There are many active research projects accessing and applying shared ADNI data. Use the search above to find specific research focuses on the active ADNI investigations. This information is requested annually as a requirement for data access.
| Principal Investigator | |
| Principal Investigator's Name: | xiangrong sun |
| Institution: | 桂林医学院 |
| Department: | 生物技术学院 |
| Country: | |
| Proposed Analysis: | Discovery Network of Potential Pathogenic Genes of Alzheimer's Disease Based on PASNet The model uses some preprocessing steps to reduce the noise and redundant information of gene expression data. Then, it uses a multi-layer neural network to model the expression data, and uses a regularization method to ensure the sparsity and interpretability of the model. At the same time, PASNet also applied the feature selection technology focused by the pathway to the feature selection step to ensure the selection of the most relevant genes. The pathway embedding layer is based on the feature selection of biological pathways. It uses the structural information of biological pathways (including metabolic pathways, signal pathways, etc.) to screen the most relevant gene features from high-dimensional gene expression data. In the feature selection technology focused on by pathway, the process of feature selection is no longer the selection between individual genes, but is based on the relationship between genes and the knowledge of biological pathway. |
| Additional Investigators |
