A5041913431- Biomedical Text Mining and Ontologies
- Computational Drug Discovery Methods
- Recommender Systems and Techniques
- Advanced Graph Neural Networks
- Machine Learning in Healthcare
Xiamen University of Technology
2022-2023
Graph attention network can generate effective feature embedding by specifying different weights to nodes. The key of the research on heterogeneous graph is way combine its rich structural information with semantic relations aggregate neighborhood information. Most existing representation learning methods guide selection neighbors defining various meta-paths graphs. However, these models only consider contained in nodes under paths and ignore potential relationships neighbor structures,...
Drug–drug interaction (DDI) prediction has received considerable attention from industry and academia. Most existing methods predict DDIs drug attributes or relationships with neighbors, which does not guarantee that informative embeddings for will be obtained. To address this limitation, we propose a multitype method based on the deep fusion of features topological relationships, abbreviated DM-DDI. The proposed adopts strategy to combine topologies learn representative DDI prediction....