Bo Li 李波 — AI for Biology: measuring, modeling, and designing cellular perturbations
I develop computational methods for measuring, modeling, and controlling cellular responses, focusing on what experiments can reliably resolve, how multimodal virtual-cell models generalize across perturbations and contexts, and how models can prioritize interventions that move cells toward desired states.
🔥 News
🔬 Research
What biological distinctions can experiments reliably resolve?
Study measurement resolution, reproducibility, and whether experimental readouts contain enough information to support the distinctions and evaluations asked of downstream models.
How do cellular responses generalize across modalities and contexts?
Develop and benchmark representations that connect perturbations with transcriptomic, morphological, molecular, and spatial measurements across biological contexts.
Which interventions are worth testing for a desired cellular transition?
Rank a feasible candidate set under a finite experimental budget and evaluate the selected top-B prefix using independently measured held-out outcomes.
📝 Selected Publications
VCDesign: Finite-Budget Intervention Design for Virtual Cells
Bo Li, Lin Wang, Bob Zhang, Mengran Li, Zhenchao Tang, Chengyang Zhang, Minghao Sun, Chengliang Liu, Zhiyuan Liu, Yang Zhang
Manuscript 2026 · Project · Manuscript · Code · Data
TL;DR: Defines virtual-cell intervention design as finite-budget ranking over variable candidate sets and evaluates the executable top-B prefix using independently measured held-out outcomes. VCDesign-CED augments direct candidate scoring with effects inferred from historical perturbation measurements and biological knowledge when a candidate’s own response is absent from the CED effect atlas.
Measurement resolution constrains fine-grained perturbation prediction
Bo Li, Chengyang Zhang, Mengran Li, Bob Zhang, Lin Wang, Zhenchao Tang, Jun Liu, Chengliang Liu, Chen Wei, Yuhao Yi, Jiancheng Lv, Yang Zhang
Manuscript 2026 · Project · Manuscript · Code · Data
TL;DR: Separates what biological distinctions experiments can reproducibly resolve from what perturbation-prediction models can learn.
MVCBench: A Multimodal Benchmark for Drug-induced Virtual Cell Phenotypes
Bo Li, Qing Wang, Shihang Wang, Bob Zhang, Yuzhong Peng, Pinxian Zeng, Chengliang Liu, Mengran Li, Ziyang Tang, Xiaojun Yao, Chuxia Deng, Qianqian Song
bioRxiv 2026 · Project · Preprint · Code · Data
TL;DR: Benchmarks molecular and gene representations for multimodal prediction of drug-induced cellular phenotypes at scale.
PhenoProfiler: Advancing Phenotypic Learning for Image-based Drug Discovery
Bo Li, Bob Zhang, Chengyang Zhang, Minghao Zhou, Weiliang Huang, Shihang Wang, Qing Wang, Mengran Li, Yong Zhang, Qianqian Song
Nature Communications 17, 793 (2026) · Paper · Webserver · Code · arXiv
TL;DR: Learns cellular representations directly from high-content microscopy for image-based phenotypic drug discovery.
SpaIM: Single-cell Spatial Transcriptomics Imputation via Style Transfer
Bo Li, Ziyang Tang, Aishwarya Budhkar, Xiang Liu, Tonglin Zhang, Baijian Yang, Jing Su, Qianqian Song
Nature Communications 16, 7861 (2025) · Paper · Code · Data
TL;DR: Connects single-cell and spatial transcriptomics through a style-transfer formulation for cross-modal gene-expression inference.
🛠 Software & Resources
Selected research software and community resources.
| Project | What it is | Stars |
|---|---|---|
| VCDesign | Finite-budget intervention design with outcome-based evaluation and CED effect inference from historical perturbation data and biological knowledge |  |
| PertResolve | Measurement-resolution framework and benchmark for perturbation prediction |  |
| MVCBench | Multimodal benchmark for drug-induced virtual cell phenotypes |  |
| Nature-Paper-Skills | Agent skills for drafting, revising, auditing, and resubmitting scientific manuscripts |  |
| Awesome-Virtual-Cell | Curated papers, datasets, benchmarks, and resources for AI virtual cells |  |
| PhenoProfiler | End-to-end phenotypic profiling for image-based drug discovery |  |
| SpaIM | Cross-modal imputation for spatial transcriptomics |  |
📖 Education
-
2026.06 – 2027.06: National University of Singapore
- Visiting Student. Host: Prof. Yang Zhang
-
2024.08 – Present: University of Macau
- Ph.D. in Computer Science, Department of Artificial Intelligence, Full Scholarship. Advisor: Prof. Bob Zhang; Co-advisor: Prof. Qianqian Song, Purdue University
-
2021.09 – 2024.07: Beijing University of Technology
- M.Eng. in Electronic Information. Advisors: Prof. Yong Zhang, Prof. Baocai Yin
-
2017.09 – 2021.07: Beijing Information Science & Technology University
- B.Eng. in Robotics Engineering. Advisor: Prof. Hongbo Huang
🎖 Selected Honors & Awards
- 2024: Ph.D. Scholarship, University of Macau
- 2024.07: Top 100 Graduates of BJUT (Top 100 / 6331)
- 2024.07 & 2021.07: Beijing Outstanding Graduate
- 2023.10: Xiaomi Scholarship
- 2022.10: National Scholarship
- 2021: First Prize, Science & Technology Innovation Scholarship, BISTU
📜 Patents
Co-inventor of three Chinese invention patents on cell image density map generation and cell localization: CN115457546A, CN115810046A, CN115457547A.
💼 Academic Service
Journal reviewer: Science Advances, IEEE TPAMI, IEEE TIP, IEEE TNNLS, Medical Image Analysis, Bioinformatics, Briefings in Bioinformatics, BMC Biology, Engineering Applications of Artificial Intelligence, and Expert Systems with Applications.
Collaborations: Purdue University, Cornell University, University of Florida, National University of Singapore, Sun Yat-sen University, Sichuan University, Beijing University of Technology, and Macao Polytechnic University.
🧭 Research Interests & Technical Stack
Research: AI for Biology · cellular perturbations · virtual cells · measurement-aware evaluation · multimodal cellular modeling · phenotypic profiling · spatial omics · intervention design · scientific agents
Technical: Python · PyTorch · CUDA · Linux
