Scalable Prediction of Acute Myeloid Leukemia Using High-Dimensional Machine Learning and Blood Transcriptomics

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 lea...

Full description

Saved in:
Bibliographic Details
Published iniScience Vol. 23; no. 1; p. 100780
Main Authors 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.
Format Journal Article
LanguageEnglish
Published United States Elsevier Inc 24.01.2020
Elsevier
Subjects
Artificial Intelligence
Biological Sciences
Cancer
Computer Science
Omics
Transcriptomics
Biological Sciences
Transcriptomics
Artificial Intelligence
Computer Science
Omics
Cancer
Online AccessGet full text

Cover

More Information
Summary: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. [Display omitted] •Study presents one of the largest transcriptomics datasets to date for AML prediction•Effective classifiers can be obtained by high-dimensional machine learning•Accuracy increases with dataset size•Includes challenging scenarios such as cross-study and cross-technology Artificial Intelligence; Biological Sciences; Cancer; Computer Science; Omics; Transcriptomics
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
Lead Contact
These authors contributed equally
ISSN:2589-0042
2589-0042
DOI:10.1016/j.isci.2019.100780