VIRTUAL IDeAS Seminar: Edgar Dobriban, University of Pennsylvania

IDeAS
Apr 8, 2021
1 pm
via Zoom - https://princeton.zoom.us/j/99362146310?pwd=a1JMbkxBVGpGMUszYmNJZjREWHhrQT09

HYPER: Flexible and effective pooled testing via hypergraph factorization

Large-scale screening is a critical tool in the life sciences but is often limited by reagents, samples, or cost. An important challenge in screening has recently manifested in the ongoing effort to achieve widespread testing for individuals with SARS-CoV-2 infection in the face of substantial resource constraints. Group testing methods utilize constrained testing resources more efficiently by pooling specimens together, potentially allowing larger populations to be screened with fewer tests. A key challenge in group testing is to design an effective pooling strategy. The global nature of the ongoing pandemic calls for something simple (to aid implementation) and flexible (to tailor for settings with differing needs) that remains efficient. Here we propose HYPER, a new group testing method based on hypergraph factorizations. We provide characterizations under a general theoretical model, and exhaustively evaluate HYPER and proposed alternatives for SARS-CoV-2 screening under realistic simulations of epidemic spread and within-host viral kinetics. We demonstrate that HYPER performs at least as well as other methods in scenarios that are well-suited to each method while outperforming those methods across a broad range of resource-constrained environments, and being more flexible and simple in design, and taking no expertise to implement.  An online tool to implement these designs is available at http://hyper.covid19-analysis.org. This is joint work with David Hong, Rounak Dey, Xihong Lin, and Brian Cleary.

Edgar Dobriban is an Assistant Professor in the Statistics Department at the Wharton School of the University of Pennsylvania. His interests include statistics for "big data" and theoretical machine learning. He obtained a Ph.D. in statistics from Stanford University in 2017, where he received the T.W. Anderson award for the best Ph.D. thesis in theoretical statistics. He has been a co-recipient of the NSF-Simons award on the Mathematical and Scientific Foundations of Deep Learning (2020), and a recipient of the NSF CAREER award (2021).