The reviewed record of science sign in
Pith

arxiv: 2605.25581 · v1 · pith:SZNN2E3M · submitted 2026-05-25 · cs.LG

Learning Latent Dynamical Causal Processes for Single-Cell Perturbation Prediction

Wenkang Jiang , Yuhang Liu , Erdun Gao , Ehsan Abbasnejad , Lina Yao , Javen Qinfeng Shi This is my paper

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel 2026-06-29 23:15 UTCgrok-4.3pith:SZNN2E3Mrecord.jsonopen to challenge →

classification cs.LG
keywords single-cell perturbationcausal generative modellatent dynamical processesidentifiabilityperturbation predictionCRISPRtemporal evolutionout-of-distribution generalization
0
0 comments X

The pith

A latent dynamical causal generative model recovers cellular programs and their perturbation-driven dynamics from single-cell data up to standard equivalence classes.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper argues that perturbation effects in single-cell experiments act through unobserved cellular programs whose states evolve over time and produce the observed gene expression profiles. It proposes a generative model that jointly represents these latent programs, the mechanisms conditioned on specific perturbations, and their temporal evolution, backed by an identifiability result that the latent causal variables can be recovered under suitable conditions. The authors then introduce CITE-VAE, a learning framework guided by that analysis, and show it improves generalization to unseen perturbations on both controlled simulations and real CRISPR perturbation datasets. A sympathetic reader would care because accurate recovery of these latent processes could support mechanistic interpretation and reliable prediction of how cells respond to new interventions without requiring exhaustive experimental testing.

Core claim

We propose a latent dynamical causal generative model for single-cell perturbation data that jointly captures latent cellular programs, perturbation-conditioned mechanisms, and temporal evolution. We further provide an identifiability analysis showing that, under suitable conditions, the latent causal variables are recoverable up to standard equivalence classes. Guided by this analysis, we develop CITE-VAE, a learning framework for recovering latent cellular programs and their perturbation-driven dynamics from single-cell sequencing data.

What carries the argument

The latent dynamical causal generative model, which encodes unobserved cellular programs evolving under perturbation-conditioned mechanisms to produce observed expression profiles.

If this is right

  • The model supports out-of-distribution generalization to unseen perturbations by recovering the underlying causal mechanisms rather than fitting static associations.
  • Temporal evolution of latent programs can be tracked explicitly, allowing predictions of how cellular responses unfold after an intervention.
  • Identifiability up to equivalence classes provides a theoretical basis for interpreting the recovered variables as representations of cellular programs.
  • CITE-VAE can be applied to CRISPR-based single-cell data to achieve better predictive performance than existing baselines on real perturbation responses.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • If the latent programs correspond to biologically meaningful modules, the recovered dynamics could guide hypothesis generation for follow-up wet-lab experiments on specific pathways.
  • The approach could extend to multi-perturbation or combinatorial intervention settings where interactions between perturbations need to be modeled through shared latent states.
  • Failure of identifiability in practice would likely manifest as inconsistent predictions across different random seeds or data subsamples, offering a diagnostic for when the modeling assumptions are violated.

Load-bearing premise

Perturbation effects act through unobserved cellular programs whose states evolve over time in a manner recoverable from observed expression profiles.

What would settle it

A dataset in which the same observed expression trajectories arise from multiple distinct latent program trajectories that cannot be distinguished even with full knowledge of the perturbation schedule and time points.

Figures

Figures reproduced from arXiv: 2605.25581 by Ehsan Abbasnejad, Erdun Gao, Javen Qinfeng Shi, Lina Yao, Wenkang Jiang, Yuhang Liu.

Figure 1
Figure 1. Figure 1: Illustration of data generation process with the [PITH_FULL_IMAGE:figures/full_fig_p003_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: CITE-VAE framework for learning latent causal dynamics from single-cell time-series data. Observed snapshots are encoded into a latent space that is explicitly partitioned into a perturbation-invariant block z𝜄 and a perturbation-responsive block z𝜈 . Temporal learning is enabled via distributional coupling between consecutive timepoints, allowing latent transitions to be learned without cell-wise pairing.… view at source ↗
Figure 3
Figure 3. Figure 3: Temporal causal structure of the synthetic bench [PITH_FULL_IMAGE:figures/full_fig_p007_3.png] view at source ↗
Figure 5
Figure 5. Figure 5: Latent-space organization under temporal perturbations. UMAP of [PITH_FULL_IMAGE:figures/full_fig_p009_5.png] view at source ↗
read the original abstract

