Machine learning guided structure function predictions enable in silico nanoparticle screening for polymeric gene delivery

Precision-Guided Stealth Missiles in Biomedicine: Biological Carrier-Mediated Nanomedicine Hitchhiking Strategy

Nanodrug delivery systems (NDDS) have demonstrated broad application prospects in disease treatment, prevention, and diagnosis due to several advantages, including functionalization capability, high drug-loading capacity, drug stability protection, and the enhanced permeability and retention (EPR) effect. However, their clinical translation still faces multiple challenges, including rapid clearance by the reticuloendothelial system (RES), poor targeting specificity, and insufficient efficiency in crossing biological barriers. To address these limitations, researchers have developed the biological carrier-mediated nanomedicine hitchhiking strategy (BCM-NHS), which leverages circulating cells, proteins, or bacteria as natural "mobile carriers" to enhance drug delivery. This approach enables nanocarriers to inherit the intrinsic biological properties, endowing them with immune evasion, prolonged circulation, dynamic targeting, biocompatibility, biodegradability, and naturally optimized biological interfaces. Here, a systematic overview of the BCM-NHS is provided. First, the review delves into the methods of nanoparticles (NPs) binding and immobilization, encompassing both the surface-attachment-mediated "backpack" strategy and the encapsulation-based "Trojan horse" strategy. Second, the classification of biological carriers, including both cell-based and non-cell-based carriers, is elucidated. Third, the physical properties and release mechanisms of these nanomaterials are thoroughly described. Finally, the latest applications of BCM-NHS in therapeutic and diagnostic contexts across various disease models including tumor, ischemic stroke, and pneumonia are highlighted.

Artificial Intelligence and Computational Biology in Gene Therapy: A Review

One of the trending fields in almost all areas of science and technology is artificial intelligence. Computational biology and artificial intelligence can help gene therapy in many steps including: gene identification, gene editing, vector design, development of new macromolecules and modeling of gene delivery. There are various tools used by computational biology and artificial intelligence in this field, such as genomics, transcriptomic and proteomics data analysis, machine learning algorithms and molecular interaction studies. These tools can introduce new gene targets, novel vectors, optimized experiment conditions, predict the outcomes and suggest the best solutions to avoid undesired immune responses following gene therapy treatment.

Landscape of small nucleic acid therapeutics: moving from the bench to the clinic as next-generation medicines

The ability of small nucleic acids to modulate gene expression via a range of processes has been widely explored. Compared with conventional treatments, small nucleic acid therapeutics have the potential to achieve long-lasting or even curative effects via gene editing. As a result of recent technological advances, efficient small nucleic acid delivery for therapeutic and biomedical applications has been achieved, accelerating their clinical translation. Here, we review the increasing number of small nucleic acid therapeutic classes and the most common chemical modifications and delivery platforms. We also discuss the key advances in the design, development and therapeutic application of each delivery platform. Furthermore, this review presents comprehensive profiles of currently approved small nucleic acid drugs, including 11 antisense oligonucleotides (ASOs), 2 aptamers and 6 siRNA drugs, summarizing their modifications, disease-specific mechanisms of action and delivery strategies. Other candidates whose clinical trial status has been recorded and updated are also discussed. We also consider strategic issues such as important safety considerations, novel vectors and hurdles for translating academic breakthroughs to the clinic. Small nucleic acid therapeutics have produced favorable results in clinical trials and have the potential to address previously "undruggable" targets, suggesting that they could be useful for guiding the development of additional clinical candidates.

Developing mRNA Nanomedicines with Advanced Targeting Functions

The emerging messenger RNA (mRNA) nanomedicines have sprung up for disease treatment. Developing targeted mRNA nanomedicines has become a thrilling research hotspot in recent years, as they can be precisely delivered to specific organs or tissues to enhance efficiency and avoid side effects. Herein, we give a comprehensive review on the latest research progress of mRNA nanomedicines with targeting functions. mRNA and its carriers are first described in detail. Then, mechanisms of passive targeting, endogenous targeting, and active targeting are outlined, with a focus on various biological barriers that mRNA may encounter during in vivo delivery. Next, emphasis is placed on summarizing mRNA-based organ-targeting strategies. Lastly, the advantages and challenges of mRNA nanomedicines in clinical translation are mentioned. This review is expected to inspire researchers in this field and drive further development of mRNA targeting technology.

