Cell Culture Glycosylation Multi-scale Mechanistic Modeling (Phase 1)

Develop software for next-generation N- and O-linked glycosylation mechanistic models for control for fed-batch Chinese Hamster Ovary (CHO) cell culture

Project status

100% Completed

Industry Need

Laboratory experiments increase new product development cost.

Solution

Use Glycosylation modeling to reduce laboratory experimentation

Outputs/Deliverables

Modelling Software in Open-Source platform (done)
Model Use Training documentation (done)
Publication – Recurrent Neural Network-based Prediction of the Location of O-GlcNAcylation Sites in Mammalian Proteins (Seber, Braatz (MIT)) http://dx.doi.org/10.1101/2023.08.24.554563
Publication – Linear and Neural Network Models for Predicting N-glycosylation in Chinese Hamster Ovary Cells Based on B4GALT Levels (Seber, Braatz (MIT)) http://dx.doi.org/10.1101/2023.04.13.536762

Impacts

Reduce process development time and cost of Antibody products

Publications

Seber, P., & Braatz, R. D. (2024). Recurrent neural network-based prediction of O-GlcNAcylation sites in mammalian proteins. Computers & Chemical Engineering, , 108818. https://doi.org/10.1016/j.compchemeng.2024.108818

Seber, P., & Braatz, R. D. (2023). Linear and neural network models for predicting N-glycosylation in chinese hamster ovary cells based on B4GALT levels. bioRxiv, https://doi.org/10.1101/2023.04.13.536762