德国慕尼黑大学Ali Ertürk课题利用深度学习揭示了全身性癌症转移和治疗性抗体靶标。相关论文于2019年12月12日发表于国际学术期刊《细胞》。
研究开发了一个集成策略，用于自动量化癌症转移和治疗性抗体靶标，称为DeepMACT。首先，研究人员通过将vDISCO方法应用于透明化小鼠的转移成像，将癌细胞的荧光信号增强了100倍以上。其次，研究人员开发了深度学习算法，用于自动量化转移并精确匹配人类专家手工注释。在5种不同的转移性癌症模型（包括乳腺癌、肺癌和胰腺癌，具有明显的器官倾向）中进行基于深度学习的量化，这使研究人员能够系统地在整个小鼠中分析诸如大小、形状、空间分布和哪些转移灶被治疗性单克隆抗体靶向的程度等特征。因此，DeepMACT可以在临床前阶段显著改善抗体有效疗法的发现。
据悉，长期以来，为了更好地了解和治疗癌症转移，需要长期可靠地检测散布的肿瘤细胞以及靶向肿瘤的治疗性抗体在体内的分布。
附：英文原文
Title: Deep Learning Reveals Cancer Metastasis and Therapeutic Antibody Targeting in the Entire Body
Author: Chenchen Pan, Oliver Schoppe, Arnaldo Parra-Damas, Ruiyao Cai, Mihail Ivilinov Todorov, Gabor Gondi, Bettina von Neubeck, Nuray Bürcü-Seidel, Sascha Seidel, Katia Sleiman, Christian Veltkamp, Benjamin Frstera, Hongcheng Mai, Zhouyi Rong, Omelyan Trompak, Alireza Ghasemigharagoz, Madita Alice Reimer, Angel M. Cuesta, Javier Coronel, Irmela Jeremias, Dieter Saur, Amparo Acker-Palmer, Till Acker, Boyan K. Garvalov, Bjoern Menze, Reinhard Zeidler, Ali Ertürk
Issue&Volume: 2019/12/12
Abstract: Reliable detection of disseminated tumor cells and of the biodistribution of tumor-targetingtherapeutic antibodies within the entire body has long been needed to better understandand treat cancer metastasis. Here, we developed an integrated pipeline for automatedquantification of cancer metastases and therapeutic antibody targeting, named DeepMACT.First, we enhanced the fluorescent signal of cancer cells more than 100-fold by applyingthe vDISCO method to image metastasis in transparent mice. Second, we developed deeplearning algorithms for automated quantification of metastases with an accuracy matchinghuman expert manual annotation. Deep learning-based quantification in 5 differentmetastatic cancer models including breast, lung, and pancreatic cancer with distinctorganotropisms allowed us to systematically analyze features such as size, shape,spatial distribution, and the degree to which metastases are targeted by a therapeuticmonoclonal antibody in entire mice. DeepMACT can thus considerably improve the discoveryof effective antibody-based therapeutics at the pre-clinical stage.
DOI: 10.1016/j.cell.2019.11.013
Source: https://www.cell.com/cell/fulltext/S0092-8674(19)31269-3