Decision Tree-PLS (DT-PLS) algorithm for the development of process: Specific local prediction models.
QbD
cell culture process
decision trees
local predictive models
partial least squares regression
Journal
Biotechnology progress
ISSN: 1520-6033
Titre abrégé: Biotechnol Prog
Pays: United States
ID NLM: 8506292
Informations de publication
Date de publication:
07 2019
07 2019
Historique:
received:
10
11
2018
revised:
15
03
2019
accepted:
25
03
2019
pubmed:
11
4
2019
medline:
2
6
2020
entrez:
11
4
2019
Statut:
ppublish
Résumé
This work presents a novel multivariate statistical algorithm, Decision Tree-PLS (DT-PLS), to improve the prediction and understanding of dynamic processes based on local partial least square regression (PLSR) models for characteristic process groups defined based on Decision Tree (DT) analysis. The DT-PLS algorithm is successfully applied to two different cell culture data sets, one obtained from bioreactors of 3.5 L lab scale and the other obtained from the 15 ml ambr microbioreactor system. Substantial improvement in the predictive capabilities of the model can be achieved based on the localization compared to the classical PLSR approach, which is implemented in the commercially available packages. Additionally, the differences in the model parameters of the local models suggest that the governing process variables vary for the different process regimes indicating the different states of the cell under different process conditions.
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
e2818Informations de copyright
© 2019 American Institute of Chemical Engineers.
Références
FDA. Guidance for Industry PAT: A Framework for Innovative Pharmaceutical Development, Manufacturing, and Quality Assurance. FDA Off Doc. 2004;16. http://www.fda.gov/CDER/guidance/6419fnl.pdf
EMA. Guideline on process validation for the manufacture of biotechnology-derived active substances and data to be provided in the regulatory submission. 2016:44. EMA/CHMP/BWP/187338/2014.
Kroll P, Hofer A, Ulonska S, Kager J, Herwig C. Model-based methods in the biopharmaceutical process lifecycle. Pharm Res. 2017;34(12):2596-2613. https://doi.org/10.1007/s11095-017-2308-y.
Mandenius CF, Gustavsson R. Mini-review: soft sensors as means for PAT in the manufacture of bio-therapeutics. J Chem Technol Biotechnol. 2015;90(2):215-227. https://doi.org/10.1002/jctb.4477.
Glassey J, Gernaey KV, Clemens C, et al. Process analytical technology (PAT) for biopharmaceuticals. Biotechnol J. 2011;6(4):369-377. https://doi.org/10.1002/biot.201000356.
Kirdar AO, Green KD, Rathore AS. Application of multivariate data analysis for identification and successful resolution of a root cause for a bioprocessing application. Biotechnol Prog. 2008;24(3):720-726. https://doi.org/10.1021/bp0704384.
Mercier SM, Diepenbroek B, Dalm MCF, Wijffels RH, Streefland M. Multivariate data analysis as a PAT tool for early bioprocess development data. J Biotechnol. 2013;167(3):262-270. https://doi.org/10.1016/j.jbiotec.2013.07.006.
Mercier SM, Diepenbroek B, Wijffels RH, Streefland M. Multivariate PAT solutions for biopharmaceutical cultivation: current progress and limitations. Trends Biotechnol. 2014;32(6):329-336. https://doi.org/10.1016/j.tibtech.2014.03.008.
Mercier SM, Rouel PM, Lebrun P, Diepenbroek B, Wijffels RH, Streefland M. Process analytical technology tools for perfusion cell culture. Eng Life Sci. 2016;16(1):25-35. https://doi.org/10.1002/elsc.201500035.
Kirdar AO, Conner JS, Baclaski J, Rathore AS. Application of multivariate analysis toward biotech processes: case study of a cell-culture unit operation. Biotechnol Prog. 2007;23(1):61-67. https://doi.org/10.1021/bp060377u.
Kourti T. Process analytical technology beyond real-time analyzers: the role of multivariate analysis. Crit Rev Anal Chem. 2006;36(3-4):257-278. https://doi.org/10.1080/10408340600969957.
