Automated optimisation of solubility and conformational stability of antibodies and proteins

Prediction of protein biophysical traits from limited data: a case study on nanobody thermostability through NanoMelt

In-silico prediction of protein biophysical traits is often hindered by the limited availability of experimental data and their heterogeneity. Training on limited data can lead to overfitting and poor generalizability to sequences distant from those in the training set. Additionally, inadequate use of scarce and disparate data can introduce biases during evaluation, leading to unreliable model performances being reported. Here, we present a comprehensive study exploring various approaches for protein fitness prediction from limited data, leveraging pre-trained embeddings, repeated stratified nested cross-validation, and ensemble learning to ensure an unbiased assessment of the performances. We applied our framework to introduce NanoMelt, a predictor of nanobody thermostability trained with a dataset of 640 measurements of apparent melting temperature, obtained by integrating data from the literature with 129 new measurements from this study. We find that an ensemble model stacking multiple regression using diverse sequence embeddings achieves state-of-the-art accuracy in predicting nanobody thermostability. We further demonstrate NanoMelt's potential to streamline nanobody development by guiding the selection of highly stable nanobodies. We make the curated dataset of nanobody thermostability freely available and NanoMelt accessible as a downloadable software and webserver.

Enhancing the Protein Stability of an Anticancer VHH-Fc Heavy Chain Antibody through Computational Modeling and Variant Design

VHHs (also known as nanobodies) are important therapeutic antibodies. To prolong their half-life in bloodstream, VHHs are usually fused to the Fc fragment of full-length antibodies. However, stability is often the main challenge for their commercialization, and methods to improve stability are still lacking. Here, an in silico pipeline is developed for analyzing the stability of an anticancer VHH-Fc fusion antibody (VFA01) and designing its stable variants. Computational modeling is used to analyze the VFA01 structure and evaluate its conformational stability, disulfide bond reduction state, and aggregation and degradation tendency. By building mechanistic models of aggregation and degradation, the hotspot residues affecting stability: C130, F57, Y106, L120, and W111 are identified. Based on them, a series of VFA01 variants are designed and obtained a variant M11 (C130S/W111F/F57K) whose stability is significantly enhanced compared to VFA01: there are no visible particles in solution, and the change rate of DLS average hydrodynamic size, SEC HMW%, and CE-SDS purity are improved by 6.2-, 3.4-, and 1.5-fold, respectively. Both antigen-binding activity and production yield are also improved by about 1.5-fold. The results show that our computational pipeline is a very promising approach for improving the protein stability of therapeutic VHH-Fc fusion antibodies.

2D Materials-Based Field-Effect Transistor Biosensors for Healthcare

The need for accurate point-of-care (POC) tools, driven by increasing demands for precise medical diagnostics and monitoring, has accelerated the evolution of biosensor technology. Integrable 2D materials-based field-effect transistor (2D FET) biosensors offer label-free, rapid, and ultrasensitive detection, aligning perfectly with current biosensor trends. Given these advancements, this review focuses on the progress, challenges, and future prospects in the field of 2D FET biosensors. The distinctive physical properties of 2D materials and recent achievements in scalable synthesis are highlighted that significantly improve the manufacturing process and performance of FET biosensors. Additionally, the advancements of 2D FET biosensors are investigated in fatal disease diagnosis and screening, chronic disease management, and environmental hazards monitoring, as well as their integration in flexible electronics. Their promising capabilities shown in laboratory trials accelerate the development of prototype products, while the challenges are acknowledged, related to sensitivity, stability, and scalability that continue to impede the widespread adoption and commercialization of 2D FET biosensors. Finally, current strategies are discussed to overcome these challenges and envision future implications of 2D FET biosensors, such as their potential as smart and sustainable POC biosensors, thereby advancing human healthcare.

Revolutionizing oncology: the role of Artificial Intelligence (AI) as an antibody design, and optimization tools

Antibodies play a crucial role in defending the human body against diseases, including life-threatening conditions like cancer. They mediate immune responses against foreign antigens and, in some cases, self-antigens. Over time, antibody-based technologies have evolved from monoclonal antibodies (mAbs) to chimeric antigen receptor T cells (CAR-T cells), significantly impacting biotechnology, diagnostics, and therapeutics. Although these advancements have enhanced therapeutic interventions, the integration of artificial intelligence (AI) is revolutionizing antibody design and optimization. This review explores recent AI advancements, including large language models (LLMs), diffusion models, and generative AI-based applications, which have transformed antibody discovery by accelerating de novo generation, enhancing immune response precision, and optimizing therapeutic efficacy. Through advanced data analysis, AI enables the prediction and design of antibody sequences, 3D structures, complementarity-determining regions (CDRs), paratopes, epitopes, and antigen-antibody interactions. These AI-powered innovations address longstanding challenges in antibody development, significantly improving speed, specificity, and accuracy in therapeutic design. By integrating computational advancements with biomedical applications, AI is driving next-generation cancer therapies, transforming precision medicine, and enhancing patient outcomes.

