KSBB Journal

The Korean Society for Biotechnology and Bioengineering (한국생물공학회)
권호 표지

Analysis of Two-Dimensional Fluorescence Spectra in Biotechnological Processes by Artificial Neural Networks I - Classification of Fluorescence Spectra using Self-Organizing Maps -

인공신경망에 의한 생물공정에서 2차원 형광스펙트럼의 분석 I - 자기조직화망에 의한 형광스펙트럼의 분류 -

  • Lee Kum-Il (Department of Industrial Engineering, Chonnam National University, Research Center for Biophotonics) ;
  • Yim Yong-Sik (Department of Industrial Engineering, Chonnam National University, BioProcess Technology Lab.) ;
  • Kim Chun-Kwang (Department of Industrial Engineering, Chonnam National University, BioProcess Technology Lab.) ;
  • Lee Seung-Hyun (Department of Industrial Engineering, Chonnam National University, BioProcess Technology Lab.) ;
  • Chung Sang-Wook (Department of Industrial Engineering, Chonnam National University, Research Center for Biophotonics) ;
  • Rhee Jong Il (Faculty of Applied Chemical Engineering, Chonnam National University, BioProcess Technology Lab.)
  • 이금일 (전남대학교 산업공학과, 바이오광 기반기술개발 사업단) ;
  • 임용식 (전남대학교 물질 생물화공과, 생물공정기술연구실) ;
  • 김춘광 (전남대학교 물질 생물화공과, 생물공정기술연구실) ;
  • 이승현 (전남대학교 물질 생물화공과, 생물공정기술연구실) ;
  • 정상욱 (전남대학교 산업공학과, 바이오광 기반기술개발 사업단) ;
  • 이종일 (전남대학교 응용화학공학부, 생물공정기술연구실)
  • Published : 2005.08.01
Download PDF
⟨ Previous Next ⟩

Abstract

Two-dimensional (2D) spectrofluorometer is often used to monitor various fermentation processes. The change in fluorescence intensities resulting from various combinations of excitation and emission wavelengths is investigated by using a spectra subtraction technique. But it has a limited capacity to classify the entire fluorescence spectra gathered during fermentations and to extract some useful information from the data. This study shows that the self-organizing map (SOM) is a useful and interpretative method for classification of the entire gamut of fluorescence spectral data and selection of some combinations of excitation and emission wavelengths, which have useful fluorometric information. Some results such as normalized weights and variances indicate that the SOM network is capable of interpreting the fermentation processes of S. cerevisiae and recombinant E. coli monitored by a 2D spectrofluorometer.

본 연구는 재조합 대장균과 S.cerevisiae의 발효공정에서 형광스펙트럼 데이터를 수집하였으며, SOM을 이용하여 형광스펙트럼 데이터를 특정 그룹으로 분류하고 발효공정을 분석하고자 하였다. 배출가스 내 이산화탄소농도와 세포농도 같은 공정변수들은 SOM 알고리즘으로부터 얻은 분산 및 정규화된 가중치들과 좋은 연관성을 나타내었다. 전체 스펙트럼 데이터의 분류는 생물공정 모델링을 위한 매우 중요한 단계인데 그 이유는 몇몇 여기파장과 방출파장의 유의한 조합들이 전체영역의 스펙트럼 데이터로부터 추출되기 때문이다. 예를 들면, 본 연구에서 SOM을 이용하여 추출한 98개의 스펙트럼 데이터의 예제들은 부분최소자승법이나 감독신경망 (supervised neural network)을 이용한 공정의 모델링에 사용될 수 있다.

