Optimal transport for single-cell and spatial omics

C Bunne, G Schiebinger, A Krause, A Regev… - Nature Reviews …, 2024 - nature.com
High-throughput single-cell profiling provides an unprecedented ability to uncover the
molecular states of millions of cells. These technologies are, however, destructive to cells …

[HTML][HTML] How to build the virtual cell with artificial intelligence: Priorities and opportunities

C Bunne, Y Roohani, Y Rosen, A Gupta, X Zhang… - Cell, 2024 - cell.com
Cells are essential to understanding health and disease, yet traditional models fall short of
modeling and simulating their function and behavior. Advances in AI and omics offer …

A computational framework for solving Wasserstein Lagrangian flows

K Neklyudov, R Brekelmans, A Tong… - arxiv preprint arxiv …, 2023 - arxiv.org
The dynamical formulation of the optimal transport can be extended through various choices
of the underlying geometry ($\textit {kinetic energy} $), and the regularization of density …

Light schr\" odinger bridge

A Korotin, N Gushchin, E Burnaev - arxiv preprint arxiv:2310.01174, 2023 - arxiv.org
Despite the recent advances in the field of computational Schrodinger Bridges (SB), most
existing SB solvers are still heavy-weighted and require complex optimization of several …

Discrete Diffusion Schr\" odinger Bridge Matching for Graph Transformation

JH Kim, S Kim, S Moon, H Kim, J Woo… - arxiv preprint arxiv …, 2024 - arxiv.org
Transporting between arbitrary distributions is a fundamental goal in generative modeling.
Recently proposed diffusion bridge models provide a potential solution, but they rely on a …

Sinkhorn Flow as Mirror Flow: A Continuous-Time Framework for Generalizing the Sinkhorn Algorithm

MR Karimi, YP Hsieh, A Krause - … Conference on Artificial …, 2024 - proceedings.mlr.press
Many problems in machine learning can be formulated as solving entropy-regularized
optimal transport on the space of probability measures. The canonical approach involves the …

Learning stochastic dynamics from snapshots through regularized unbalanced optimal transport

Z Zhang, T Li, P Zhou - arxiv preprint arxiv:2410.00844, 2024 - arxiv.org
Reconstructing dynamics using samples from sparsely time-resolved snapshots is an
important problem in both natural sciences and machine learning. Here, we introduce a new …

Sinkhorn Flow: A Continuous-Time Framework for Understanding and Generalizing the Sinkhorn Algorithm

MR Karimi, YP Hsieh, A Krause - arxiv preprint arxiv:2311.16706, 2023 - arxiv.org
Many problems in machine learning can be formulated as solving entropy-regularized
optimal transport on the space of probability measures. The canonical approach involves the …

Categorical Schr\" odinger Bridge Matching

G Ksenofontov, A Korotin - arxiv preprint arxiv:2502.01416, 2025 - arxiv.org
The Schr\" odinger Bridge (SB) is a powerful framework for solving generative modeling
tasks such as unpaired domain translation. Most SB-related research focuses on continuous …

ARTEMIS integrates autoencoders and schrodinger bridges to predict continuous dynamics of gene expression, cell population and perturbation from time-series …

SA Alatkar, D Wang - bioRxiv, 2025 - biorxiv.org
Cellular processes like development, differentiation, and disease progression are highly
complex and dynamic (eg, gene expression). These processes often undergo cell …