LANL NEWS RELEASE
A new multi-laboratory effort funded by the Defense Threat Reduction Agency is underway, creating a machine-learning tool to revolutionize the future of vaccine development, rapidly choosing a suitable vaccine platform for any viral and bacterial pathogen. Led by Los Alamos National Laboratory, the Rapid Assessment of Platform Technologies to Expedite Response (RAPTER) tool will quantify to what degree the immunological correlates of protection match between what can be generated by each vaccine platform and what is required to resist an infection by that class of pathogen.
“Developing safe and effective vaccines is a critical component to establishing a robust response to combat any current, emerging or future biological threat. However, vaccine design, testing, and manufacturing are time-consuming and expensive activities,” said project lead Jessica Kubicek-Sutherland of Los Alamos. To streamline this process, the team proposes the development of a machine-learning tool to predict the most suitable vaccine technologies for a given pathogen to increase the rate of success and reduce the number of initial vaccine candidates required.
The cost of developing a single vaccine can be up to $68 million, with failure rates as high as 94%, so vaccine development typically starts with multiple candidates following a lengthy linear workflow to mitigate these costs and risks. Each vaccine platform generates a defined immune response based on its mechanism of presenting antigens to the host. Similarly, the host immune system is required to generate a distinct immune response to survive an infection by a pathogen.
“The team will apply computational modeling and broad text-mining techniques to normalize and draw conclusions from a variety of data sources and identify an immunological profile for each vaccine platform and entire classes of pathogens,” Kubicek-Sutherland said. Targeted experiments with standardized protocols will be performed to fill data gaps, ensuring a direct comparison of seven vaccine platform technologies while also validating the accuracy of the machine-learning tool predictions.
The organizations in the new consortium are Los Alamos National Laboratory, Pacific Northwest National Laboratory, Lawrence Livermore National Laboratory, Sandia National Laboratories, U.S. Army Medical Research Institute of Infectious Diseases, Harvard University, Northern Arizona University, Tulane University, University of California San Diego, University of New Mexico and University of Nevada at Reno. The funding for the project will cover four years of research.