Predicting cellular responses to perturbation across diverse contexts with State
Cell · 2026-09 · 189 (19) · 5914-5931.e20
DOI: 10.1016/j.cell.2026.07.052 ↗Kurz gefasst
Fachartikel in der Zeitschrift Cell, 2026-09. Verfasst von Abhinav K Adduri und 31 weiteren Autor:innen. Beteiligte Einrichtung: Arc Institute, Palo Alto, CA, USA. Hauptthemen laut MEDLINE: Machine Learning, Transcriptome. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 119 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
While machine learning models offer potential for predicting transcriptomic effects of perturbation, they currently struggle to generalize across cellular contexts. Here, we introduce State, a machine learning model that predicts perturbation effects while accounting for cellular heterogeneity within and across experiments. State is trained using single-cell gene expression data to predict perturbation effects across sets of cells. State improved discrimination of effects on large datasets by more than 30% and identified differentially expressed genes across genetic, signaling, and chemical perturbations with significantly improved accuracy compared with baselines. Its cell embeddings trained on observational data from 167 million cells enable the identification of strong perturbations in cellular contexts where no perturbations were observed during training. We further introduce Cell-Eval, a comprehensive evaluation framework that can be used to evaluate future models. Overall, the performance and flexibility of State set the stage for scaling the development of AI models of cell state.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Arc Institute, Palo Alto, CA, USA.
- Arc Institute, Palo Alto, CA, USA; University of California, Berkeley, Berkeley, CA, USA.
- Arc Institute, Palo Alto, CA, USA; University of Pennsylvania, Philadelphia, PA, USA.
- Arc Institute, Palo Alto, CA, USA; University of California, San Francisco, San Francisco, CA, USA.
- Arc Institute, Palo Alto, CA, USA; Stanford University, Stanford, CA, USA.
- Arc Institute, Palo Alto, CA, USA; Yale University, New Haven, CT, USA.
Zitieren
APA
Adduri, A. K., Gautam, D., Bevilacqua, B., Naghipourfar, M., Imran, A., Shah, R., Teyssier, N., Verma, R., Carpenter, C., Eraslan, B., Chalissery, F., Ilango, R., Subramanyam, V., Ricci-Tam, C., Nagaraj, S., Winters, A., Dong, M., Fellinger, S., Krejci, A., …, & Roohani, Y. H. (2026). Predicting cellular responses to perturbation across diverse contexts with State. Cell, 189(19), 5914-5931.e20. https://doi.org/10.1016/j.cell.2026.07.052
Vancouver
Adduri AK, Gautam D, Bevilacqua B, Naghipourfar M, Imran A, Shah R, et al. Predicting cellular responses to perturbation across diverse contexts with State. Cell. 2026;189(19):5914-5931.e20. doi:10.1016/j.cell.2026.07.052
BibTeX
@article{Adduri2026,
author = {Adduri, Abhinav K and Gautam, Dhruv and Bevilacqua, Beatrice and Naghipourfar, Mohsen and Imran, Alishba and Shah, Rohan and Teyssier, Noam and Verma, Rishi and Carpenter, Christopher and Eraslan, Basak and Chalissery, Francis and Ilango, Rajesh and Subramanyam, Vishvak and Ricci-Tam, Chiara and Nagaraj, Sanjay and Winters, Aidan and Dong, Mingze and Fellinger, Stefanie and Krejci, Adam and Burckstummer, Tilmann and Tirukkovular, Sravya and Sullivan, Jeremy and Plosky, Brian S and Youngblut, Nicholas D and Leskovec, Jure and Gilbert, Luke A and Konermann, Silvana and Hsu, Patrick D and Dobin, Alexander and Burke, Dave P and Goodarzi, Hani and Roohani, Yusuf H},
title = {Predicting cellular responses to perturbation across diverse contexts with State},
journal = {Cell},
year = {2026},
volume = {189},
number = {19},
pages = {5914--5931.e20},
doi = {10.1016/j.cell.2026.07.052}
}
EUVIMED