Rathore AS, Bhushan N, Hadpe S. Chemometrics applications in biotech processes: a review. Biotechnol Prog. 2011;27(2):307-315. https://doi.org/10.1002/btpr.561.
Abdi H, Williams LJ. Principal component analysis. Wiley Interdiscip Rev Comput Stat. 2010;2(4):433-459. https://doi.org/10.1002/wics.101.
Tie JS. SIMPLS: an alternative approach squares regression to partial least. Chemometr Intell Lab Syst. 1993;18:251-263. https://doi.org/10.1016/0169-7439(93)85002-X.
Wold S, Sjöström M, Eriksson L. PLS-regression: a basic tool of chemometrics. Chemometr Intell Lab Syst. 2001;58(2):109-130. https://doi.org/10.1016/S0169-7439(01)00155-1.
Wise BM, Gallagher NB, Bro R, Shaver JM, Windig W, Koch RS. PLS_Toolbox Version 4.0 for Use with MATLAB ™. 2006. http://mitr.p.lodz.pl/raman/jsurmacki/pliki/zajecia/LMDiT/cw4i5/LMDiT_PLS_Manual_4.pdf. Accessed August 20, 2017.
Umetrics User Guide to SIMCA 13. Umetrics. 2012; https://umetrics.com/products/simca. Accessed November 20, 2017.
Kulkarni SG, Chaudhary AK, Nandi S, Tambe SS, Kulkarni BD. Modeling and monitoring of batch processes using principal component analysis (PCA) assisted generalized regression neural networks (GRNN). Biochem Eng J. 2004;18(3):193-210. https://doi.org/10.1016/j.bej.2003.08.009.
Sokolov M, Soos M, Neunstoecklin B, et al. Fingerprint detection and process prediction by multivariate analysis of fed-batch monoclonal antibody cell culture data. Biotechnol Prog. 2015;31(6):1633-1644. https://doi.org/10.1002/btpr.2174.
Kirdar AO, Chen G, Weidner J, Rathore AS. Application of near-infrared (NIR) spectroscopy for screening of raw materials used in the cell culture medium for the production of a recombinant therapeutic protein. Biotechnol Prog. 2010;26(2):527-531. https://doi.org/10.1002/btpr.329.
Clavaud M, Roggo Y, Von Daeniken R, Liebler A, Schwabe JO. Chemometrics and in-line near infrared spectroscopic monitoring of a biopharmaceutical Chinese hamster ovary cell culture: prediction of multiple cultivation variables. Talanta. 2013;111:28-38. https://doi.org/10.1016/j.talanta.2013.03.044.
Li B, Ray BH, Leister KJ, Ryder AG. Performance monitoring of a mammalian cell based bioprocess using Raman spectroscopy. Anal Chim Acta. 2013;796:84-91. https://doi.org/10.1016/j.aca.2013.07.058.
Krause D, Hussein MA, Becker T. Online monitoring of bioprocesses via multivariate sensor prediction within swarm intelligence decision making. Chemometr Intell Lab Syst. 2015;145:48-59. https://doi.org/10.1016/j.chemolab.2015.04.012.
Whelan J, Craven S, Glennon B. In situ Raman spectroscopy for simultaneous monitoring of multiple process parameters in mammalian cell culture bioreactors. Biotechnol Prog. 2012;28(5):1355-1362. https://doi.org/10.1002/btpr.1590.
André S, Saint CL, Gaillard S, Devos O, Calvosa É, Duponchel L. In-line and real-time prediction of recombinant antibody titer by in situ Raman spectroscopy. Anal Chim Acta. 2015;892:148-152. https://doi.org/10.1016/j.aca.2015.08.050.
Berry B, Moretto J, Matthews T, Smelko J, Wiltberger K. Cross-scale predictive modeling of CHO cell culture growth and metabolites using Raman spectroscopy and multivariate analysis. Biotechnol Prog. 2015;31(2):566-577. https://doi.org/10.1002/btpr.2035.
