Transcriptomic forecasting with neural ordinary differential equations

Rossin Erbe; Genevieve Stein-O'Brien; Elana J Fertig

doi:10.1016/j.patter.2023.100793

Transcriptomic forecasting with neural ordinary differential equations

Patterns (N Y). 2023 Jul 6;4(8):100793. doi: 10.1016/j.patter.2023.100793. eCollection 2023 Aug 11.

Authors

Rossin Erbe^{1

2

3}, Genevieve Stein-O'Brien^{1

2

4

5

6}, Elana J Fertig^{2

3

7

8

9}

Affiliations

¹ Department of Genetic Medicine, Johns Hopkins University School of Medicine, Baltimore, MD, USA.
² Johns Hopkins Convergence Institute, Johns Hopkins University School of Medicine, Baltimore, MD, USA.
³ Department of Oncology, Sidney Kimmel Comprehensive Cancer Center, Johns Hopkins University, Baltimore, MD, USA.
⁴ Department of Neuroscience, Johns Hopkins University School of Medicine, Baltimore, MD, USA.
⁵ Kavli Neurodiscovery Institute, Baltimore, MD, USA.
⁶ Single Cell Training and Analysis Center, Johns Hopkins University School of Medicine, Baltimore, MD, USA.
⁷ Johns Hopkins Bloomberg Kimmel Institute for Immunotherapy, Johns Hopkins University School of Medicine, Baltimore, MD, USA.
⁸ Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA.
⁹ Department of Applied Mathematics and Statistics, Johns Hopkins University, Baltimore, MD, USA.

Abstract

Single-cell transcriptomics technologies can uncover changes in the molecular states that underlie cellular phenotypes. However, understanding the dynamic cellular processes requires extending from inferring trajectories from snapshots of cellular states to estimating temporal changes in cellular gene expression. To address this challenge, we have developed a neural ordinary differential-equation-based method, RNAForecaster, for predicting gene expression states in single cells for multiple future time steps in an embedding-independent manner. We demonstrate that RNAForecaster can accurately predict future expression states in simulated single-cell transcriptomic data with cellular tracking over time. We then show that by using metabolic labeling single-cell RNA sequencing (scRNA-seq) data from constitutively dividing cells, RNAForecaster accurately recapitulates many of the expected changes in gene expression during progression through the cell cycle over a 3-day period. Thus, RNAForecaster enables short-term estimation of future expression states in biological systems from high-throughput datasets with temporal information.

Keywords: artificial intelligence; cellular phenotypes; machine learning; neural ODE; predictive biology; single-cell RNA-seq; temporalomics.

Associated data

figshare/10.6084/m9.figshare.20123804

Abstract

Associated data

Grants and funding