CellPlex: Benchmarking Single-Cell Spatial Proteomics Prediction from H&E
cs.CV
Submitted: 2026-11-02
Updated: 2026-11-02
License: http://creativecommons.org/licenses/by/4.0/
The gist: Spatial proteomics measures tens of proteins in every cell of a tissue section, but its cost confines it to small research cohorts…
Terminology
Abstract
Spatial proteomics measures tens of proteins in every cell of a tissue section, but its cost confines it to small research cohorts, whereas hematoxylin and eosin (H&E) slides exist for nearly every patient. Inferring single-cell spatial proteomics from H&E would bring its analyses to routine pathology, and a growing number of virtual staining models pursue this goal. Each is evaluated on its own cohort, panel and pixel-level metric, and released models transfer poorly to new cohorts, leaving open which approach to build on and which proteins H&E can reveal. We introduce CellPlex, a benchmark that poses the task at the level of the cell: seven cohorts with same-section H&E and multiplexed immunofluorescence, from colorectal and breast cancer to lymph-node metastases, bone marrow and glioma, with 717 samples, 44.8 million cells and 149 proteins, processed by one pipeline into per-cell targets. Pathology foundation models (PFMs) are adapted with one cell-level protocol, specialist models are fine-tuned under a matched budget, and all are scored on the same cells. Adapted PFMs are the most accurate models on every cohort, ahead of the specialists even after fine-tuning, but keep less than half of their accuracy on cohorts they were not trained on. Which proteins can be predicted depends on the tissue, not on how many cells were measured for them. By fixing the cells, targets and splits on which predictions are judged, CellPlex sets a common standard for inferring costly molecular measurements from routine H&E and shows how far H&E can stand in for spatial proteomics. We will release the data, splits, evaluation code and baselines as a testbed for developing and comparing future pathology foundation models and virtual staining methods.
Sources
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Towards Scalable Context-Aware Single-Cell Spatial Transcriptomics Prediction from Histology Images
- Decoupled Weight Decay Regularization
- DINOv2: Learning Robust Visual Features without Supervision
- A Foundation Model for Spatial Proteomics
- spora: A Unified Multimodal Dataset and Platform for Spatial Proteomics
- A Multimodal Foundation Model of Spatial Transcriptomics and Histology for Biological Discovery and Clinical Prediction
- Virchow2: Scaling Self-Supervised Mixed Magnification Models in Pathology
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs