Hybrid Model Captures Lactate Run-Away and Back-Metabolism
A hybrid model provides hard-to-achieve insights into lactate performance during bioprocessing, creating conditions for more accurate predictions to better manage key batch parameters and variability. The post Hybrid Model Captures Lactate Run-Away and Back-Metabolism appeared first on GEN - Genetic Engineering and Biotechnology News .
Scientists from University College London and AstraZeneca have developed a hybrid model that accurately predicts lactate back-metabolism and run-away in mammalian cell cultures. This model, outlined in a recent paper, offers real-time predictions of viable cell density, monoclonal antibody, glucose, and lactate concentrations during bioprocessing.
Led by principal investigator Li Qin and senior researcher Stephen Goldrick, the team refined the original model's 88% accuracy rate by reducing the root mean squared error for glucose and lactate by 50% and 30%, respectively. A key feature of this model is its lactate switch detection algorithm, which uses pH as a soft sensor to identify whether cells will undergo lactate back-metabolism around day 5.
By incorporating online and offline measurements, the model enables process adjustments to prevent lactate run-away. Trained on online data like pH values and glucose flow rates, as well as historical data such as glucose, lactate, mAb concentrations, and cell densities, the model was tested on five runs that switched from lactate production to consumption, three runs for predictive performance evaluation, one for lactate run-away, and one for an external lactate run-away scenario.
This targeted training strategy reduced model update time without compromising predictive accuracy. Although the number of training runs is relatively small, the model's predictions closely matched actual measured values, indicating its potential to significantly contribute to the biopharmaceutical industry. Future work will expand the measured production values to include amino acid consumption, ammonia accumulation, osmolality dynamics, and product quality attributes.
Written by urgent.news from GEN Biotechnology's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
