Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

GENOT: Entropic (Gromov) Wasserstein Flow Matching with Applications to Single-Cell Genomics (2310.09254v4)

Published 13 Oct 2023 in stat.ML and cs.LG

Abstract: Single-cell genomics has significantly advanced our understanding of cellular behavior, catalyzing innovations in treatments and precision medicine. However, single-cell sequencing technologies are inherently destructive and can only measure a limited array of data modalities simultaneously. This limitation underscores the need for new methods capable of realigning cells. Optimal transport (OT) has emerged as a potent solution, but traditional discrete solvers are hampered by scalability, privacy, and out-of-sample estimation issues. These challenges have spurred the development of neural network-based solvers, known as neural OT solvers, that parameterize OT maps. Yet, these models often lack the flexibility needed for broader life science applications. To address these deficiencies, our approach learns stochastic maps (i.e. transport plans), allows for any cost function, relaxes mass conservation constraints and integrates quadratic solvers to tackle the complex challenges posed by the (Fused) Gromov-Wasserstein problem. Utilizing flow matching as a backbone, our method offers a flexible and effective framework. We demonstrate its versatility and robustness through applications in cell development studies, cellular drug response modeling, and cross-modality cell translation, illustrating significant potential for enhancing therapeutic strategies.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (73)
  1. Gromov-wasserstein alignment of word embedding spaces. arXiv preprint arXiv:1809.00013, 2018.
  2. Neural optimal transport with general cost functionals, 2022. URL https://arxiv.org/abs/2205.15403.
  3. Robust optimal transport with applications in generative modeling and domain adaptation. Advances in Neural Information Processing Systems, 33:12934–12944, 2020.
  4. Comprehensive single cell mrna profiling reveals a detailed roadmap for pancreatic endocrinogenesis. Development, 146(12):dev173849, 2019.
  5. JAX: composable transformations of Python+NumPy programs, 2018. URL http://github.com/google/jax.
  6. Learning Single-Cell Perturbation Responses using Neural Optimal Transport. bioRxiv, 2021.
  7. Supervised training of conditional monge maps. In Advances in Neural Information Processing Systems (NeurIPS), 2022.
  8. Neural ordinary differential equations. Advances in neural information processing systems, 31, 2018.
  9. Likelihood training of schr\\\backslash\” odinger bridge using forward-backward sdes theory. arXiv preprint arXiv:2110.11291, 2021.
  10. Unbalanced optimal transport: geometry and Kantorovich formulation. Journal of Functional Analysis, 274(11):3090–3123, 2018.
  11. Geodesics in heat: A new approach to computing distance based on heat flow. ACM Transactions on Graphics (TOG), 32(5):1–11, 2013.
  12. Marco Cuturi. Sinkhorn Distances: Lightspeed Computation of Optimal Transport. In Advances in Neural Information Processing Systems (NeurIPS), volume 26, 2013.
  13. Optimal Transport Tools (OTT): A JAX Toolbox for all things Wasserstein. arXiv Preprint arXiv:2201.12324, 2022.
  14. Score-based generative neural networks for large-scale optimal transport. Advances in neural information processing systems, 34:12955–12965, 2021.
  15. Diffusion schrödinger bridge with applications to score-based generative modeling. Advances in Neural Information Processing Systems, 34:17695–17709, 2021.
  16. Scot: single-cell multi-omics alignment with optimal transport. Journal of Computational Biology, 29(1):3–18, 2022.
  17. On the existence of monge maps for the gromov-wasserstein problem. 2022.
  18. Stochastic gene expression in a single cell. Science, 297(5584):1183–1186, 2002.
  19. Modeling single-cell dynamics using unbalanced parameterized monge maps. bioRxiv, 2022. doi: 10.1101/2022.10.04.510766. URL https://www.biorxiv.org/content/early/2022/10/05/2022.10.04.510766.
  20. Scalable computations of wasserstein barycenter via input convex neural networks. arXiv preprint arXiv:2007.04462, 2020.
  21. Interpolating between Optimal Transport and MMD using Sinkhorn Divergences. In International Conference on Artificial Intelligence and Statistics (AISTATS), volume 22, 2019a.
  22. Interpolating between optimal transport and mmd using sinkhorn divergences. In The 22nd International Conference on Artificial Intelligence and Statistics, pp.  2681–2690. PMLR, 2019b.
  23. Learning with a wasserstein loss. Advances in neural information processing systems, 28, 2015.
  24. Deep generative modeling of transcriptional dynamics for rna velocity analysis in single cells. bioRxiv, pp.  2022–08, 2022.
  25. An optimal transport perspective on unpaired image super-resolution, 2022. URL https://arxiv.org/abs/2202.01116.
  26. Sample Complexity of Sinkhorn Divergences. In International Conference on Artificial Intelligence and Statistics (AISTATS), volume 22, 2019.
  27. Entropic neural optimal transport via diffusion processes. arXiv preprint arXiv:2211.01156, 2022.
