CVMar 20

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

arXiv:2603.1976653.71 citationsh-index: 9
Predicted impact top 65% in CV · last 90 daysOriginality Incremental advance
AI Analysis

This work addresses the high cost and limited throughput of spatial transcriptomics for researchers in genomics and computational biology, offering a practical generative approach that is incremental but enhances existing methods.

The paper tackled the problem of predicting spatial gene expression from histology images by adapting a pre-trained single-cell foundation model, achieving state-of-the-art performance with higher Pearson correlation and improved biological coherence on three datasets.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes