Learning Relationships Between Chemical and Physical Stability for Peptide Drug Development.

Autor: Fine J; Department of Chemistry, Purdue University, West Lafayette, IN, USA.; Analytical Research & Development, MRL, Merck & Co., Inc., Rahway, NJ, USA., Wijewardhane PR; Department of Chemistry, Purdue University, West Lafayette, IN, USA., Mohideen SDB; Department of Chemistry, Purdue University, West Lafayette, IN, USA., Smith K; Analytical Research & Development, MRL, Merck & Co., Inc., Rahway, NJ, USA., Bothe JR; Analytical Research & Development, MRL, Merck & Co., Inc., Rahway, NJ, USA., Krishnamachari Y; Sterile and Specialty Products, Pharmaceutical Sciences, MRL, Merck & Co., Inc., Rahway, NJ, USA., Andrews A; Analytical Research & Development, MRL, Merck & Co., Inc., Rahway, NJ, USA., Liu Y; Tango Therapeutics, Boston, MA, USA., Chopra G; Department of Chemistry, Purdue University, West Lafayette, IN, USA. gchopra@purdue.edu.; Department of Computer Science (by courtesy), Purdue University, West Lafayette, NJ, USA. gchopra@purdue.edu.
Jazyk: angličtina
Zdroj: Pharmaceutical research [Pharm Res] 2023 Mar; Vol. 40 (3), pp. 701-710. Date of Electronic Publication: 2023 Feb 16.
DOI: 10.1007/s11095-023-03475-3
Abstrakt: Purpose or Objective: Chemical and physical stabilities are two key features considered in pharmaceutical development. Chemical stability is typically reported as a combination of potency and degradation product. Moreover, fluorescent reporter Thioflavin-T is commonly used to measure physical stability. Executing stability studies is a lengthy process and requires extensive resources. To reduce the resources and shorten the process for stability studies during the development of a drug product, we introduce a machine learning-based model for predicting the chemical stability over time using both formulation conditions as well as aggregation curves.
Methods: In this work, we develop the relationships between the formulation, stability timepoint, and the chemical stability measurements and evaluated the performance on a random test set. We have developed a multilayer perceptron (MLP) for total degradation prediction and a random forest (RF) model for potency.
Results: The coefficient of determination (R 2 ) of 0.945 and a mean absolute error (MAE) of 0.421 were achieved on the test set when using MLP for total degradation. Similarly, we achieved a R 2 of 0.908 and MAE of 1.435 when predicting potency using the RF model. When physical stability measurements are included into the MLP model, the MAE of predicting TD decreases to 0.148. Using a similar strategy for potency prediction, the MAE decreases to 0.705 for the RF model.
Conclusions: We conclude two important points: first, chemical stability can be modeled using machine learning techniques and second there is a relationship between the physical stability of a peptide and its chemical stability.
(© 2023. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.)
Databáze: MEDLINE