Mingqing Wang

scEvolver enables continual cell-type annotation across expanding single-cell atlases, revealing cellular state transitions in disease contexts.

This paper introduces Tx2Mol, a framework that translates gene-expression signatures into candidate molecules, outperforming baselines in chemical plausibility and phenotypic preservation.

This paper improves variant effect prediction by modifying protein language models with sparse mechanistic features, achieving significant performance gains across multiple datasets.