Can Chen

HANAMI improves drug-gene-disease motif prediction by integrating heterogeneous biomedical data and using graph contrastive learning, achieving up to 6% better performance than existing methods.

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

MuSHIN improves genome-scale metabolic models by predicting missing reactions using a deep hypergraph learning method, enhancing their predictive accuracy and phenotypic predictions.

This study introduces VAE-PRS, a deep learning model that improves polygenic prediction for blood cell traits by capturing interaction effects and outperforming traditional methods in 14 out of 16 traits.

DREAM-GNN improves drug repositioning by integrating heterogeneous biomedical data through a dual-route graph neural network framework, outperforming existing methods in recovering repositioning candidates.

The paper maps multi-way chromatin contacts using long reads and identifies cell type-specific transcription clusters by integrating contacts with chromatin accessibility and gene expression.

The paper introduces CHESHIRE, a deep learning method to predict missing reactions in metabolic networks using topology, outperforming existing methods and improving phenotypic predictions.

The paper investigates allele-specific relationships between gene expression and genome structure in human cells using integrated haplotype-resolved data.

The paper introduces 4DNvestigator, a toolbox for analyzing time series Hi-C and RNA-seq data, with methods to quantify network and tensor entropy and detect significant changes over time.