# A virtual cancer cell that predicts what a drug will do before you test it

Source: https://onco.cc/ideas/idea-bio1-virtual-cell-perturbation/  
OnCo record `idea-bio1-virtual-cell-perturbation` (Idea). Data CC BY-NC 4.0, attribute "Data from OnCo (onco.cc)"; commercial use needs a licence.

## TL;DR

Train a model on millions of experiments where genes and drugs were altered, so it can predict the effect of a new combination without running the experiment.

## Summary

Perturbation foundation models trained on Perturb-seq, CRISPR screens and compound-response atlases aim to predict transcriptional and viability responses to unseen perturbations and combinations. The critical missing element is prospective, blinded validation against held-out wet-lab experiments and, eventually, clinical outcomes. Without that, these models risk repeating the overfitting seen in earlier drug-response prediction efforts.

## Fields

- Kind: Idea
- Last checked: 2026-09-08
- Hypothesis: A perturbation model prospectively predicts the direction and rank order of combination effects in held-out cell contexts substantially better than a strong statistical baseline, and its errors are systematic and characterisable.
- Rationale: Combination space is far too large to screen exhaustively, so some form of prediction is unavoidable; the question is whether current models generalise beyond their training distribution, which only blinded prospective tests can answer.
- Proposed test: A blinded challenge in which teams predict outcomes of 500 unseen perturbation experiments that are then run in a reference laboratory, with results and baselines published in full.
- Maturity: speculative
- Actor: data

## Sources

- Bottleneck evidence (Lab models that fail to predict what happens in patients): Wong, Siah & Lo, Estimation of clinical trial success rates (Biostatistics 2019): https://doi.org/10.1093/biostatistics/kxx069

## Connected records

- technologies: [AI-driven drug & target discovery](https://onco.cc/technologies/ai-drug-design/), [CRISPR functional genomics](https://onco.cc/technologies/crispr-screens/), [RNA sequencing & expression profiling](https://onco.cc/technologies/rna-seq/)
- companies: [Insilico Medicine](https://onco.cc/companies/insilico-medicine/), [Recursion Pharmaceuticals](https://onco.cc/companies/recursion/)
- bottlenecks: [AI that is built but not validated or deployed](https://onco.cc/bottlenecks/b-ai-validation/), [Lab models that fail to predict what happens in patients](https://onco.cc/bottlenecks/b-preclinical-models/), [Too many combinations to test](https://onco.cc/bottlenecks/b-combination-space/)
- key papers: [Estimation of clinical trial success rates and related parameters](https://onco.cc/key-papers/paper-wong-biostatistics/)

---
JSON: https://onco.cc/api/v1/entities/idea-bio1-virtual-cell-perturbation.json