Role of Polymers in Microfluidic Devices.

Polymers are sustainable and renewable materials that are in high demand due to their excellent properties. Natural and synthetic polymers with high flexibility, good biocompatibility, good degradation rate, and stiffness are widely used for various applications, such as tissue engineering, drug delivery, and microfluidic chip fabrication. Indeed, recent advances in microfluidic technology allow the fabrication of polymeric matrix to construct microfluidic scaffolds for tissue engineering and to set up a well-controlled microenvironment for manipulating fluids and particles. In this review, polymers as materials for the fabrication of microfluidic chips have been highlighted. Successful models exploiting polymers in microfluidic devices to generate uniform particles as drug vehicles or artificial cells have been also discussed. Additionally, using polymers as bioink for 3D printing or as a matrix to functionalize the sensing surface in microfluidic devices has also been mentioned. The rapid progress made in the combination of polymers and microfluidics presents a low-cost, reproducible, and scalable approach for a promising future in the manufacturing of biomimetic scaffolds for tissue engineering.

Microfluidic Synthesis of Indomethacin-Loaded PLGA Microparticles Optimized by Machine Learning.

Several attempts have been made to encapsulate indomethacin (IND), to control its sustained release and reduce its side effects. To develop a successful formulation, drug release from a polymeric matrix and subsequent biodegradation need to be achieved. In this study, we focus on combining microfluidic and artificial intelligence (AI) technologies, alongside using biomaterials, to generate drug-loaded polymeric microparticles (MPs). Our strategy is based on using Poly (D,L-lactide-co-glycolide) (PLGA) as a biodegradable polymer for the generation of a controlled drug delivery vehicle, with IND as an example of a poorly soluble drug, a 3D flow focusing microfluidic chip as a simple device synthesis particle, and machine learning using artificial neural networks (ANNs) as an in silico tool to generate and predict size-tunable PLGA MPs. The influence of different polymer concentrations and the flow rates of dispersed and continuous phases on PLGA droplet size prediction in a microfluidic platform were assessed. Subsequently, the developed ANN model was utilized as a quick guide to generate PLGA MPs at a desired size. After conditions optimization, IND-loaded PLGA MPs were produced, and showed larger droplet sizes than blank MPs. Further, the proposed microfluidic system is capable of producing monodisperse particles with a well-controllable shape and size. IND-loaded-PLGA MPs exhibited acceptable drug loading and encapsulation efficiency (7.79 and 62.35%, respectively) and showed sustained release, reaching approximately 80% within 9 days. Hence, combining modern technologies of machine learning and microfluidics with biomaterials can be applied to many pharmaceutical applications, as a quick, low cost, and reproducible strategy.

Artificial intelligence application for rapid fabrication of size-tunable PLGA microparticles in microfluidics.

In this study, synthetic polymeric particles were effectively fabricated by combining modern technologies of artificial intelligence (AI) and microfluidics. Because size uniformity is a key factor that significantly influences the stability of polymeric particles, therefore, this work aimed to establish a new AI application using machine learning technology for prediction of the size of poly(D,L-lactide-co-glycolide) (PLGA) microparticles produced by diverse microfluidic systems either in the form of single or multiple particles. Experimentally, the most effective factors for tuning droplet/particle sizes are PLGA concentrations and the flow rates of dispersed and aqueous phases in microfluidics. These factors were utilized to develop five different and simple in structure artificial neural network (ANN) models that are capable of predicting PLGA particle sizes produced by different microfluidic systems either individually or jointly merged. The systematic development of ANN models allowed ultimate construction of a single in silico model which consists of data for three different microfluidic systems. This ANN model eventually allowed rapid prediction of particle sizes produced using various microfluidic systems. This AI application offers a new platform for further rapid and economical exploration of polymer particles production in defined sizes for various applications including biomimetic studies, biomedicine, and pharmaceutics.

Digital Pharmaceutical Sciences.

Artificial intelligence (AI) and machine learning, in particular, have gained significant interest in many fields, including pharmaceutical sciences. The enormous growth of data from several sources, the recent advances in various analytical tools, and the continuous developments in machine learning algorithms have resulted in a rapid increase in new machine learning applications in different areas of pharmaceutical sciences. This review summarizes the past, present, and potential future impacts of machine learning technologies on different areas of pharmaceutical sciences, including drug design and discovery, preformulation, and formulation. The machine learning methods commonly used in pharmaceutical sciences are discussed, with a specific emphasis on artificial neural networks due to their capability to model the nonlinear relationships that are commonly encountered in pharmaceutical research. AI and machine learning technologies in common day-to-day pharma needs as well as industrial and regulatory insights are reviewed. Beyond traditional potentials of implementing digital technologies using machine learning in the development of more efficient, fast, and economical solutions in pharmaceutical sciences are also discussed.

