Back

Machine-Learning-Based Prediction of Chinese Hamster Ovary Cell Stability Due to Epigenetic Changes

Seber, P.; Braatz, R. D.

2025-03-17 bioinformatics
10.1101/2025.03.14.643414 bioRxiv
Show abstract

Chinese hamster ovary (CHO) cells are the main system for producing biopharmaceuticals, but they suffer from instability, affecting their long-term productivity. This instability prevents their use in perfusion bioreactors, which are more productive, and increases the costs of biopharmaceuticals. In this work, we create the first models for predicting long-term CHO cell stability due to changes in chromatin modification levels and methylation. Multilayer perceptrons are the best-performing models, reaching an F1 score of 59.1% and a Matthews correlation co-efficient of 19.4% on this task. Furthermore, Shapley values and inter-pretable models are used to investigate model coefficients, contributing biological insight to this problem and helping focus future data collection efforts. We freely provide the models trained in this work.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.