微泡
支持向量机
外体
主成分分析
人工智能
原子力显微镜
粒子(生态学)
机器学习
表征(材料科学)
特征向量
寄主(生物学)
计算机科学
生物系统
模式识别(心理学)
纳米技术
化学
材料科学
生物
小RNA
生物化学
基因
生态学
作者
Kazuki Ito,Yuta Ogawa,Keiji Yokota,Shigenobu Matsumura,Tamiko Minamisawa,Kazuyoshi Suga,Kiyotaka Shiba,Yasuo Kimura,Ayumi Hirano‐Iwata,Yuzuru Takamura,T. Ogino
标识
DOI:10.1021/acs.jpcb.8b01646
摘要
Exosomes are extracellular nanovesicles released from any cells and found in any body fluid. Because exosomes exhibit information of their host cells (secreting cells), their analysis is expected to be a powerful tool for early diagnosis of cancers. To predict the host cells, we extracted multidimensional feature data about size, shape, and deformation of exosomes immobilized on solid surfaces by atomic force microscopy (AFM). The key idea is combination of support vector machine (SVM) learning for individual exosome particles and their interpretation by principal component analysis (PCA). We observed exosomes derived from three different cancer cells on SiO2/Si, 3-aminopropyltriethoxysilane-modified-SiO2/Si, and TiO2 substrates by AFM. Then, 14-dimensional feature vectors were extracted from AFM particle data, and classifiers were trained in 14-dimensional space. The prediction accuracy for host cells of test AFM particles was examined by the cross-validation test. As a result, we obtained prediction of exosome host cells with the best accuracy of 85.2% for two-class SVM learning and 82.6% for three-class one. By PCA of the particle classifiers, we concluded that the main factors for prediction accuracy and its strong dependence on substrates are incremental decrease in the PCA-defined aspect ratio of the particles with their volume.
科研通智能强力驱动
Strongly Powered by AbleSci AI