Machine learning prediction of methionine and tryptophan photooxidation susceptibility.

Photooxidation of methionine (Met) and tryptophan (Trp) residues is common and includes major degradation pathways that often pose a serious threat to the success of therapeutic proteins. Oxidation impacts all steps of protein production, manufacturing, and shelf life. Prediction of oxidation liability as early as possible in development is important because many more candidate drugs are discovered than can be tested experimentally. Undetected oxidation liabilities necessitate expensive and time-consuming remediation strategies in development and may lead to good drugs reaching patients slowly. Conversely, sites mischaracterized as oxidation liabilities could result in overengineering and lead to good drugs never reaching patients. To our knowledge, no predictive model for photooxidation of Met or Trp is currently available. We applied the random forest machine learning algorithm to in-house liquid chromatography-tandem mass spectrometry (LC-MS/MS) datasets (Met, n = 421; Trp, n = 342) of tryptic therapeutic protein peptides to create computational models for Met and Trp photooxidation. We show that our machine learning models predict Met and Trp photooxidation likelihood with 0.926 and 0.860 area under the curve (AUC), respectively, and Met photooxidation rate with a correlation coefficient (Q2) of 0.511 and root-mean-square error (RMSE) of 10.9%. We further identify important physical, chemical, and formulation parameters that influence photooxidation. Improvement of biopharmaceutical liability predictions will result in better, more stable drugs, increasing development throughput, product quality, and likelihood of clinical success.

Effectiveness of mouse minute virus inactivation by high temperature short time treatment technology: a statistical assessment.

Viral contamination of mammalian cell cultures in GMP manufacturing facility represents a serious safety threat to biopharmaceutical industry. Such adverse events usually require facility shutdown for cleaning/decontamination, and thus result in significant loss of production and/or delay of product development. High temperature short time (HTST) treatment of culture media has been considered as an effective method to protect GMP facilities from viral contaminations. Log reduction factor (LRF) has been commonly used to measure the effectiveness of HTST treatment for viral inactivation. However, in order to prevent viral contaminations, HTST treatment must inactivate all infectious viruses (100%) in the medium batch since a single virus is sufficient to cause contamination. Therefore, LRF may not be the most appropriate indicator for measuring the effectiveness of HTST in preventing viral contaminations. We report here the use of the probability to achieve complete (100%) virus inactivation to assess the effectiveness of HTST treatment. By using mouse minute virus (MMV) as a model virus, we have demonstrated that the effectiveness of HTST treatment highly depends upon the level of viral contaminants in addition to treatment temperature and duration. We believe that the statistical method described in this report can provide more accurate information about the power and potential limitation of technologies such as HTST in our shared quest to mitigate the risk of viral contamination in manufacturing facilities.