Zhen He

MIRACLE enables efficient continual integration of single-cell multimodal data, updating cell atlases with new data without reintegration, and identifies novel cell types and transfers labels across datasets.

MIDAS integrates and transfers knowledge from single-cell multimodal data by addressing modality alignment and batch effects through a deep probabilistic framework.

MetaLogo generates sequence logos for heterogeneous sequence groups, allowing users to visualize conservation patterns and annotate unknown sequences.