Search

Interpretability has drawn increasing attention in machine learning. Most works focus on post-hoc explanations rather than building a self-explaining model. So, we propose a Neural Partially Linear Additive Model (NPLAM), which automatically distinguishes insignificant, linear, and nonlinear features in neural networks. On the one hand, neural network construction fits data better than spline function under the same parameter amount; on the other hand, learnable gate design and sparsity regular-term maintain the ability of feature selection and structure discovery. We theoretically establish the generalization error bounds of the proposed method with Rademacher complexity. Experiments based on both simulations and real-world datasets verify its good performance and interpretability.

Arsenic trioxide (ATO or As2O3) has beneficial effects on suppressing neointimal hyperplasia and restenosis, but the mechanism is still unclear. The goal of this study is to further understand the mechanism of ATO's inhibitory effect on vascular smooth muscle cells (VSMCs).

Breast cancer is one of the leading causes of death worldwide. Early diagnosis and treatment of breast cancer are very effective in reducing mortality. Due to the need for small sample size, rapid analysis and high sensitivity, biosensors have emerged as promising tools for clinical breast cancer marker detection. MOFs are promising choice of sensing material with large surface area, tunable pore size, high adsorption capacity, and synergistic catalysis. The combination of MOFs and various nanomaterials effectively enhances sensing performance, providing new insights into the detection of breast cancer biomarkers. This paper reviews the biomarkers related to breast cancer and the different strategies for constructing biosensors based on MOF composites. It also points out the challenges and application prospects of MOF composites. Considering all these factors, the results of this study will be helpful in designing MOF-based sensors with excellent performance for breast cancer detection.