Kai Zheng

TopoLa enhances cell representations in single-cell and spatial omics by using topology-encoded latent hyperbolic geometry, improving performance across multiple tasks.

DLDTI predicts drug-target interactions using network representation and neural networks, achieving high AUC performance and validating results with biomedical experiments.

GCNCDA predicts circRNA-disease associations using a graph convolutional network, achieving high accuracy and confirming predictions with literature.

This paper introduces MeSHHeading2vec, a method that represents MeSH headings as vectors using graph embedding algorithms, showing improved performance in node classification and relationship prediction tasks.

This paper introduces GAPDA, a graph attention network method for identifying piRNA-disease associations, achieving high AUC in cross-validation and outperforming existing methods.

The paper introduces iMDA-BN, a computational model for predicting miRNA-disease associations using biological networks and graph embedding, achieving high accuracy on benchmark datasets.