Zunpeng Liu

This study uses sequence-to-function deep learning to identify lineage-specific cis-regulatory elements in human evolution, finding they are shorter, less conserved, and enriched in neurodevelopmental pathways.

This paper introduces Phenoverse, a deep learning framework that learns disease state representations from single-cell transcriptomic data, enabling disease prediction and severity assessment using binary labels.

The paper identifies circadian misalignment between cancer and immune cells in breast tumors as a mechanism of immune evasion and therapeutic resistance.

Hydra is a deep generative framework for single-cell omics data that improves cell type annotation and feature selection, particularly for rare populations.

scMoE introduces a framework for multi-modal, multi-task single-cell learning that addresses optimization conflicts and interpretability challenges through Sparse Mixture-of-Experts and activation vectors.