Abe H, Kumazawa S, Taji T, Sasaki S
Biomed Mass Spectrom. 1976 Aug;3(4):151-4. doi: 10.1002/bms.1200030402.
Correlations between mass spectra and pharmacological activities were surveyed by means of computerized learning machine and cluster analysis. The principal component analysis and the nonlinear mapping techniques were used for the feature selection of the data set.
通过计算机学习机和聚类分析研究了质谱与药理活性之间的相关性。主成分分析和非线性映射技术用于数据集的特征选择。