Related Experiment Video
Updated: May 2, 2026
MicroRNA Based Liquid Biopsy: The Experience of the Plasma miRNA Signature Classifier MSC for Lung Cancer Screening
Published on: October 26, 2017
AutoML identification of microRNA biomarkers in high-risk pediatric acute lymphoblastic leukemia
Ioannis Kyriakidis1, Zacharias Papadovasilakis2, Georgios Papoutsoglou2
1Department of Pediatric Hematology-Oncology & Autologous Hematopoietic Stem Cell Transplantation Unit, University Hospital of Heraklion & Laboratory of Blood Diseases and Childhood Cancer Biology, School of Medicine, University of Crete, 71003, Heraklion, Greece.
Abstract:
Despite significant advancements in overall survival rates for childhood acute lymphoblastic leukemia (ALL), relapse continues to pose a major challenge. MicroRNAs have proven valuable for improving diagnosis, treatment, and survival outcomes, establishing themselves as key biomarkers. Using RNA-seq data from 123 ALL patients and employing predictive modeling via automated machine learning (AutoML) alongside causal-inspired biomarker discovery, we identified highly predictive microRNA signatures linked to high-risk strata and clinical features in unfavorable cases. We further identified predictive signatures for each genetic subtype of childhood ALL, highlighting shared miRNAs throughout the study. A thorough literature review of the relationships between miRNA differential expression and key high-risk features in childhood ALL [immunophenotype, elevated white blood cell counts at diagnosis, central nervous system involvement, measurable residual disease (MRD), and chemoresistance] confirmed the signatures generated in this study. Our results revealed a highly predictive signature distinguishing B- and T-ALL, associated with apoptosis, confirming the reported difference between the two immunophenotypes. Additionally, miR-223 emerged as crucial for high-risk stratification and chemoresistant MRD-positive cases. These findings demonstrate the potential of AutoML tools to reveal novel biological insights in pediatric ALL, driving future advancements.
Insights
MicroRNAs are key biomarkers for childhood acute lymphoblastic leukemia (ALL). Automated machine learning identified microRNA signatures predicting high-risk ALL and treatment resistance, offering new diagnostic and therapeutic insights.
Area of Science:
- Oncology
- Genetics
- Biomarker Discovery
Background:
- Childhood acute lymphoblastic leukemia (ALL) survival rates have improved, but relapse remains a significant challenge.
- MicroRNAs (miRNAs) are emerging as critical biomarkers for improving ALL diagnosis, treatment, and patient outcomes.
- Identifying reliable biomarkers is crucial for stratifying patients and personalizing treatment strategies in pediatric ALL.
Purpose of the Study:
- To identify novel microRNA signatures associated with high-risk features and genetic subtypes in childhood ALL.
- To leverage automated machine learning (AutoML) and causal-inspired methods for biomarker discovery.
- To validate identified miRNA signatures against established high-risk clinical features.
Main Methods:
- RNA sequencing data from 123 pediatric ALL patients were analyzed.
- Predictive modeling was performed using automated machine learning (AutoML).
- Causal-inspired biomarker discovery methods were employed to identify significant miRNA signatures.
Main Results:
- Highly predictive miRNA signatures were identified for high-risk ALL strata and unfavorable clinical features.
- Distinct miRNA signatures were discovered for each genetic subtype of childhood ALL, with shared miRNAs noted across subtypes.
- A signature distinguishing B-cell ALL (B-ALL) from T-cell ALL (T-ALL) was found, linked to apoptosis.
- miR-223 was identified as a crucial miRNA for high-risk stratification and chemoresistant measurable residual disease (MRD)-positive cases.
Conclusions:
- Automated machine learning (AutoML) can uncover novel biological insights in pediatric ALL.
- Identified miRNA signatures hold potential for improved diagnosis, risk stratification, and treatment strategies in childhood ALL.
- These findings underscore the value of miRNA biomarkers in understanding and combating pediatric ALL relapse.
