Related Experiment Video
Updated: Jul 4, 2025
Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
Published on: August 16, 2020
A machine learning model identifies M3-like subtype in AML based on PML/RARα targets
Tingting Shao1, Jianing Li1, Minghai Su1
1College of Bioinformatics Science and Technology, Harbin Medical University, Harbin, Heilongjiang Province 150001, China.
Abstract:
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.
Insights
A new machine-learning model identifies Acute Myeloid Leukemia (AML) M3 subtype and similar patients. This approach may expand eligibility for ATRA/ATO therapy, improving outcomes for more AML patients.
Area of Science:
- Hematology
- Genomics
- Computational Biology
Background:
- Acute Myeloid Leukemia (AML) M3 subtype is characterized by the PML/RARα fusion event.
- Current standard treatment for M3 AML involves ATRA/ATO combination therapy.
Purpose of the Study:
- Develop a machine-learning model to accurately identify M3 AML patients based on gene expression.
- Identify 'M3-like' non-M3 AML patients who could potentially benefit from ATRA/ATO therapy.
Main Methods:
- Analysis of gene expression data from 1228 AML patients.
- Machine learning model development focusing on PML/RARα target gene expression.
- Identification of M3-like patients using myeloid progenitor cell proportions and gene expression patterns.
Main Results:
- The developed machine-learning model achieved high accuracy in identifying M3 AML patients.
- M3-like patients were identified, exhibiting strong common myeloid progenitor (GMP) features and distinct genomic profiles.
- M3-like patients demonstrated lower immune activity and better clinical survival rates.
Conclusions:
- Machine learning can effectively identify M3 AML and M3-like patients.
- Identifying M3-like patients may broaden the application of ATRA/ATO therapy.
- This research deepens the understanding of AML pathogenesis and treatment strategies.