Single-cell perturbation prediction aims to infer how cells respond to unseen interventions and to achieve out-of-distribution (OOD) generalization, providing a computational route to understanding how perturbations reshape cellular programs over time. Existing machine learning methods have made important progress, but typically capture only one side of the response. Latent causal approaches seek mechanisms that support generalization and interpretation, yet often treat perturbation effects as static outcomes. Temporal models describe how gene expression changes across time, but usually do not explicitly recover the latent causal generative mechanisms driving these changes. In practice, perturbation effects are both latent and dynamical: interventions act through unobserved cellular programs, whose states evolve over time and give rise to observed expression profiles. Motivated by this view, we propose a latent dynamical causal generative model for single-cell perturbation data that jointly captures latent cellular programs, perturbation-conditioned mechanisms, and temporal evolution. We further provide an identifiability analysis showing that, under suitable conditions, the latent causal variables are recoverable up to standard equivalence classes. Guided by this analysis, we develop CITE-VAE, a learning framework for recovering latent cellular programs and their perturbation-driven dynamics from single-cell sequencing data. Experiments on Causal-3DIdent validate the theoretical results and the effectiveness of the proposed method in controlled settings. Additional experiments on real-world CRISPR-based single-cell perturbation data show improved generalization to unseen perturbations compared with state-of-the-art baselines, highlighting the practical robustness of our approach.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The paper proposes a latent dynamical causal generative model for single-cell perturbation data that jointly captures latent cellular programs, perturbation-conditioned mechanisms, and temporal evolution. It provides an identifiability analysis claiming that, under suitable conditions, the latent causal variables are recoverable up to standard equivalence classes. Guided by this, the authors develop CITE-VAE and report improved OOD generalization to unseen perturbations on synthetic Causal-3DIdent data and real CRISPR single-cell perturbation datasets compared to baselines.

Significance. If the identifiability result is rigorously established and the generalization gains are robust to realistic violations of the modeling assumptions, the work could advance causal modeling for temporal single-cell data by providing a framework that links latent programs to perturbation-driven dynamics. The explicit combination of identifiability analysis with a practical VAE-based implementation is a positive feature.

major comments (2)
  1. [Identifiability Analysis] Identifiability Analysis (likely §3 or equivalent): The claim that latent causal variables are recoverable rests on 'suitable conditions' whose precise statement (e.g., functional form of the dynamical system, independence of causal mechanisms, injectivity of perturbation effects through the latent programs) is not visible in the abstract and must be checked against whether they are plausibly satisfied by single-cell expression data. If these conditions are not verified or shown to be approximately satisfied, the recovery guarantee does not transfer to the real-data experiments and weakens the OOD generalization interpretation.
  2. [Experiments] Experiments on Causal-3DIdent (synthetic validation section): The synthetic data is generated under conditions that match the model assumptions by construction; this validates internal consistency but does not address the skeptic concern that the assumed dynamical class or Markovian evolution may fail on real single-cell data. A load-bearing test would require either sensitivity analysis under controlled violations or additional synthetic regimes that break the assumptions while remaining biologically plausible.
minor comments (2)
  1. [Abstract] The abstract states an identifiability result and improved generalization but contains no equations, proof sketches, or error bars; the full manuscript should ensure these are clearly presented with explicit statements of all assumptions.
  2. [Model Definition] Notation for the latent variables, perturbation conditioning, and temporal evolution should be introduced consistently and early to aid readability for readers outside the immediate subfield.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments, which help clarify the scope of our identifiability claims and the role of the synthetic experiments. We respond point-by-point below and indicate where revisions will be made.

read point-by-point responses

  1. Referee: [Identifiability Analysis] Identifiability Analysis (likely §3 or equivalent): The claim that latent causal variables are recoverable rests on 'suitable conditions' whose precise statement (e.g., functional form of the dynamical system, independence of causal mechanisms, injectivity of perturbation effects through the latent programs) is not visible in the abstract and must be checked against whether they are plausibly satisfied by single-cell expression data. If these conditions are not verified or shown to be approximately satisfied, the recovery guarantee does not transfer to the real-data experiments and weakens the OOD generalization interpretation.

