Comparison of data science workflows for root cause analysis of bioprocesses

Abstract

Root cause analysis (RCA) is one of the most prominent tools used to comprehensively evaluate a biopharmaceutical production process. Despite of its widespread use in industry, the Food and Drug Administration has observed a lot of unsuitable approaches for RCAs within the last years. The reasons for those unsuitable approaches are the use of incorrect variables during the analysis and the lack in process understanding, which impede correct model interpretation. Two major approaches to perform RCAs are currently dominating the chemical and pharmaceutical industry: raw data analysis and feature-based approach. Both techniques are shown to be able to identify the significant variables causing the variance of the response. Although they are different in data unfolding, the same tools as principal component analysis and partial least square regression are used in both concepts. Within this article we demonstrate the strength and weaknesses of both approaches. We proved that a fusion of both results in a comprehensive and effective workflow, which not only increases better process understanding. We demonstrate this workflow along with an example. Hence, the presented workflow allows to save analysis time and to reduce the effort of data mining by easy detection of the most important variables within the given dataset. Subsequently, the final obtained process knowledge can be translated into new hypotheses, which can be tested experimentally and thereby lead to effectively improving process robustness.

Monte Carlo-Based Error Propagation for a More Reliable Regression Analysis across Specific Rates in Bioprocesses

“…This is especially important for the determination of uncertainties on specific rates, as shown by [ 7 ]. Although specific rates offer the possibility to deduce transferable and scalable knowledge from experiments, they are subject to high errors, which is important to consider before drawing any conclusion or using them for subsequent root cause analysis, as proposed by [ 32 ].…”

Molecular function recognition by supervised projection pursuit machine learning

“…The RNN setup maps each mode to a perceptron, each with access to two distinct classes of data packet cubes 39 . Each perceptron has a rectifying unit to quantify mode efficacy as a function of signal-to-noise and clustering quality within the MFSP.…”

Development of Novel Bioreactor Control Systems Based on Smart Sensors and Actuators

“…Furthermore, very large amounts of historical bioprocess data have been accumulated in the bioindustry, and successful utilization of this digital resource calls for more intelligent control systems. KBCSs have emerged and ripened during the last decade, with the aim of solving this problem (Rathore et al, 2017;Borchert et al, 2019;. The KBCS has been implemented at two levels.…”