Arash Jamshidi, Minetta C Liu, Eric A Klein, Oliver Venn, Earl Hubbell, John F Beausang, Samuel Gross, Collin Melton, Alexander P Fields, Qinwen Liu, Nan Zhang, Eric T Fung, Kathryn N Kurtzman, Hamed Amini, Craig Betts, Daniel Civello, Peter Freese, Robert Calef, Konstantin Davydov, Saniya Fayzullina, Chenlu Hou, Roger Jiang, Byoungsok Jung, Susan Tang, Vasiliki Demas, Joshua Newman, Onur Sakarya, Eric Scott, Archana Shenoy, Seyedmehdi Shojaee, Kristan K Steffen, Virgil Nicula, Tom C Chien, Siddhartha Bagaria, Nathan Hunkapiller, Mohini Desai, Zhao Dong, Donald A Richards, Timothy J Yeatman, Allen L Cohn, David D Thiel, Donald A Berry, Mohan K Tummala, Kristi McIntyre, Mikkael A Sekeres, Alan Bryce, Alexander M Aravanis, Michael V Seiden, Charles Swanton
In the Circulating Cell-free Genome Atlas (NCT02889978) substudy 1, we evaluate several approaches for a circulating cell-free DNA (cfDNA)-based multi-cancer early detection (MCED) test by defining clinical limit of detection (LOD) based on circulating tumor allele fraction (cTAF), enabling performance comparisons. Among 10 machine-learning classifiers trained on the same samples and independently validated, when evaluated at 98% specificity, those using whole-genome (WG) methylation, single nucleotide variants with paired white blood cell background removal, and combined scores from classifiers evaluated in this study show the highest cancer signal detection sensitivities...
December 12, 2022: Cancer Cell