Format

Send to

Choose Destination
Nat Methods. 2019 Aug;16(8):715-721. doi: 10.1038/s41592-019-0494-8. Epub 2019 Jul 29.

scGen predicts single-cell perturbation responses.

Author information

1
Helmholtz Zentrum München - German Research Center for Environmental Health, Institute of Computational Biology, Neuherberg, Germany.
2
School of Life Sciences Weihenstephan, Technical University of Munich, Munich, Germany.
3
Helmholtz Zentrum München - German Research Center for Environmental Health, Institute of Computational Biology, Neuherberg, Germany. alex.wolf@helmholtz-muenchen.de.
4
Helmholtz Zentrum München - German Research Center for Environmental Health, Institute of Computational Biology, Neuherberg, Germany. fabian.theis@helmholtz-muenchen.de.
5
School of Life Sciences Weihenstephan, Technical University of Munich, Munich, Germany. fabian.theis@helmholtz-muenchen.de.
6
Department of Mathematics, Technical University of Munich, Munich, Germany. fabian.theis@helmholtz-muenchen.de.

Abstract

Accurately modeling cellular response to perturbations is a central goal of computational biology. While such modeling has been based on statistical, mechanistic and machine learning models in specific settings, no generalization of predictions to phenomena absent from training data (out-of-sample) has yet been demonstrated. Here, we present scGen (https://github.com/theislab/scgen), a model combining variational autoencoders and latent space vector arithmetics for high-dimensional single-cell gene expression data. We show that scGen accurately models perturbation and infection response of cells across cell types, studies and species. In particular, we demonstrate that scGen learns cell-type and species-specific responses implying that it captures features that distinguish responding from non-responding genes and cells. With the upcoming availability of large-scale atlases of organs in a healthy state, we envision scGen to become a tool for experimental design through in silico screening of perturbation response in the context of disease and drug treatment.

PMID:
31363220
DOI:
10.1038/s41592-019-0494-8

Supplemental Content

Full text links

Icon for Nature Publishing Group
Loading ...
Support Center