Trends and challenges in bispecific antibody production

Bispecific antibodies (bsAbs) represent a rapidly growing field of therapeutic agents. More bsAbs are being approved worldwide and are in various stages of clinical trials. However, the discovery and production of novel bsAbs presents significant challenges due to their complex structure. Thus, precise control of assembly and stability is required, given the many formats developed. This review examines recent trends in bsAb production, focusing on advancements in engineering platforms, production strategies, and challenges in large-scale manufacturing. Key developments include improvements in modular antibody design, novel expression systems, and optimization of bioprocessing techniques to enhance stability, yield, and efficacy. Additionally, the article explores the future potential of bsAbs as next-generation therapeutics, underscoring the growing impact of these innovations on expanding treatment options for patients with unmet medical needs.

Interpretable and explainable predictive machine learning models for data-driven protein engineering

Protein engineering through directed evolution and (semi)rational design has become a powerful approach for optimizing and enhancing proteins with desired properties. The integration of artificial intelligence methods has further accelerated protein engineering process by enabling the development of predictive models based on data-driven strategies. However, the lack of interpretability and transparency in these models limits their trustworthiness and applicability in real-world scenarios. Explainable Artificial Intelligence addresses these challenges by providing insights into the decision-making processes of machine learning models, enhancing their reliability and interpretability. Explainable strategies has been successfully applied in various biotechnology fields, including drug discovery, genomics, and medicine, yet its application in protein engineering remains underexplored. The incorporation of explainable strategies in protein engineering holds significant potential, as it can guide protein design by revealing how predictive models function, benefiting approaches such as machine learning-assisted directed evolution. This perspective work explores the principles and methodologies of explainable artificial intelligence, highlighting its relevance in biotechnology and its potential to enhance protein design. Additionally, three theoretical pipelines integrating predictive models with explainable strategies are proposed, focusing on their advantages, disadvantages, and technical requirements. Finally, the remaining challenges of explainable artificial intelligence in protein engineering and future directions for its development as a support tool for traditional protein engineering methodologies are discussed.

Challenges and compromises: Predicting unbound antibody structures with deep learning

Therapeutic antibodies are manufactured, stored and administered in the free state; this makes understanding the unbound form key to designing and improving development pipelines. Prediction of unbound antibodies is challenging, specifically modelling of the CDRH3 loop, where inaccuracies are potentially worse due to a bias in structural data towards antibody-antigen complexes. This class imbalance provides a challenge for deep learning models trained on this data, potentially limiting generalisation to unbound forms. Here we discuss the importance of unbound structures in antibody development pipelines. We explore how the latest generation of structure predictors can provide new insights and assess how conformational heterogeneity may influence binding kinetics. We hypothesise that generative models may address some of these issues. While prediction of antibodies in complex is essential, we should not ignore the need for progress in modelling the unbound form.

Enhancing the Thermostability and solubility of a single-domain catalytic antibody

Catalytic antibodies have the ability to bind to and degrade antigens, offering a significant potential for therapeutic use. The light chain of an antibody, UA15-L, can cleave the peptide bond of Helicobacter pylori urease, thus inhibiting the spread of the bacteria. However, the variable domain of UA15-L has a poor thermostability and solubility. In this study, we employed a combined computational and experimental approach to enhance the protein's stability and solubility properties. The protein unfolding hotspots were initially identified using molecular dynamics simulations. Following this, a disulfide bond was designed in an unfolding hotspot to stabilize the protein. Subsequently, protein solubility was enhanced with the assistance of computational methods by introducing polar or charged residues on the protein surface. The combination of multiple mutations resulted in UA15-L variable domain variants with improved thermostability, solubility, expression, and enhanced activity at elevated temperatures. These variants represent promising candidates for further engineering of catalytic activity and specificity.