Machine learning-driven optimization of mRNA-lipid nanoparticle vaccine quality with XGBoost/Bayesian method and ensemble model approaches

To enhance the efficiency of vaccine manufacturing, this study focuses on optimizing the microfluidic conditions and lipid mix ratios of messenger RNA-lipid nanoparticles (mRNA-LNP). Different mRNA-LNP formulations (n = 24) were developed using an I-optimal design, where machine learning tools (XGBoost/Bayesian optimization and self-validated ensemble (SVEM)) were used to optimize the process and predict lipid mix ratio. The investigation included material attributes, their respective ratios, and process attributes. The critical responses like particle size (PS), polydispersity index (PDI), Zeta potential, pKa, heat trend cycle, encapsulation efficiency (EE), recovery ratio, and encapsulated mRNA were evaluated. Overall prediction of SVEM (>97%) was comparably better than that of XGBoost/Bayesian optimization (>94%). Moreover, in actual experimental outcomes, SVEM prediction is close to the actual data as confirmed by the experimental PS (94-96 nm) is close to the predicted one (95-97 nm). The other parameters including PDI and EE were also close to the actual experimental data.

The Dawn of a New Pharmaceutical Epoch: Can AI and Robotics Reshape Drug Formulation?

Over the last four decades, pharmaceutical companies' expenditures on research and development have increased 51-fold. During this same time, clinical success rates for new drugs have remained unchanged at about 10 percent, predominantly due to lack of efficacy and/or safety concerns. This persistent problem underscores the need to innovate across the entire drug development process, particularly in drug formulation, which is often deprioritized and under-resourced.

Machine Learning Elucidates Design Features of Plasmid Deoxyribonucleic Acid Lipid Nanoparticles for Cell Type-Preferential Transfection

To broaden the accessibility of cell and gene therapies, it is essential to develop and optimize nonviral, cell type-preferential gene carriers such as lipid nanoparticles (LNPs). While high-throughput screening (HTS) approaches have proven effective in accelerating LNP discovery, they are often costly, labor-intensive, and do not consistently yield actionable design rules that direct screening efforts toward the most relevant chemical and formulation parameters. In this study, we employed a machine learning (ML) workflow, utilizing well-curated plasmid DNA LNP transfection data sets across six cell types, to extract compositional and chemical insights from HTS studies. Our approach achieved prediction errors averaging between 5 and 10%, depending on the cell type. By applying SHapley Additive exPlanations to our ML models, we uncovered key composition-function relationships that govern cell type-preferential LNP transfection efficiency. Notably, we identified consistent LNP composition parameters that enhance in vitro transfection efficiency across diverse cell types, including a helper lipid molar percentage of charged lipids between 9 and 50% and the inclusion of cationic/zwitterionic helper lipids. Additionally, several parameters were found to modulate cell type-preferentiality, such as the total molar percentage of ionizable and helper lipids, N/P ratio, PEGylated lipid molar percentage of uncharged lipids, and hydrophobicity of the helper lipid. This study leverages HTS of compositionally diverse LNP libraries combined with ML analysis to elucidate the interactions between lipid components in LNP formulations, providing insights that contribute to the design of LNP compositions tailored for cell type-preferential transfection.

Computer-aided nanodrug discovery: recent progress and future prospects

Nanodrugs, which utilise nanomaterials in disease prevention and therapy, have attracted considerable interest since their initial conceptualisation in the 1990s. Substantial efforts have been made to develop nanodrugs for overcoming the limitations of conventional drugs, such as low targeting efficacy, high dosage and toxicity, and potential drug resistance. Despite the significant progress that has been made in nanodrug discovery, the precise design or screening of nanomaterials with desired biomedical functions prior to experimentation remains a significant challenge. This is particularly the case with regard to personalised precision nanodrugs, which require the simultaneous optimisation of the structures, compositions, and surface functionalities of nanodrugs. The development of powerful computer clusters and algorithms has made it possible to overcome this challenge through in silico methods, which provide a comprehensive understanding of the medical functions of nanodrugs in relation to their physicochemical properties. In addition, machine learning techniques have been widely employed in nanodrug research, significantly accelerating the understanding of bio-nano interactions and the development of nanodrugs. This review will present a summary of the computational advances in nanodrug discovery, focusing on the understanding of how the key interfacial interactions, namely, surface adsorption, supramolecular recognition, surface catalysis, and chemical conversion, affect the therapeutic efficacy of nanodrugs. Furthermore, this review will discuss the challenges and opportunities in computer-aided nanodrug discovery, with particular emphasis on the integrated "computation + machine learning + experimentation" strategy that can potentially accelerate the discovery of precision nanodrugs.

