CellPainTR: Generalizable Representation Learning for Cross-Dataset Cell Painting Analysis
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911143108280320 |
|---|---|
| author | Caruzzo, Cedric Ye, Jong Chul |
| author_facet | Caruzzo, Cedric Ye, Jong Chul |
| contents | Large-scale biological discovery requires integrating massive, heterogeneous datasets like those from the JUMP Cell Painting consortium, but technical batch effects and a lack of generalizable models remain critical roadblocks. To address this, we introduce CellPainTR, a Transformer-based architecture designed to learn foundational representations of cellular morphology that are robust to batch effects. Unlike traditional methods that require retraining on new data, CellPainTR's design, featuring source-specific context tokens, allows for effective out-of-distribution (OOD) generalization to entirely unseen datasets without fine-tuning. We validate CellPainTR on the large-scale JUMP dataset, where it outperforms established methods like ComBat and Harmony in both batch integration and biological signal preservation. Critically, we demonstrate its robustness through a challenging OOD task on the unseen Bray et al. dataset, where it maintains high performance despite significant domain and feature shifts. Our work represents a significant step towards creating truly foundational models for image-based profiling, enabling more reliable and scalable cross-study biological analysis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_06986 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CellPainTR: Generalizable Representation Learning for Cross-Dataset Cell Painting Analysis Caruzzo, Cedric Ye, Jong Chul Computer Vision and Pattern Recognition Artificial Intelligence Large-scale biological discovery requires integrating massive, heterogeneous datasets like those from the JUMP Cell Painting consortium, but technical batch effects and a lack of generalizable models remain critical roadblocks. To address this, we introduce CellPainTR, a Transformer-based architecture designed to learn foundational representations of cellular morphology that are robust to batch effects. Unlike traditional methods that require retraining on new data, CellPainTR's design, featuring source-specific context tokens, allows for effective out-of-distribution (OOD) generalization to entirely unseen datasets without fine-tuning. We validate CellPainTR on the large-scale JUMP dataset, where it outperforms established methods like ComBat and Harmony in both batch integration and biological signal preservation. Critically, we demonstrate its robustness through a challenging OOD task on the unseen Bray et al. dataset, where it maintains high performance despite significant domain and feature shifts. Our work represents a significant step towards creating truly foundational models for image-based profiling, enabling more reliable and scalable cross-study biological analysis. |
| title | CellPainTR: Generalizable Representation Learning for Cross-Dataset Cell Painting Analysis |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2509.06986 |