RESUMEN

According to the standard guidelines by the FDA, process validation in biopharma manufacturing encompasses a life cycle consisting of three stages: process design (PD), process qualification (PQ), and continued process verification (CPV). The validity and efficiency of the analytics methods employed during the CPV require extensive knowledge of the process. However, for new processes and new drugs, such knowledge is often not available from Process performance qualification and Validation (PPQV). In this work, the suitability of methods based on machine learning/artificial intelligence (ML/AI) for the CPV applied in bioprocess monitoring and cell physiological control of the yeast Pichia pastoris (Komagataella phaffii) was studied with limited historical data. In particular, the production of recombinant Candida rugosa lipase 1 (Crl1) under hypoxic conditions in fed-batch cultures was considered as a case study. Supervised and unsupervised machine learning models using data from fed-batch bioprocesses with different gene dosage clones under normoxic and hypoxic conditions were evaluated. Firstly, a multivariate anomaly detection (isolation forest) model was applied to the batch phase of the bioprocess. Secondly, a supervised random forest model for prediction of required operator's control actions during the semiautomated fed-batch phase under hypoxic conditions was assessed to maintain the respiratory quotient (RQ) within the desired range for maximizing the specific production rate (qP ). The performance of these models was tested on historical data using independent evaluation of the process by the process control engineer (subject matter expert-SME), and on real-time data in the case of manual action prediction, where the model was implemented to guide the control of the bioprocess. The work presented here constitutes a proof-of-concept that multivariate analytics methods, based on machine learning, can be a valuable tool for real-time monitoring and control of biopharma manufacturing bioprocesses to improve its efficiency and to assure product quality.

Asunto(s)

RESUMEN

Quality is defined by the American Society for Quality (ASQ) as "the totality of features and characteristics of a product or service that bears on its ability to satisfy given needs." Therefore, quality is applicable to processes that supply outcomes with values that can be measured. Statistical control is an effective methodology that provides the outcome of quality of goods, bringing an added value that other methods, like quality by inspection, do not offer. The statistical methods applied to process control have been thoroughly developed, and the mathematics that supports them have been broadly demonstrated. Artificial Intelligence (AI) is a field in which mathematics, statistics, and programming play a joint role, and its results can also be applied to disciplines like quality control. Nevertheless, its utilization is subordinate to the qualification of the implemented algorithms. This research presents a standard procedure to AI algorithms, allowing their usage in regulated environments to ensure the quality of the delivered products or services (e.g., in drugs and medicines manufacturing). The regulated principles are defined by the concept of quality by design (QbD), which is a notion introduced in the pharmaceutical industry as a good practice for process management under multivariate analysis. This study intended to provide guidance for qualifying AI algorithms using QbD guidelines as the foundation for this purpose.

Asunto(s)

RESUMEN

Erratum for Toni Manzano, Cristina Fernandez, Toni Ruiz, and Hugo Richard, "AI Algorithm Qualification," Accepted Article, August 2020.