Vann L, Sheppard J. Use of near-infrared spectroscopy (NIRs) in the biopharmaceutical industry for real-time determination of critical process parameters and integration of advanced feedback control strategies using MIDUS control. J Ind Microbiol Biotechnol. 2017;44(12):1589-1603. https://doi.org/10.1007/s10295-017-1984-2.
Bhatia H, Mehdizadeh H, Drapeau D, Yoon S. In-line monitoring of amino acids in mammalian cell cultures using Raman spectroscopy and multivariate chemometrics models. Eng Life Sci. 2017;18:55-61. https://doi.org/10.1002/elsc.201700084.
de Oña J, Garrido C. Extracting the contribution of independent variables in neural network models: a new approach to handle instability. Neural Comput Appl. 2014;25(3-4):859-869. https://doi.org/10.1007/s00521-014-1573-5.
Postma GJ, Krooshof PWT, Buydens LMC. Opening the kernel of kernel partial least squares and support vector machines. Anal Chim Acta. 2011;705(1-2):123-134. https://doi.org/10.1016/j.aca.2011.04.025.
Tøndel K, Indahl UG, Gjuvsland AB, et al. Hierarchical cluster-based partial least squares regression (HC-PLSR) is an efficient tool for metamodelling of nonlinear dynamic models. BMC Syst Biol. 2011;5:1-17. https://doi.org/10.1186/1752-0509-5-90.
Ke SW, Lin WC, Tsai CF, Hu YH. Soft estimation by hierarchical classification and regression. Neurocomputing. 2017;234(2015):27-37. https://doi.org/10.1016/j.neucom.2016.12.037.
Kim S, Okajima R, Kano M, Hasebe S. Development of soft-sensor using locally weighted PLS with adaptive similarity measure. Chemometr Intell Lab Syst. 2013;124:43-49. https://doi.org/10.1016/j.chemolab.2013.03.008.
Perez-Guaita D, Kuligowski J, Quintás G, Garrigues S, GMDL. Modified locally weighted - partial least squares regression improving clinical predictions from infrared spectra of human serum samples. Talanta. 2013;107:368-375.
Hazama K, Kano M. Covariance-based locally weighted partial least squares for high-performance adaptive modeling. Chemometr Intell Lab Syst. 2015;146:55-62. https://doi.org/10.1016/j.chemolab.2015.05.007.
Rouiller Y, Solacroup T, Deparis V, et al. Application of quality by design to the characterization of the cell culture process of an Fc-Fusion protein. Eur J Pharm Biopharm. 2012;81(2):426-437. https://doi.org/10.1016/j.ejpb.2012.02.018.
Sokolov M, Ritscher J, MacKinnon N, et al. Enhanced process understanding and multivariate prediction of the relationship between cell culture process and monoclonal antibody quality. Biotechnol Prog. 2017;33(5):1368-1380. https://doi.org/10.1002/btpr.2502.
Folch-Fortuny A, Villaverde AF, Ferrer A, Banga JR. Enabling network inference methods to handle missing data and outliers. BMC Bioinformatics. 2015;16(1):283. https://doi.org/10.1186/s12859-015-0717-7.
Deng BC, Yun YH, Liang YZ. Model population analysis in chemometrics. Chemometr Intell Lab Syst. 2015;149:166-176.
Li F, Vijayasankaran N, Shen A, Kiss R, Amanullah A. Cell culture processes for monoclonal antibody production. MAbs. 2010;2(5):466-479. https://doi.org/10.4161/mabs.2.5.12720.
Konakovsky V, Clemens C, Müller M, et al. Metabolic control in mammalian fed-batch cell cultures for reduced lactic acid accumulation and improved process robustness. Bioengineering. 2016;3(1):5. https://doi.org/10.3390/bioengineering3010005.
Brühlmann D, Jordan M, Hemberger J, Sauer M, Stettler M, Broly H. Tailoring recombinant protein quality by rational media design. Biotechnol Prog. 2015;31(3):615-629. https://doi.org/10.1002/btpr.2089.