Peng Zhou

DERIVE predicts antigenic change across viruses using disentangled latent representations of evolutionary history, showing strong transferability to diverse viral families.

This study identifies HGS as a host factor critical for coronavirus infection and discovers RTB as a broad-spectrum antiviral by disrupting HGS-M protein interaction.

This paper develops a deep-learning framework to predict real-world prevalent SARS-CoV-2 mutations using in silico virus evolution and protein language models, achieving accurate predictions of future dominant mutations.

The paper identifies over 900 lncRNA-derived fusions in pediatric neuroblastoma using LncFusion, revealing their potential as biomarkers and therapeutic targets.

This study identifies unconventional IFNω-like genes as dominant in bat type I IFN loci and constitutive antiviral responses, revealing pan-bat immune system characteristics.

E2VD predicts virus variation drivers using an evolution-driven framework, outperforming existing methods and identifying critical mutations for viral survival and risk.

The paper examines genetic dependence features of genes and their role in determining pathogenicity and clinical features of genetic diseases.

This study identifies ZFHX3 variants as a cause of childhood partial epilepsy and infantile spasms, with favorable treatment outcomes and insights into the developmental expression pattern of the gene.

This study creates a spatial proteomic atlas of lung tissues from COVID-19 victims, identifying protein dysregulations and markers of pathological changes.