point out that our results can lead to designing of novel molecular therapeutics strategies.

High-Accuracy Prediction of Stabilizing Surface Mutations to the Three-Helix Bundle, UBA(1), with EmCAST

The accurate modeling of energetic contributions to protein structure is a fundamental challenge in computational approaches to protein analysis and design. We describe a general computational method, EmCAST (empirical Cα stabilization), to score and optimize the sequence to the structure in proteins. The method relies on an empirical potential derived from the database of the Cα dihedral angle preferences for all possible four-residue sequences, using the data available in the Protein Data Bank. Our method produces stability predictions that naturally correlate one-to-one with the experimental results for solvent-exposed mutation sites. EmCAST predicted four mutations that increased the stability of a three-helix bundle, UBA(1), from 2.4 to 4.8 kcal/mol by optimizing residues in both helices and turns. For a set of eight variants, the predicted and experimental stabilizations correlate very well (R2 = 0.97) with a slope near 1 and with a 0.16 kcal/mol standard error for EmCAST predictions. Tests against literature data for the stability effects of surface-exposed mutations show that EmCAST outperforms the existing stability prediction methods. UBA(1) variants were crystallized to verify and analyze their structures at an atomic resolution. Thermodynamic and kinetic folding experiments were performed to determine the magnitude and mechanism of stabilization. Our method has the potential to enable the rapid, rational optimization of natural proteins, expand the analysis of the sequence/structure relationship, and supplement the existing protein design strategies.

Comparative Analysis of Conformational Dynamics and Systematic Characterization of Cryptic Pockets in the SARS-CoV-2 Omicron BA.2, BA.2.75 and XBB.1 Spike Complexes with the ACE2 Host Receptor: Confluence of Binding and Structural Plasticity in Mediating Networks of Conserved Allosteric Sites

In the current study, we explore coarse-grained simulations and atomistic molecular dynamics together with binding energetics scanning and cryptic pocket detection in a comparative examination of conformational landscapes and systematic characterization of allosteric binding sites in the SARS-CoV-2 Omicron BA.2, BA.2.75 and XBB.1 spike full-length trimer complexes with the host receptor ACE2. Microsecond simulations, Markov state models and mutational scanning of binding energies of the SARS-CoV-2 BA.2 and BA.2.75 receptor binding domain complexes revealed the increased thermodynamic stabilization of the BA.2.75 variant and significant dynamic differences between these Omicron variants. Molecular simulations of the SARS-CoV-2 Omicron spike full-length trimer complexes with the ACE2 receptor complemented atomistic studies and enabled an in-depth analysis of mutational and binding effects on conformational dynamic and functional adaptability of the Omicron variants. Despite considerable structural similarities, Omicron variants BA.2, BA.2.75 and XBB.1 can induce unique conformational dynamic signatures and specific distributions of the conformational states. Using conformational ensembles of the SARS-CoV-2 Omicron spike trimer complexes with ACE2, we conducted a comprehensive cryptic pocket screening to examine the role of Omicron mutations and ACE2 binding on the distribution and functional mechanisms of the emerging allosteric binding sites. This analysis captured all experimentally known allosteric sites and discovered networks of inter-connected and functionally relevant allosteric sites that are governed by variant-sensitive conformational adaptability of the SARS-CoV-2 spike structures. The results detailed how ACE2 binding and Omicron mutations in the BA.2, BA.2.75 and XBB.1 spike complexes modulate the distribution of conserved and druggable allosteric pockets harboring functionally important regions. The results are significant for understanding the functional roles of druggable cryptic pockets that can be used for allostery-mediated therapeutic intervention targeting conformational states of the Omicron variants.

