Reconstructing growth and dynamic trajectories from single-cell transcriptomics data

Authors:
Open Access
Publisher website
Google Scholar
Abstract
Time-series single-cell RNA sequencing (scRNA-seq) datasets provide unprecedented opportunities to learn dynamic processes of cellular systems. Due to the destructive nature of sequencing, it remains challenging to link the scRNA-seq snapshots sampled at different time points. Here we present TIGON, a dynamic, unbalanced optimal transport algorithm that reconstructs dynamic trajectories and population growth simultaneously as well as the underlying gene regulatory network from multiple snapshots. To tackle the high-dimensional optimal transport problem, we introduce a deep learning method using a dimensionless formulation based on the Wasserstein–Fisher–Rao (WFR) distance. TIGON is evaluated on simulated data and compared with existing methods for its robustness and accuracy in predicting cell state transition and cell population growth. Using three scRNA-seq datasets, we show the importance of growth in the temporal inference, TIGON’s capability in reconstructing gene expression at unmeasured time points and its applications to temporal gene regulatory networks and cell–cell communication inference.
Funding Information
  • NSF | Directorate for Mathematical and Physical Sciences (DMS1763272)
  • NSF | BIO | Division of Molecular and Cellular Biosciences (MCB2028424)
  • U.S. Department of Health & Human Services | NIH | National Institute of Arthritis and Musculoskeletal and Skin Diseases (R01AR079150, U01AR073159)
  • Simons Foundation (594598)

This publication has 60 references indexed in Scilit: