Modeling Temporal scRNA-seq Data with Latent Gaussian Process and Optimal Transport

TL;DR

This paper introduces a generative modeling approach for temporal single-cell RNA-seq data using latent Gaussian processes and optimal transport, effectively capturing biological heterogeneity and inferring trajectories.

Contribution

It proposes a novel framework combining latent heteroscedastic Gaussian processes with optimal transport to model temporal dynamics in scRNA-seq data, addressing biological variability.

Findings

Achieves state-of-the-art results on interpolation and extrapolation benchmarks.

Introduces a gradient-based method for inferring perturbation trajectories.

Explicitly models biological heterogeneity with cell-specific latent time and cell type conditioning.

Abstract

Single-cell RNA sequencing provides insights into gene expression at single-cell resolution, yet inferring temporal processes from these static snapshot measurements remains a fundamental challenge. Current approaches utilizing neural differential equations and flows are sensitive to overfitting and lack careful considerations of biological variability. In this work, we propose a generative framework that models population trends using a latent heteroscedastic Gaussian process (GP) approximated by Hilbert space methods. To address the absence of genuine cell trajectories, we leverage an optimal transport (OT) objective that aligns generated and observed population distributions. Our method explicitly captures biological heterogeneity by incorporating cell-specific latent time and cell type conditioning to disentangle temporal asynchrony and trajectories to different cell types. We demonstrate state-of-the-art performance on complex interpolation and extrapolation benchmarks and introduce a novel gradient-based strategy for inferring perturbation trajectories.