Feng BAO 鲍峰
Principal Investigator · College for Future Information Technology, Fudan University, Shanghai
My research develops statistical learning and AI methods to answer fundamental biological questions and advance medicine — spanning self-supervised representation learning, multi-modal information fusion, causal inference in complex biological systems, and deep generative models for spatial omics.
Previously: Postdoc (2019–2024) at Altschuler and Wu Lab, UCSF, and visiting scholar at Dana-Farber Cancer Institute, Harvard Medical School (2018–2019). PhD from Tsinghua University (2019).
Research Interests
- Self-supervised representation learning for biological data
- Multi-modal information fusion (transcriptomics, proteomics, spatial data, imaging)
- Causal inference in gene regulatory networks and drug perturbation experiments
- Quantify interactions across multiple omics types
- Improve throughput of spatially resolved transcriptomics statistically
- Causal drug target discovery and transferable prediction of small-molecule function
Selected Publications
Molecular and cellular cartography of the laboratory mouse using whole-body sections.
doi:10.1016/j.cell.2026.03.006 →Transitive prediction of small molecule function through alignment of high-content screening resources.
doi:10.1038/s41587-025-02729-2 →Tissue characterization at an enhanced resolution across spatial omics platforms with deep generative model.
Nature Commun. 15, 6541 (2024) →Integrative spatial analysis of cell morphologies and transcriptional states with MUSE.
Nature Biotechnol. 40, 1200–1209 (2022) →Scalable analysis of cell type composition from single-cell transcriptomics using deep recurrent learning.
Nature Methods 16, 311–314 (2019) →Career Path
Awards & Honors
Academic Service
Reviewer for:
Last update: April 2026