将预训练单细胞基础模型适配于从组织学图像生成空间基因表达
Adapting a Pre-trained Single-Cell Foundation Model to Spatial Gene Expression Generation from Histology Images
将预训练单细胞基础模型通过轻量级视觉条件调制（SoftAdaLN）和掩码扩散目标适配到组织学图像条件生成，为视觉-组学跨模态生成提供可复用的条件注入与目标对齐策略。
原文依据 we propose HINGE, which retrofits a pre-trained sc-FM into a conditional expression generator while mostly preserving its learned gene relationships.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论空间转录组学（ST）能够实现斑点级原位表达谱分析，但其高成本和有限吞吐量促使人们直接从H&E染色的组织学图像预测表达。近期进展探索使用基于分数或流的生成模型从组织学图像估计基因表达的条件分布，为确定性回归方法提供了灵活的替代方案。然而，大多数现有生成方法忽略了对基因-基因依赖关系的显式建模，削弱了生物一致性。单细胞基础模型（sc-FM）在多样细胞群体上预训练，能够捕捉仅凭组织学图像无法揭示的关键基因关系。然而，将仅表达数据的sc-FM应用于组织学条件表达建模并非易事，原因包括缺乏视觉通路、其预训练目标与条件ST目标之间的不匹配，以及混合细胞ST监督的稀缺。为应对这些挑战，我们提出HINGE（组织学条件生成），将预训练的sc-FM改造为条件表达生成器，同时基本保留其学到的基因关系。我们通过引入SoftAdaLN——一种轻量级、恒等初始化的调制，将逐层视觉上下文注入主干网络——并结合表达空间掩码扩散目标和热启动课程来确保目标对齐和训练稳定性。在三个ST数据集上评估，HINGE在平均皮尔逊相关性上优于最优基线，并产生更准确的空间标记表达模式和更高的成对共表达一致性，为将预训练sc-FM适配于组织学条件空间表达生成建立了一条实用路径。
英文原文摘要 1802 字符
Spatial transcriptomics (ST) enables spot-level in situ expression profiling, but its high cost and limited throughput motivate predicting expression directly from H&E-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** (**HI**stology-co**N**ditioned **GE**neration), 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, HINGE 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.