Understanding the self-assembly and molecular structure of mRNA lipid nanoparticles at real size: Insights from the ultra-large-scale simulation.

Messenger RNA (mRNA) encapsulated in lipid nanoparticles (LNPs) represents a cutting-edge delivery technology that played a pivotal role during the COVID-19 pandemic and in advancing vaccine development. However, molecular structure of mRNA-LNPs at real size remains poorly understood, with conflicting results from various experimental studies. In this study, we aim to explore the assembly process and structural characteristics of mRNA-LNPs at realistic sizes using coarse-grained molecular dynamic simulations.

Artificial intelligence-driven rational design of ionizable lipids for mRNA delivery.

Lipid nanoparticles (LNPs) have proven effective in mRNA delivery, as evidenced by COVID-19 vaccines. Its key ingredient, ionizable lipids, is traditionally optimized by inefficient and costly experimental screening. This study leverages artificial intelligence (AI) and virtual screening to facilitate the rational design of ionizable lipids by predicting two key properties of LNPs, apparent pKa and mRNA delivery efficiency.

AI-directed formulation strategy design initiates rational drug development.

Rational drug development would be impossible without selecting the appropriate formulation route. However, pharmaceutical scientists often rely on limited personal experiences to perform trial-and-error tests on diverse formulation strategies. Such an inefficient screening manner not only wastes research investments but also threatens the safety of clinical volunteers and patients.

Harnessing the power of machine learning into tissue engineering: current progress and future prospects.

Tissue engineering is a discipline based on cell biology and materials science with the primary goal of rebuilding and regenerating lost and damaged tissues and organs. Tissue engineering has developed rapidly in recent years, while scaffolds, growth factors, and stem cells have been successfully used for the reconstruction of various tissues and organs. However, time-consuming production, high cost, and unpredictable tissue growth still need to be addressed.

FormulationBCS: A Machine Learning Platform Based on Diverse Molecular Representations for Biopharmaceutical Classification System (BCS) Class Prediction.

The Biopharmaceutics Classification System (BCS) has facilitated biowaivers and played a significant role in enhancing drug regulation and development efficiency. However, the productivity of measuring the key discriminative properties of BCS, solubility and permeability, still requires improvement, limiting high-throughput applications of BCS, which is essential for evaluating drug candidate developability and guiding formulation decisions in the early stages of drug development. In recent years, advancements in machine learning (ML) and molecular characterization have revealed the potential of quantitative structure-performance relationships (QSPR) for rapid and accurate BCS classification.

Quantitative Analysis of Physical Stability Mechanisms of Amorphous Solid Dispersions by Molecular Dynamic Simulation.

Amorphous solid dispersions (ASDs) represent a promising strategy for enhancing the solubility of poorly soluble drugs. However, the mechanisms underlying the physical stability of ASDs remain insufficiently understood. This study aims to investigate these mechanisms and propose quantitative thresholds to predict the maximum stable drug loading using molecular dynamics simulations.

Profiling patent compounds in lipid nanoparticle formulations of siRNA.

Lipid nanoparticles (LNPs) have emerged as a prominent delivery system for nucleic acid drugs, attracting significant attention, especially through the successful development of several commercial products. As a key component in LNPs, cationic lipids have long served as a key technical barrier to block competitors by building up a complex patent thicket. However, there have been few studies as yet that have comprehensively analyzed the patented compounds in LNP formulations, despite a large number of technical reviews and original articles.

Quantitative analysis of excipients to the permeability of BCS class III drugs.

BCS III drugs exhibit high solubility and low permeability, and some excipients were reported to increase their permeability. Although some permeability-enhancing excipients were investigated, permeability-enhancing strategy still need to be improved. Firstly, we established a database and analyzed the possible effects of excipients.

Modeling on disposition and cellular transportation of RNA lipid nanoparticles quantum mechanics/physiologically-based pharmacokinetic approaches.

The lipid nanoparticle (LNP) has been so far proven as a strongly effective delivery system for mRNA and siRNA. However, the mechanisms of LNP's distribution, metabolism, and elimination are complicated, while the transportation and pharmacokinetics (PK) of LNP are just sparsely investigated and simply described. This study aimed to build a model for the transportation of RNA-LNP in Hela cells, rats, mice, and humans by physiologically based pharmacokinetic (PBPK) and quantum mechanics (QM) models with integrated multi-source data.

Introducing enzymatic cleavage features and transfer learning realizes accurate peptide half-life prediction across species and organs.

Peptide drugs are becoming star drug agents with high efficiency and selectivity which open up new therapeutic avenues for various diseases. However, the sensitivity to hydrolase and the relatively short half-life have severely hindered their development. In this study, a new generation artificial intelligence-based system for accurate prediction of peptide half-life was proposed, which realized the half-life prediction of both natural and modified peptides and successfully bridged the evaluation possibility between two important species (human, mouse) and two organs (blood, intestine).

Predicting Peptide Permeability Across Diverse Barriers: A Systematic Investigation.

Peptide-based therapeutics hold immense promise for the treatment of various diseases. However, their effectiveness is often hampered by poor cell membrane permeability, hindering targeted intracellular delivery and oral drug development. This study addressed this challenge by introducing a novel graph neural network (GNN) framework and advanced machine learning algorithms to build predictive models for peptide permeability.

