Comparison of data science workflows for root cause analysis of bioprocesses

• DOI: 10.1007/s00449-018-2029-6
• Publication Date: 2018-10-30T21:23:36Z
• Authors: Daniel Borchert; Diego A. Suarez-Z...; Patrick Sagmeister; Yvonne E. Thomassen; Christoph Herwig
• Keywords: Robustness; Root Cause Analysis; Process Analytical Technology

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