Generative modeling of single-cell gene expression for dose-dependent chemical perturbations

Omar Kana; Rance Nault; David Filipovic; Daniel Marri; Tim Zacharewski; Sudin Bhattacharya

doi:10.1016/j.patter.2023.100817

Generative modeling of single-cell gene expression for dose-dependent chemical perturbations

Patterns (N Y). 2023 Aug 11;4(8):100817. doi: 10.1016/j.patter.2023.100817.

Authors

Omar Kana^{1

2

3}, Rance Nault^{2

4}, David Filipovic^{3

5

6}, Daniel Marri^{3

5}, Tim Zacharewski^{2

4}, Sudin Bhattacharya^{1

2

3

5}

Affiliations

¹ Department of Pharmacology and Toxicology, Michigan State University, East Lansing, MI 48824, USA.
² Institute for Integrative Toxicology, Michigan State University, East Lansing, MI 48824, USA.
³ Institute for Quantitative Health Science & Engineering, Michigan State University, East Lansing, MI 48824, USA.
⁴ Department of Biochemistry and Molecular Biology Michigan State University, Michigan State University, East Lansing, MI 48824, USA.
⁵ Department of Biomedical Engineering, Michigan State University, East Lansing, MI 48824, USA.
⁶ Department of Computational Mathematics, Science and Engineering, Michigan State University, East Lansing, MI 48824, USA.

Abstract

Single-cell sequencing reveals the heterogeneity of cellular response to chemical perturbations. However, testing all relevant combinations of cell types, chemicals, and doses is a daunting task. A deep generative learning formalism called variational autoencoders (VAEs) has been effective in predicting single-cell gene expression perturbations for single doses. Here, we introduce single-cell variational inference of dose-response (scVIDR), a VAE-based model that predicts both single-dose and multiple-dose cellular responses better than existing models. We show that scVIDR can predict dose-dependent gene expression across mouse hepatocytes, human blood cells, and cancer cell lines. We biologically interpret the latent space of scVIDR using a regression model and use scVIDR to order individual cells based on their sensitivity to chemical perturbation by assigning each cell a "pseudo-dose" value. We envision that scVIDR can help reduce the need for repeated animal testing across tissues, chemicals, and doses.

Keywords: chemical perturbation; computational modeling; deep learning; dose response; gene expression; pharmacology; risk assessment; single-cell RNA–seq; toxicology; variational autoencoders.

Abstract

Grants and funding