Xu‐Wen Wang

PEARL is a deep graph learning method for multi-omics integration that outperforms existing methods and identifies functionally important genes in Alzheimer's disease.

This paper develops an optimization-based dietary recommendation approach to improve diet scores using simulated annealing and evaluates it on Diet-Microbiome Association study data.

PHILM, a deep learning framework, predicts phage-host interactions from metagenomic data with higher accuracy than traditional methods, identifying more interactions and capturing microbial succession patterns.

The paper identifies nutritional redundancy in dietary intake and shows its association with lower risks of cardiovascular disease and type 2 diabetes after adjusting for age.

This paper introduces a statistical physics approach using the random-field Ising model to detect disease modules, showing improved efficiency and robustness compared to existing methods.

The paper introduces a deep learning framework to predict microbial community compositions from species assemblages using synthetic and experimental data.

The paper evaluates 24 network-based methods for predicting protein-protein interactions across five interactomes, identifies top-performing methods, and validates their predictions experimentally.

This paper introduces a deep generative model for link prediction that works across different network types and domains, showing superior performance compared to existing methods.