Hongpeng Zhou

NexuST is a hierarchical foundation model for spatial transcriptomics that improves cell-type annotation and spatial prediction by integrating gene-level and cell-level modeling.

This paper surveys foundation models for non-invasive brain decoding, reviewing their applications and challenges in visual, language, and auditory domains.

This paper develops a framework to evaluate fluorescence trace quality for transcription kinetics by identifying thresholds for signal-to-noise ratio and trace length using synthetic data.

BioBatchNet corrects batch effects in imaging mass cytometry data using a dual-encoder framework, outperforming existing methods and showing generalizability to scRNA-seq data.

The paper investigates how transcription burst amplitude modulation mediates dosage compensation in Drosophila embryos by analyzing gene expression dynamics.