Novel machine learning application for prediction of membrane insertion potential of cell-penetrating peptides.

Cell-penetrating peptides (CPPs) are often used as transporter systems to deliver various therapeutic agents into the cell. We developed a novel machine learning application which can quantitatively screen the insertion/interaction potential of various CPPs into three model phospholipid monolayers. An artificial neural network (ANN) was designed, trained, and ultimately tested on an external dataset using Langmuir experimental data for 13 CPPs (hydrophilic and amphiphilic) together with various features related to the insertion/interaction efficiency of CPPs. The trained ANN provided accurate predictions of the maximum change in surface pressure of CPPs when injected below three membrane models at pH 7.4. The accuracy of predictions was high for the dataset which was used to construct the model (r2 = 0.986) as well as for the external "prospective" dataset (r2 = 0.969). In conclusion, this study demonstrates the promising potential of ANNs for screening the insertion potential of CPPs into membrane models for efficient intracellular delivery of therapeutic agents.

Albumin-bound nanodiscs as delivery vehicle candidates: Development and characterization.

Development of synthetic bioarchitectures to improve our understanding of biological systems and produce biosynthetic models with new functions has attracted substantial interest. Synthetic HDL-like phospholipid nanodiscs are a relatively new model of nanoparticles that present a promising carrier for drug delivery and membrane protein investigations. Nanodiscs are soluble nanoscale phospholipid bilayers that are produced based on the self-assembly of phospholipids, membrane scaffold proteins (MSP) and an embedded peptide/protein of interest. To determine the effect of conjugating a protein with a probe, the model protein bovine serum albumin (BSA) with or without FITC conjugation was attached onto 100% 1-palmitoyl-2-oleoyl-sn-glycero-3-phospho-choline (POPC) nanodiscs. The generated discs were analyzed by Fast Protein Liquid Chromatography (FPLC), dynamic light scattering (DLS), and UV-VIS spectroscopy. Empty, BSA- and FITC-BSA-Nanodiscs exhibited different size, charge and elution characteristics as well as different release profiles. Thus, conjugation of proteins to be adsorbed onto nanodiscs surfaces with fluorophores can affect the physical and release properties of nanodiscs, thereby potentially impacting their biophysical, delivery and imaging applications.

Microfluidic Devices for Drug Delivery Systems and Drug Screening.

Microfluidic devices present unique advantages for the development of efficient drug carrier particles, cell-free protein synthesis systems, and rapid techniques for direct drug screening. Compared to bulk methods, by efficiently controlling the geometries of the fabricated chip and the flow rates of multiphase fluids, microfluidic technology enables the generation of highly stable, uniform, monodispersed particles with higher encapsulation efficiency. Since the existing preclinical models are inefficient drug screens for predicting clinical outcomes, microfluidic platforms might offer a more rapid and cost-effective alternative. Compared to 2D cell culture systems and in vivo animal models, microfluidic 3D platforms mimic the in vivo cell systems in a simple, inexpensive manner, which allows high throughput and multiplexed drug screening at the cell, organ, and whole-body levels. In this review, the generation of appropriate drug or gene carriers including different particle types using different configurations of microfluidic devices is highlighted. Additionally, this paper discusses the emergence of fabricated microfluidic cell-free protein synthesis systems for potential use at point of care as well as cell-, organ-, and human-on-a-chip models as smart, sensitive, and reproducible platforms, allowing the investigation of the effects of drugs under conditions imitating the biological system.

Application of machine learning in prediction of hydrotrope-enhanced solubilisation of indomethacin.

Systematic in-vitro studies have been conducted to determine the ability of a range of 10 potential hydrotropes to improve the apparent aqueous solubility of the poorly water soluble drug, indomethacin. Solubilisation of the drug in the presence of the hydrotropes was determined experimentally using high-performance liquid chromatography (HPLC) with ultraviolet (UV) detection. These experimental data, together with various known and computed physicochemical properties of the hydrotropes were thereafter used in silico to train an artificial neural network (ANN) to allow for predictions of indomethacin solubilisation. The trained ANN was found to give highly accurate predictions of indomethacin solubilisation in the presence of hydrotropes and was thus shown to provide a valuable means by which hydrotrope efficacy could be screened computationally. Interrogation of the network connection weights afforded a quantitative assessment of the relative importance of the various hydrotrope physicochemical properties in determining the extent of the enhancement in indomethacin solubilisation. It is concluded that in-silico screening of drug/hydrotrope systems using artificial neural networks offers significant potential to reduce the need for extensive laboratory testing of these systems, and could thus provide an economy in terms of reduced costs and time in drug formulation development.