The association of machine learning (ML) tools with the synthesis of nanoparticles has the potential to streamline the development of more efficient and effective nanomedicines. The continuous-flow synthesis of nanoparticles via microfluidics represents an ideal playground for ML tools, where multiple engineering parameters – flow rates and mixing configurations, type and concentrations of the reagents – contribute in a non-trivial fashion to determine the resultant morphological and pharmacological attributes of nanomedicines. Here we present the application of ML models towards the microfluidic-based synthesis of liposomes loaded with a model hydrophobic therapeutic agent, curcumin. After generating over 200 different liposome configurations by systematically modulating flow rates, lipid concentrations, organic:water mixing volume ratios, support-vector machine models and feed-forward artificial neural networks were trained to predict, respectively, the liposome dispersity/stability and size. This work presents an initial step towards the application and cultivation of ML models to instruct the microfluidic formulation of nanoparticles.
Osteoarthritis (OA) is treated with the intra-articular injection of steroids such as dexamethasone (DEX) to provide short-term pain management. However, DEX treatment suffers from rapid joint clearance. Here, 20 × 10 μm, shape-defined poly(d,l-lactide-co-glycolide)acid microPlates (μPLs) are created and intra-articularly deposited for the sustained release of DEX. Under confined conditions, DEX release is projected to persist for several months, with only ∼20% released in the first month. In a highly rigorous murine knee overload injury model (post-traumatic osteoarthritis), a single intra-articular injection of Cy5-μPLs is detected in the cartilage surface, infrapatellar fat pad/synovium, joint capsule, and posterior joint space up to 30 days. One intra-articular injection of DEX-μPL (1 mg kg–1) decreased the expression of interleukin (IL)-1β, tumor necrosis factor (TNF)-α, IL-6, and matrix metalloproteinase (MMP)-13 by approximately half compared to free DEX at 4 weeks post-treatment. DEX-μPL also reduced load-induced histological changes in the articular cartilage and synovial tissues relative to saline or free DEX. In sum, the μPLs provide sustained drug release along with the capability to precisely control particle geometry and mechanical properties, yielding long-lasting benefits in overload-induced OA. This work motivates further study and development of particles that provide combined pharmacological and mechanical benefits.
28 July 2020 in ACS Applied Materials & Interfaces
Theranostics, literally derived from the combination of the words diagnostics and therapy, is an emerging field of clinical and preclinical research, where contrast agents, drugs and diagnostic techniques are combined to simultaneously diagnose and treat pathologies. Nanoparticles are extensively employed in theranostics due to their potential to target specific organs and their multifunctional capacity. In this review, we will discuss the current state of theranostic nanomedicine, providing key examples of its application in the imaging and treatment of cardiovascular inflammation.