Advancing Enzyme's Stability and Catalytic Efficiency through Synergy of Force-Field Calculations, Evolutionary Analysis, and Machine Learning

Thermostability is an essential requirement for the use of enzymes in the bioindustry. Here, we compare different protein stabilization strategies using a challenging target, a stable haloalkane dehalogenase DhaA115. We observe better performance of automated stabilization platforms FireProt and PROSS in designing multiple-point mutations over the introduction of disulfide bonds and strengthening the intra- and the inter-domain contacts by in silico saturation mutagenesis. We reveal that the performance of automated stabilization platforms was still compromised due to the introduction of some destabilizing mutations. Notably, we show that their prediction accuracy can be improved by applying manual curation or machine learning for the removal of potentially destabilizing mutations, yielding highly stable haloalkane dehalogenases with enhanced catalytic properties. A comparison of crystallographic structures revealed that current stabilization rounds were not accompanied by large backbone re-arrangements previously observed during the engineering stability of DhaA115. Stabilization was achieved by improving local contacts including protein-water interactions. Our study provides guidance for further improvement of automated structure-based computational tools for protein stabilization.

Searching similar local 3D micro-environments in protein structure databases with MicroMiner

The available protein structure data are rapidly increasing. Within these structures, numerous local structural sites depict the details characterizing structure and function. However, searching and analyzing these sites extensively and at scale poses a challenge. We present a new method to search local sites in protein structure databases using residue-defined local 3D micro-environments. We implemented the method in a new tool called MicroMiner and demonstrate the capabilities of residue micro-environment search on the example of structural mutation analysis. Usually, experimental structures for both the wild-type and the mutant are unavailable for comparison. With MicroMiner, we extracted $>255 \times 10^{6}$ amino acid pairs in protein structures from the PDB, exemplifying single mutations' local structural changes for single chains and $>45 \times 10^{6}$ pairs for protein-protein interfaces. We further annotate existing data sets of experimentally measured mutation effects, like $\Delta \Delta G$ measurements, with the extracted structure pairs to combine the mutation effect measurement with the structural change upon mutation. In addition, we show how MicroMiner can bridge the gap between mutation analysis and structure-based drug design tools. MicroMiner is available as a command line tool and interactively on the https://proteins.plus/ webserver.

Examining Functional Linkages Between Conformational Dynamics, Protein Stability and Evolution of Cryptic Binding Pockets in the SARS-CoV-2 Omicron Spike Complexes with the ACE2 Host Receptor: Recombinant Omicron Variants Mediate Variability of Conserved Allosteric Sites and Binding Epitopes

In the current study, we explore coarse-grained simulations and atomistic molecular dynamics together with binding energetics scanning and cryptic pocket detection in a comparative examination of conformational landscapes and systematic characterization of allosteric binding sites in the SARS-CoV-2 Omicron BA.2, BA.2.75 and XBB.1 spike full-length trimer complexes with the host receptor ACE2. Microsecond simulations, Markov state models and mutational scanning of binding energies of the SARS-CoV-2 BA.2 and BA.2.75 receptor binding domain complexes revealed the increased thermodynamic stabilization of the BA.2.75 variant and significant dynamic differences between these Omicron variants. Molecular simulations of the SARS-CoV-2 Omicron spike full length trimer complexes with the ACE2 receptor complemented atomistic studies and enabled an in-depth analysis of mutational and binding effects on conformational dynamic and functional adaptability of the Omicron variants. Despite considerable structural similarities, Omicron variants BA.2, BA.2.75 and XBB.1 can induce unique conformational dynamic signatures and specific distributions of the conformational states. Using conformational ensembles of the SARS-CoV-2 Omicron spike trimer complexes with ACE2, we conducted a comprehensive cryptic pocket screening to examine the role of Omicron mutations and ACE2 binding on the distribution and functional mechanisms of the emerging allosteric binding sites. This analysis captured all experimentally known allosteric sites and discovered networks of inter-connected and functionally relevant allosteric sites that are governed by variant-sensitive conformational adaptability of the SARS-CoV-2 spike structures. The results detailed how ACE2 binding and Omicron mutations in the BA.2, BA.2.75 and XBB.1 spike complexes modulate the distribution of conserved and druggable allosteric pockets harboring functionally important regions. The results of are significant for understanding functional roles of druggable cryptic pockets that can be used for allostery-mediated therapeutic intervention targeting conformational states of the Omicron variants.

