对从大量基因表达中解卷积细胞组成的方法进行社区评估。
Community assessment of methods to deconvolve cellular composition from bulk gene expression.
发表日期：2024 Aug 27
作者：
Brian S White, Aurélien de Reyniès, Aaron M Newman, Joshua J Waterfall, Andrew Lamb, Florent Petitprez, Yating Lin, Rongshan Yu, Martin E Guerrero-Gimenez, Sergii Domanskyi, Gianni Monaco, Verena Chung, Jineta Banerjee, Daniel Derrick, Alberto Valdeolivas, Haojun Li, Xu Xiao, Shun Wang, Frank Zheng, Wenxian Yang, Carlos A Catania, Benjamin J Lang, Thomas J Bertus, Carlo Piermarocchi, Francesca P Caruso, Michele Ceccarelli, Thomas Yu, Xindi Guo, Julie Bletz, John Coller, Holden Maecker, Caroline Duault, Vida Shokoohi, Shailja Patel, Joanna E Liliental, Stockard Simon, , Julio Saez-Rodriguez, Laura M Heiser, Justin Guinney, Andrew J Gentles
来源：
BIOMEDICINE & PHARMACOTHERAPY
摘要：
我们通过社区范围的 DREAM Challenge 评估反卷积方法，该方法根据肿瘤样本的大量表达推断免疫浸润水平。我们使用混合癌症和健康免疫细胞的体外和计算机转录谱评估了 6 种已发表的方法和 22 种社区贡献的方法。一些已发表的方法可以很好地预测大多数细胞类型，尽管它们要么没有经过训练来评估所有功能性 CD8 T 细胞状态，要么准确度较低。一些社区贡献的方法解决了这一差距，包括基于深度学习的方法，其强大的性能确立了该范例对反卷积的适用性。尽管解卷积方法主要使用来自健康组织的免疫细胞来开发，但它可以很好地预测肿瘤来源的免疫细胞的水平。我们混合和纯化的转录谱将成为开发反卷积方法的宝贵资源，包括应对我们在不同方法中观察到的常见挑战，例如功能性 CD4 T 细胞状态的敏感识别。© 2024。作者。
We evaluate deconvolution methods, which infer levels of immune infiltration from bulk expression of tumor samples, through a community-wide DREAM Challenge. We assess six published and 22 community-contributed methods using in vitro and in silico transcriptional profiles of admixed cancer and healthy immune cells. Several published methods predict most cell types well, though they either were not trained to evaluate all functional CD8+ T cell states or do so with low accuracy. Several community-contributed methods address this gap, including a deep learning-based approach, whose strong performance establishes the applicability of this paradigm to deconvolution. Despite being developed largely using immune cells from healthy tissues, deconvolution methods predict levels of tumor-derived immune cells well. Our admixed and purified transcriptional profiles will be a valuable resource for developing deconvolution methods, including in response to common challenges we observe across methods, such as sensitive identification of functional CD4+ T cell states.© 2024. The Author(s).