A comprehensive overview of recent advances in generative models for antibodies

Therapeutic antibodies are an important class of biopharmaceuticals. With the rapid development of deep learning methods and the increasing amount of antibody data, antibody generative models have made great progress recently. They aim to solve the antibody space searching problems and are widely incorporated into the antibody development process. Therefore, a comprehensive introduction to the development methods in this field is imperative. Here, we collected 34 representative antibody generative models published recently and all generative models can be divided into three categories: sequence-generating models, structure-generating models, and hybrid models, based on their principles and algorithms. We further studied their performance and contributions to antibody sequence prediction, structure optimization, and affinity enhancement. Our manuscript will provide a comprehensive overview of the status of antibody generative models and also offer guidance for selecting different approaches.

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.

Discovery of alkaline laccases from basidiomycete fungi through machine learning-based approach

BACKGROUND

Laccases can oxidize a broad spectrum of substrates, offering promising applications in various sectors, such as bioremediation, biomass fractionation in future biorefineries, and synthesis of biochemicals and biopolymers. However, laccase discovery and optimization with a desirable pH optimum remains a challenge due to the labor-intensive and time-consuming nature of the traditional laboratory methods.

RESULTS

This study presents a machine learning (ML)-integrated approach for predicting pH optima of basidiomycete fungal laccases, utilizing a small, curated dataset against a vast metagenomic data. Comparative computational analyses unveiled the structural and pH-dependent solubility differences between acidic and neutral-alkaline laccases, helping us understand the molecular bases of enzyme pH optimum. The pH profiling of the two ML-predicted alkaline laccase candidates from the basidiomycete fungus Lepista nuda further validated our computational approach, showing the accuracy of this comprehensive method.

CONCLUSIONS

This study uncovers the efficacy of ML in the prediction of enzyme pH optimum from minimal datasets, marking a significant step towards harnessing computational tools for systematic screening of enzymes for biotechnology applications.

Advancements in the preparation technology of small molecule artificial antigens and their specific antibodies: a comprehensive review

Small molecules find extensive application in medicine, food safety, and environmental studies, particularly in biomedicine. Immunoassay technology, leveraging the specific recognition between antigens and antibodies, offers a superior alternative to traditional physical and chemical analysis methods. This approach allows for the rapid and accurate detection of small molecular compounds, owing to its high sensitivity, specificity, and swift analytical capabilities. However, small molecular compounds often struggle to effectively stimulate an immune response due to their low molecular weight, weak antigenicity, and limited antigenic epitopes. To overcome this, coupling small molecule compounds with macromolecular carriers to form complete antigens is typically required to induce specific antibodies in animals. Consequently, the preparation of small-molecule artificial antigens and the production of efficient specific antibodies are crucial for achieving precise immunoassays. This paper reviews recent advancements in small molecule antibody preparation technology, emphasizing the design and synthesis of haptens, the coupling of haptens with carriers, the purification and identification of artificial antigens, and the preparation of specific antibodies. Additionally, it evaluates the current technological shortcomings and limitations while projecting future trends in artificial antigen synthesis and antibody preparation technology.

Opportunities and challenges in design and optimization of protein function

The field of protein design has made remarkable progress over the past decade. Historically, the low reliability of purely structure-based design methods limited their application, but recent strategies that combine structure-based and sequence-based calculations, as well as machine learning tools, have dramatically improved protein engineering and design. In this Review, we discuss how these methods have enabled the design of increasingly complex structures and therapeutically relevant activities. Additionally, protein optimization methods have improved the stability and activity of complex eukaryotic proteins. Thanks to their increased reliability, computational design methods have been applied to improve therapeutics and enzymes for green chemistry and have generated vaccine antigens, antivirals and drug-delivery nano-vehicles. Moreover, the high success of design methods reflects an increased understanding of basic rules that govern the relationships among protein sequence, structure and function. However, de novo design is still limited mostly to α-helix bundles, restricting its potential to generate sophisticated enzymes and diverse protein and small-molecule binders. Designing complex protein structures is a challenging but necessary next step if we are to realize our objective of generating new-to-nature activities.

AggreProt: a web server for predicting and engineering aggregation prone regions in proteins

Recombinant proteins play pivotal roles in numerous applications including industrial biocatalysts or therapeutics. Despite the recent progress in computational protein structure prediction, protein solubility and reduced aggregation propensity remain challenging attributes to design. Identification of aggregation-prone regions is essential for understanding misfolding diseases or designing efficient protein-based technologies, and as such has a great socio-economic impact. Here, we introduce AggreProt, a user-friendly webserver that automatically exploits an ensemble of deep neural networks to predict aggregation-prone regions (APRs) in protein sequences. Trained on experimentally evaluated hexapeptides, AggreProt compares to or outperforms state-of-the-art algorithms on two independent benchmark datasets. The server provides per-residue aggregation profiles along with information on solvent accessibility and transmembrane propensity within an intuitive interface with interactive sequence and structure viewers for comprehensive analysis. We demonstrate AggreProt efficacy in predicting differential aggregation behaviours in proteins on several use cases, which emphasize its potential for guiding protein engineering strategies towards decreased aggregation propensity and improved solubility. The webserver is freely available and accessible at https://loschmidt.chemi.muni.cz/aggreprot/.

