Predicting and Evaluating the Stability of Therapeutic Protein Formulations by Dynamic Light Scattering and Machine Learning
Presented Live: October 23, 2018
PIPPI, which stands for Protein-excipient Interactions and Protein-Protein Interactions, is a European academic-industrial consortium addressing the challenges in formulation of protein-based drugs. Its overall objective is to develop methodologies, tools and databases to guide the rational formulation of robust protein-based therapeutics. Much of the effort carried out under PIPPI has utilized dynamic light scattering (DLS), the primary biophysical technique for screening aggregation in a high-throughput fashion.
Thanks to efficient utilization of resources and high flexibility, DLS can be applied in multiple ways to increase the progression of new-drug candidates into phase 1 clinical trial. In this webinar a series of DLS methods are presented for evaluating stability under different formulations, including standard protocols and the latest applications. All, if not most, of these methods are carried out in high-throughput fashion using convenient microwell plates in order to test a large variety of candidates and formulation conditions.
Due to the overwhelming amount of data available from high throughput techiniques such as plate-based DLS, there is a staggering increase in opportunities for finding patterns in data. Such a patterns are helpful in ab initio prediction of stability-indicating parameters. A machine learning application developed to identify those patterns, and trained using a standard formulation screening dataset, is shown.