    Authors: The precise conditions (first-order Markov dynamics, independent causal mechanisms, and injective perturbation mapping through latent programs) are stated in Section 3. They are omitted from the abstract for brevity. We do not claim exact satisfaction on real single-cell data; instead, the CRISPR results demonstrate that the learned model yields improved OOD generalization even when assumptions hold only approximately. We will add a dedicated paragraph in the Discussion section on the biological plausibility of these conditions and the limits of the identifiability transfer. revision: partial

  2. Referee: [Experiments] Experiments on Causal-3DIdent (synthetic validation section): The synthetic data is generated under conditions that match the model assumptions by construction; this validates internal consistency but does not address the skeptic concern that the assumed dynamical class or Markovian evolution may fail on real single-cell data. A load-bearing test would require either sensitivity analysis under controlled violations or additional synthetic regimes that break the assumptions while remaining biologically plausible.

    Authors: The Causal-3DIdent experiments are intended to confirm that the identifiability result holds when the data-generating process matches the model class. We agree that this leaves open the question of robustness to violations. In the revision we will add a sensitivity analysis that introduces controlled, biologically motivated violations (e.g., mild non-Markovian noise or dependent mechanisms) and report the resulting degradation in OOD performance. revision: yes

Circularity Check

0 steps flagged

No significant circularity in derivation chain

full rationale

The provided abstract and description present a proposed latent dynamical causal model together with an identifiability analysis under suitable conditions, plus validation experiments on Causal-3DIdent. No equations, self-citations, or reductions are exhibited that make any claimed prediction or identifiability result equivalent to its inputs by construction. The derivation remains self-contained against external benchmarks at the level of description given; the synthetic experiments are framed as validation rather than the source of the theoretical claim.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Only the abstract is available; no specific free parameters, background axioms, or new postulated entities beyond the general latent programs are detailed enough to enumerate.

pith-pipeline@v0.9.1-grok · 5801 in / 1190 out tokens · 30912 ms · 2026-06-29T23:15:45.892833+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

49 extracted references · 6 canonical work pages · 1 internal anchor

  1. [1]

    Kartik Ahuja, Divyat Mahajan, Yixin Wang, and Yoshua Bengio. 2023. Inter- ventional causal representation learning. InInternational conference on machine learning. PMLR, 372–407

    2023

  2. [2]

    Michael Ashburner, Catherine A Ball, Judith A Blake, David Botstein, Heather Butler, J Michael Cherry, Allan P Davis, Kara Dolinski, Selina S Dwight, Janan T Eppig, et al. 2000. Gene ontology: tool for the unification of biology.Nature genetics25, 1 (2000), 25–29

    2000

  3. [3]

    Elisa Balmas, Maria L Ratto, Kirsten E Snijders, Silvia Becca, Carla Liaci, Irene Ricca, Giorgio R Merlo, Raffaele A Calogero, Luca Alessandrì, Sasha Mendjan, et al. 2025. Single cell transcriptional perturbome in pluripotent stem cell models. Molecular Systems Biology22, 2 (2025), 179

    2025

  4. [4]

    Michael Bereket and Theofanis Karaletsos. 2023. Modelling cellular perturbations with the sparse additive mechanism shift variational autoencoder.Advances in Neural Information Processing Systems36 (2023), 1–12

    2023

  5. [5]

    Beatrice Borsari, Mor Frank, Eve S Wattenberg, Ke Xu, Susanna X Liu, Xuezhu Yu, and Mark Gerstein. 2025. The chronODE framework for modelling multi-omic time series with ordinary differential equations and machine learning.Nature Communications16, 1 (2025), 7021

    2025

  6. [6]

    Charlotte Bunne, Stefan G Stark, Gabriele Gut, Jacobo Sarabia Del Castillo, Mitch Levesque, Kjong-Van Lehmann, Lucas Pelkmans, Andreas Krause, and Gunnar Rätsch. 2023. Learning single-cell perturbation responses using neural optimal transport.Nature methods20, 11 (2023), 1759–1768

    2023

  7. [7]

    Haotian Cui, Chloe Wang, Hassaan Maan, Kuan Pang, Fengning Luo, Nan Duan, and Bo Wang. 2024. scGPT: toward building a foundation model for single-cell multi-omics using generative AI.Nature methods21, 8 (2024), 1470–1480

    2024

  8. [8]