Keywords

References

  1. Sonnleitner, B. (2000), Instrumentation of biotechnological processes, In: Advances in Biochemical Engineering and Biotechnology, Springer, Berlin, 1-64
  2. Harms P., Y. Kostov, G. Rao (2002), Bioprocess monitoring, Curro Opin. Biotechnol. 13, 124-127
  3. Marose S., C. Lindemann, R. Ulber, T. Scheper (1999), Optical sensor systems for bioprocess monitoring, Trends Biotechnol. 17,30-33
  4. Li J. K., E. C. Asali, A. E. Humphrey (1992), Monitoring cell concentration and activity by multiple excitation fluorometry, Biotechnol. Prog. 7,21-27 https://doi.org/10.1021/bp00007a004
  5. Schiigerl K., C. Lindemann, S. Marose, T. Scheper (1998), Twodimensional fluorescence spectroscopy for on-line bioprocess monitoring, Course material for the Bioprocess Engineering Course, Supertar, Island of Brac, Croatia, 27, Sept.-02 Oct
  6. Tartakovsky B., M. Scheintuch, 1. M. Hilmer, T. Scheper (1996), Application of scanning fluorometery for monitoring of a fermentation process, Biotechnol. Prog. 12, 126-131 https://doi.org/10.1021/bp950045h
  7. Mukherjee J., C. Lindermann, T. Scheper (1999), Fluorescence monitoring during cultivation of Enterobacter aerogenes at different oxygen levels, Appl. Microbiol. Biotechnol. 52, 489-494 https://doi.org/10.1007/s002530051550
  8. Skibsted E., C. Lindemann, C. Roca, L. Olsson (2001), On-line bioprocess monitoring with a multi-wavelength fluorescence sensor using multivariate calibration, J. Biotechnol. 88,47-57 https://doi.org/10.1016/S0168-1656(01)00257-7
  9. Marose S., C. Lindemann, 1. Scheper (1998), Two-dimensional fluore¬scence spectroscopy: A new tool for on-line bioprocess monitoring, Biotechnol. Prog. 14,63-74 https://doi.org/10.1021/bp970124o
  10. Lindemann C., S. Marose, RO. Nielson, T. Scheper, (1998), 2-Dimensional fluorescence spectroscopy for on-line bioprocess monitoring, Sens. Actual. B. 51, 271-277
  11. Low L. D., S. Kalelkar, E. R. Dow (2004), Self-organizing maps for the analysis ofNMR spectra, BioSilico. 2, 157-163
  12. Kolehmainen M., P. Ronkko, O. Raatikainen (2003), Monitoring of yeast fennentation by ion mobility spectrometry measurement and data visualization with Self-Organizing Maps, Anal. Chim. Acta. 484, 93-100 https://doi.org/10.1016/S0003-2670(03)00307-6
  13. Debeljak Z., M. Strapac, M. Medic-Sanc (2001), Application of self-organizing maps for the classification of chromatographic systems and prediction of values of chromatographic quantities, J. Chromatog. A. 925,31-40 https://doi.org/10.1016/S0021-9673(01)01010-X
  14. Yang, H., I. R. Lewis, P. R. Griffiths (1999), Raman spectrometry and neural networks for the classification of wood type. 2. Kohonen self-organizing maps, Spectrochim. Acta. Part A. 55, 2783-2791 https://doi.org/10.1016/S1386-1425(99)00088-8
  15. Chung, S. Y., K. H. Seo, J. I. Rhee (2005), Influence of culture conditions on the production of extra-cellular 5-aminolevulinic acid (ALA) by recombinant E. coli, Process Biochem. 40, 385-394 https://doi.org/10.1016/j.procbio.2004.01.024
  16. Shimizu, H., K. Araki, S. Shioya, K. I. Suga (1991), Optimal production of glutathione by controlling the specific growth rate of yeast in fed-batch culture, Biotechnol. Bioeng. 38, 196-205 https://doi.org/10.1002/bit.260380212
  17. Tietze, F. (1969), Enzymic method for quantitative detennination of nanogram amount of total and oxidized glutathione, Anal. Biochem. 27, 502-522 https://doi.org/10.1016/0003-2697(69)90064-5
  18. Teshima, N., H. Katsumate, M. Kurihara, T. Sakai, T. Kawashima (1999), Flow-injection detennination of copper( II) based on its catalysis on the redox reaction of cysteine with iron(III) in the presence of 1,100phenanthroline, Talanta 50, 41-47 https://doi.org/10.1016/S0039-9140(99)00108-3
  19. Kohonen, T. (1998), The self-organizing map, Neurocomputing 21, 1-6 https://doi.org/10.1016/S0925-2312(98)00030-7
  20. Vesanto, J. (1999), SOM-based data visualization methods, Intell. Data Anal. 3,111-126 https://doi.org/10.1016/S1088-467X(99)00013-X
  21. Kohonen, T. (2001), Self-Organizing Maps, 3rd ed, Springer, Berlin, Gennany
  22. Zupan, J., J. Gasteiger (1999), Neural Networks in Chemistry and Drug Design, 2nd ed, Wiley- VCH, Weinheim, USA