Topological deep learning based deep mutational scanning

High-throughput deep mutational scanning (DMS) experiments have significantly impacted protein engineering, drug discovery, immunology, cancer biology, and evolutionary biology by enabling the systematic understanding of protein functions. However, the mutational space associated with proteins is astronomically large, making it overwhelming for current experimental capabilities. Therefore, alternative methods for DMS are imperative. We propose a topological deep learning (TDL) paradigm to facilitate in silico DMS. We utilize a new topological data analysis (TDA) technique based on the persistent spectral theory, also known as persistent Laplacian, to capture both topological invariants and the homotopic shape evolution of data. To validate our TDL-DMS model, we use SARS-CoV-2 datasets and show excellent accuracy and reliability for binding interface mutations. This finding is significant for SARS-CoV-2 variant forecasting and designing effective antibodies and vaccines. Our proposed model is expected to have a significant impact on drug discovery, vaccine design, precision medicine, and protein engineering.

Bioinformatic analysis of the effect of SNPs in the pig TERT gene on the structural and functional characteristics of the enzyme to develop new genetic markers of productivity traits

BACKGROUND

Telomerase reverse transcriptase (TERT) plays a crucial role in synthesizing telomeric repeats that safeguard chromosomes from damage and fusion, thereby maintaining genome stability. Mutations in the TERT gene can lead to a deviation in gene expression, impaired enzyme activity, and, as a result, abnormal telomere shortening. Genetic markers of productivity traits in livestock can be developed based on the TERT gene polymorphism for use in marker-associated selection (MAS). In this study, a bioinformatic-based approach is proposed to evaluate the effect of missense single-nucleotide polymorphisms (SNPs) in the pig TERT gene on enzyme function and structure, with the prospect of developing genetic markers.

RESULTS

A comparative analysis of the coding and amino acid sequences of the pig TERT was performed with corresponding sequences of other species. The distribution of polymorphisms in the pig TERT gene, with respect to the enzyme's structural-functional domains, was established. A three-dimensional model of the pig TERT structure was obtained through homological modeling. The potential impact of each of the 23 missense SNPs in the pig TERT gene on telomerase function and stability was assessed using predictive bioinformatic tools utilizing data on the amino acid sequence and structure of pig TERT.

CONCLUSIONS

According to bioinformatic analysis of 23 missense SNPs of the pig TERT gene, a predictive effect of rs789641834 (TEN domain), rs706045634 (TEN domain), rs325294961 (TRBD domain) and rs705602819 (RTD domain) on the structural and functional parameters of the enzyme was established. These SNPs hold the potential to serve as genetic markers of productivity traits. Therefore, the possibility of their application in MAS should be further evaluated in associative analysis studies.

Predicting the Effect of Single Mutations on Protein Stability and Binding with Respect to Types of Mutations

The development of methods and algorithms to predict the effect of mutations on protein stability, protein-protein interaction, and protein-DNA/RNA binding is necessitated by the needs of protein engineering and for understanding the molecular mechanism of disease-causing variants. The vast majority of the leading methods require a database of experimentally measured folding and binding free energy changes for training. These databases are collections of experimental data taken from scientific investigations typically aimed at probing the role of particular residues on the above-mentioned thermodynamic characteristics, i.e., the mutations are not introduced at random and do not necessarily represent mutations originating from single nucleotide variants (SNV). Thus, the reported performance of the leading algorithms assessed on these databases or other limited cases may not be applicable for predicting the effect of SNVs seen in the human population. Indeed, we demonstrate that the SNVs and non-SNVs are not equally presented in the corresponding databases, and the distribution of the free energy changes is not the same. It is shown that the Pearson correlation coefficients (PCCs) of folding and binding free energy changes obtained in cases involving SNVs are smaller than for non-SNVs, indicating that caution should be used in applying them to reveal the effect of human SNVs. Furthermore, it is demonstrated that some methods are sensitive to the chemical nature of the mutations, resulting in PCCs that differ by a factor of four across chemically different mutations. All methods are found to underestimate the energy changes by roughly a factor of 2.