    Jesus de la Fuente, Robert Lehmann, Carlos Ruiz-Arenas, Jan Voges, Irene Marin- Goñi, Xabier Martinez-de Morentin, David Gomez-Cabrero, Idoia Ochoa, Jesper Tegner, Vincenzo Lagani, et al. 2025. Interpretable Causal Representation Learn- ing for Biological Data in the Pathway Space.arXiv preprint arXiv:2506.12439 (2025)

    work page arXiv 2025

  9. [9]

    Erdun Gao, Howard Bondell, Shaoli Huang, and Mingming Gong. 2025. Domain generalization via content factors isolation: a two-level latent variable modeling approach.Machine Learning114, 4 (2025), 1–33

    2025

  10. [10]

    Aapo Hyvärinen, Jarmo Hurri, and Patrik O Hoyer. 2001. Independent com- ponent analysis. InNatural Image Statistics: A Probabilistic Approach to Early Computational Vision. Springer, 151–175

    2001

  11. [11]

    Aapo Hyvarinen and Hiroshi Morioka. 2016. Unsupervised feature extraction by time-contrastive learning and nonlinear ica.Advances in neural information processing systems29 (2016)

    2016

  12. [12]

    Aapo Hyvarinen and Hiroshi Morioka. 2017. Nonlinear ICA of temporally dependent stationary sources. InArtificial intelligence and statistics. PMLR, 460– 469

    2017

  13. [13]

    Aapo Hyvärinen and Petteri Pajunen. 1999. Nonlinear independent component analysis: Existence and uniqueness results.Neural networks12, 3 (1999), 429–439

    1999

  14. [14]

    Masato Ishikawa, Seiichi Sugino, Yoshie Masuda, Yusuke Tarumoto, Yusuke Seto, Nobuko Taniyama, Fumi Wagai, Yuhei Yamauchi, Yasuhiro Kojima, Hisanori Kiryu, et al. 2023. RENGE infers gene regulatory networks using time-series single-cell RNA-seq data with CRISPR perturbations.Communications Biology6, 1 (2023), 1290

    2023

  15. [15]

    Wenkang Jiang, Yuhang Liu, Yichao Cai, Erdun Gao, Jiayi Dong, Ehsan Abbasne- jad, Lina Yao, and Javen Qinfeng Shi. 2026. What Makes a Representation Good for Single-Cell Perturbation Prediction?arXiv preprint arXiv:2605.19343(2026)

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  16. [16]

    Ilyes Khemakhem, Diederik Kingma, Ricardo Monti, and Aapo Hyvarinen. 2020. Variational autoencoders and nonlinear ica: A unifying framework. InInterna- tional conference on artificial intelligence and statistics. PMLR, 2207–2217

    2020

  17. [17]

    Diederik P Kingma, Max Welling, et al. 2013. Auto-encoding variational bayes

    2013

  18. [18]

    Sebastien Lachapelle, Pau Rodriguez, Yash Sharma, Katie E Everett, Rémi LE PRIOL, Alexandre Lacoste, and Simon Lacoste-Julien. 2022. Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICA. InFirst Conference on Causal Learning and Reasoning. https://openreview.net/forum? id=dHsFFekd_-o

    2022

  19. [19]

    Phillip Lippe, Sara Magliacane, Sindy Löwe, Yuki M Asano, Taco Cohen, and Efstratios Gavves. 2022. Causal representation learning for instantaneous and temporal effects in interactive systems.arXiv preprint arXiv:2206.06169(2022)

    work page arXiv 2022

  20. [20]

    Phillip Lippe, Sara Magliacane, Sindy Löwe, Yuki M Asano, Taco Cohen, and Stratis Gavves. 2022. Citris: Causal identifiability from temporal intervened sequences. InInternational Conference on Machine Learning. PMLR, 13557–13603

    2022

  21. [21]

    Yuhang Liu, Dong Gong, Yichao Cai, Erdun Gao, Zhen Zhang, Biwei Huang, Mingming Gong, Anton van den Hengel, and Javen Qinfeng Shi. 2026. I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data?. InThe Fourteenth International Conference on Learning Representations

    2026

  22. [22]

    Yuhang Liu, Zhen Zhang, Dong Gong, Erdun Gao, Biwei Huang, Mingming Gong, Anton van den Hengel, Kun Zhang, and Javen Qinfeng Shi. 2024. Towards Identifiable Latent Additive Noise Models.arXiv preprint arXiv:2403.15711(2024)

    work page arXiv 2024

  23. [23]

