TY - JOUR T1 - Diagnostic design with machine learning model-based optimization JF - bioRxiv DO - 10.1101/2020.11.28.401877 SP - 2020.11.28.401877 AU - Hayden C. Metsky AU - Nicole L. Welch AU - Nicholas J. Haradhvala AU - Laurie Rumker AU - Yibin B. Zhang AU - Priya P. Pillai AU - David K. Yang AU - Cheri M. Ackerman AU - Juliane Weller AU - Paul C. Blainey AU - Cameron Myhrvold AU - Michael Mitzenmacher AU - Pardis C. Sabeti Y1 - 2021/01/01 UR - http://biorxiv.org/content/early/2021/02/01/2020.11.28.401877.abstract N2 - Diagnostics, particularly for rapidly evolving viruses, can greatly benefit from principled machine learning-based design. Concentrating here on CRISPR-based viral diagnostics, we screen ~19,000 guide-target pairs and devise a deep neural network to predict a design’s diagnostic signal; we then leverage this model to generate assays that are optimal in expectation over a virus’s genomic variation. We introduce ADAPT, a system for rapid and fully-automated design using our approach. We design CRISPR-based diagnostics for the 1,933 vertebrate-infecting viral species, and experimentally show ADAPT’s designs are sensitive and specific to the lineage-level against extensive viral variation and exhibit lower limits of detection than designs from standard techniques. Model-based optimization is primed to advance CRISPR-based viral diagnostics and many genome-informed technologies for detecting and responding to pathogens.Competing Interest StatementH.C.M., N.J.H., C.M., and P.C.S. are co-inventors on a patent application filed by the Broad Institute related to work in this manuscript. N.J.H. is a consultant to Constellation Pharmaceuticals. P.C.B. is a consultant to and equity holder in 10X Genomics, GALT, Celsius Therapeutics, and Next Generation Diagnostics. P.C.S. is a co-founder of and consultant to Sherlock Biosciences and a Board Member of Danaher Corporation, and holds equity in the companies. ER -