# scDFM: Distributional Flow Matching for Robust Single-Cell Perturbation Prediction (ICLR 2026) [](https://openreview.net/forum?id=QSGanMEcUV) [](https://github.com/AI4Science-WestlakeU/scDFM) [](LICENSE) [](https://youtu.be/T4vNEsp7eLs) [](assets/scdfm_PPT.pdf) Official repo for the paper [scDFM](URL), ICLR 2026.
Chenglei Yu^∗1,2, [Chuanrui Wang](https://wang-cr.github.io/)^∗1, Bangyan Liao^∗1,2 & [Tailin Wu](https://tailin.org/)^†1.
¹School of Engineering, Westlake University; ²Zhejaing University; *Equal contribution, †Corresponding authors ---- ## Overview We propose a novel distributional flow matching framework (scDFM) for robust single-cell perturbation prediction, which models the full distribution of perturbed cellular expression profiles conditioned on control states, thereby overcoming limitations of existing methods that rely on cell-level correspondences and fail to capture population-level transcriptional shifts. Framework of paper: ## Install dependencies ``` conda env create -f environment.yml ``` ## ⏬ Dataset download Put dataset into data file: - [Norman](https://figshare.com/articles/dataset/Norman_et_al_2019_Science_labeled_Perturb-seq_data/24688110) - [Combosciplex subset of sciplex v3](https://figshare.com/articles/dataset/combosciplex/25062230?file=44229635) ### Alternative Data Access We also provide the datasets via [Google Drive](https://drive.google.com/drive/folders/1cNpYAt9jVWZN82miNZtkP10YeSo7hufL?usp=sharing). This folder contains: - The **Norman** dataset and its corresponding data splits. - The **ComboSciPlex** dataset. Example directory layout after download (relative to repo root): ``` scDFM/ ├─ data/ │ ├─ norman.h5ad │ └─ combosciplex.h5ad ├─ src/ │ └─ ... └─ run.sh ``` ## 📥 Training An example on additive task. ```bash bash run.sh ``` ## 🫡 Citation If you find our work and/or our code useful, please cite us via: ```bibtex @inproceedings{yu2026scdfm, title={sc{DFM}: Distributional Flow Matching Model for Robust Single-Cell Perturbation Prediction}, author={Chenglei Yu and Chuanrui Wang and Bangyan Liao and Tailin Wu}, booktitle={The Fourteenth International Conference on Learning Representations}, year={2026}, url={https://openreview.net/forum?id=QSGanMEcUV} } ``` ## 📚 Related Resources - AI for Scientific Simulation and Discovery Lab: https://github.com/AI4Science-WestlakeU