PRiMeFlow: Capturing Complex Expression Heterogeneity in Perturbation Response Modelling
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918499938467840 |
|---|---|
| author | Yan, Zichao Wu, Yan Ji, Mica Xu Agrahar, Chaitra Wershof, Esther Nassar, Marcel Sadria, Mehrshad Eksi, Ridvan Trifonov, Vladimir Ibarra, Ignacio Felgueira, Telmo Osiński, Błażej Stark, Rory |
| author_facet | Yan, Zichao Wu, Yan Ji, Mica Xu Agrahar, Chaitra Wershof, Esther Nassar, Marcel Sadria, Mehrshad Eksi, Ridvan Trifonov, Vladimir Ibarra, Ignacio Felgueira, Telmo Osiński, Błażej Stark, Rory |
| contents | Predicting the effects of perturbations in-silico on cell state can identify drivers of cell behavior at scale and accelerate drug discovery. However, modeling challenges remain due to the inherent heterogeneity of single cell gene expression and the complex, latent gene dependencies. Here, we present PRiMeFlow, an end-to-end flow matching based approach to directly model the effects of genetic and small molecule perturbations in the gene expression space. The distribution-fitting approach taken by PRiMeFlow enables it to accurately approximate the empirical distribution of single-cell gene expression, which we demonstrate through extensive benchmarking inside PerturBench. Through ablation studies, we also validate important model design choices such as operating in gene expression space and parameterizing the velocity field with a U-Net architecture. Finally, by scaling PRiMeFlow to a broad perturbation data atlas spanning multiple datasets and employing a carefully designed pretraining-finetuning strategy, we demonstrate its outstanding performance on the H1 human embryonic stem cells from the ARC Virtual Cell Challenge benchmark. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_13986 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PRiMeFlow: Capturing Complex Expression Heterogeneity in Perturbation Response Modelling Yan, Zichao Wu, Yan Ji, Mica Xu Agrahar, Chaitra Wershof, Esther Nassar, Marcel Sadria, Mehrshad Eksi, Ridvan Trifonov, Vladimir Ibarra, Ignacio Felgueira, Telmo Osiński, Błażej Stark, Rory Machine Learning Predicting the effects of perturbations in-silico on cell state can identify drivers of cell behavior at scale and accelerate drug discovery. However, modeling challenges remain due to the inherent heterogeneity of single cell gene expression and the complex, latent gene dependencies. Here, we present PRiMeFlow, an end-to-end flow matching based approach to directly model the effects of genetic and small molecule perturbations in the gene expression space. The distribution-fitting approach taken by PRiMeFlow enables it to accurately approximate the empirical distribution of single-cell gene expression, which we demonstrate through extensive benchmarking inside PerturBench. Through ablation studies, we also validate important model design choices such as operating in gene expression space and parameterizing the velocity field with a U-Net architecture. Finally, by scaling PRiMeFlow to a broad perturbation data atlas spanning multiple datasets and employing a carefully designed pretraining-finetuning strategy, we demonstrate its outstanding performance on the H1 human embryonic stem cells from the ARC Virtual Cell Challenge benchmark. |
| title | PRiMeFlow: Capturing Complex Expression Heterogeneity in Perturbation Response Modelling |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2604.13986 |