Search

This paper presents a multi-algorithm fusion model (StackingGroup) based on the Stacking ensemble learning framework to address the variable selection problem in high-dimensional group structure data. The proposed algorithm takes into account the differences in data observation and training principles of different algorithms. It leverages the strengths of each model and incorporates Stacking ensemble learning with multiple group structure regularization methods. The main approach involves dividing the data set into K parts on average, using more than 10 algorithms as basic learning models, and selecting the base learner based on low correlation, strong prediction ability, and small model error. Finally, we selected the grSubset + grLasso, grLasso, and grSCAD algorithms as the base learners for the Stacking algorithm. The Lasso algorithm was used as the meta-learner to create a comprehensive algorithm called StackingGroup. This algorithm is designed to handle high-dimensional group structure data. Simulation experiments showed that the proposed method outperformed other R2, RMSE, and MAE prediction methods. Lastly, we applied the proposed algorithm to investigate the risk factors of low birth weight in infants and young children. The final results demonstrate that the proposed method achieves a mean absolute error (MAE) of 0.508 and a root mean square error (RMSE) of 0.668. The obtained values are smaller compared to those obtained from a single model, indicating that the proposed method surpasses other algorithms in terms of prediction accuracy. [ABSTRACT FROM AUTHOR]

In recent years, the exceptional biocatalytic properties of glucose oxidase (GOx) have spurred the development of various GOx-functionalized nanocatalysts for cancer diagnosis and treatment. Carbon dots, renowned for their excellent biocompatibility and distinctive fluorescence properties, effectively incorporate GOx. Given the paramount importance of GOx's enzymatic activity in therapeutic efficacy, this study conducts a thorough exploration of the molecular-level binding dynamics between GOx and near-infrared carbon dots (NIR-CDs). Utilizing various spectrometric and molecular simulation techniques, we reveal that NIR-CDs form a ground-state complex with GOx primarily via hydrogen bonds and van der Waals forces, interacting directly with amino acid residues in GOx's active site. This binding leads to conformational change and reduces thermal stability of GOx, slightly inhibiting its enzymatic activity and demonstrating a competitive inhibition effect. In vitro experiments demonstrate that NIR-CDs attenuate the GOx's capacity to produce H 2 O 2 in HeLa cells, mitigating enzyme-induced cytotoxicity and cellular damage. This comprehensive elucidation of the intricate binding mechanisms between NIR-CDs and GOx provides critical insights for the design of NIR-CD-based nanotherapeutic platforms to augment cancer therapy. Such advancements lay the groundwork for innovative and efficacious cancer treatment strategies. • This study delves into the molecular binding mechanism between GOx and NIR-CDs. • NIR-CDs form a ground-state complex with GOx under hydrogen bonds and van der Waals forces. • NIR-CDs induces a conformational change in GOx and further reduces its thermal stability. • NIR-CDs slightly inhibit the catalytic activity of GOx via competitive inhibition mode. • NIR-CDs suppress H 2 O 2 production catalyzed by GOx, regulating cells from enzyme-induced damage. [ABSTRACT FROM AUTHOR]