Research focus

Reconstruct and predict cellular trajectories and state transitions.

Identify robust biomarkers and build predictive models for patient outcomes.

Integrate heterogeneous omics data with biological interpretability and clinical relevance.

Research Directions

Algorithm innovation × biomedical translation

We reconstruct lineage trajectories and disease-associated microenvironments from high-dimensional single-cell and spatial datasets.

single-cell spatial trajectory

We develop robust machine learning models for diagnosis, prognosis, and treatment-response prediction with clinical interpretability.

AI clinical prediction

We connect transcriptome, epigenome, and proteome with interpretable computational frameworks to uncover disease mechanisms.

network multi-omics mechanism

Data-rich, method-driven, clinically oriented

Single-cell + Spatial

Core data modalities

AI + Statistics

Methodological engine

Bench to Bedside

Translational focus

Our CAPTAIN paper has been published in Nature Communications, congrats to Tingting and Jiawen.

We are delighted to share that our recent work has been published in npj Digital Medicine, BMC Medicine, and BIBM.

Lab BBQ!