Insight into the Nucleotide Based Modulation of the Grp94 Molecular Chaperone Using Multiscale Dynamics

Grp94, an ER-localized molecular chaperone, is required for the folding and activation of many membrane and secretory proteins. Client activation by Grp94 is mediated by nucleotide and conformational changes. In this work, we aim to understand how microscopic changes from nucleotide hydrolysis can potentiate large-scale conformational changes of Grp94. We performed all-atom molecular dynamics simulations on the ATP-hydrolysis competent state of the Grp94 dimer in four different nucleotide bound states. We found that Grp94 was the most rigid when ATP was bound. ATP hydrolysis or nucleotide removal enhanced mobility of the N-terminal domain and ATP lid, resulting in suppression of interdomain communication. In an asymmetric conformation with one hydrolyzed nucleotide, we identified a more compact state, similar to experimental observations. We also identified a potential regulatory role of the flexible linker, as it formed electrostatic interactions with the Grp94 M-domain helix near the region where BiP is known to bind. These studies were complemented with normal-mode analysis of an elastic network model to investigate Grp94's large-scale conformational changes. SPM analysis identified residues that are important in signaling conformational change, many of which have known functional relevance in ATP coordination and catalysis, client binding, and BiP binding. Our findings suggest that ATP hydrolysis in Grp94 alters allosteric wiring and facilitates conformational changes.

Balancing Functional Tradeoffs between Protein Stability and ACE2 Binding in the SARS-CoV-2 Omicron BA.2, BA.2.75 and XBB Lineages: Dynamics-Based Network Models Reveal Epistatic Effects Modulating Compensatory Dynamic and Energetic Changes

Evolutionary and functional studies suggested that the emergence of the Omicron variants can be determined by multiple fitness trade-offs including the immune escape, binding affinity for ACE2, conformational plasticity, protein stability and allosteric modulation. In this study, we systematically characterize conformational dynamics, structural stability and binding affinities of the SARS-CoV-2 Spike Omicron complexes with the host receptor ACE2 for BA.2, BA.2.75, XBB.1 and XBB.1.5 variants. We combined multiscale molecular simulations and dynamic analysis of allosteric interactions together with the ensemble-based mutational scanning of the protein residues and network modeling of epistatic interactions. This multifaceted computational study characterized molecular mechanisms and identified energetic hotspots that can mediate the predicted increased stability and the enhanced binding affinity of the BA.2.75 and XBB.1.5 complexes. The results suggested a mechanism driven by the stability hotspots and a spatially localized group of the Omicron binding affinity centers, while allowing for functionally beneficial neutral Omicron mutations in other binding interface positions. A network-based community model for the analysis of epistatic contributions in the Omicron complexes is proposed revealing the key role of the binding hotspots R498 and Y501 in mediating community-based epistatic couplings with other Omicron sites and allowing for compensatory dynamics and binding energetic changes. The results also showed that mutations in the convergent evolutionary hotspot F486 can modulate not only local interactions but also rewire the global network of local communities in this region allowing the F486P mutation to restore both the stability and binding affinity of the XBB.1.5 variant which may explain the growth advantages over the XBB.1 variant. The results of this study are consistent with a broad range of functional studies rationalizing functional roles of the Omicron mutation sites that form a coordinated network of hotspots enabling a balance of multiple fitness tradeoffs and shaping up a complex functional landscape of virus transmissibility.

