哈卡特
细胞
计算机科学
脂质体
电池类型
癌细胞
人工智能
材料科学
生物系统
细胞培养
纳米技术
化学
生物信息学
生物
癌症
脂类学
生物化学
遗传学
作者
Joanna Filippi,Davide Di Giuseppe,Paola Casti,Arianna Mencattini,Gianni Antonelli,Michele D'Orazio,Francesca Corsi,D. Della-Morte Canosci,Lina Ghibelli,Christian Witte,Corrado Di Natale,Steven L. Neale,Eugenio Martinelli
标识
DOI:10.1016/j.snb.2022.132200
摘要
Cell responses to varying electric fields can reveal insights on cell biology with important implications for pharmaceutical and basic research. In this work, we exploit spectral information content in Opto-Electronic Tweezers (OET) systems through machine learning for label-free characterization of cell dielectric properties aimed at cell classification and drug response evaluation. A customized Polymethyl-methacrylate (PMMA) chip with ITO substrates and an a-Si layer was designed for OET-based manipulation of cells and integrated with an inverted microscope. We obtained OET cell signatures as spectra responses of kinematic and dynamic descriptors, which are the result of time-lapse measurements at increasing frequencies of the OET. Machine learning algorithms enable automatic selection and characterization of the information content present in the OET signature so derived. Experiments are performed on three biological case studies, involving 1) the discrimination of cell types among U937 human leukemia cells, PC-3 human prostate cancer cells and HaCaT human immortalized keratinocytes; 2) the evaluation of the effects of the chemotherapeutic agent etoposide on U937 cells at different concentrations; and 3) the evaluation of the effects of different exposure times of etoposide on U937 cells. The obtained results demonstrate that multiple levels of dielectric information can be extracted via OET cell signatures and clearly pose OET as a promising tool for cell discrimination and drug response evaluation.
科研通智能强力驱动
Strongly Powered by AbleSci AI