Plate design confounds donor variation and model evaluation in single-cell perturbation screens
- 1Wright State University
Abstract
Single-cell screens of immune cells from many donors are used to study why individuals respond differently and to benchmark response models. Each donor-perturbation combination typically occupies one well, controls are grouped, and donors share one layout, so technical effects can look biological. Using a 90-cytokine screen, two compound screens, four cohorts and simulations, we show that well effects explain most replicate-control variation in abundant cell types, controls carry a shared offset, and identical control wells differ by hundreds of differentially expressed genes at a standard threshold, about as many as two receptor-negative proteins do. Negative controls, design-aware estimators and perturbation-specific evaluation change the interpretation of four recent analyses. A deep-learning model that scores below a perturbation-agnostic predictor under standard evaluation outperforms a simple baseline on perturbation-specific differences in two of three cell types (significantly in one with stricter controls), but predicts less well the component shared with inert wells.
Related
- Averaging in gene perturbation benchmarks hides perturbation-strength variation: Consequences for model evaluation
- How many cells resolve a perturbation direction? A closed-form, control-aware cell quota for single-cell perturbation screens
- PHAROS: turning single-cell perturbation models into target-directed drug-combination screens
- ISP Platform powered by Geneformer: Framework for Cross-Species, Sequential, and Multi-Gene In Silico Perturbation Screens with Application to iPS Cell State Transitions
- Evaluation Resolution Confounds Learning-Rule Comparisons in Model-Brain RSA of Early Visual Cortex
BibTeX
@misc{ghajari2026plate,
title = {{Plate design confounds donor variation and model evaluation in single-cell perturbation screens}},
author = {G. Ghajari and K. Thirunarayan and F. Amsaad},
howpublished = {bioRxiv},
year = {2026},
month = nov,
doi = {10.64898/2026.11.04.764088},
url = {https://www.biorxiv.org/content/10.64898/2026.11.04.764088v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Plate design confounds donor variation and model evaluation in single-cell perturbation screens
AU - G. Ghajari
AU - K. Thirunarayan
AU - F. Amsaad
PY - 2026
DA - 2026/11/04
PB - bioRxiv
DO - 10.64898/2026.11.04.764088
UR - https://www.biorxiv.org/content/10.64898/2026.11.04.764088v1
AB - Single-cell screens of immune cells from many donors are used to study why individuals respond differently and to benchmark response models. Each donor-perturbation combination typically occupies one well, controls are grouped, and donors share one layout, so technical effects can look biological. Using a 90-cytokine screen, two compound screens, four cohorts and simulations, we show that well effects explain most replicate-control variation in abundant cell types, controls carry a shared offset, and identical control wells differ by hundreds of differentially expressed genes at a standard threshold, about as many as two receptor-negative proteins do. Negative controls, design-aware estimators and perturbation-specific evaluation change the interpretation of four recent analyses. A deep-learning model that scores below a perturbation-agnostic predictor under standard evaluation outperforms a simple baseline on perturbation-specific differences in two of three cell types (significantly in one with stricter controls), but predicts less well the component shared with inert wells.
ER -