Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
125 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

DynGFN: Towards Bayesian Inference of Gene Regulatory Networks with GFlowNets (2302.04178v4)

Published 8 Feb 2023 in cs.LG and cs.AI

Abstract: One of the grand challenges of cell biology is inferring the gene regulatory network (GRN) which describes interactions between genes and their products that control gene expression and cellular function. We can treat this as a causal discovery problem but with two non-standard challenges: (1) regulatory networks are inherently cyclic so we should not model a GRN as a directed acyclic graph (DAG), and (2) observations have significant measurement noise, so for typical sample sizes there will always be a large equivalence class of graphs that are likely given the data, and we want methods that capture this uncertainty. Existing methods either focus on challenge (1), identifying cyclic structure from dynamics, or on challenge (2) learning complex Bayesian posteriors over DAGs, but not both. In this paper we leverage the fact that it is possible to estimate the "velocity" of gene expression with RNA velocity techniques to develop an approach that addresses both challenges. Because we have access to velocity information, we can treat the Bayesian structure learning problem as a problem of sparse identification of a dynamical system, capturing cyclic feedback loops through time. Since our objective is to model uncertainty over discrete structures, we leverage Generative Flow Networks (GFlowNets) to estimate the posterior distribution over the combinatorial space of possible sparse dependencies. Our results indicate that our method learns posteriors that better encapsulate the distributions of cyclic structures compared to counterpart state-of-the-art Bayesian structure learning approaches.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (54)
  1. Beyond predictions in neural odes: Identification and interventions. arXiv preprint 2106.12430, 2021.
  2. Sparsity in continuous-depth neural networks. Advances in Neural Information Processing Systems (NeurIPS), 2022.
  3. Structure learning for cyclic linear causal models. Uncertainty in Artificial Intelligence (UAI), 2020.
  4. Variational causal networks: Approximate bayesian inference over causal structures. arXiv preprint, 2021.
  5. CausalNex, 2021. URL https://github.com/quantumblacklabs/causalnex.
  6. Neural Graphical Modelling in Continuous Time: Consistency Guarantees and Algorithms. International Conference on Learning Representations (ICLR), 2022.
  7. Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation. Advances in Neural Information Processing Systems (NeurIPS), 2021.
  8. GFlowNet Foundations. arXiv preprint 2111.09266, 2022.
  9. Generalizing RNA velocity to transient cell states through dynamical modeling. BioRxiv preprint 820936, 2019.
  10. Neural Ordinary Differential Equations. Advances in Neural Information Processing Systems (NeurIPS), 2018.
  11. BCD Nets: Scalable Variational Approaches for Bayesian Causal Discovery. Advances in Neural Information Processing Systems (NeurIPS), 2021.
  12. Bayesian Structure Learning with Generative Flow Networks. Uncertainty in Artificial Intelligence (UAI), 2022.
  13. Learning the structure of dynamic probabilistic networks. Uncertainty in Artificial Intelligence (UAI), 1998.
  14. Review of Causal Discovery Methods Based on Graphical Models. Frontiers in Genetics, 2019.
  15. Granger, C. W. Investigating causal relations by econometric models and cross-spectral methods. Econometrica: journal of the Econometric Society, 1969.
  16. Hypernetworks. International Conference on Learning Representations (ICLR), 2017.
  17. Learning Population-Level Diffusions with Generative Recurrent Networks. International Conference on Machine Learning (ICML), 2016.
  18. Characterization and greedy learning of interventional markov equivalence classes of directed acyclic graphs. Journal of Machine Learning Research (JMLR), 13(1), 2012.
  19. Active learning of causal networks with intervention experiments and optimal designs. Journal of Machine Learning Research (JMLR), 9, 2008.
  20. Causal discovery and forecasting in nonstationary environments with state-space models. International Conference on Machine Learning (ICML), 2019.
