发表机构
Kyushu University; The University of Osaka; National Cancer Center（九州大学; 大阪大学; 国立癌症研究中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对传统空间基因表达预测目标与差异表达基因发现不匹配的问题，提出基于图像的差异表达排序（IDER）方法，通过可微分目标对齐差异统计量，在公开数据集上提升了DEG排序一致性和通路富集重叠。
AI 中文摘要
从组织学图像预测空间基因表达可将空间转录组学（ST）扩展到仅含图像的队列，但传统的基于组织学的ST预测主要按每个基因的空间谱重建进行训练和评估。这一目标与ST的一个关键下游用途——差异表达基因（DEG）发现——不一致，在该用途中，基因根据组间表达差异的证据，针对生物学或形态学定义的对比进行排序。我们提出了基于图像的差异表达排序（IDER），它询问预测的表达谱是否保留了从测量谱中获得的对比特异性排序基因列表。IDER比较由差异表达统计量诱导的基因排序，而非原始表达幅度或每个基因的空间相关性。我们进一步引入了一个可微分的IDER目标，该目标跨基因对齐这些统计量，并且可以在没有预定义生物学组标签的情况下，使用形态学衍生的代理对比进行训练。在公开ST数据集上的实验表明，与传统的重建目标相比，包括形态学衍生和病理学家注释的组织区域评估，IDER在DEG排序一致性和通路富集重叠方面均有改进。
英文摘要
Predicting spatial gene expression from histology images could scale spatial transcriptomics (ST) to image-only cohorts, but conventional histology-based ST prediction is trained and evaluated mainly by per-gene spatial-profile reconstruction. This objective is misaligned with a key downstream use of ST: differentially expressed gene (DEG) discovery, where genes are ranked for a biological or morphology-defined contrast by evidence of between-group expression differences. We formulate image-based differential expression ranking (IDER), which asks whether predicted expression profiles preserve the contrast-specific ranked gene list obtained from measured profiles. IDER compares gene rankings induced by differential-expression statistics, rather than raw expression magnitudes or per-gene spatial correlations. We further introduce a differentiable IDER objective that aligns these statistics across genes and can be trained with morphology-derived proxy contrasts without predefined biological group labels. Experiments on public ST datasets show improved DEG-ranking agreement and pathway-enrichment overlap over conventional reconstruction objectives, including morphology-derived and pathologist-annotated tissue-region evaluations.
CommentsAccepted to NeurIPS 2026
