高等学校化学研究 ›› 2002, Vol. 18 ›› Issue (4): 453-457.
ZHANG Zhuo-yong1, WANG Dan2, LIU Si-dong2, HARRINGTON Peter de B.3, VOORHEES Kent J.4, REES Jon4
ZHANG Zhuo-yong1, WANG Dan2, LIU Si-dong2, HARRINGTON Peter de B.3, VOORHEES Kent J.4, REES Jon4
摘要: The radial basis function networks were applied to bacterial classification based on the matrix-assisted laser desorption/ionization time-of-flight mass spectrometric (MALDI-TOF-MS) data. The classification of bacteria cultured at different time was discussed and the effect of the network parameters on the classification was investigated. The cross-validation method was used to test the trained networks. The correctness of the classification of different bacteria investigated changes in a wide range from 61.5% to 92.8%. Owing to the complexity of biological effects in bacterial growth, the more rigid control of bacterial culture conditions seems to be a critical factor for improving the rate of correctness for bacterial classification.