Antibody Recognition of Human Epidermal Growth Factor Receptor-2 (HER2) Juxtamembrane Domain Enhances Anti-Tumor Response of Chimeric Antigen Receptor (CAR)-T Cells.

Chimeric antigen receptor (CAR) T cell therapy shows promise in treating malignant tumors. However, the use of human epidermal growth factor receptor-2 (HER2) CAR-T cells carries the risk of severe toxicity, including cytokine release syndrome, due to their "on-target off-tumor" recognition of HER2. Enhancing the quality and functionality of HER2 CARs could greatly improve the therapeutic potential of CAR-T cells.

Organic crystal structure prediction via coupled generative adversarial networks and graph convolutional networks.

Organic crystal structures exert a profound impact on the physicochemical properties and biological effects of organic compounds. Quantum mechanics (QM)-based crystal structure predictions (CSPs) have somewhat alleviated the dilemma that experimental crystal structure investigations struggle to conduct complete polymorphism studies, but the high computing cost poses a challenge to its widespread application. The present study aims to construct DeepCSP, a feasible pure machine learning framework for minute-scale rapid organic CSP.

PBPK/PD Modeling of Nifedipine for Precision Medicine in Pregnant Women: Enhancing Clinical Decision-Making for Optimal Drug Therapy.

Objective: This study aims to develop physiologically based pharmacokinetic and pharmacodynamic (PBPK/PD) predictive models for nifedipine in pregnant women, enhancing precision medicine and reducing adverse reactions for both mothers and infants.

Methods: A PBPK/PD model was constructed using PK-Sim, MoBi, and MATLAB software, integrating literature and pregnancy-specific physiological information. The process involved: (1) establishing and validating a PBPK model for serum clearance after intravenous administration in non-pregnant individuals, (2) establishing and validating a PBPK model for serum clearance after oral administration in non-pregnant individuals, (3) constructing and validating a PBPK model for enzyme clearance after oral administration in non-pregnant individuals, and (4) adjusting the PBPK model structure and enzyme parameters according to pregnant women and validating it in oral administration.

Dynamic immuno-nanomedicines in oncology.

Anti-cancer therapeutics have achieved significant advances due to the emergence of immunotherapies that rely on the identification of tumors by the patients' immune system and subsequent tumor eradication. However, tumor cells often escape immunity, leading to poor responsiveness and easy tolerance to immunotherapy. Thus, the potentiated anti-tumor immunity in patients resistant to immunotherapies remains a challenge.

Progress in oncolytic viruses modified with nanomaterials for intravenous application.

In oncolytic virus (OV) therapy, a critical component of tumor immunotherapy, viruses selectively infect, replicate within, and eventually destroy tumor cells. Simultaneously, this therapy activates immune responses and mobilizes immune cells, thereby eliminating residual or distant cancer cells. However, because of OVs' high immunogenicity and immune clearance during circulation, their clinical applications are currently limited to intratumoral injections, and their use is severely restricted.

Erythrocyte-Leveraged Oncolytic Virotherapy (ELeOVt): Oncolytic Virus Assembly on Erythrocyte Surface to Combat Pulmonary Metastasis and Alleviate Side Effects.

Despite being a new promising tool for cancer therapy, intravenous delivery of oncolytic viruses (OVs) is greatly limited by poor tumor targeting, rapid clearance in the blood, severe organ toxicity, and cytokine release syndrome. Herein, a simple and efficient strategy of erythrocyte-leveraged oncolytic virotherapy (ELeOVt) is reported, which for the first time assembled OVs on the surface of erythrocytes with up to near 100% efficiency and allowed targeted delivery of OVs to the lung after intravenous injection to achieve excellent treatment of pulmonary metastases while greatly improving the biocompatibility of OVs as a drug. Polyethyleneimine (PEI) as a bridge to assemble OVs on erythrocytes also played an important role in promoting the transfection of OVs.

FormulationAI: a novel web-based platform for drug formulation design driven by artificial intelligence.

Today, pharmaceutical industry faces great pressure to employ more efficient and systematic ways in drug discovery and development process. However, conventional formulation studies still strongly rely on personal experiences by trial-and-error experiments, resulting in a labor-consuming, tedious and costly pipeline. Thus, it is highly required to develop intelligent and efficient methods for formulation development to keep pace with the progress of the pharmaceutical industry.

Combining MSC Exosomes and Cerium Oxide Nanocrystals for Enhanced Dry Eye Syndrome Therapy.

Dry eye syndrome (DES) is a prevalent ocular disorder involving diminishe·d tear production and increased tear evaporation, leading to ocular discomfort and potential surface damage. Inflammation and reactive oxygen species (ROS) have been implicated in the pathophysiology of DES. Inflammation is one core cause of the DES vicious cycle.

Predicting liposome formulations by the integrated machine learning and molecular modeling approaches.

Liposome is one of the most widely used carriers for drug delivery because of the great biocompatibility and biodegradability. Due to the complex formulation components and preparation process, formulation screening mostly relies on trial-and-error process with low efficiency. Here liposome formulation prediction models have been built by machine learning (ML) approaches.

Physiologically Based Pharmacokinetic Modeling for Multiple Oral Administration Labetalol in Pregnant Women.

Background: Labetalol has an irreplaceable role in treating Hypertensive disorders of pregnancy (HDP), a common disease during pregnancy with a prevalence of 5.2-8.2%.