Human leukocyte antigen loss of heterozygosity (HLA LOH) allows cancer cells to escape immune recognition. This study develops DASH, a machine learning algorithm to detect HLA LOH from paired tumor-normal sequencing data, demonstrating increased sensitivity compared to existing tools. Validation using digital PCR confirmed DASH's accuracy. Analysis of 610 patients across 15 tumor types revealed HLA LOH in 18% of patients, correlating with immune resistance strategies.
Publisher
Nature Communications
Published On
Apr 12, 2022
Authors
Rachel Marty Pyke, Dattatreya Mellacheruvu, Steven Dea, Charles W. Abbott, Lee McDaniel, Devayani P. Bhave, Simo V. Zhang, Eric Levy, Gabor Bartha, John West, Michael P. Snyder, Richard O. Chen, Sean Michael Boyle
Tags
HLA LOH
machine learning
digital PCR
tumor-normal sequencing
immune resistance
cancer
Related Publications
Explore these studies to deepen your understanding of the subject.
