Pop-Corn: Predicting Perturbation Phenotype Effects Across Single-Cell and Spatial Contexts
- 1Whitehead Institute for Biomedical Research
Abstract
Genetic perturbations can reshape cell populations by altering the relative abundance of specific cell types and states within the profiled population, including increases, decreases and states that become detectable after perturbation. Pooled single-cell screens, such as Perturb-seq, measure such responses at scale. However, only a small fraction of possible perturbations can be tested experimentally. A central challenge is therefore to predict compositional shifts induced by unseen perturbations. Many perturbation-prediction methods do not directly optimize for this outcome; instead, they predict gene-expression responses and infer cell-type and cell-state composition downstream. Surprisingly, we find that even models that accurately predict perturbation-induced changes in average gene expression perform poorly at forecasting these compositional shifts. To address this gap, we present Pop-Corn, a method that directly predicts how a perturbation reshapes cell-type composition without reconstructing gene expression. In the primary T-cell benchmark, Pop-Corn predicted the overall cell-state composition of held-out perturbations more accurately than the evaluated expression-prediction pipelines, while better preserving the diversity of observed cell states. We further extend Pop-Corn to intact tissue, where it predicts perturbation-induced cell-type proportion changes in local cellular neighborhoods and uses attention patterns to generate hypotheses about context-dependent cellular interactions. Retrospective virtual screens support the use of Pop-Corn to prioritize perturbations for experimental follow-up according to their predicted effects on cell-state composition.
Related
- MultiFlow: coupled flow matching for predicting single-cell multiomic perturbation responses in unseen cellular contexts
- PIE: Generalizing perturbation effects across unseen perturbations, contexts and datasets
- Random mtDNA mutagenesis maps genotype-phenotype associations across metabolic contexts and lineages
- Human-wildlife conflict shows shared spatial predictors across ecological and geographic contexts
- Effect of Spatial Release from Masking on Listening Effort in Different Semantic Contexts
BibTeX
@misc{chen2026popcorn,
title = {{Pop-Corn: Predicting Perturbation Phenotype Effects Across Single-Cell and Spatial Contexts}},
author = {J. Chen and Y. Cui and Y. Shao and N. Sun and M. R. Martinez},
howpublished = {bioRxiv},
year = {2026},
month = sep,
doi = {10.64898/2026.09.25.754560},
url = {https://www.biorxiv.org/content/10.64898/2026.09.25.754560v1},
note = {CC BY},
}
RIS
TY - UNPB
TI - Pop-Corn: Predicting Perturbation Phenotype Effects Across Single-Cell and Spatial Contexts
AU - J. Chen
AU - Y. Cui
AU - Y. Shao
AU - N. Sun
AU - M. R. Martinez
PY - 2026
DA - 2026/09/25
PB - bioRxiv
DO - 10.64898/2026.09.25.754560
UR - https://www.biorxiv.org/content/10.64898/2026.09.25.754560v1
AB - Genetic perturbations can reshape cell populations by altering the relative abundance of specific cell types and states within the profiled population, including increases, decreases and states that become detectable after perturbation. Pooled single-cell screens, such as Perturb-seq, measure such responses at scale. However, only a small fraction of possible perturbations can be tested experimentally. A central challenge is therefore to predict compositional shifts induced by unseen perturbations. Many perturbation-prediction methods do not directly optimize for this outcome; instead, they predict gene-expression responses and infer cell-type and cell-state composition downstream. Surprisingly, we find that even models that accurately predict perturbation-induced changes in average gene expression perform poorly at forecasting these compositional shifts. To address this gap, we present Pop-Corn, a method that directly predicts how a perturbation reshapes cell-type composition without reconstructing gene expression. In the primary T-cell benchmark, Pop-Corn predicted the overall cell-state composition of held-out perturbations more accurately than the evaluated expression-prediction pipelines, while better preserving the diversity of observed cell states. We further extend Pop-Corn to intact tissue, where it predicts perturbation-induced cell-type proportion changes in local cellular neighborhoods and uses attention patterns to generate hypotheses about context-dependent cellular interactions. Retrospective virtual screens support the use of Pop-Corn to prioritize perturbations for experimental follow-up according to their predicted effects on cell-state composition.
ER -