Probing Conformational Landscapes of Binding and Allostery in the SARS-CoV-2 Omicron Variant Complexes Using Microsecond Atomistic Simulations and Perturbation-Based Profiling Approaches: Hidden Role of Omicron Mutations as Modulators of Allosteric Signaling and Epistatic Relationships

In this study, we systematically examine the conformational dynamics, binding and allosteric communications in the Omicron BA.1, BA.2, BA.3 and BA.4/BA.5 complexes with the ACE2 host receptor using molecular dynamics simulations and perturbation-based network profiling approaches. Microsecond atomistic simulations provided a detailed characterization of the conformational landscapes and revealed the increased thermodynamic stabilization of the BA.2 variant which is contrasted with the BA.4/BA.5 variants inducing a significant mobility of the complexes. Using ensemble-based mutational scanning of binding interactions, we identified binding affinity and structural stability hotspots in the Omicron complexes. Perturbation response scanning and network-based mutational profiling approaches probed the effect of the Omicron variants on allosteric communications. The results of this analysis revealed specific roles of Omicron mutations as "plastic and evolutionary adaptable" modulators of binding and allostery which are coupled to the major regulatory positions through interaction networks. Through perturbation network scanning of allosteric residue potentials in the Omicron variant complexes, which is performed in the background of the original strain, we identified that the key Omicron binding affinity hotspots N501Y and Q498R could mediate allosteric interactions and epistatic couplings. Our results suggested that the synergistic role of these hotspots in controlling stability, binding and allostery can enable for compensatory balance of fitness tradeoffs with conformationally and evolutionary adaptable immune-escape Omicron mutations. Through integrative computational approaches, this study provides a systematic analysis of the effects of Omicron mutations on thermodynamics, binding and allosteric signaling in the complexes with ACE2 receptor. The findings support a mechanism in which Omicron mutations can evolve to balance thermodynamic stability and conformational adaptability in order to ensure proper tradeoff between stability, binding and immune escape.

Coarse-Grained Molecular Simulations and Ensemble-Based Mutational Profiling of Protein Stability in the Different Functional Forms of the SARS-CoV-2 Spike Trimers: Balancing Stability and Adaptability in BA.1, BA.2 and BA.2.75 Variants

Evolutionary and functional studies have suggested that the emergence of Omicron variants can be determined by multiple fitness tradeoffs including immune escape, binding affinity, conformational plasticity, protein stability, and allosteric modulation. In this study, we embarked on a systematic comparative analysis of the conformational dynamics, electrostatics, protein stability, and allostery in the different functional states of spike trimers for BA.1, BA.2, and BA.2.75 variants. Using efficient and accurate coarse-grained simulations and atomistic reconstruction of the ensembles, we examined the conformational dynamics of the spike trimers that agree with the recent functional studies, suggesting that BA.2.75 trimers are the most stable among these variants. A systematic mutational scanning of the inter-protomer interfaces in the spike trimers revealed a group of conserved structural stability hotspots that play a key role in the modulation of functional dynamics and are also involved in the inter-protomer couplings through local contacts and interaction networks with the Omicron mutational sites. The results of mutational scanning provided evidence that BA.2.75 trimers are more stable than BA.2 and comparable in stability to the BA.1 variant. Using dynamic network modeling of the S Omicron BA.1, BA.2, and BA.2.75 trimers, we showed that the key network mediators of allosteric interactions are associated with the major stability hotspots that are interconnected along potential communication pathways. The network analysis of the BA.1, BA.2, and BA.2.75 trimers suggested that the increased thermodynamic stability of the BA.2.75 variant may be linked with the organization and modularity of the residue interaction network that allows for allosteric communications between structural stability hotspots and Omicron mutational sites. This study provided a plausible rationale for a mechanism in which Omicron mutations may evolve by targeting vulnerable sites of conformational adaptability to elicit immune escape while maintaining their control on balancing protein stability and functional fitness through robust allosteric communications with the stability hotspots.

