mlsanityData to 7 Oct 2026

CellFlux: Simulating Cellular Morphology Changes via Flow Matching

arXiv 2502.09775 ↗First posted 13 Feb 2025q-bio.QM cs.CV cs.LGcited by 19

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

Building a virtual cell capable of accurately simulating cellular behaviors in silico has long been a dream in computational biology. We introduce CellFlux, an image-generative model that simulates cellular morphology changes induced by chemical and genetic perturbations using flow matching. Unlike prior methods, CellFlux models distribution-wise transformations from unperturbed to perturbed cell states, effectively distinguishing actual perturbation effects from experimental artifacts such as batch effects -- a major challenge in biological data. Evaluated on chemical (BBBC021), genetic (RxRx1), and combined perturbation (JUMP) datasets, CellFlux generates biologically meaningful cell images that faithfully capture perturbation-specific morphological changes, achieving a 35% improvement in FID scores and a 12% increase in mode-of-action prediction accuracy over existing methods. Additionally, CellFlux enables continuous interpolation between cellular states, providing a potential tool for studying perturbation dynamics. These capabilities mark a significant step toward realizing virtual cell modeling for biomedical research. Project page: https://yuhui-zh15.github.io/CellFlux/.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 15 of its 39 references that are in the map. First posted on arXiv 13 Feb 2025.

Builds on

15 of 39 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Flow Matching Guide and Code9 Dec
  2. 2023Guided Flows for Generative Modeling and Decision Making22 Nov
  3. 2022Flow Matching for Generative Modeling6 Oct
  4. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow7 Sep

Other references · 11

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  3. 2022Classifier-Free Diffusion Guidancecited by 5,717
  4. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  5. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  6. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  7. 2016Pixel Recurrent Neural Networkscited by 814
  8. 2023VideoPoet: A Large Language Model for Zero-Shot Video Generationcited by 479
  9. 2024How to Build the Virtual Cell with Artificial Intelligence: Priorities and Opportunitiescited by 50
  10. 2023RxRx1: A Dataset for Evaluating Experimental Batch Correction Methodscited by 45
  11. 2023PhenDiff: Revealing Subtle Phenotypes with Diffusion Models in Real Imagescited by 10

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 10; 2026: 9.

19 papers.

Sort:

By area:

  1. 2025Flow Matching Meets Biology and Life Science: A Surveycited by 14
  2. 2025Branched Schr"odinger Bridge Matchingcited by 4
  3. 2025MorphGen: Controllable and Morphologically Plausible Generative Cell-Imagingcited by 3
  4. 2025ContextFlow: Context-Aware Flow Matching For Trajectory Inference From Spatial Omics Datacited by 2
  5. 2025Three Forms of Stochastic Injection for Improved Distribution-to-Distribution Generative Modelingcited by 1
  6. 2025Compressing Biology: Evaluating the Stable Diffusion VAE for Phenotypic Drug Discoverycited by 1
  7. 2025Entangled Schr"odinger Bridge Matchingcited by 1
  8. 2025Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platformcited by 1
  9. 2026Uncertainty-Aware Distribution-to-Distribution Flow Matching for Scientific Imagingcited by 1
  10. 2026CellFluxRL: Biologically-Constrained Virtual Cell Modeling via Reinforcement Learningcited by 1
  11. 2026Elucidating the Design Space of Flow Matching for Cellular Microscopycited by 1
  12. 2025SPATIA: Multimodal Generation and Prediction of Spatial Cell Phenotypescited by 0
7 more
  1. 2025Artificial Intelligence Virtual Cells: From Measurements to Decisions across Modality, Scale, Dynamics, and Evaluationcited by 0
  2. 2026Shortest-Path Flow Matching with Mixture-Conditioned Bases for OOD Generalization to Unseen Conditionscited by 0
  3. 2026Intervention-Aware Multiscale Representation Learning from Imaging Phenomics and Perturbation Transcriptomicscited by 0
  4. 2026FreeBridge: Variational Schr"odinger Bridges for Cellular Transition Dynamicscited by 0
  5. 2026PerturbCellRL: Aligning Distributions and Grounding Biology via Post-Training Perturbation Generatorscited by 0
  6. 2026Conditional Neural Optimal Transport for Predicting Cellular Phenotypes from Molecular Structurecited by 0
  7. 2026Joint Flow Matching Enables Continuous Dose-Conditioned Cell Morphingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026PerturbDiff: Functional Diffusion for Single-Cell Perturbation Modeling
  2. 2026scDFM: Distributional Flow Matching Model for Robust Single-Cell Perturbation Prediction
  3. 2025CFM-GP: Unified Conditional Flow Matching to Learn Gene Perturbation Across Cell Types
  4. 2026Generalizable single-cell perturbation response prediction using energy-guided flow matching
  5. 2024Multi-Modal and Multi-Attribute Generation of Single Cells with CFGen
  6. 2026Chreode: A Cell World Model for One-Step Temporal Dynamics and Perturbation Prediction
  7. 2026DRIFT: Disentangled Responsive-Invariant Flow Transport for Single-Cell Perturbation Prediction
  8. 2026VCLMU: Mechanism-Centric Virtual Cell World Modeling for Perturbation Response