CellJClub
Predicting cellular responses to perturbation across diverse contexts with State.
Cell · · Journal Article
Adduri, Gautam + more
Abstract ↗AI summary
The abstract is read at the publisher; the summary is JClub's.
State predicts cellular perturbation effects across diverse contexts with over 30% improved discrimination on large datasets.
- Why it matters: Understanding how cells respond to various perturbations is crucial for advancing personalized medicine and biological research, but current models lack generalization across cellular heterogeneity.
- What they did: The authors trained State using single-cell gene expression data from 167 million cells to predict perturbation effects across different cell types and conditions, and developed Cell-Eval for model assessment.
- The result: State's cell embeddings enable detection of strong perturbations in unobserved cellular contexts, paving the way for scalable AI models that can better predict cell responses in complex biological systems.
The findingWhy it mattersWhat they didThe result
- 2 cited this week