Performance Period: 10/1/2020 to 12/31/2021
This project is in the NIIMBL Project Call 3.1 “Big Data Analytics & Automation” topic area. In response to regulatory requirements, a variety of imaging techniques are routinely used to measure particle levels and particle size distributions within therapeutic protein formulations in both drug substance and drug product. As a result, vast amounts of data are recorded. Currently, much of the information contained within these “big data” sets is not utilized.
In this project, machine learning approaches using convolutional neural networks will be used to extract useful information from collections of images of particles measured after biopharmaceutical fill-finish operations. Algorithms will be developed and tested to a) facilitate root-cause analysis for protein aggregation, b) enable process monitoring for fill-finish process-induced aggregation; and c) allow more rapid automated discrimination between innocuous particles such as air bubbles and particles of regulatory concern in automated visual inspection for fill-finish operations.
Machine learning approaches using convolutional neural networks will be used to extract useful information from collections of images of particles measured after biopharmaceutical fill-finish operations
Not yet a member? Learn more about which level of NIIMBL membership is right for you and your organization.
Regents of the University of Colorado (Boulder)