Achieving eco-innovative smart glass design with the integration of opinion mining, QFD and TRIZ.

Modern consumption patterns lead to massive waste, which poses challenges in storage and highlights the urgent need for more sustainable product development. Customer feedback on products plays a crucial role in product design, yet previous studies overlooked these invaluable insights. In response, this study introduces a novel systematic methodology that integrates the strengths of text mining, Quality Function Deployment (QFD), and the Theory of Inventive Problem Solving (TRIZ). Text mining techniques are utilized to extract customer requirements from online platforms, while QFD is used to translate these requirements into technical specifications. By integrating the contradiction matrix from TRIZ theory with the triptych, technical conflicts are resolved. The design process for next-generation smart glasses is employed as an illustrative case to validate the proposed integrated innovation design approach. Analytical outcomes suggest that the introduced methodology can effectively address sustainable product design challenges and sets the stage for future advancements in smart glasses.

The effect of spent coffee ground (SCG) loading, matrix ratio and biological treatment of SCG on poly(hydroxybutyrate) (PHB)/poly(lactic acid) (PLA) polymer blend.

This study investigates the effects of SCG embedded into biodegradable polymer blends and aimed to formulate and characterise biomass-reinforced biocomposites using spent coffee ground (SCG) as reinforcement in PHB/PLA polymer blend. The effect of SCG filler loading and varying PHB/PLA ratios on the tensile properties and morphological characteristics of the biocomposites were examined. The results indicated that tensile properties reduction could be due to its incompatibility with the PHB/PLA matrixSCG aggregation at 40 wt% content resulted in higher void formation compared to lower content at 10 wt%. A PHB/PLA ratio of 50/50 with SCG loading 20 wt% was chosen for biocomposites with treated SCG. Biological treatment of SCG using Phanerochaete chrysosporium CK01 and Aspergillus niger DWA8 indicated P. chrysosporium CK01 necessitated a higher moisture content for optimum growth and enzyme production, whereas the optimal conditions for enzyme production (50-55 %, w/w) differed from those promoting A. niger DWA8 growth (40 %, w/w). SEM micrographs highlighted uniform distribution and effective wetting of treated SCG, resulting in improvements of tensile strength and modulus of biocomposites, respectively. The study demonstrated the effectiveness of sustainable fungal treatment in enhancing the interfacial adhesion between treated SCG and the PHB/PLA matrix.

Predicting blood-brain barrier permeability of molecules with a large language model and machine learning.

Predicting the blood-brain barrier (BBB) permeability of small-molecule compounds using a novel artificial intelligence platform is necessary for drug discovery. Machine learning and a large language model on artificial intelligence (AI) tools improve the accuracy and shorten the time for new drug development. The primary goal of this research is to develop artificial intelligence (AI) computing models and novel deep learning architectures capable of predicting whether molecules can permeate the human blood-brain barrier (BBB). The in silico (computational) and in vitro (experimental) results were validated by the Natural Products Research Laboratories (NPRL) at China Medical University Hospital (CMUH). The transformer-based MegaMolBART was used as the simplified molecular input line entry system (SMILES) encoder with an XGBoost classifier as an in silico method to check if a molecule could cross through the BBB. We used Morgan or Circular fingerprints to apply the Morgan algorithm to a set of atomic invariants as a baseline encoder also with an XGBoost classifier to compare the results. BBB permeability was assessed in vitro using three-dimensional (3D) human BBB spheroids (human brain microvascular endothelial cells, brain vascular pericytes, and astrocytes). Using multiple BBB databases, the results of the final in silico transformer and XGBoost model achieved an area under the receiver operating characteristic curve of 0.88 on the held-out test dataset. Temozolomide (TMZ) and 21 randomly selected BBB permeable compounds (Pred scores = 1, indicating BBB-permeable) from the NPRL penetrated human BBB spheroid cells. No evidence suggests that ferulic acid or five BBB-impermeable compounds (Pred scores < 1.29423E-05, which designate compounds that pass through the human BBB) can pass through the spheroid cells of the BBB. Our validation of in vitro experiments indicated that the in silico prediction of small-molecule permeation in the BBB model is accurate. Transformer-based models like MegaMolBART, leveraging the SMILES representations of molecules, show great promise for applications in new drug discovery. These models have the potential to accelerate the development of novel targeted treatments for disorders of the central nervous system.