Fan Zhong

AttentioFuse is an interpretable deep learning framework for multi-omics integration in lung cancer that matches state-of-the-art performance and uncovers biological insights.

The paper identifies long Polycomb loops as a biomarker for sensitivity to Polycomb inhibition in certain cancers, particularly in AMLs with specific mutations.

This study uses gene set embeddings to uncover biological function associations across species by integrating node2vec with MSigDB data.

This paper fine-tunes pre-trained genomic models on genotype-phenotype datasets to improve DNA sequence classification, achieving high accuracy on the HERV dataset.