CellPainTR: Generalizable Representation Learning for Cross-Dataset Cell Painting Analysis
This work addresses the challenge of integrating heterogeneous biological datasets for researchers in computational biology, representing a significant but incremental step towards foundational models for image-based profiling.
The paper tackled the problem of technical batch effects and lack of generalizable models in cross-dataset cell painting analysis by introducing CellPainTR, a Transformer-based architecture that learns robust representations, outperforming established methods like ComBat and Harmony on the JUMP dataset and maintaining high performance on an unseen dataset without fine-tuning.
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.