Nanoparticle Targeting Strategies for Lipid and Polymer-Based Gene Delivery to Immune Cells In Vivo

Lipid nanoparticles and polymeric nanoparticles are promising biomaterial platforms for robust intracellular DNA and mRNA delivery, highlighted by the widespread use of nanoparticle- (NP) based mRNA vaccines to help end the COVID-19 pandemic. Recent research has sought to adapt this nanotechnology to transfect and engineer immune cells in vivo. The immune system is an especially appealing target due to its involvement in many different diseases, and ex vivo-engineered immune cell therapies like chimeric antigen receptor (CAR) T therapy have already demonstrated remarkable clinical success in certain blood cancers. Although gene delivery can potentially address some of the cost and manufacturing concerns associated with current autologous immune cell therapies, transfecting immune cells in vivo is challenging. Not only is extrahepatic NP delivery to lymphoid organs difficult, but immune cells like T cells have demonstrated particular resistance to transfection. Despite these challenges, the modular nature of NPs allows researchers to examine critical structure-function relationships between a particle's properties and its ability to specifically engineer immune cells in vivo. Herein, several nanomaterial components are outlined, including targeting ligands, nucleic acid cargo, chemical properties, physical properties, and the route of administration to specifically target NPs to immune cells for optimal in vivo transfection.

Beyond Lipids: Exploring Advances in Polymeric Gene Delivery in the Lipid Nanoparticles Era

The recent success of gene therapy during the COVID-19 pandemic has underscored the importance of effective and safe delivery systems. Complementing lipid-based delivery systems, polymers present a promising alternative for gene delivery. Significant advances have been made in the recent past, with multiple clinical trials progressing beyond phase I and several companies actively working on polymeric delivery systems which provides assurance that polymeric carriers can soon achieve clinical translation. The massive advantage of structural tunability and vast chemical space of polymers is being actively leveraged to mitigate shortcomings of traditional polycationic polymers and improve the translatability of delivery systems. Tailored polymeric approaches for diverse nucleic acids and for specific subcellular targets are now being designed to improve therapeutic efficacy. This review describes the recent advances in polymer design for improved gene delivery by polyplexes and covalent polymer-nucleic acid conjugates. The review also offers a brief note on novel computational techniques for improved polymer design. The review concludes with an overview of the current state of polymeric gene therapies in the clinic as well as future directions on their translation to the clinic.

Nucleic acids in modern molecular therapies: A realm of opportunities for strategic drug design

RNA vaccines have made evident to society what was already known by the scientific community: nucleic acids will be the "drugs of the future." By modifying the genome, interfering in transcription or translation, and by introducing new catalysts into the cell or by mimicking antibody effects, nucleic acids can generate therapeutic activities that are not accessible by any other therapeutic agents. There are, however, challenges that need to be solved in the next few years to make nucleic acids usable in a wide range of therapeutic scenarios. This review illustrates how simulation methods can help achieve this goal.

Synergistic Polymer Blending Informs Efficient Terpolymer Design and Machine Learning Discerns Performance Trends for pDNA Delivery

Cationic polymers offer an alternative to viral vectors in nucleic acid delivery. However, the development of polymer vehicles capable of high transfection efficiency and minimal toxicity has remained elusive, and continued exploration of the vast design space is required. Traditional single polymer syntheses with large monomer bases are very time-intensive, limiting the speed at which new formulations are identified. In this work, we present an experimental method for the quick probing of the design space, utilizing a combinatorial set of 90 polymer blends, derived from 6 statistical copolymers, to deliver pDNA. This workflow facilitated rapid screening of polyplex compositions, successfully tailoring polyplex hydrophobicity, particle size, and payload binding affinity. This workflow identified blended polyplexes with high levels of transfection efficiency and cell viability relative to single copolymer controls and commercial JetPEI, indicating synergistic benefits from copolymer blending. Polyplex composition was coupled with biological outputs to guide the synthesis of single terpolymer vehicles, with high-performing polymers P10 and M20, providing superior transfection of HEK293T cells in serum-free and serum-containing media, respectively. Machine learning coupled with SHapley Additive exPlanations (SHAP) was used to identify polymer/polyplex attributes that most impact transfection efficiency, viability, and overall effective efficiency. Subsequent transfections on ARPE-19 and HDFn cells found that P10 and M20 were surpassed in performance by M10, contrasting with results in HEK293T cells. This cell type dependency reinforced the need to evaluate transfection conditions with multiple cell models to potentially identify moieties more beneficial to delivery in certain tissues. Overall, the workflow employed can be used to expedite the exploration of the polymer design space, bypassing extensive synthesis, and to develop improved polymer delivery vehicles more readily for nucleic acid therapies.

