RESUMEN
Managing user bias in large-scale user review data is a significant challenge in optimizing children's book recommendation systems. To tackle this issue, this study introduces a novel hybrid model that combines graph convolutional networks (GCN) based on bipartite graphs and neural matrix factorization (NMF). This model aims to enhance the precision and efficiency of children's book recommendations by accurately capturing user biases. In this model, the complex interactions between users and books are modeled as a bipartite graph, with the users' book ratings serving as the weights of the edges. Through GCN and NMF, we can delve into the structure of the graph and the behavioral patterns of users, more accurately identify and address user biases, and predict their future behaviors. Compared to traditional recommendation systems, our hybrid model excels in handling large-scale user review data. Experimental results confirm that our model has significantly improved in terms of recommendation accuracy and scalability, positively contributing to the advancement of children's book recommendation systems.
RESUMEN
As a minimally invasive drug delivery platform, microneedles (MNs) overcome many drawbacks of the conventional transdermal drug delivery systems, therefore are favorable in biomedical applications. Microneedles with a combined burst and sustained release profile and maintained therapeutic molecular bioactivity could further broaden its applications as therapeutics. Here, we developed a double-network microneedles (DN MNs) based on gelatin methacrylate and acellular neural matrix (GelMA-ACNM). ACNM could function as an early drug release matrix, whereas the addition of GelMA facilitates sustained drug release. In particular, the double-network microneedles comprising GelMA-ACNM hydrogel has distinctive biological features in maintaining drug activity to meet the needs of application in treating different diseases. In this study, we prepared the double-network microneedles and evaluated its morphology, mechanical properties, drug release properties and biocompatibility, which shows great potential for delivery of therapeutic molecules that needs different release profiles in transdermal treatment.
RESUMEN
Glial scars formed after brain injuries provide permissive cues for endogenous neural precursor/stem cells (eNP/SCs) to undergo astrogenesis rather than neurogenesis. Following brain injury, eNP/SCs from the subventricular zone leave their niche, migrate to the injured cortex, and differentiate into reactive astrocytes that contribute to glial scar formation. In vivo neuronal reprogramming, directly converting non-neuronal cells such as reactive astrocytes or NG2 glia into neurons, has greatly improved brain injury repair strategies. However, reprogramming carries a high risk of future clinical applications such as tumorigenicity, involving virus. In this study, we constructed a neural matrix to alter the adverse niche at the injured cortex, enabling eNP/SCs to differentiate into functional neurons. We found that the neural matrix functioned as a "glial trap" that largely concentrated and limited reactive astrocytes to the core of the lesion area, thus altering the adverse niche. The eNP/SCs migrated toward the injured cortex and differentiated into functional neurons. In addition, regenerated neurites extended across the boundary of the injured cortex. Mice treated with the neural matrix demonstrated significant behavioral recovery. For the first time, we induced eNP/SC-derived functional neurons in the cortex after brain injury without the use of viruses, microRNAs, or small molecules. Our novel strategy of applying this "glial trap" to obtain functional neurons in the injured cortex may provide a safer and more natural therapeutic alternative to reprogramming in future clinical applications.