  21. Causal discovery from heterogeneous/nonstationary data. The Journal of Machine Learning Research (JMLR), 21, 2020.
  22. Manifold interpolating optimal-transport flows for trajectory inference. Advances in Neural Information Processing Systems (NeurIPS), 2022a.
  23. Geodesic Sinkhorn: Optimal transport for high-dimensional datasets. arXiv preprint 2211.00805, 2022b.
  24. Structure learning in causal cyclic networks. Proceedings of Workshop on Causality: Objectives and Assessment at NIPS 2008, 2010.
  25. Modelling and analysis of gene regulatory networks. Nature reviews Molecular cell biology, 9, 2008.
  26. Learning neural causal models from unknown interventions. arXiv preprint 1910.01075, 2019.
  27. RNA velocity of single cells. Nature, 560, 2018.
  28. Discovering cyclic causal models by independent components analysis. arXiv preprint 1206.3273, 2012.
  29. Gradient-Based Neural DAG Learning. International Conference on Learning Representations (ICLR), 2020.
  30. Stein variational gradient descent: A general purpose bayesian inference algorithm. Advances in Neural Information Processing Systems (NeurIPS), 2016.
  31. Large-scale differentiable causal discovery of factor graphs. Advances in Neural Information Processing Systems (NeurIPS), 2022.
  32. DiBS: Differentiable Bayesian Structure Learning. Advances in Neural Information Processing Systems (NeurIPS), 2021.
  33. Learning gflownets from partial episodes for improved convergence and stability. arXiv preprint 2209.12782, 2022.
  34. Trajectory Balance: Improved Credit Assignment in GFlowNets. Advances in Neural Information Processing Systems (NeurIPS), 2022.
  35. Causal discovery with general non-linear relationships using non-linear ica. Uncertainty in Artificial Intelligence (UAI), 2020.
  36. On causal discovery with cyclic additive noise models. Advances in Neural Information Processing Systems (NeurIPS), 2011.
  37. From Ordinary Differential Equations to Structural Causal Models: The deterministic case. Uncertainty in Artificial Intelligence (UAI), 2013.
  38. Joint causal inference from multiple contexts. The Journal of Machine Learning Research (JMLR), 21, 2020.
  39. Murphy, K. P. Active learning of causal bayes net structure. Technical report, UC Berkeley, 2001.
  40. Dynotears: Structure learning from time-series data. International Conference on Artificial Intelligence and Statistics (AISTATS), 2020.
  41. Pearl, J. Causality. Caimbridge University Press, second edition, 2009.
  42. Elements of causal inference: foundations and learning algorithms. The MIT Press, 2017.
  43. Causal models for dynamical systems. Probabilistic and Causal Inference: The Works of Judea Pearl, 2022.
  44. Benchmarking algorithms for gene regulatory network inference from single-cell transcriptomic data. Nature methods, 17, 2020.
  45. Mapping transcriptomic vector fields of single cells. Cell, 185, 2022.
  46. Cell cycle gene regulation dynamics revealed by RNA velocity and deep-learning. Nature Communications, 13, 2022.
  47. A comparison of single-cell trajectory inference methods. Nature Biotechnology, 37, 2019.
  48. Optimal-Transport Analysis of Single-Cell Gene Expression Identifies Developmental Trajectories in Reprogramming. Cell, 176, 2019.
  49. An algorithm for fast recovery of sparse causal graphs. Social Science Computer Review, 9, 1991.
  50. Neural Granger Causality. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021.
  51. TrajectoryNet: A Dynamic Optimal Transport Network for Modeling Cellular Dynamics. International Conference on Machine Learning (ICML), 2020.
  52. Active learning for structure in bayesian networks. International Joint Conference on Artificial Intelligence (IJCAI), 17, 2001.
  53. Causal discovery from nonstationary/heterogeneous data: Skeleton estimation and orientation determination. International Joint Conference on Artificial Intelligence (IJCAI), 2017.
  54. DAGs with NO TEARS: Continuous Optimization for Structure Learning. Advances in Neural Information Processing Systems (NeurIPS), 2018.
Citations (17)
View on Semantic Scholar

Summary

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

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