Cell and Gene Therapy
WHITE PAPER
Leveraging Model Interpretability Methods to Predict Gene Therapy Manufacturing Failures
Model interpretability methods provide an understanding of complex model decisions and verify that a meaningful difference in the data has been identified. We have applied model interpretability methods to our predictive model of genome truncation within adeno-associated virus (AAV) manufacturing and revealed that the model uses a set of DNA secondary structures predictive of truncation. These secondary structures provide a simple mechanism for understanding AAV truncations and a strong basis for independently validating our model’s predictions. Moreover, these structures have been well studied and are shown to be related to DNA replication errors; however, only one of these structures (i.e., hairpins) has been previously implicated in AAV manufacturing failures. Future research will concentrate on additional contributors to our truncation model to gain a deeper understanding of AAV manufacturing failures more generally.
AUTHOR
Nick Ketz, PhD
Dr. Nick Ketz is a Senior Computational Scientist at Form Bio where he focuses on developing neural network based solutions to various life science research, development and manufacturing problems. Prior to joining Form Bio, Dr. Ketz’s six year post-graduate career included a DARPA funded computational scientist role at HRL laboratories researching and developing biologically informed deep learning architectures which led to the development of a prototype device to enhance learning and memory in humans. He holds a PhD in Psychology, Neuroscience and Cognitive Science from the University Colorado Boulder and a BA in Physics at University of Minnesota Twin Cities.