Poly(β-aminoester) Physicochemical Properties Govern the Delivery of siRNA from Electrostatically Assembled Coatings

Localized short interfering RNA (siRNA) therapy has the potential to drive high-specificity molecular-level treatment of a variety of disease states. Unfortunately, effective siRNA therapy suffers from several barriers to its intracellular delivery. Thus, drug delivery systems that package and control the release of therapeutic siRNAs are necessary to overcome these obstacles to clinical translation. Layer-by-layer (LbL) electrostatic assembly of thin film coatings containing siRNA and protonatable, hydrolyzable poly(β-aminoester) (PBAE) polymers is one such drug delivery strategy. However, the impact of PBAE physicochemical properties on the transfection efficacy of siRNA released from LbL thin film coatings has not been systematically characterized. In this study, we investigate the siRNA transfection efficacy of four structurally similar PBAEs in vitro. We demonstrate that small changes in structure yield large changes in physicochemical properties, such as hydrophobicity, pKa, and amine chemical structure, driving differences in the interactions between PBAEs and siRNA in polyplexes and in LbL thin film coatings for wound dressings. In our polymer set, Poly3 forms the most stable interactions with siRNA (Keff,w/w = 0.298) to slow release kinetics and enhance transfection of reporter cells in both colloidal and thin film coating approaches. This is due to its unique physiochemical properties: high hydrophobicity (clog P = 7.86), effective pKa closest to endosomal pH (pKa = 6.21), and high cooperativity in buffering (nhill = 7.2). These properties bestow Poly3 with enhanced endosomal buffering and escape properties. Taken together, this work elucidates the connections between small changes in polymer structure, emergent properties, and polyelectrolyte theory to better understand PBAE transfection efficacy.

Strategies for non-viral vectors targeting organs beyond the liver

In recent years, nanoparticles have evolved to a clinical modality to deliver diverse nucleic acids. Rising interest in nanomedicines comes from proven safety and efficacy profiles established by continuous efforts to optimize physicochemical properties and endosomal escape. However, despite their transformative impact on the pharmaceutical industry, the clinical use of non-viral nucleic acid delivery is limited to hepatic diseases and vaccines due to liver accumulation. Overcoming liver tropism of nanoparticles is vital to meet clinical needs in other organs. Understanding the anatomical structure and physiological features of various organs would help to identify potential strategies for fine-tuning nanoparticle characteristics. In this Review, we discuss the source of liver tropism of non-viral vectors, present a brief overview of biological structure, processes and barriers in select organs, highlight approaches available to reach non-liver targets, and discuss techniques to accelerate the discovery of non-hepatic therapies.

Integrating Artificial Intelligence for Drug Discovery in the Context of Revolutionizing Drug Delivery

Drug development is expensive, time-consuming, and has a high failure rate. In recent years, artificial intelligence (AI) has emerged as a transformative tool in drug discovery, offering innovative solutions to complex challenges in the pharmaceutical industry. This manuscript covers the multifaceted role of AI in drug discovery, encompassing AI-assisted drug delivery design, the discovery of new drugs, and the development of novel AI techniques. We explore various AI methodologies, including machine learning and deep learning, and their applications in target identification, virtual screening, and drug design. This paper also discusses the historical development of AI in medicine, emphasizing its profound impact on healthcare. Furthermore, it addresses AI's role in the repositioning of existing drugs and the identification of drug combinations, underscoring its potential in revolutionizing drug delivery systems. The manuscript provides a comprehensive overview of the AI programs and platforms currently used in drug discovery, illustrating the technological advancements and future directions of this field. This study not only presents the current state of AI in drug discovery but also anticipates its future trajectory, highlighting the challenges and opportunities that lie ahead.

Machine Learning Elucidates Design Features of Plasmid DNA Lipid Nanoparticles for Cell Type-Preferential Transfection

For cell and gene therapies to become more broadly accessible, it is critical to develop and optimize non-viral cell type-preferential gene carriers such as lipid nanoparticles (LNPs). Despite the effectiveness of high throughput screening (HTS) approaches in expediting LNP discovery, they are often costly, labor-intensive, and often do not provide actionable LNP design rules that focus screening efforts on the most relevant chemical and formulation parameters. Here we employed a machine learning (ML) workflow using well-curated plasmid DNA LNP transfection datasets across six cell types to maximize chemical insights from HTS studies and has achieved predictions with 5-9% error on average depending on cell type. By applying Shapley additive explanations to our ML models, we unveiled composition-function relationships dictating cell type-preferential LNP transfection efficiency. Notably, we identified consistent LNP composition parameters that enhance in vitro transfection efficiency across diverse cell types, such as ionizable to helper lipid ratios near 1:1 or 10:1 and the incorporation of cationic/zwitterionic helper lipids. In addition, several parameters were found to modulate cell type-preferentiality, including the ionizable and helper lipid total molar percentage, N/P ratio, cholesterol to PEGylated lipid ratio, and the chemical identity of the helper lipid. This study leverages HTS of compositionally diverse LNP libraries and ML analysis to understand the interactions between lipid components in LNP formulations; and offers fundamental insights that contribute to the establishment of unique sets of LNP compositions tailored for cell type-preferential transfection.

