TY - JOUR
T1 - scGen predicts single-cell perturbation responses
AU - Lotfollahi, Mohammad
AU - Wolf, F. Alexander
AU - Theis, Fabian J.
N1 - Publisher Copyright:
© 2019, The Author(s), under exclusive licence to Springer Nature America, Inc.
PY - 2019/8/1
Y1 - 2019/8/1
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85069972336&partnerID=8YFLogxK
U2 - 10.1038/s41592-019-0494-8
DO - 10.1038/s41592-019-0494-8
M3 - Article
C2 - 31363220
AN - SCOPUS:85069972336
SN - 1548-7091
VL - 16
SP - 715
EP - 721
JO - Nature Methods
JF - Nature Methods
IS - 8
ER -