On-Line Mid-Infrared Spectroscopic Data and Chemometrics for the Monitoring of an Enzymatic Hydrolysis

Multivariate models have been designed in order to be implemented at pilot plant scale. They allow the prediction of the degree of the enzymatic hydrolysis of bovine hemoglobin from on-line mid-infrared (MIR) attenuated total reflection (ATR) measurements. The procedure is very safe and practical, but the spectral information is unfortunately difficult to use. First, remote MIR optical fiber measurements induce a significant energy loss. Secondly, the spectra of proteins in aqueous solutions generally consist of broad and overlapping signals. Principal component analysis (PCA) of the full data set reveals some variations between the different batches as well as definite deviations from the ideal linear situation. This suggests the use of artificial neural networks (ANNs), which have the useful qualities of generalization ability and robustness. Preprocessing of the spectral data (including PCA and wavelet transforms) have been tested. In addition, the reliability of the calibration is ensured by the interpretation of the spectroscopic information. This permits the construction of very parsimonious models and contributes to greater confidence in the analytical tool built for process monitoring. Finally, the estimations of the prediction error are demonstrated to be acceptable. With an unknown proteolysis batch, this error is found to be lower than 0.4 for the degree of hydrolysis covering the range 0 to 8.7.

[1]  K. Fahmy.  Binding of transducin and transducin-derived peptides to rhodopsin studies by attenuated total reflection-Fourier transform infrared difference spectroscopy. , 1998, Biophysical journal.

[2]  P. Griffiths,et al.  Comparison of the Amide I/II Intensity Ratio of Solution and Solid-State Proteins Sampled by Transmission, Attenuated Total Reflectance, and Diffuse Reflectance Spectrometry , 1993 .

[3]  Elie Bienenstock,et al.  Neural Networks and the Bias/Variance Dilemma , 1992, Neural Computation.

[4]  Nathalie Dupuy,et al.  Identification of Modified Starches Using Infrared Spectroscopy and Artificial Neural Network Processing , 1998 .

[5]  Johann Gasteiger,et al.  Neural Networks for Chemists: An Introduction , 1993 .

[6]  G. Krim,et al.  Comparaison de l'absorption intestinale de deux hydrolysats de protéines à base de caséine et d'hémoglobine bovine chez le porc éveillé , 1990 .

[7]  Desire L. Massart,et al.  Variable selection for neural networks in multivariate calibration , 1998 .

[8]  Gerald M. Maggiora,et al.  Computational neural networks as model-free mapping devices , 1992, J. Chem. Inf. Comput. Sci..

[9]  Osamu Fujita,et al.  Statistical estimation of the number of hidden units for feedforward neural networks , 1998, Neural Networks.

[10]  F Despagne,et al.  Neural networks in multivariate calibration. , 1998, The Analyst.

[11]  Despagne,et al.  Development of a robust calibration model for nonlinear in-line process data , 2000, Analytical chemistry.

[12]  L. Duponchel,et al.  Standardisation of near Infrared Spectrometers Using Artificial Neural Networks , 1999 .

[13]  J. A. Rupley.  [90] Susceptibility to attack by proteolytic enzymes , 1967 .

[14]  Desire L. Massart,et al.  Multivariate calibration with Raman spectroscopic data: a case study , 2000 .

[15]  Paul J. Gemperline.  Rugged spectroscopic calibration for process control , 1997 .

[16]  Evaluation techniques for two-way data from in situ fourier transform mid-infrared reaction monitoring in aqueous solution. , 1998, Analytical chemistry.

[17]  P. Dhulster,et al.  Antibacterial activity of a pepsin‐derived bovine hemoglobin fragment , 2001, FEBS letters.

[18]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[19]  Pascal Dhulster,et al.  Hydrolysis of hemoglobin surveyed by infrared spectroscopy : II. Progress predicted by chemometrics , 1999 .

[20]  G. Ricart,et al.  Isolation and characterization of a bradykinin‐potentiating peptide from a bovine peptic hemoglobin hydrolysate , 1992, FEBS letters.

[21]  J. A. Haseth.  Stability of Rapid Scanning Interferometers , 1982 .

[22]  Beata Walczak,et al.  Comparison of Multivariate Calibration Techniques Applied to Experimental NIR Data Sets , 2000 .

[23]  I. Daubechies.  Orthonormal bases of compactly supported wavelets , 1988 .

[24]  Cyril Ruckebusch,et al.  Neural network modelling for very small spectral data sets: reduction of the spectra and hierarchical approach , 2000 .

[25]  Johanna Smeyers-Verbeke,et al.  Handbook of Chemometrics and Qualimetrics: Part A , 1997 .

[26]  Nathalie Dupuy,et al.  Quantitative analysis of paper coatings using artificial neural networks , 1997 .