Dongsheng Li

This paper trains neural networks on biophysical simulations to infer single-neuron activity and cell-type properties across species and brain regions without using real data.

scIsoAgent improves long-read single-cell RNA-seq analysis by creating reproducible, isoform-resolved workflows and linking sequence data to functional hypotheses.

CausCell improves explainability and controllability of single-cell data through causal disentanglement learning and counterfactual generation.