PD Dr. Marc Beyer
Deutsches Zentrum für Neurodegenerative Erkrankungen e. V. (DZNE)
marc.beyer@dzne.de View member: PD Dr. Marc Beyer
iScience
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.
Copyright © 2020 The Authors. Published by Elsevier Inc. All rights reserved.
PMID: 31918046
Deutsches Zentrum für Neurodegenerative Erkrankungen e. V. (DZNE)
marc.beyer@dzne.de View member: PD Dr. Marc BeyerLife & Medical Sciences Institute (LIMES)
t.ulas@uni-bonn.de View member: Dr. Thomas UlasLife & Medical Sciences Institute (LIMES)
j.schultze@uni-bonn.de View member: Prof. Dr. med. Joachim L. Schultze