Exploring the Transferability of Replica Exchange Structure Reservoirs to Accelerate Generation of Ensembles for Alternate Hamiltonians or Protein Mutations

Generating precise ensembles is commonly a prerequisite to understand the energetics of biological processes using Molecular Dynamics (MD) simulations. Previously, we have shown how unweighted reservoirs built from high temperature MD simulations can accelerate convergence of Boltzmann-weighted ensembles by at least 10× with the Reservoir Replica Exchange MD (RREMD) method. Therefore, in this work, we explore whether an unweighted structure reservoir generated with one Hamiltonian (solute force field plus solvent model) can be reused to quickly generate accurately weighted ensembles for Hamiltonians other than the one that was used to generate the reservoir. We also extended this methodology to rapidly estimate the effects of mutations on peptide stability by using a reservoir of diverse structures obtained from wild-type simulations. These results suggest that structures generated via fast methods such as coarse-grained models or structures predicted by Rosetta or deep learning approaches could be integrated into a reservoir to accelerate generation of ensembles using more accurate representations.

Mutually beneficial confluence of structure-based modeling of protein dynamics and machine learning methods

Proteins sample an ensemble of conformers under physiological conditions, having access to a spectrum of modes of motions, also called intrinsic dynamics. These motions ensure the adaptation to various interactions in the cell, and largely assist in, if not determine, viable mechanisms of biological function. In recent years, machine learning frameworks have proven uniquely useful in structural biology, and recent studies further provide evidence to the utility and/or necessity of considering intrinsic dynamics for increasing their predictive ability. Efficient quantification of dynamics-based attributes by recently developed physics-based theories and models such as elastic network models provides a unique opportunity to generate data on dynamics for training ML models towards inferring mechanisms of protein function, assessing pathogenicity, or estimating binding affinities.

Deep mutational scanning of essential bacterial proteins can guide antibiotic development

Deep mutational scanning is a powerful approach to investigate a wide variety of research questions including protein function and stability. Here, we perform deep mutational scanning on three essential E. coli proteins (FabZ, LpxC and MurA) involved in cell envelope synthesis using high-throughput CRISPR genome editing, and study the effect of the mutations in their original genomic context. We use more than 17,000 variants of the proteins to interrogate protein function and the importance of individual amino acids in supporting viability. Additionally, we exploit these libraries to study resistance development against antimicrobial compounds that target the selected proteins. Among the three proteins studied, MurA seems to be the superior antimicrobial target due to its low mutational flexibility, which decreases the chance of acquiring resistance-conferring mutations that simultaneously preserve MurA function. Additionally, we rank anti-LpxC lead compounds for further development, guided by the number of resistance-conferring mutations against each compound. Our results show that deep mutational scanning studies can be used to guide drug development, which we hope will contribute towards the development of novel antimicrobial therapies.

Predicting protein stability changes upon mutation using a simple orientational potential

MOTIVATION

Structure-based stability prediction upon mutation is crucial for protein engineering and design, and for understanding genetic diseases or drug resistance events. For this task, we adopted a simple residue-based orientational potential that considers only three backbone atoms, previously applied in protein modeling. Its application to stability prediction only requires parametrizing 12 amino acid-dependent weights using cross-validation strategies on a curated dataset in which we tried to reduce the mutations that belong to protein-protein or protein-ligand interfaces, extreme conditions and the alanine over-representation.

RESULTS

Our method, called KORPM, accurately predicts mutational effects on an independent benchmark dataset, whether the wild-type or mutated structure is used as starting point. Compared with state-of-the-art methods on this balanced dataset, our approach obtained the lowest root mean square error (RMSE) and the highest correlation between predicted and experimental ΔΔG measures, as well as better receiver operating characteristics and precision-recall curves. Our method is almost anti-symmetric by construction, and it performs thus similarly for the direct and reverse mutations with the corresponding wild-type and mutated structures. Despite the strong limitations of the available experimental mutation data in terms of size, variability, and heterogeneity, we show competitive results with a simple sum of energy terms, which is more efficient and less prone to overfitting.

AVAILABILITY AND IMPLEMENTATION

https://github.com/chaconlab/korpm.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.