A machine learning model identifies M3-like subtype in AML based on PML/RARα targets
Tingting Shao,
Jianing Li,
Minghai Su,
Changbo Yang,
Yingying Ma,
Chongwen Lv,
Wei Wang,
Yunjin Xie,
Gang Xu,
Ce Shi,
Xinying Zhou,
Huitao Fan,
Yongsheng Li,
Juan Xu
Affiliations
Tingting Shao
College of Bioinformatics Science and Technology, Harbin Medical University, Harbin, Heilongjiang Province 150001, China
Jianing Li
College of Bioinformatics Science and Technology, Harbin Medical University, Harbin, Heilongjiang Province 150001, China
Minghai Su
College of Bioinformatics Science and Technology, Harbin Medical University, Harbin, Heilongjiang Province 150001, China
Changbo Yang
College of Bioinformatics Science and Technology, Harbin Medical University, Harbin, Heilongjiang Province 150001, China
Yingying Ma
College of Bioinformatics Science and Technology, Harbin Medical University, Harbin, Heilongjiang Province 150001, China
Chongwen Lv
College of Bioinformatics Science and Technology, Harbin Medical University, Harbin, Heilongjiang Province 150001, China
Wei Wang
The Second Affiliated Hospital, Harbin Medical University, Harbin, Heilongjiang Province 150001, China
Yunjin Xie
College of Bioinformatics Science and Technology, Harbin Medical University, Harbin, Heilongjiang Province 150001, China
Gang Xu
College of Bioinformatics Science and Technology, Harbin Medical University, Harbin, Heilongjiang Province 150001, China
Ce Shi
Key Laboratory of Hepatosplenic Surgery of Ministry of Education, NHC Key Laboratory of Cell Transplantation, the First Affiliated Hospital, Harbin Medical University, Harbin, Heilongjiang Province 150001, China
Xinying Zhou
Key Laboratory of Hepatosplenic Surgery of Ministry of Education, NHC Key Laboratory of Cell Transplantation, the First Affiliated Hospital, Harbin Medical University, Harbin, Heilongjiang Province 150001, China
Huitao Fan
Key Laboratory of Hepatosplenic Surgery of Ministry of Education, NHC Key Laboratory of Cell Transplantation, the First Affiliated Hospital, Harbin Medical University, Harbin, Heilongjiang Province 150001, China; Corresponding author
Yongsheng Li
School of Interdisciplinary Medicine and Engineering, Harbin Medical University, Harbin 150001, China; Corresponding author
Juan Xu
College of Bioinformatics Science and Technology, Harbin Medical University, Harbin, Heilongjiang Province 150001, China; Corresponding author
Summary: The typical genomic feature of acute myeloid leukemia (AML) M3 subtype is the fusion event of PML/RARα, and ATRA/ATO-based combination therapy is current standard treatment regimen for M3 subtype. Here, a machine-learning model based on expressions of PML/RARα targets was developed to identify M3 patients by analyzing 1228 AML patients. Our model exhibited high accuracy. To enable more non-M3 AML patients to potentially benefit from ATRA/ATO therapy, M3-like patients were further identified. We found that M3-like patients had strong GMP features, including the expression patterns of M3 subtype marker genes, the proportion of myeloid progenitor cells, and deconvolution of AML constituent cell populations. M3-like patients exhibited distinct genomic features, low immune activity and better clinical survival. The initiative identification of patients similar to M3 subtype may help to identify more patients that would benefit from ATO/ATRA treatment and deepen our understanding of the molecular mechanism of AML pathogenesis.
