Applying machine learning to predict viral assembly for adeno-associated virus capsid libraries

Machine learning (ML) can aid in novel discoveries in the field of viral gene therapy. Specifically, big data gathered through next-generation sequencing (NGS) of complex capsid libraries is an especially prominent source of lost potential in data analysis and prediction. Furthermore, adeno-associated virus (AAV)-based capsid libraries are becoming increasingly popular as a tool to select candidates for gene therapy vectors. These higher complexity AAV capsid libraries have previously been created and selected in vivo; however, in silico analysis using ML computer algorithms may augment smarter and more robust libraries for selection. In this study, data of AAV capsid libraries gathered before and after viral assembly are used to train ML algorithms. We found that two ML computer algorithms, artificial neural networks (ANNs), and support vector machines (SVMs), can be trained to predict whether unknown capsid variants may assemble into viable virus-like structures. Using the most accurate models constructed, hypothetical mutation patterns in library construction were simulated to suggest the importance of N495, G546, and I554 in AAV2-derived capsids. Finally, two comparative libraries were generated using ML-derived data to biologically validate these findings and demonstrate the predictive power of ML in vector design. [Display omitted] Marques et al. develop a bioinformatics pipeline implementing machine learning to predict whether AAV2-based amino acid sequences will produce viable capsids. The ability to make these predictions may facilitate researchers to optimize AAV gene therapy vector libraries by selecting pools with fewer dead-end variants in silico.