Revolutionizing drug formulation development: The increasing impact of machine learning

Over the past few years, the adoption of machine learning (ML) techniques has rapidly expanded across many fields of research including formulation science. At the same time, the use of lipid nanoparticles to enable the successful delivery of mRNA vaccines in the recent COVID-19 pandemic demonstrated the impact of formulation science. Yet, the design of advanced pharmaceutical formulations is non-trivial and primarily relies on costly and time-consuming wet-lab experimentation. In 2021, our group published a review article focused on the use of ML as a means to accelerate drug formulation development. Since then, the field has witnessed significant growth and progress, reflected by an increasing number of studies published in this area. This updated review summarizes the current state of ML directed drug formulation development, introduces advanced ML techniques that have been implemented in formulation design and shares the progress on making self-driving laboratories a reality. Furthermore, this review highlights several future applications of ML yet to be fully exploited to advance drug formulation research and development.

Oral delivery of RNAi for cancer therapy

Cancer is a major health concern worldwide and is still in a continuous surge of seeking for effective treatments. Since the discovery of RNAi and their mechanism of action, it has shown promises in targeted therapy for various diseases including cancer. The ability of RNAi to selectively silence the carcinogenic gene makes them ideal as cancer therapeutics. Oral delivery is the ideal route of administration of drug administration because of its patients' compliance and convenience. However, orally administered RNAi, for instance, siRNA, must cross various extracellular and intracellular biological barriers before it reaches the site of action. It is very challenging and important to keep the siRNA stable until they reach to the targeted site. Harsh pH, thick mucus layer, and nuclease enzyme prevent siRNA to diffuse through the intestinal wall and thereby induce a therapeutic effect. After entering the cell, siRNA is subjected to lysosomal degradation. Over the years, various approaches have been taken into consideration to overcome these challenges for oral RNAi delivery. Therefore, understanding the challenges and recent development is crucial to offer a novel and advanced approach for oral RNAi delivery. Herein, we have summarized the delivery strategies for oral delivery RNAi and recent advancement towards the preclinical stages.

Enhanced ASO-Mediated Gene Silencing with Lipophilic pH-Responsive Micelles

Herein, we examine the ASO-mediated gene silencing efficiency of pH-responsive micelles, by incorporating 2-(diisopropylamino)ethyl methacrylate (DIP) into the micelle core and comparing physical and biological properties with non-pH-responsive micelles. Additionally, the lipophilic effect of the micelle cores was examined in both types of micelles. Varying lipophilicity was achieved by varying alkyl monomer chain lengths─butyl (4), lauryl (12), and stearyl (18) methacrylate. Each of the micelles formed within our family offered the added benefit of well-defined and uniform templates for loading antisense oligonucleotide (ASO) payloads. Overall, the micelles followed previously established trends of outperforming their linear polymer (nonmicelle) analogs and ASO only control. More specifically, the highest performing micelles were the pH-responsive micelles with longer alkyl chains or higher lipophilicity─D-DIP+LMA and D-DIP+SMA (∼90% silencing). These two micelles demonstrated silencing efficiencies similar to Jet-PEI and Lipofectamine 2000 and caused lower toxicity than Lipofectamine 2000. The shortest alkyl chain pH-responsive micelle, D-DIP+BMA (64%), displayed strong gene silencing similar to that about that of its non-pH-responsive micelle, D-BMA (68%), and the pH-responsive micelle without an alkyl chain incorporated, D-DIP (59%). This work illuminates a minimum alkyl chain length dependence to allow gene silencing within our micelle family. However, including only longer alkyl chains into the micelle core without the pH-responsive unit DIP had a hindering effect, thus demonstrating the requirement of the DIP unit when including longer alkyl chain lengths. This work demonstrates the exemplary gene silencing efficiencies of polymeric micelles and uncovers the relationship between pH responsiveness and performance with lipophilic polymer micelles for enhancing ASO-mediated gene silencing.