    Yuhang Liu, Zhen Zhang, Dong Gong, Erdun Gao, Biwei Huang, Mingming Gong, Anton van den Hengel, Kun Zhang, and Javen Qinfeng Shi. 2026. Beyond DAGs: A Latent Partial Causal Model for Multimodal Learning. InThe Fourteenth International Conference on Learning Representations

    2026

  24. [24]

    Yuhang Liu, Zhen Zhang, Dong Gong, Mingming Gong, Biwei Huang, Anton van den Hengel, Kun Zhang, and Javen Qinfeng Shi. 2024. Identifiable Latent Polynomial Causal Models through the Lens of Change. InThe Twelfth Interna- tional Conference on Learning Representations

    2024

  25. [25]

    Yuhang Liu, Zhen Zhang, Dong Gong, Mingming Gong, Biwei Huang, Anton van den Hengel, Kun Zhang, and Javen Qinfeng Shi. 2025. Latent Covariate Shift: Unlocking Partial Identifiability for Multi-Source Domain Adaptation. Transactions on Machine Learning Research(2025)

    2025

  26. [26]

    Yuhang Liu, Zhen Zhang, Dong Gong, Mingming Gong, Biwei Huang, Anton van den Hengel, Kun Zhang, and Javen Qinfeng Shi. 2026. Identifying weight- variant latent causal models.Journal of Machine Learning Research27, 4 (2026), 1–49

    2026

  27. [27]

    Romain Lopez, Natasa Tagasovska, Stephen Ra, Kyunghyun Cho, Jonathan Pritchard, and Aviv Regev. 2022. Learning Causal Representations of Single Cells via Sparse Mechanism Shift Modeling. InNeurIPS 2022 Workshop on Causal- ity for Real-world Impact. https://openreview.net/forum?id=gdTXCy7fZf7

    2022

  28. [28]

    Mohammad Lotfollahi, Anna Klimovskaia Susmelj, Carlo De Donno, Leon Hetzel, Yuge Ji, Ignacio L Ibarra, Sanjay R Srivatsan, Mohsen Naghipourfar, Riza M Daza, Beth Martin, et al. 2023. Predicting cellular responses to complex perturbations in high-throughput screens.Molecular systems biology19, 6 (2023), e11517

    2023

  29. [29]

    Haiyi Mao, Minxue Jia, Marissa Di, Eleanor Valenzi, Xiaoyu Tracy Cai, Robert Lafyatis, Kun Zhang, and Panayiotis V Benos. 2025. HALO: hierarchical causal modeling for single cell multi-omics data.Nature Communications16, 1 (2025), 8892

    2025

  30. [30]

    María Moscardó García, Atte Aalto, Arthur N Montanari, Alexander Skupin, and Jorge Gonçalves. 2025. Multi-omic network inference from time-series data.npj Systems Biology and Applications11, 1 (2025), 114

    2025

  31. [31]

    Thomas M Norman, Max A Horlbeck, Joseph M Replogle, Alex Y Ge, Albert Xu, Marco Jost, Luke A Gilbert, and Jonathan S Weissman. 2019. Exploring genetic interaction manifolds constructed from rich single-cell phenotypes.Science365, 6455 (2019), 786–793

    2019

  32. [32]

    Chethan Pandarinath, Daniel J O’Shea, Jasmine Collins, Rafal Jozefowicz, Sergey D Stavisky, Jonathan C Kao, Eric M Trautmann, Matthew T Kaufman, Stephen I Ryu, Leigh R Hochberg, et al. 2018. Inferring single-trial neural popu- lation dynamics using sequential auto-encoders.Nature methods15, 10 (2018), 805–815

    2018

  33. [33]

    Joseph M Replogle, Thomas M Norman, Albert Xu, Jeffrey A Hussmann, Jin Chen, J Zachery Cogan, Elliott J Meer, Jessica M Terry, Daniel P Riordan, Niranjan Srinivas, et al. 2020. Combinatorial single-cell CRISPR screens by direct guide RNA capture and targeted sequencing.Nature biotechnology38, 8 (2020), 954– 961

    2020

  34. [34]

    Danilo Jimenez Rezende, Shakir Mohamed, and Daan Wierstra. 2014. Stochas- tic backpropagation and approximate inference in deep generative models. In International conference on machine learning. PMLR, 1278–1286

    2014

  35. [35]

