RAPID IDENTIFICATION OF STREPTOMYCETES BY ARTIFICIAL NEURAL-NETWORK ANALYSIS OF PYROLYSIS MASS-SPECTRA

被引：18

作者：

CHUN, J ^{[1
]}

ATALAN, E ^{[1
]}

KIM, SB ^{[1
]}

KIM, HJ ^{[1
]}

HAMID, ME ^{[1
]}

TRUJILLO, ME ^{[1
]}

MAGEE, JG ^{[1
]}

MANFIO, GP ^{[1
]}

WARD, AC ^{[1
]}

GOODFELLOW, M ^{[1
]}

机构：

[1] REG PUBL HLTH LAB,NEWCASTLE TYNE,ENGLAND

来源：

FEMS MICROBIOLOGY LETTERS | 1993年 / 114卷 / 01期

关键词：

PYROLYSIS MASS SPECTROMETRY; ARTIFICIAL NEURAL NETWORK; IDENTIFICATION; ACTINOMYCETES;

D O I：

10.1016/0378-1097(93)90151-Q

中图分类号：

Q93 [微生物学];

学科分类号：

071005 ; 100705 ;

摘要：

An artificial neural network was trained to distinguish between three putatively novel species of Streptomyces using normalised, scaled pyrolysis mass spectra from three representative strains of each of the taxa, each sampled in triplicate. Once trained, the artificial neural network was challenged with spectral data from the original organisms, the 'training set', from additional members of the putative novel taxa and from over a hundred strains representing six other actinomycete genera. All of the streptomycetes were correctly identified but many of the other actinomycetes were mis-identified. A modified network topology was developed to recognise the mass spectral patterns of the non-streptomycete strains. The resultant neural network correctly identified the streptomycetes, whereas all of the remaining actinomycetes were recognised as unknown organisms. The improved artificial neural network provides a rapid, reliable and cost-effective method of identifying members of the three target streptomycete taxa.

引用

页码：115 / 119

页数：5

共 14 条

[1]

ARIES RE, 1986, J ANAL APPL PYROL, V9, P91

[2]

CHUN J, 1993, FEMS MICROBIOL LETT, V107, P321

[3]

Freeman J. A., 1991, NEURAL NETWORKS ALGO

[4]

FREEMAN R, 1993, IN PRESS J MED MICRO