The Virtual Cell, Honestly: What Actually Works

The "virtual cell" is one of biology's most exciting goals — a model that predicts how a cell responds to a perturbation without running the experiment. Our Virtual Cell Modeling survey maps the field. But the most important recent development isn't a new model; it's an honesty correction — and it's worth being clear-eyed about where the technology really stands.

The correction the field needed

Two 2025 benchmarks landed hard: Ahlmann-Eltze et al. showed deep perturbation predictors do not yet beat a simple additive model (combinatorial) or the training mean (unseen genes), and Kedzierska et al. showed single-cell foundation models often lose to plain baselines zero-shot. Even the AI-Virtual-Cell roadmap concedes no system today is a true virtual cell. The strongest results came from hybrids — curated data + explicit statistical priors — not brute-force neural nets.

What BioMate does

• Mechanistic virtual-cell workflows, today. Four workflows run on AWS Batch — CiPA cardiac-safety ODE, ODE signaling, metabolic-flux FBA, and LINCS-L1000 transcriptomic mechanism-of-action — the regulatorily-accepted end of the virtual-cell spectrum, wired to existing ADMET/PBPK/RNA-seq pipelines.
• Baseline-anchored evaluation. BioMate measures any model against simple baselines (cell-mean, additive) and an oracle ceiling on Perturb-seq-style data — trusting mechanistic and statistically-grounded methods over headline claims that don't replicate.