利用Nimbus对多路成像数据中的细胞表达进行自动分类，这一成果由斯坦福大学Michael Angelo小组经过不懈努力而取得。相关论文于2025年10月8日发表在《自然—方法学》杂志上。

该课题组研究人员构建了Pan-Multiplex （Pan-M）数据集，包含197在15种不同的细胞类型中有数百万个不同的标记表达注释。研究小组以Pan-M为主题创建了Nimbthem，这是一个深度学习模型，用于从多路图像数据中预测标记的积极性。Nimbthem是一种预先训练的模型，它对基础图像进行主题化，将个体细胞的标记表达分为阳性或阴性，这些标记表达来自不同的细胞类型，来自不同的组织，在不同的显微镜平台上获得，无需任何再训练。

课题组人员证明Nimbthem预测捕获了Pan-M中存在的全部标记多样性的潜在染色模式，并且Nimbthem匹配或超过了之前需要在每个数据集上重新训练的方法的准确性。然后，该课题组人员展示了如何将Nimbthem预测与下游聚类算法集成在一起，以自动识别图像数据中的细胞亚型。课题组已经开放了Nimbthem和Pan-M，以便社区使用https://github.com/angelolab/Nimbthem-Inference。

据介绍，多路成像提供了一种强大的方法来表征健康和疾病组织的空间地形。为了分析这些数据，必须列举每个细胞中存在的特定标记组合，以实现准确的表型，这一过程通常依赖于无监督的克隆。

附：英文原文

Title: Automated classification of cellular expression in multiplexed imaging data with Nimbus

Author: Rumberger, Josef Lorenz, Greenwald, Noah F., Ranek, Jolene S., Boonrat, Potchara, Walker, Cameron, Franzen, Jannik, Varra, Sricharan Reddy, Kong, Alex, Sowers, Cameron, Liu, Candace C., Averbukh, Inna, Piyadasa, Hadeesha, Vanguri, Rami, Nederlof, Iris, Wang, Xuefei Julie, Van Valen, David, Kok, Marleen, Bendall, Sean C., Hollmann, Travis J., Kainmueller, Dagmar, Angelo, Michael

Issue&Volume: 2025-10-08

Abstract: Multiplexed imaging offers a powerful approach to characterize the spatial topography of tissues in both health and disease. To analyze such data, the specific combination of markers that are present in each cell must be enumerated to enable accurate phenotyping, a process that often relies on unsupervised clustering. We constructed the Pan-Multiplex (Pan-M) dataset containing 197million distinct annotations of marker expression across 15 different cell types. We used Pan-M to create Nimbus, a deep learning model to predict marker positivity from multiplexed image data. Nimbus is a pretrained model that uses the underlying images to classify marker expression of individual cells as positive or negative across distinct cell types, from different tissues, acquired using different microscope platforms, without requiring any retraining. We demonstrate that Nimbus predictions capture the underlying staining patterns of the full diversity of markers present in Pan-M, and that Nimbus matches or exceeds the accuracy of previous approaches that must be retrained on each dataset. We then show how Nimbus predictions can be integrated with downstream clustering algorithms to robustly identify cell subtypes in image data. We have open-sourced Nimbus and Pan-M to enable community use at https://github.com/angelolab/Nimbus-Inference.

DOI: 10.1038/s41592-025-02826-9

Source: https://www.nature.com/articles/s41592-025-02826-9