Do Perturbation Predictors Learn Gene Interactions? Diagnosing Extrapolation in Agentic Screening
arXiv:2610.18880v1 Announce Type: new Abstract: High-throughput perturbation screens increasingly use machine-learning models to predict the effects of gene combinations that were never measured. A difficult case arises when both genes in a test pair were seen individually during training, but thei…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-10-15 04:00 · arXiv cs.LG
Do Perturbation Predictors Learn Gene Interactions? Diagnosing Extrapolation in Agentic Screening