A data-driven predictive approach for drug delivery using machine learning techniques

Blood-brain barrier disruption in dementia: Nano-solutions as new treatment options

Candidate drugs targeting the central nervous system (CNS) demonstrate extremely low clinical success rates, with more than 98% of potential treatments being discontinued due to poor blood-brain barrier (BBB) permeability. Neurological conditions were shown to be the second leading cause of death globally in 2016, with the number of people currently affected by neurological disorders increasing rapidly. This increasing trend, along with an inability to develop BBB permeating drugs, is presenting a major hurdle in the treatment of CNS-related disorders, like dementia. To overcome this, it is necessary to understand the structure and function of the BBB, including the transport of molecules across its interface in both healthy and pathological conditions. The use of CNS drug carriers is rapidly gaining popularity in CNS research due to their ability to target BBB transport systems. Further research and development of drug delivery vehicles could provide essential information that can be used to develop novel treatments for neurological conditions. This review discusses the BBB and its transport systems and evaluates the potential of using nanoparticle-based delivery systems as drug carriers for CNS disease with a focus on dementia.

Inhibition Ability of Natural Compounds on Receptor-Binding Domain of SARS-CoV2: An In Silico Approach

The lack of medication to treat COVID-19 is still an obstacle that needs to be addressed by all possible scientific approaches. It is essential to design newer drugs with varied approaches. A receptor-binding domain (RBD) is a key part of SARS-CoV-2 virus, located on its surface, that allows it to dock to ACE2 receptors present on human cells, which is followed by admission of virus into cells, and thus infection is triggered. Specific receptor-binding domains on the spike protein play a pivotal role in binding to the receptor. In this regard, the in silico method plays an important role, as it is more rapid and cost effective than the trial and error methods using experimental studies. A combination of virtual screening, molecular docking, molecular simulations and machine learning techniques are applied on a library of natural compounds to identify ligands that show significant binding affinity at the hydrophobic pocket of the RBD. A list of ligands with high binding affinity was obtained using molecular docking and molecular dynamics (MD) simulations for protein–ligand complexes. Machine learning (ML) classification schemes have been applied to obtain features of ligands and important descriptors, which help in identification of better binding ligands. A plethora of descriptors were used for training the self-organizing map algorithm. The model brings out descriptors important for protein–ligand interactions.

Artificial intelligence and machine learning assisted drug delivery for effective treatment of infectious diseases

In the era of antimicrobial resistance, the prevalence of multidrug-resistant microorganisms that resist conventional antibiotic treatment has steadily increased. Thus, it is now unquestionable that infectious diseases are significant global burdens that urgently require innovative treatment strategies. Emerging studies have demonstrated that artificial intelligence (AI) can transform drug delivery to promote effective treatment of infectious diseases. In this review, we propose to evaluate the significance, essential principles, and popular tools of AI in drug delivery for infectious disease treatment. Specifically, we will focus on the achievements and key findings of current research, as well as the applications of AI on drug delivery throughout the whole antimicrobial treatment process, with an emphasis on drug development, treatment regimen optimization, drug delivery system and administration route design, and drug delivery outcome prediction. To that end, the challenges of AI in drug delivery for infectious disease treatments and their current solutions and future perspective will be presented and discussed.

Spectrum of deep learning algorithms in drug discovery

Deep learning (DL) algorithms are a subset of machine learning algorithms with the aim of modeling complex mapping between a set of elements and their classes. In parallel to the advance in revealing the molecular bases of diseases, a notable innovation has been undertaken to apply DL in data/libraries management, reaction optimizations, differentiating uncertainties, molecule constructions, creating metrics from qualitative results, and prediction of structures or interactions. From source identification to lead discovery and medicinal chemistry of the drug candidate, drug delivery, and modification, the challenges can be subjected to artificial intelligence algorithms to aid in the generation and interpretation of data. Discovery and design approach, both demand automation, large data management and data fusion by the advance in high-throughput mode. The application of DL can accelerate the exploration of drug mechanisms, finding novel indications for existing drugs (drug repositioning), drug development, and preclinical and clinical studies. The impact of DL in the workflow of drug discovery, design, and their complementary tools are highlighted in this review. Additionally, the type of DL algorithms used for this purpose, and their pros and cons along with the dominant directions of future research are presented.

