Insights into cell classification based on combination of multiple cellular mechanical phenotypes by using machine learning algorithm. (April 2022)

• Record Type: Journal Article
• Authors: Tian, Yanling; Lin, Wangjiang; Qu, Kaige; Wang, Zuobin; Zhu, Xinyao
• Is Part Of: Journal of the mechanical behavior of biomedical materials. Volume 128(2022)
• Publication Date: 2022-04
• Subjects: Cellular elastic property (CEP) -- Cellular mechanical phenotype (CMP) -- Work of adhesion (WoA) -- Adhesiveness -- Cellular membrane tension (CMT) -- Cellular classification; Biomedical materials -- Periodicals; Biomedical materials -- Mechanical properties -- Periodicals; Biomedical materials; Biomedical materials -- Mechanical properties; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.jmbbm.2022.105097
• Languages: English
• ISSNs: 1751-6161

Abstract

Abstract: Although cellular elastic property (CEP, also known as cellular elastic modulus) has been frequently reported as a biomarker to distinguish some cancerous cells from their benign counterparts, it cannot be adopted as a universal hallmark to be applied to every kind cell. In the present study, we report that insignificant difference is observed between normal gastric cell and its cancer counterpart which is one of the common human malignancies, in terms of CEP statistical distribution. In this regard, we propose multiple cellular mechanical phenotypes (CMPs) to differentiate the above two cell types, which is realized by machine learning algorithm (MLA). The results show that the cellular classification effect proves better with more CMPs adopted, regardless of the exact MLA employed. Moreover, the MLA-based method remains effective if we add two more cell lines to the above two cell categories. Our study indicates that MLA-based cellular classification can potentially serve as an efficient and objective means to assist or even validate cancer prognostics.