← Back to articles

An operational perturbation proteomics-based virtual cell model

2026-09-09 | original

read original get Bio-Rad Mini-PROTEAN Tetra Cell → more articles

Why This Matters

The push to build an AI "virtual cell" has so far been dominated by single-cell transcriptomics foundation models; this work argues for grounding virtual cell models in perturbation proteomics, the layer where drug effects and cellular function actually play out. Because proteins are the targets of most therapeutics, a proteomics-anchored, perturbation-driven model could make in-silico cell simulation more actionable for drug discovery. It also underscores that the bottleneck is data generation in closed-loop with modeling, not just bigger models.

Key Takeaways

Virtual cell efforts are shifting from RNA-centric foundation models toward proteomics and perturbation response data.
Predicting how cells react to perturbations, across contexts, is emerging as the key benchmark for these models.
Progress depends on closed-loop pipelines that pair large-scale experimental perturbation data with AI training, not model scale alone.

Worth a Look

Bio-Rad Mini-PROTEAN Tetra Cell — Proteomics work still starts at the bench, and the Mini-PROTEAN Tetra Cell is a workhorse for running SDS-PAGE gels to check protein samples before they head to the mass spec. It's a practical companion for anyone whose lab is generating the perturbation proteomics data feeding these virtual cell models.

See Bio-Rad Mini-PROTEAN Tetra Cell on Amazon → Affiliate link — we may earn a commission on purchases, at no extra cost to you. Product picked by AI based on this article; it is not a tested recommendation.

Bunne, C. et al. How to build the virtual cell with artificial intelligence: priorities and opportunities. Cell 187, 7045–7063 (2024).

Qian, L., Dong, Z. & Guo, T. Grow AI virtual cells: three data pillars and closed-loop learning. Cell Res. 35, 319–321 (2025).

Cui, H. et al. Towards multimodal foundation models in molecular cell biology. Nature 640, 623–633 (2025).

Theodoris, C. V. et al. Transfer learning enables predictions in network biology. Nature 618, 616–624 (2023).

Hao, M. et al. Large-scale foundation model on single-cell transcriptomics. Nat. Methods 21, 1481–1491 (2024).

Rosen, Y. R. et al. Universal cell embeddings: a foundation model for cell biology. Nature 656, 183–191 (2026).

Abhinav K. et al. Predicting cellular responses to perturbation across diverse contexts with state. Preprint at bioRxiv https://doi.org/10.1101/2025.06.26.661135 (2025).

Dong, M. et al. Stack: in-context learning of single-cell biology. Preprint at bioRxiv https://doi.org/10.64898/2026.01.09.698608 (2026).

Wang, C. et al. X-Cell: scaling causal perturbation prediction across diverse cellular contexts via diffusion language models. Preprint at bioRxiv https://doi.org/10.64898/2026.03.18.712807 (2026).

Bunne, C. et al. Learning single-cell perturbation responses using neural optimal transport. Nat. Methods 20, 1759–1768 (2023).

... continue reading

Explore topics: virtual cell perturbation proteomics foundation models single-cell transcriptomics neural optimal transport