当前位置: X-MOL 学术Nat. Biomed. Eng. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Integrating spatial gene expression and breast tumour morphology via deep learning.
Nature Biomedical Engineering ( IF 28.1 ) Pub Date : 2020-06-22 , DOI: 10.1038/s41551-020-0578-x
Bryan He 1 , Ludvig Bergenstråhle 2 , Linnea Stenbeck 2 , Abubakar Abid 3 , Alma Andersson 2 , Åke Borg 4 , Jonas Maaskola 2 , Joakim Lundeberg 2 , James Zou 1, 3, 5, 6
Affiliation  

Spatial transcriptomics allows for the measurement of RNA abundance at a high spatial resolution, making it possible to systematically link the morphology of cellular neighbourhoods and spatially localized gene expression. Here, we report the development of a deep learning algorithm for the prediction of local gene expression from haematoxylin-and-eosin-stained histopathology images using a new dataset of 30,612 spatially resolved gene expression data matched to histopathology images from 23 patients with breast cancer. We identified over 100 genes, including known breast cancer biomarkers of intratumoral heterogeneity and the co-localization of tumour growth and immune activation, the expression of which can be predicted from the histopathology images at a resolution of 100 µm. We also show that the algorithm generalizes well to The Cancer Genome Atlas and to other breast cancer gene expression datasets without the need for re-training. Predicting the spatially resolved transcriptome of a tissue directly from tissue images may enable image-based screening for molecular biomarkers with spatial variation.



中文翻译:

通过深度学习整合空间基因表达和乳腺肿瘤形态。

空间转录组学允许以高空间分辨率测量RNA丰度,从而有可能系统地联系细胞邻域的形态和空间定位的基因表达。在这里,我们报告了一种深度学习算法的开发,该算法使用苏木精和曙红染色的组织病理学图像预测新的局部基因表达,并使用新的30,612个空间分辨的基因表达数据集与来自23例乳腺癌患者的组织病理学图像进行匹配。我们鉴定了100多个基因,包括已知的肿瘤内异质性以及肿瘤生长和免疫激活共定位的乳腺癌生物标志物,可以从组织病理学图像中以100 µm的分辨率预测其表达。我们还表明,该算法可以很好地推广到《癌症基因组图谱》和其他乳腺癌基因表达数据集,而无需重新训练。直接从组织图像预测组织的空间分辨的转录组可能使基于图像的具有空间变化的分子生物标记物筛选成为可能。

更新日期:2020-06-23
down
wechat
bug