Hai-Cheng Yi

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.

The paper introduces Biomarker2vec, a method that predicts multi-type relationships between biomarkers using a heterogeneous network and vector representation, achieving high performance on 18 relationships.

The paper constructs a large-scale molecular associations network integrating multiple biomolecules and predicts interactions with high accuracy.