Mathematical artificial intelligence design of mutation-proof COVID-19 monoclonal antibodies

Recent advances in antibody optimization based on deep learning methods

Antibodies currently comprise the predominant treatment modality for a variety of diseases; therefore, optimizing their properties rapidly and efficiently is an indispensable step in antibody-based drug development. Inspired by the great success of artificial intelligence-based algorithms, especially deep learning-based methods in the field of biology, various computational methods have been introduced into antibody optimization to reduce costs and increase the success rate of lead candidate generation and optimization. Herein, we briefly review recent progress in deep learning-based antibody optimization, focusing on the available datasets and algorithm input data types that are crucial for constructing appropriate deep learning models. Furthermore, we discuss the current challenges and potential solutions for the future development of general-purpose deep learning algorithms in antibody optimization.

Clinical microbiology and artificial intelligence: Different applications, challenges, and future prospects

Conventional clinical microbiological techniques are enhanced by the introduction of artificial intelligence (AI). Comprehensive data processing and analysis enabled the development of curated datasets that has been effectively used in training different AI algorithms. Recently, a number of machine learning (ML) and deep learning (DL) algorithms are developed and evaluated using diverse microbiological datasets. These datasets included spectral analysis (Raman and MALDI-TOF spectroscopy), microscopic images (Gram and acid fast stains), and genomic and protein sequences (whole genome sequencing (WGS) and protein data banks (PDBs)). The primary objective of these algorithms is to minimize the time, effort, and expenses linked to conventional analytical methods. Furthermore, AI algorithms are incorporated with quantitative structure-activity relationship (QSAR) models to predict novel antimicrobial agents that address the continuing surge of antimicrobial resistance. During the COVID-19 pandemic, AI algorithms played a crucial role in vaccine developments and the discovery of new antiviral agents, and introduced potential drug candidates via drug repurposing. However, despite their significant benefits, the implementation of AI encounters various challenges, including ethical considerations, the potential for bias, and errors related to data training. This review seeks to provide an overview of the most recent applications of artificial intelligence in clinical microbiology, with the intention of educating a wider audience of clinical practitioners regarding the current uses of machine learning algorithms and encouraging their implementation. Furthermore, it will discuss the challenges related to the incorporation of AI into clinical microbiology laboratories and examine future opportunities for AI within the realm of infectious disease epidemiology.

Prompt engineering-enabled LLM or MLLM and instigative bioinformatics pave the way to identify and characterize the significant SARS-CoV-2 antibody escape mutations

The research aims to identify and characterize the antibody escape mutations of NTD and RBD regions of SARS-CoV-2 using prompt engineering-enabled combined LLMs (large language models) and instigative bioinformatics techniques. We used two LLMs (ChatGPT and Mistral 7B) and one MLLM (Gemini model) to retrieve the significant NTD and RBD mutations. The retrieved significant mutations were characterized through the in silico servers. The retrieved 15 NTD significant mutations (six deletions and nine-point mutations) and 17 RBD point mutations were noted. We further characterized them in terms of distribution, count, ΔΔG of mutation (ΔΔG stability mCSM, ΔΔGstability DUET, ΔΔGstabilitySDM) to understand the stabilized or destabilized mutation, interaction interface, distance to PPI interface, Δvibrational entropy energy (ΔΔSVib ENCoM), and change in the flexibility. Here, we analyzed every mutation's ΔΔG, interaction, and related parameters using the trimeric Spike protein complex. In NTD mutations, our five analyzed mutations show two destabilising (G142D, R190S) and three showing stabilising properties (D215G, A222V, and R246I). Some RBD mutations are noted as entirely destabilising (K417N, K417T, L452R, F490S). N440K, N460K, and Q493R show stabilising and neutral properties. Combined LLMs and instigative bioinformatics techniques were used to identify and characterize the antibody escape mutations. With our strategy, the LLM and MLLM can help to fight future pandemic viruses by quickly identifying mutations and their significance.

Computational Mutagenesis of Antibody Fragments: Disentangling Side Chains from ΔΔG Predictions

The development of highly potent antibodies and antibody fragments as binding agents holds significant implications in fields such as biosensing and biotherapeutics. Their binding strength is intricately linked to the arrangement and composition of residues at the binding interface. Computational techniques offer a robust means to predict the three-dimensional structure of these complexes and to assess the affinity changes resulting from mutations. Given the interdependence of structure and affinity prediction, our objective here is to disentangle their roles. We aim to evaluate independently six side-chain reconstruction methods and ten binding affinity estimation techniques. This evaluation was pivotal in predicting affinity alterations due to single mutations, a key step in computational affinity maturation protocols. Our analysis focuses on a data set comprising 27 distinct antibody/hen egg white lysozyme complexes, each with crystal structures and experimentally determined binding affinities. Using six different side-chain reconstruction methods, we transformed each structure into its corresponding mutant via in silico single-point mutations. Subsequently, these structures undergo minimization and molecular dynamics simulation. We therefore estimate ΔΔG values based on the original crystal structure, its energy-minimized form, and the ensuing molecular dynamics trajectories. Our research underscores the critical importance of selecting reliable side-chain reconstruction methods and conducting thorough molecular dynamics simulations to accurately predict the impact of mutations. In summary, our study demonstrates that the integration of conformational sampling and scoring is a potent approach to precisely characterizing mutation processes in single-point mutagenesis protocols and crucial for computational antibody design.

A novel mutation-proof, next-generation vaccine to fight against upcoming SARS-CoV-2 variants and subvariants, designed through AI enabled approaches and tools, along with the machine learning based immune simulation: A vaccine breakthrough

Emerging SARS-CoV-2 variants and subvariants are great concerns for their significant mutations, which are also responsible for vaccine escape. Therefore, the study was undertaken to develop a mutation-proof, next-generation vaccine to protect against all upcoming SARS-CoV-2 variants. We used advanced computational and bioinformatics approaches to develop a multi-epitopic vaccine, especially the AI model for mutation selection and machine learning (ML) strategies for immune simulation. AI-enabled and the top-ranked antigenic selection approaches were used to select nine mutations from 835 RBD mutations. We selected twelve common antigenic B cell and T cell epitopes (CTL and HTL) containing the nine RBD mutations and joined them with the adjuvants, PADRE sequence, and suitable linkers. The constructs' binding affinity was confirmed through docking with TLR4/MD2 complex and showed significant binding free energy (-96.67 kcal mol^-1) with positive binding affinity. Similarly, the calculated eigenvalue (2.428517e-05) from the NMA of the complex reveals proper molecular motion and superior residues' flexibility. Immune simulation shows that the candidate can induce a robust immune response. The designed mutation-proof, multi-epitopic vaccine could be a remarkable candidate for upcoming SARS-CoV-2 variants and subvariants. The study method might guide researchers in developing AI-ML and immunoinformatics-based vaccines for infectious disease.