通过高阶多细胞交互建模从组织学图像预测空间转录组
Predicting Spatial Transcriptomics from Histology Images via High-Order Multi-Cell Interaction Modeling
把多体注意力（many-body attention）与分层耦合引入全切片图像的多细胞建模，为病理图像中建模高阶、多对多的细胞间依赖提供了可复用的注意力设计，可迁移到其他需要超长程、多实体交互的密集预测任务。
原文依据 explicitly models multi-cell interactions via many-body attention with hierarchical coupling to predict spatial gene expression
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）将基因表达与组织结构联系起来，使得从H&E染色的全切片图像（WSI）预测空间表达成为可能。然而，现有的位点级或切片级预测器关注单个位点特征或成对关系，无法捕捉高阶、多对多的跨细胞交互。因此，它们遗漏了多个相邻细胞之间的协同与拮抗效应。本文提出MCToGene，一个可扩展且准确的框架，通过带分层耦合的多体注意力显式建模多细胞交互以预测空间基因表达。MCToGene采用多体注意力模块编码高阶、多对多的跨细胞依赖，实现上下文感知的微环境建模。为缓解多体建模的组合负担，我们设计分层交互模块，将成对表示与多体表示耦合以进行特征聚合与预测，在控制计算与内存的同时保留多体表达能力。在HEST-1k与STImage-1K4M上，MCToGene以7.85%的相对提升超越最优基线。消融实验证实显式高阶、多对多建模是这些增益的来源，可视化表明多细胞交互对生物学上连贯的空间预测至关重要。
英文原文摘要 1367 字符
Spatial transcriptomics (ST) links gene expression to tissue architecture and enables predicting spatial expression from H&E-stained whole-slide images (WSIs). However, existing spot- or slide-level predictors focus on single-spot features or pairwise relations, failing to capture high-order, many-to-many cross-cell interactions. As a result, they miss synergistic and antagonistic effects among multiple neighboring cells. Here, we introduce MCToGene, a scalable and accurate framework that explicitly models multi-cell interactions via many-body attention with hierarchical coupling to predict spatial gene expression. MCToGene employs a many-body attention module to encode high-order, many-to-many cross-cell dependencies, enabling context-aware microenvironment modeling. To mitigate the combinatorial burden of many-body modeling, we design a hierarchical interaction module that couples pairwise and many-body representations for feature aggregation and prediction, preserving many-body expressiveness while controlling computation and memory. On HEST-1k and STImage-1K4M, MCToGene surpasses state-of-the-art baselines with 7.85% relative improvement. Ablations confirm that explicit high-order, many-to-many modeling drives these gains, and visualizations demonstrate that multi-cell interactions are essential for biologically coherent spatial predictions.