  28. Best practices for single-cell analysis across modalities. Nature Reviews Genetics, pp.  1–23, 2023.
  29. Geodesic sinkhorn: optimal transport for high-dimensional datasets. arXiv preprint arXiv:2211.00805, 2022.
  30. Olav Kallenberg. Foundations of Modern Probability. Springer, 2002. URL https://link.springer.com/book/10.1007/978-3-030-61871-1.
  31. L Kantorovich. On the transfer of masses (in russian). In Doklady Akademii Nauk, volume 37, pp.  227, 1942.
  32. Mapping cells through time and space with moscot. bioRxiv, pp.  2023–05, 2023.
  33. Wasserstein-2 generative networks. In International Conference on Learning Representations, 2020.
  34. Kernel neural optimal transport. 2022a. doi: 10.48550/ARXIV.2205.15269. URL https://arxiv.org/abs/2205.15269.
  35. Neural optimal transport. 2022b. doi: 10.48550/ARXIV.2201.12220. URL https://arxiv.org/abs/2201.12220.
  36. Mapping lineage-traced cells across time points with moslin. bioRxiv, pp.  2023–04, 2023.
  37. Optimal entropy-transport problems and a new hellinger–kantorovich distance between positive measures. Inventiones Mathematicae, 211(3):969–1117, 2018.
  38. Flow matching for generative modeling, 2023.
  39. I22{}^{2}start_FLOATSUPERSCRIPT 2 end_FLOATSUPERSCRIPTsb: Image-to-image schrödinger bridge, 2023.
  40. Deep generative modeling for single-cell transcriptomics. Nature methods, 15(12):1053–1058, 2018a.
  41. Deep generative modeling for single-cell transcriptomics. Nature methods, 15(12), 2018b.
  42. Neural unbalanced optimal transport via cycle-consistent semi-couplings. arXiv preprint arXiv:2209.15621, 2022.
  43. A sandbox for prediction and integration of dna, rna, and proteins in single cells. In Thirty-fifth conference on neural information processing systems datasets and benchmarks track (Round 2), 2021.
  44. Christian Léonard. A survey of the schrödinger problem and some of its connections with optimal transport, 2013.
  45. Optimal transport mapping via input convex neural networks. In International Conference on Machine Learning (ICML), volume 37, 2020.
  46. Umap: Uniform manifold approximation and projection for dimension reduction. arXiv preprint arXiv:1802.03426, 2018.
  47. Facundo Mémoli. Gromov–wasserstein distances and the metric approach to object matching. Foundations of computational mathematics, 11:417–487, 2011.
  48. Energy-guided entropic neural optimal transport. arXiv preprint arXiv:2304.06094, 2023.
  49. Manifold learning-based methods for analyzing single-cell rna-sequencing data. Current Opinion in Systems Biology, 7:36–46, 2018.
  50. Neural gromov-wasserstein optimal transport. arXiv preprint arXiv:2303.05978, 2023.
  51. Gene expression cartography. Nature, 576(7785):132–137, 2019.
  52. Marcel Nutz. Introduction to entropic optimal transport.
  53. Gromov-wasserstein averaging of kernel and distance matrices. In International Conference on Machine Learning, pp. 2664–2672, 2016.
  54. Filippo Santambrogio. Optimal Transport for Applied Mathematicians. Birkhäuser, NY, 55(58-63):94, 2015.
  55. Low-rank sinkhorn factorization. In International Conference on Machine Learning, pp. 9344–9354. PMLR, 2021.
  56. Linear-time gromov wasserstein distances using low rank couplings and costs. In International Conference on Machine Learning, pp. 19347–19365. PMLR, 2022.
  57. Optimal-Transport Analysis of Single-Cell Gene Expression Identifies Developmental Trajectories in Reprogramming. Cell, 176(4), 2019.
  58. The unbalanced gromov wasserstein distance: Conic formulation and relaxation. Advances in Neural Information Processing Systems, 34:8766–8779, 2021.
  59. Diffusion schr\\\backslash\” odinger bridge matching. arXiv preprint arXiv:2303.16852, 2023.
  60. Massively multiplex chemical transcriptomics at single-cell resolution. Science, 367(6473), 2020.
  61. Single-cell chromatin state analysis with signac. Nature methods, 18(11):1333–1341, 2021.
  62. Karl-Theodor Sturm. The space of spaces: curvature bounds and gradient flows on the space of metric measure spaces, 2020.
  63. Unbalanced optimal transport, from theory to numerics, 2023a.
  64. The unbalanced gromov wasserstein distance: Conic formulation and relaxation, 2023b.
  65. Aligning individual brains with fused unbalanced gromov-wasserstein, 2023.
  66. TrajectoryNet: A Dynamic Optimal Transport Network for Modeling Cellular Dynamics. In International Conference on Machine Learning (ICML), 2020.
  67. Simulation-free schr\\\backslash\” odinger bridges via score and flow matching. arXiv preprint arXiv:2307.03672, 2023a.
  68. Conditional flow matching: Simulation-free dynamic optimal transport. arXiv preprint arXiv:2302.00482, 2023b.
  69. The monge gap: A regularizer to learn all transport maps, 2023.
  70. Solving schrödinger bridges via maximum likelihood. Entropy, 23(9):1134, 2021.
  71. Optimal transport for structured data with application on graphs. arXiv preprint arXiv:1805.09114, 2018.
  72. Scalable Unbalanced Optimal Transport using Generative Adversarial Networks. International Conference on Learning Representations (ICLR), 2019.
  73. Alignment and integration of spatial transcriptomics data. Nature Methods, 19(5):567–575, 2022.
Citations (2)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets