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.

PAPER: Stefanie Warnat-Herresthal Konstantinos Perrakis, Bernd Taschler, Matthias Becker, Kevin Baßler, Marc Beyer, Patrick Gu¨ nther,1 Jonas Schulte-Schrepping, Lea Seep, Kathrin Klee, Thomas Ulas, Torsten Haferlach, Sach Mukherjee, and Joachim L. Schultze