RESUMEN
In the current work, the attempt was made to apply best-fitted artificial neural network (ANN) architecture and the respective training process for predicting final titer of hepatitis B surface antigen (HBsAg), produced intracellularly by recombinant Pichia pastoris Mut+ in the commercial scale. For this purpose, in large-scale fed-batch fermentation, using methanol for HBsAg induction and cell growth, three parameters of average specific growth rate, biomass yield, and dry biomass concentration-in the definite integral form with respect to fermentation time-were selected as input vectors; the final concentration of HBsAg was selected for the ANN output. Used dataset consists of 38 runs from previous batches; feed-forward ANN 3:5:1 with training algorithm of backpropagation based on a Bayesian regularization was trained and tested with a high degree of accuracy. Implementing the verified ANN for predicting the HBsAg titer of the five new fermentation runs, excluded from the dataset, in the full-scale production, the coefficient of regression and root-mean-square error were found to be 0.969299 and 2.716774, respectively. These results suggest that this verified soft sensor could be an excellent alternative for the current relatively expensive and time-intensive analytical techniques such as enzyme-linked immunosorbent assay in the biopharmaceutical industry.
Asunto(s)
Reactores Biológicos , Fermentación , Antígenos de Superficie de la Hepatitis B/metabolismo , Redes Neurales de la Computación , Pichia/metabolismo , Reactores Biológicos/economía , Antígenos de Superficie de la Hepatitis B/química , Antígenos de Superficie de la Hepatitis B/economía , Pichia/química , Proteínas Recombinantes/química , Proteínas Recombinantes/economía , Proteínas Recombinantes/metabolismoRESUMEN
BACKGROUND AND AIM: Hepatitis B surface antigen quantification (qHBsAg) is a relevant biomarker assay in the therapeutic management of hepatitis B virus-infected patients; however, little is known about its use in France. The aim of this study was to describe the knowledge of qHBsAg use and the indications for the prescription of qHBsAg in France. METHODS: From March 2014 to May 2014, 135 questionnaires were sent to hepatologists and gastroenterologists from several health centers (private practice, public practice, and outlying health centers). There were 20 items in each questionnaire on the use of qHBsAg. RESULTS: Seventy-six percent of the practitioners had previously used qHBsAg, among whom 88% had prescribed the use of qHBsAg before treatment, 73% had prescribed the use of qHBsAg in combination with hepatitis B virus viral load, 64% had prescribed the use of qHBsAg at week 12 or week 24 of treatment, 62% had prescribed the use of qHBsAg for stopping rules, and 49% had prescribed the use of qHBsAg to identify inactive carriers. The reason for nonprescription of qHBsAg was mainly because of difficulty accessing the test (50% of the practitioners), followed by nonreimbursement of the test (27%); 97% of the practitioners who did not prescribe qHBsAg indicated an interest in accessing the test. CONCLUSION: This survey describes the characteristics of the prescription of qHBsAg in France. More than three out of four practitioners have previously used qHBsAg. The use of the qHBsAg just before treatment was the main reason for prescription. The main reason for nonprescription was because of difficulty in accessing the test.