Research Center for Advanced Measurement and Characterization, National Institute for Materials Science, Tsukuba, Ibaraki, Japan.
Research and Services Division of Materials Data and Integrated System, National Institute for Materials Science, Tsukuba, Ibaraki, Japan.
Nano Lett. 2021 Feb 10;21(3):1538-1545. doi: 10.1021/acs.nanolett.1c00003. Epub 2021 Jan 21.
Cellular mechanical properties are potential cancer biomarkers used for objective cytology to replace the current subjective method relying on cytomorphology. However, heterogeneity among intra/intercellular mechanics and the interplay between cytoskeletal prestress and elastic modulus obscured the difference detectable between malignant and benign cells. In this work, we collected high density nanoscale prestress and elastic modulus data from a single cell by AFM indentation to generate a cellular mechanome. Such high dimensional mechanome data was used to train a malignancy classifier through machine learning. The classifier was tested on 340 single cells of various origins, malignancy, and degrees of similarity in morphology and elastic modulus. The classifier showed instrument-independent robustness and classification accuracy of 89% with an AUC-ROC value of 93%. A signal-to-noise ratio 8 times that of the human-cytologist-based morphological method was also demonstrated, in differentiating precancerous hyperplasia cells from normal cells derived from the same lung cancer patient.
细胞力学特性是潜在的癌症生物标志物，可用于客观细胞学，以替代目前依赖于细胞形态学的主观方法。然而，细胞内/间力学的异质性以及细胞骨架预应力和弹性模量之间的相互作用，掩盖了恶性和良性细胞之间可检测到的差异。在这项工作中，我们通过原子力显微镜压痕从单个细胞中收集高密度纳米级预应力和弹性模量数据，以生成细胞力学组。通过机器学习，使用这种高维力学组数据来训练恶性肿瘤分类器。该分类器在 340 个具有不同起源、恶性程度和形态及弹性模量相似性的单细胞上进行了测试。该分类器具有仪器独立性，其分类准确率为 89%，ROC-AUC 值为 93%。与基于人类细胞学家的形态学方法相比，该分类器还具有 8 倍的信噪比，可用于区分来自同一肺癌患者的正常细胞和癌前增生细胞。
