A novel method based on nonparametric regression with a Gaussian kernel algorithm identifies the critical components in CHO media and feed optimization

  • Mao Zou
  • Zi-Wei Zhou
  • Li Fan
  • Wei-Jian Zhang
  • Liang Zhao
  • Xu-Ping Liu
  • Hai-Bin Wang
  • Wen-Song TanEmail author
Fermentation, Cell Culture and Bioengineering - Original Paper


As the composition of animal cell culture medium becomes more complex, the identification of key variables is important for simplifying and guiding the subsequent medium optimization. However, the traditional experimental design methods are impractical and limited in their ability to explore such large feature spaces. Therefore, in this work, we developed a NRGK (nonparametric regression with Gaussian kernel) method, which aimed to identify the critical components that affect product titres during the development of cell culture media. With this nonparametric model, we successfully identified the important components that were neglected by the conventional PLS (partial least squares regression) method. The superiority of the NRGK method was further verified by ANOVA (analysis of variance). Additionally, it was proven that the selection accuracy was increased with the NRGK method because of its ability to model both the nonlinear and linear relationships between the medium components and titres. The application of this NRGK method provides new perspectives for the more precise identification of the critical components that further enable the optimization of media in a shorter timeframe.


Variable selection Nonparametric regression with Gaussian kernel Chinese hamster ovary cells Medium optimization 



This work was supported by the Fundamental Research Funds for the Central Universities (No. 22221818014).


