Premium
Application of a kNN ‐based similarity method to biopharmaceutical manufacturing
Author(s) -
Ren Jun,
Zhou Roland,
Farrow Michael,
Peiris Ramila,
Alosi Tim,
Guenard Rob,
RomeroTorres Saly
Publication year - 2019
Publication title -
biotechnology progress
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.572
H-Index - 129
eISSN - 1520-6033
pISSN - 8756-7938
DOI - 10.1002/btpr.2945
Subject(s) - benchmarking , similarity (geometry) , univariate , computer science , biopharmaceutical , data mining , process (computing) , artificial intelligence , manufacturing process , multivariate statistics , pattern recognition (psychology) , machine learning , microbiology and biotechnology , operating system , marketing , business , image (mathematics) , biology , materials science , composite material
Machine learning‐based similarity analysis is commonly found in many artificial intelligence applications like the one utilized in e‐commerce and digital marketing. In this study, a kNN‐based (k‐nearest neighbors) similarity method is proposed for rapid biopharmaceutical process diagnosis and process performance monitoring. Our proposed application measures the spatial distance between batches, identifies the most similar historical batches, and ranks them in order of similarity. The proposed method considers the similarity in both multivariate and univariate feature spaces and measures batch deviations to a benchmarking batch. The feasibility and effectiveness of the proposed method are tested on a drug manufacturing process at Biogen.