PharmSD: A novel AI-based computational platform for solid dispersion formulation design

Solid dispersion is an effective way to improve the dissolution and oral bioavailability of water-insoluble drugs. To obtain an effective solid dispersion formulation, researchers need to evaluate a series of important properties of the designed formulation, including in vitro dissolution and physical stability of solid dispersion. It is usually time-consuming and labor-intensive to explore these properties by traditional experimental methods. However, the development of machine learning technology provides a powerful way to solve such problems. By using advanced machine learning algorithms, we established a series of robust models and finally formed a systematic strategy to assist the formulation design. Based on these works, we developed a new formulation prediction platform of solid dispersion: PharmSD. This platform provides efficient functionalities for the prediction of physical stability, dissolution type and dissolution rate of solid dispersion independently. Then, a virtual screening pipeline can be produced by considering those prediction results as a whole, which enables users to filter different kinds of drug-polymer combinations in various experimental situations and figure out which combination could form the best formulation. Moreover, it also provides two tools that enable researchers to evaluate the application domain of models and calculate the similarity of dissolution curves. PharmSD is expected to be the first freely available web-based platform that is fully designed for the formulation design of solid dispersion driven by machine learning. We hope this platform could provide a powerful solution to assist the formulation design in the related research area. It is available at: http://pharmsd.computpharm.org.

Nanoplatforms for Targeted Stimuli-Responsive Drug Delivery: A Review of Platform Materials and Stimuli-Responsive Release and Targeting Mechanisms

To achieve the promise of stimuli-responsive drug delivery systems for the treatment of cancer, they should (1) avoid premature clearance; (2) accumulate in tumors and undergo endocytosis by cancer cells; and (3) exhibit appropriate stimuli-responsive release of the payload. It is challenging to address all of these requirements simultaneously. However, the numerous proof-of-concept studies addressing one or more of these requirements reported every year have dramatically expanded the toolbox available for the design of drug delivery systems. This review highlights recent advances in the targeting and stimuli-responsiveness of drug delivery systems. It begins with a discussion of nanocarrier types and an overview of the factors influencing nanocarrier biodistribution. On-demand release strategies and their application to each type of nanocarrier are reviewed, including both endogenous and exogenous stimuli. Recent developments in stimuli-responsive targeting strategies are also discussed. The remaining challenges and prospective solutions in the field are discussed throughout the review, which is intended to assist researchers in overcoming interdisciplinary knowledge barriers and increase the speed of development. This review presents a nanocarrier-based drug delivery systems toolbox that enables the application of techniques across platforms and inspires researchers with interdisciplinary information to boost the development of multifunctional therapeutic nanoplatforms for cancer therapy.

A Novel Computational Approach for the Discovery of Drug Delivery System Candidates for COVID-19

In order to treat Coronavirus Disease 2019 (COVID-19), we predicted and implemented a drug delivery system (DDS) that can provide stable drug delivery through a computational approach including a clustering algorithm and the Schrödinger software. Six carrier candidates were derived by the proposed method that could find molecules meeting the predefined conditions using the molecular structure and its functional group positional information. Then, just one compound named glycyrrhizin was selected as a candidate for drug delivery through the Schrödinger software. Using glycyrrhizin, nafamostat mesilate (NM), which is known for its efficacy, was converted into micelle nanoparticles (NPs) to improve drug stability and to effectively treat COVID-19. The spherical particle morphology was confirmed by transmission electron microscopy (TEM), and the particle size and stability of 300-400 nm were evaluated by measuring DLSand the zeta potential. The loading of NM was confirmed to be more than 90% efficient using the UV spectrum.

A data-driven acute inflammation therapy

Acute inflammation is a severe medical condition defined as an inflammatory response of the body to an infection. Its rapid progression requires quick and accurate decisions from clinicians. Inadequate and delayed decisions makes acute inflammation the 10th leading cause of death overall in United States with the estimated cost of treatment about $17 billion annually. However, despite the need, there are limited number of methods that could assist clinicians to determine optimal therapies for acute inflammation. We developed a data-driven method for suggesting optimal therapy by using machine learning model that is learned on historical patients' behaviors. To reduce both the risk of failure and the expense for clinical trials, our method is evaluated on a virtual patients generated by a mathematical model that emulates inflammatory response. In conducted experiments, acute inflammation was handled with two complimentary pro- and anti-inflammatory medications which adequate timing and doses are crucial for the successful outcome. Our experiments show that the dosage regimen assigned with our data-driven method significantly improves the percentage of healthy patients when compared to results by other methods used in clinical practice and found in literature. Our method saved 88% of patients that would otherwise die within a week, while the best method found in literature saved only 73% of patients. At the same time, our method used lower doses of medications than alternatives. In addition, our method achieved better results than alternatives when only incomplete or noisy measurements were available over time as well as it was less affected by therapy delay. The presented results provide strong evidence that models from the artificial intelligence community have a potential for development of personalized treatment strategies for acute inflammation.