# Adapting a Pre-trained Single-Cell Foundation Model to Spatial Gene Expression Generation from Histology Images

arXiv: https://arxiv.org/abs/2603.19766 · HTML: https://mlsanity.com/paper/2603.19766/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 44 references that are in the map.
- First posted on arXiv 20 Mar 2026.

## Builds on (most cited first, 14 of 14)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [A Reparameterized Discrete Diffusion Model for Text Generation](https://mlsanity.com/paper/2302.05737/) (2023)
- [HEST-1k: A Dataset for Spatial Transcriptomics and Histology Image Analysis](https://mlsanity.com/paper/2406.16192/) (2024)
- [Spatially Resolved Gene Expression Prediction from H&E Histology Images via Bi-modal Contrastive Learning](https://mlsanity.com/paper/2306.01859/) (2023)
- [Accurate Spatial Gene Expression Prediction by integrating Multi-resolution features](https://mlsanity.com/paper/2403.07592/) (2024)
- [Benchmarking foundation models as feature extractors for weakly-supervised computational pathology](https://mlsanity.com/paper/2408.15823/) (2024)
- [Diffusion Generative Modeling for Spatially Resolved Gene Expression Inference from Histology Images](https://mlsanity.com/paper/2501.15598/) (2025)
- [Multimodal contrastive learning for spatial gene expression prediction using histology images](https://mlsanity.com/paper/2407.08216/) (2024)
- [Scalable Generation of Spatial Transcriptomics from Histology Images via Whole-Slide Flow Matching](https://mlsanity.com/paper/2506.05361/) (2025)
- [MERGE: Multi-faceted Hierarchical Graph-based GNN for Gene Expression Prediction from Whole Slide Histopathology Images](https://mlsanity.com/paper/2412.02601/) (2024)
- [M2OST: Many-to-one Regression for Predicting Spatial Transcriptomics from Digital Pathology Images](https://mlsanity.com/paper/2409.15092/) (2024)
- [SToFM: a Multi-scale Foundation Model for Spatial Transcriptomics](https://mlsanity.com/paper/2507.11588/) (2025)

## Built on by (most cited first, 3 of 3)

- [Cross-Slice Knowledge Transfer via Masked Multi-Modal Heterogeneous Graph Contrastive Learning for Spatial Gene Expression Inference](https://mlsanity.com/paper/2603.22821/) (2026)
- [HierarchicalDAEW: Domain-Aware Edge-Weighted Graph Convolution with Evidential Uncertainty for Multi-Section Spatial Gene Expression Prediction from H&E Histology](https://mlsanity.com/paper/2607.20896/) (2026)
- [SpaFactor: Lightweight Spatial Context-Aware Gene Program Modeling for Histology-to-Transcriptomics Inference](https://mlsanity.com/paper/2609.28563/) (2026)

## Abstract (arXiv)

Spatial transcriptomics (ST) enables spot-level in situ expression profiling, but its high cost and limited throughput motivate predicting expression directly from HE-stained histology. Recent advances explore using score- or flow-based generative models to estimate the conditional distribution of gene expression from histology, offering a flexible alternative to deterministic regression approaches. However, most existing generative approaches omit explicit modeling of gene-gene dependencies, undermining biological coherence. Single-cell foundation models (sc-FMs), pre-trained across diverse cell populations, capture these critical gene relationships that histology alone cannot reveal. Yet, applying expression-only sc-FMs to histology-conditioned expression modeling is nontrivial due to the absence of a visual pathway, a mismatch between their pre-training and conditional ST objectives, and the scarcity of mixed-cell ST supervision. To address these challenges, we propose HINGE (HIstology-coNditioned GEneration), which retrofits a pre-trained sc-FM into a conditional expression generator while mostly preserving its learned gene relationships. We achieve this by introducing SoftAdaLN, a lightweight, identity-initialized modulation that injects layer-wise visual context into the backbone, coupled with an expression-space masked diffusion objective and a warm-start curriculum to ensure objective alignment and training stability. Evaluated on three ST datasets, ours outperforms state-of-the-art baselines on mean Pearson correlation and yields more accurate spatial marker expression patterns and higher pairwise co-expression consistency, establishing a practical route to adapt pre-trained sc-FMs for histology-conditioned spatial expression generation.