Guangzheng Weng

The paper evaluates the reliability of confidence measures from single-cell models on new data and shows that raw confidence scores are unreliable, requiring recalibration with target-specific labels.

The paper introduces PIC-seq to study cell-cell contact-specific gene expression during mouse embryonic development and identifies novel gene expression signatures dependent on neighboring cell types.

scmTE infers gene regulatory networks from scRNA-seq data by reducing false predictions, identifying known and novel regulatory interactions in biological processes.

VeTra infers cell trajectories using RNA velocity and identifies key regulators by grouping cells based on transition direction.