Scalable prediction of acute myeloid leukemia using high-dimensional machine learning and blood transcriptomics

Warnat-Herresthal, Stefanie; Perrakis, Konstantinos; Taschler, Bernd; Becker, Matthias; Baßler, Kevin; Beyer, Marc; Günther, Patrick; Schulte-Schrepping, Jonas; Seep, Lea; Klee, Kathrin; Ulas, Thomas; Haferlach, Torsten; Mukherjee, Sach; Schultze, Joachim L.

Abstract

Acute myeloid leukemia (AML) is a severe, mostly fatal hematopoietic malignancy. We were interested in whether transcriptomic-based machine learning could predict AML status without requiring expert input. Using 12,029 samples from 105 different studies, we present a large-scale study of machine learning-based prediction of AML in which we address key questions relating to the combination of machine learning and transcriptomics and their practical use. We find data-driven, high-dimensional approaches—in which multivariate signatures are learned directly from genome-wide data with no prior knowledge—to be accurate and robust. Importantly, these approaches are highly scalable with low marginal cost, essentially matching human expert annotation in a near-automated workflow. Our results support the notion that transcriptomics combined with machine learning could be used as part of an integrated -omics approach wherein risk prediction, differential diagnosis, and subclassification of AML are achieved by genomics while diagnosis could be assisted by transcriptomic-based machine learning.

Citation

Warnat-Herresthal, S., Perrakis, K., Taschler, B., Becker, M., Baßler, K., Beyer, M., Günther, P., Schulte-Schrepping, J., Seep, L., Klee, K., Ulas, T., Haferlach, T., Mukherjee, S., & Schultze, J. L. (2020). Scalable prediction of acute myeloid leukemia using high-dimensional machine learning and blood transcriptomics. iScience, 23(1), Article 100780. https://doi.org/10.1016/j.isci.2019.100780

• Journal Article Type: Article
• Acceptance Date: Dec 12, 2019
• Online Publication Date: Dec 18, 2019
• Publication Date: Jan 24, 2020
• Deposit Date: Jun 10, 2020
• Publicly Available Date: Jun 18, 2020
• Journal: iScience
• Publisher: Cell Press
• Peer Reviewed: Peer Reviewed
• Volume: 23
• Issue: 1
• Article Number: 100780
• DOI: https://doi.org/10.1016/j.isci.2019.100780
• Public URL: https://durham-repository.worktribe.com/output/1262894
• Related Public URLs: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6992905/