Medicine and Health

A machine learning algorithm with subclonal sensitivity reveals widespread pan-cancer human leukocyte antigen loss of heterozygosity

R. M. Pyke, D. Mellacheruvu, et al.

Discover how Rachel Marty Pyke and colleagues at Personalis, Inc developed DASH, a groundbreaking machine learning algorithm that outperforms existing tools in detecting human leukocyte antigen loss of heterozygosity (HLA LOH) from tumor-normal sequencing data. This innovative approach, validated by digital PCR, suggests a significant correlation between HLA LOH and immune resistance strategies in cancer patients.

00:00

Playback language: English

Index

Abstract

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

Related Publications

Explore these studies to deepen your understanding of the subject.

Medicine and Health

A machine learning contest enhances automated freezing of gait detection and reveals time-of-day effects

A. Salomon, E. Gazit, et al.

Medicine and Health

Insights to the neural response to food cues in class III compared with class I and II obese adults using a sample of endometrial cancer survivors seeking weight loss

N. L. Nock, H. Jiang, et al.

Medicine and Health

Diagnostic Accuracy of Machine Learning AI Architectures in Detecting and Classifying Lung Cancer: A Systematic Review

A. Pacurari, S. Bhattarai, et al.

Medicine and Health

Predictive model of castration resistance in advanced prostate cancer by machine learning using genetic and clinical data: KYUCOG-1401-A study

M. Shiota, S. Nemoto, et al.

Listen, Learn & Level Up

Over 10,000 hours of research content in 25+ fields, available in 12+ languages.

No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.

listen to research audio papers with researchbunny