    Yanay Rosen, Yusuf Roohani, Ayush Agarwal, Leon Samotorčan, Tabula Sapi- ens Consortium, Stephen R Quake, and Jure Leskovec. 2023. Universal cell embeddings: A foundation model for cell biology.bioRxiv(2023), 2023–11

    2023

  36. [36]

    Bernhard Schölkopf, Francesco Locatello, Stefan Bauer, Nan Rosemary Ke, Nal Kalchbrenner, Anirudh Goyal, and Yoshua Bengio. 2021. Toward causal repre- sentation learning.Proc. IEEE109, 5 (2021), 612–634

    2021

  37. [37]

    Rohit Singh, Alexander P Wu, Anish Mudide, and Bonnie Berger. 2024. Causal gene regulatory analysis with RNA velocity reveals an interplay between slow and fast transcription factors.Cell systems15, 5 (2024), 462–474

    2024

  38. [38]

    Peter Sorrenson, Carsten Rother, and Ullrich Köthe. 2020. Disentanglement by nonlinear ica with general incompressible-flow networks (gin).arXiv preprint arXiv:2001.04872(2020)

    work page arXiv 2020

  39. [39]

    Alejandro Tejada-Lapuerta, Paul Bertin, Stefan Bauer, Hananeh Aliee, Yoshua Bengio, and Fabian J Theis. 2025. Causal machine learning for single-cell ge- nomics.Nature Genetics(2025), 1–12

    2025

  40. [40]

    Jan-Philipp von Bassewitz, Adeel Pervez, Marco Fumero, Matthew Robinson, Theofanis Karaletsos, and Francesco Locatello. 2025. Learning Explicit Single- Cell Dynamics Using ODE Representations.arXiv preprint arXiv:2510.02903 (2025)

    work page arXiv 2025

  41. [41]

    Julius von Kügelgen, Michel Besserve, Liang Wendong, Luigi Gresele, Armin Kekić, Elias Bareinboim, David Blei, and Bernhard Schölkopf. 2023. Nonpara- metric identifiability of causal representations from unknown interventions. Advances in Neural Information Processing Systems36 (2023), 48603–48638

    2023

  42. [42]

    Julius Von Kügelgen, Yash Sharma, Luigi Gresele, Wieland Brendel, Bernhard Schölkopf, Michel Besserve, and Francesco Locatello. 2021. Self-supervised learning with data augmentations provably isolates content from style.Advances in neural information processing systems34 (2021), 16451–16467

    2021

  43. [43]

    Alexander P Wu, Rohit Singh, Christopher A Walsh, and Bonnie Berger. 2025. Unveiling causal regulatory mechanisms through cell-state parallax.Nature Communications16, 1 (2025), 8096. 10 Learning Latent Dynamical Causal Processes for Single-Cell Perturbation Prediction

    2025

  44. [44]

    Mengyue Yang, Furui Liu, Zhitang Chen, Xinwei Shen, Jianye Hao, and Jun Wang

  45. [45]

    InProceedings of the IEEE/CVF conference on computer vision and pattern recognition

    Causalvae: Disentangled representation learning via neural structural causal models. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition. 9593–9602

  46. [46]

    Jiaqi Zhang, Kristjan Greenewald, Chandler Squires, Akash Srivastava, Karthikeyan Shanmugam, and Caroline Uhler. 2023. Identifiability guarantees for causal disentanglement from soft interventions.Advances in Neural Information Processing Systems36 (2023), 50254–50292

    2023

  47. [47]

    Jiaqi Zhang, Erica Larschan, Jeremy Bigness, and Ritambhara Singh. 2024. scN- ODE: generative model for temporal single cell transcriptomic data prediction. Bioinformatics40, Supplement_2 (2024), ii146–ii154

    2024

  48. [48]

    Roland S Zimmermann, Yash Sharma, Steffen Schneider, Matthias Bethge, and Wieland Brendel. 2021. Contrastive learning inverts the data generating process. InInternational conference on machine learning. PMLR, 12979–12990

    2021

  49. [49]

    Hui Zou and Trevor Hastie. 2005. Regularization and variable selection via the elastic net.Journal of the Royal Statistical Society Series B: Statistical Methodology 67, 2 (2005), 301–320. A Proof of Theorem 4.1 Proof. We proceed in three steps: (I) reduce transition matching to innovation matching, (II) identify the innovations (n𝑡 𝜄 , n𝑡 𝜈), and (III) l...

    2005