Skip to content

In Silico Perturbation Prediction

Definition
AI-generated

In silico perturbation prediction forecasts how a cell’s molecular profile would change under a genetic or chemical perturbation not observed in the training experiment—using deep generative models, graph networks, optimal transport, or foundation models trained on atlas and perturbation compendia (e.g. scPerturb).

Why it matters in GWAS

It offers a scalable way to prioritize GWAS genes by simulating knockdown or overexpression effects on disease-relevant programs in reference cell types, complementing Perturb-seq when experiments are infeasible—subject to validation and calibration concerns.

Example usage

"The methods include In Silico Perturbation Prediction to support interpretation of the main results."

References

  • Roohani Y, et al. (2024). Predicting transcriptional outcomes of novel multigene perturbations with GEARS. Nat Biotechnol.
  • Ji Y, Lotfollahi M, Wolf FA, Theis FJ. (2021). Machine learning for perturbational single-cell omics. Cell Syst.
  • Dimitrov D, Schrod S, Rohbeck M, et al. (2026). Interpretation, extrapolation and perturbation of single cells. Nat Rev Genet. https://doi.org/10.1038/s41576-025-00920-4

Last updated (UTC · Git history)