Bo Li 李波 — AI for Biology: from multimodal virtual cells to experimental decisions

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  ·  BibTeX

TL;DR: Learns cellular representations directly from high-content microscopy for phenotypic profiling and drug discovery, connecting image-derived features to biological differences between diverse cellular perturbations.

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  ·  BibTeX

TL;DR: Integrates single-cell and spatial transcriptomics through style-transfer imputation, predicting spatial gene-expression patterns to connect complementary measurements of cellular identity and tissue organization.

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  ·  BibTeX

TL;DR: Ranks feasible interventions under a limited experimental budget, using historical perturbation data and biological knowledge to prioritize response-unseen candidates. Evaluates the selected experiments against independently measured outcomes.

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  ·  BibTeX

TL;DR: Separates measurement limits from modeling limits by testing whether experiments can reproducibly distinguish fine-grained perturbation effects, and whether predictive models recover those distinctions rather than only shared response patterns.

DrugDis: Disentangling general and context-specific effects in drug-response prediction

Bo Li^†, Chengliang Liu^†, Yuzhong Peng^†, Bob Zhang^*, Qing Wang, Pinxian Zeng, Mengran Li, Shenghui Huang, Chuxia Deng^*, Yang Zhang^*

Manuscript 2026  ·  Project  ·  Manuscript  ·  Supplement  ·  Code  ·  Data  ·  BibTeX

TL;DR: Separates general drug and sample effects from context-specific interactions, revealing what drives aggregate prediction accuracy and whether model improvements recover the response components needed for biological interpretation.

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  ·  BibTeX

TL;DR: Benchmarks molecular and cellular representations for drug-induced transcriptomic and morphological responses, testing which predictive gains persist across compounds, cell lines, experimental batches, and datasets.