Yuntao Lu

The paper uses machine learning to predict metabolomic variation across cancer cell lines using 8 omic layers, identifying key predictors and signaling pathways.

The paper introduces TopoMPI, a graph-based framework for predicting metabolite-protein-drug interactions by integrating multiple biological relationships and achieving AUCs between 0.79 and 0.86 across various datasets.

This study introduces a hierarchical network-based approach to analyze functional gene interactions within microbial genomes, identifying key subnetworks and functional motifs across diverse environments.

This paper constructs a comprehensive dataset of triadic high-order protein interactions and demonstrates their value over pairwise interactions in understanding biological networks.

This study identifies gut microbiota and metabolite signatures in gliomas and shows their predictive value for prognosis and tumor growth.