  1. 1.
    Aggarwal SR (2014) What’s fueling the biotech engine—2012 to 2013. Nat Biotechnol 32(1):32. CrossRefPubMedGoogle Scholar
  2. 2.
    Berry B, Moretto J, Matthews T, Smelko J, Wiltberger K (2015) Cross-scale predictive modeling of CHO cell culture growth and metabolites using Raman spectroscopy and multivariate analysis. Biotechnol Prog 31(2):566–577. CrossRefPubMedGoogle Scholar
  3. 3.
    Bothinah AS (2014) Application of dynamic partial least squares to complex processes. Doctoral dissertation, Newcastle UniversityGoogle Scholar
  4. 4.
    Carrascal LM, Galván I, Gordo O (2009) Partial least squares regression as an alternative to current regression methods used in ecology. Oikos 118(5):681–690. CrossRefGoogle Scholar
  5. 5.
    Cheng JL, Zheng M, Lou JQ (2012) Comparison of several common optimal experimental design methods. Res Explor Lab 7:7–11Google Scholar
  6. 6.
    Cleveland WS, Devlin SJ (1988) Locally weighted regression: an approach to regression analysis by local fitting. Publ Am Stat Assoc 83(403):596–610. CrossRefGoogle Scholar
  7. 7.
    Dietmair S, Hodson MP, Quek LE, Timmins NE, Chrysanthopoulos P, Jacob SS, Gray P, Nielsen LK (2012) Metabolite profiling of CHO cells with different growth characteristics. Biotechnol Bioeng 109(6):1404–1414CrossRefGoogle Scholar
  8. 8.
    Fang KT, Lin DK, Liu MQ (2013) Optimal mixed-level supersaturated design. Metrika 58(3):279–291. CrossRefGoogle Scholar
  9. 9.
    GregoriaMateos-Aparicio GM (2011) Partial least squares (PLS) methods: origins, evolution, and application to social sciences. Commun Stat 40(13):2305–2317. CrossRefGoogle Scholar
  10. 10.
    Hemmateenejad B, Baumann K (2018) Screening for linearly and nonlinearly related variables in predictive cheminformatic models: screening for linearly and nonlinearly related variables. J Chemom 32(4):e3009CrossRefGoogle Scholar
  11. 11.
    Jiang Z, Droms K, Geng Z, Casnocha S, Xiao Z, Gorfien S (2012) Fed-batch cell culture process optimization. BioProcess Int 10(3):40–45Google Scholar
  12. 12.
    Kuhn M, Johnson K (2013) Applied predictive modeling, vol 26. Springer, New YorkCrossRefGoogle Scholar
  13. 13.
    Li L, Zhang X, Ning Z, Mayne J, Moore JI, Butcher J, Chiang CK, Mack DR, Stintzi A, Figeys D (2017) Evaluating in vitro culture medium of gut microbiome with orthogonal experimental design and metaproteomics approach. J Proteome Res 17(1):154–163. CrossRefPubMedGoogle Scholar
  14. 14.
    Liang W, Liu X, Tan W (2015) Optimization of suspended serum-free medium for BHK-21 cells by combining mixture with response surface analysis. Biotechnol Bull 31(9):70–78Google Scholar
  15. 15.
    Matasci M, Hacker DL, Baldi L, Wurm FM (2008) Recombinant therapeutic protein production in cultivated mammalian cells: current status and future prospects. Drug Discov Today Technol 5(2):e37–e42. CrossRefPubMedGoogle Scholar
  16. 16.
    Mehmood T, Liland KH, Snipen L, Sæbø S (2012) A review of variable selection methods in partial least squares regression. Chemom Intell Lab Syst 118:62–69. CrossRefGoogle Scholar
  17. 17.
    Michael B (2005) Animal cell cultures: recent achievements and perspectives in the production of biopharmaceuticals. Appl Microbiol Biotechnol 68(3):283–291. CrossRefGoogle Scholar
  18. 18.
    Puente-Massaguer E, Badiella L, Gutiérrez-Granados S, Cervera L, Gòdia F (2019) A statistical approach to improve compound screening in cell culture media. Eng Life Sci 19(4):315–327. CrossRefGoogle Scholar
  19. 19.
    Rouiller Y, Périlleux A, Collet N, Jordan M, Stettler M, Broly H (2013) A high-throughput media design approach for high performance mammalian fed-batch cultures. Mabs 5(3):501–511. CrossRefPubMedPubMedCentralGoogle Scholar
  20. 20.
    Selvarasu S, Kim DY, Karimi IA, Lee DY (2010) Combined data preprocessing and multivariate statistical analysis characterizes fed-batch culture of mouse hybridoma cells for rational medium design. J Biotechnol 150(1):94–100. CrossRefPubMedGoogle Scholar
  21. 21.
    Shi C, Tang B (2019) Supersaturated designs robust to two-factor interactions. J Stat Plan Inference 200:119–128. CrossRefGoogle Scholar
  22. 22.
    Tsang VL, Wang AX, Yusuf-Makagiansar H, Ryll T (2014) Development of a scale down cell culture model using multivariate analysis as a qualification tool. Biotechnol Prog 30(1):152–160. CrossRefPubMedGoogle Scholar
  23. 23.
    Xing Z, Li Z, Chow V, Lee SS (2010) Identifying inhibitory threshold values of repressing metabolites in CHO cell culture using multivariate analysis methods. Biotechnol Prog 24(3):675–683. CrossRefGoogle Scholar
  24. 24.
    You W, Yang Z, Ji G (2014) PLS-based recursive feature elimination for high-dimensional small sample. Knowledge-Based Syst 55:15–28CrossRefGoogle Scholar
  25. 25.
    Zambom AZ (2012) Hypothesis testing and variable selection in nonparametric regression. Doctoral dissertation, The Pennsylvania State UniversityGoogle Scholar
  26. 26.
    Zhang CQ (2005) Research on mixture experimental designs. J Guangzhou Univ 4(5):381–385Google Scholar
  27. 27.
    Zhang H, Wang H, Liu M, Zhang T, Zhang J, Wang X, Xiang W (2013) Rational development of a serum-free medium and fed-batch process for a GS-CHO cell line expressing recombinant antibody. Cytotechnology 65(3):363–378. CrossRefPubMedGoogle Scholar

Copyright information

© Society for Industrial Microbiology and Biotechnology 2019

Authors and Affiliations

  1. 1.State Key Laboratory of Bioreactor EngineeringEast China University of Science and TechnologyShanghaiChina
  2. 2.Shanghai Bioengine Sci-Tech Co. LtdShanghaiChina
  3. 3.Hisun Pharmaceutical (Hangzhou) Co. LtdHangzhouChina

Personalised recommendations