Automated optimization of the solubility of a hyper-stable α-amylase

Most successes in computational protein engineering to date have focused on enhancing one biophysical trait, while multi-trait optimization remains a challenge. Different biophysical properties are often conflicting, as mutations that improve one tend to worsen the others. In this study, we explored the potential of an automated computational design strategy, called CamSol Combination, to optimize solubility and stability of enzymes without affecting their activity. Specifically, we focus on Bacillus licheniformis α-amylase (BLA), a hyper-stable enzyme that finds diverse application in industry and biotechnology. We validate the computational predictions by producing 10 BLA variants, including the wild-type (WT) and three designed models harbouring between 6 and 8 mutations each. Our results show that all three models have substantially improved relative solubility over the WT, unaffected catalytic rate and retained hyper-stability, supporting the algorithm's capacity to optimize enzymes. High stability and solubility embody enzymes with superior resilience to chemical and physical stresses, enhance manufacturability and allow for high-concentration formulations characterized by extended shelf lives. This ability to readily optimize solubility and stability of enzymes will enable the rapid and reliable generation of highly robust and versatile reagents, poised to contribute to advancements in diverse scientific and industrial domains.

Improvement of α-amino Ester Hydrolase Stability via Computational Protein Design

Amino ester hydrolases (AEHs) are capable of rapid synthesis of cephalexin but suffer from rapid deactivation even at low temperatures. Previous efforts to engineer AEH have generated several improved variants but have been limited in scope in part due to limitations in activity assay throughput for β-lactam synthesis reactions. Rational design of 'whole variants' was explored to rapidly improve AEH thermostability by mutating between 3-15% of residues. Most variants were found to be inactive due to a mutated calcium binding site, the function of which has not previously been described. Four active variants, all with improved melting temperatures, were characterized in terms of synthesis and hydrolysis activity, melting temperature, and deactivation at 25°C. Two variants were found to have improved total turnover numbers relative to the initial AEH variant; however, a clear tradeoff exists between improved stability and overall activity of each variant.

Quantitative size-resolved characterization of mRNA nanoparticles by in-line coupling of asymmetrical-flow field-flow fractionation with small angle X-ray scattering

We present a generically applicable approach to determine an extensive set of size-dependent critical quality attributes inside nanoparticulate pharmaceutical products. By coupling asymmetrical-flow field-flow fractionation (AF4) measurements directly in-line with solution small angle X-ray scattering (SAXS), vital information such as (i) quantitative, absolute size distribution profiles, (ii) drug loading, (iii) size-dependent internal structures, and (iv) quantitative information on free drug is obtained. Here the validity of the method was demonstrated by characterizing complex mRNA-based lipid nanoparticle products. The approach is particularly applicable to particles in the size range of 100 nm and below, which is highly relevant for pharmaceutical products-both biologics and nanoparticles. The method can be applied as well in other fields, including structural biology and environmental sciences.

How can we discover developable antibody-based biotherapeutics?

Antibody-based biotherapeutics have emerged as a successful class of pharmaceuticals despite significant challenges and risks to their discovery and development. This review discusses the most frequently encountered hurdles in the research and development (R&D) of antibody-based biotherapeutics and proposes a conceptual framework called biopharmaceutical informatics. Our vision advocates for the syncretic use of computation and experimentation at every stage of biologic drug discovery, considering developability (manufacturability, safety, efficacy, and pharmacology) of potential drug candidates from the earliest stages of the drug discovery phase. The computational advances in recent years allow for more precise formulation of disease concepts, rapid identification, and validation of targets suitable for therapeutic intervention and discovery of potential biotherapeutics that can agonize or antagonize them. Furthermore, computational methods for de novo and epitope-specific antibody design are increasingly being developed, opening novel computationally driven opportunities for biologic drug discovery. Here, we review the opportunities and limitations of emerging computational approaches for optimizing antigens to generate robust immune responses, in silico generation of antibody sequences, discovery of potential antibody binders through virtual screening, assessment of hits, identification of lead drug candidates and their affinity maturation, and optimization for developability. The adoption of biopharmaceutical informatics across all aspects of drug discovery and development cycles should help bring affordable and effective biotherapeutics to patients more quickly.