A machine learning approach to integrate big data for precision medicine in acute myeloid leukemia

• Published in: Nature communications Vol. 9; no. 1; pp. 42 - 13
• Main Authors: Lee, Su-In, Celik, Safiye, Logsdon, Benjamin A., Lundberg, Scott M., Martins, Timothy J., Oehler, Vivian G., Estey, Elihu H., Miller, Chris P., Chien, Sylvia, Dai, Jin, Saxena, Akanksha, Blau, C. Anthony, Becker, Pamela S.
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 03.01.2018; Nature Publishing Group; Nature Portfolio
• Subjects: 13/109; 13/31; 38/61; 49/39; 49/47; 49/91; 631/114/1305; 631/67/1990/283/1897; 631/67/69; 692/4017; Acute myeloid leukemia; Algorithms; Antineoplastic Agents - pharmacology; Antineoplastic Agents - therapeutic use; Biomarkers, Tumor - metabolism; Cancer; Cell Line; Chemotherapy; Computer applications; Data management; Datasets as Topic; DNA Helicases - genetics; DNA topoisomerase (ATP-hydrolysing); Drug Resistance, Neoplasm - genetics; Etoposide; Etoposide - pharmacology; Etoposide - therapeutic use; Gene expression; Genomes; Humanities and Social Sciences; Humans; Learning algorithms; Leukemia; Leukemia, Myeloid, Acute - drug therapy; Leukemia, Myeloid, Acute - genetics; Machine Learning; Markers; Mitoxantrone; multidisciplinary; Myeloid leukemia; Nuclear Proteins - genetics; Patients; Precision medicine; Precision Medicine - methods; Science; Science (multidisciplinary); Sensitivity; Topoisomerase II Inhibitors - pharmacology; Topoisomerase II Inhibitors - therapeutic use; Transcription Factors - genetics
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-017-02465-5

Cancers that appear pathologically similar often respond differently to the same drug regimens. Methods to better match patients to drugs are in high demand. We demonstrate a promising approach to identify robust molecular markers for targeted treatment of acute myeloid leukemia (AML) by introducing: data from 30 AML patients including genome-wide gene expression profiles and in vitro sensitivity to 160 chemotherapy drugs, a computational method to identify reliable gene expression markers for drug sensitivity by incorporating multi-omic prior information relevant to each gene’s potential to drive cancer. We show that our method outperforms several state-of-the-art approaches in identifying molecular markers replicated in validation data and predicting drug sensitivity accurately. Finally, we identify SMARCA4 as a marker and driver of sensitivity to topoisomerase II inhibitors, mitoxantrone, and etoposide, in AML by showing that cell lines transduced to have high  SMARCA4 expression reveal dramatically increased sensitivity to these agents. Identification of markers of drug response is essential for precision therapy. Here the authors introduce an algorithm that uses prior information about each gene’s importance in AML to identify the most predictive gene-drug associations from transcriptome and drug response data from 30 AML samples.