Department of Computer Science and Engineering, University of Minnesota, Minneapolis, MN 55455, United States.
Machine Learning Department, NEC Laboratories America, Princeton, NJ 08540, United States.
Bioinformatics. 2024 Sep 1;40(Suppl 2):ii111-ii119. doi: 10.1093/bioinformatics/btae383.
Spatial transcriptomics technologies, which generate a spatial map of gene activity, can deepen the understanding of tissue architecture and its molecular underpinnings in health and disease. However, the high cost makes these technologies difficult to use in practice. Histological images co-registered with targeted tissues are more affordable and routinely generated in many research and clinical studies. Hence, predicting spatial gene expression from the morphological clues embedded in tissue histological images provides a scalable alternative approach to decoding tissue complexity.
Here, we present a graph neural network based framework to predict the spatial expression of highly expressed genes from tissue histological images. Extensive experiments on two separate breast cancer data cohorts demonstrate that our method improves the prediction performance compared to the state-of-the-art, and that our model can be used to better delineate spatial domains of biological interest.
空间转录组学技术可生成基因活性的空间图谱，从而加深对健康和疾病组织架构及其分子基础的理解。然而，这些技术的高成本使其难以在实际中应用。与靶向组织共注册的组织学图像更经济实惠，并且在许多研究和临床研究中经常生成。因此，从组织学图像中嵌入的形态学线索预测空间基因表达为解码组织复杂性提供了一种可扩展的替代方法。
本文提出了一种基于图神经网络的框架，用于从组织学图像预测高表达基因的空间表达。在两个独立的乳腺癌数据集上的广泛实验表明，与最先进的方法相比，我们的方法提高了预测性能，并且我们的模型可用于更好地描绘生物感兴趣的空间域。
