AI-Powered Liquid Biopsy Classifies Pediatric Brain Tumors

New M-PACT tool uses AI to analyze cerebrospinal fluid and molecularly classify tumors based on DNA methylation patterns.

Published on Feb. 20, 2026

Got story updates? Submit your updates here. ›

Researchers at St. Jude Children's Research Hospital, in collaboration with scientists at the Hopp Children's Cancer Center Heidelberg (KiTZ), German Cancer Research Center (DKFZ) and other international centers, have created Methylation-based Predictive Algorithm for CNS Tumors (M-PACT), an AI-powered tool that can successfully identify 92% of brain tumors in a benchmarking test by analyzing circulating tumor DNA (ctDNA) in cerebrospinal fluid. M-PACT can differentiate relapse from secondary tumors and track cancer progression or treatment response.

Why it matters

Liquid biopsies are a noninvasive way to learn about a cancer's biology, but technological limitations with the small amount of ctDNA available from pediatric brain tumor liquid biopsies have previously stymied broad use of the approach for those patients. M-PACT addresses this challenge and sets a new standard for pediatric brain tumor diagnostics, treatment monitoring and surveillance.

The details

M-PACT utilizes a novel deep neural network training strategy using more than 5,000 DNA methylation profiles across roughly 100 tumor entities. This brings methylation-based ctDNA analysis up to, and beyond, current standards seen from tissue biopsies. M-PACT's sensitivity also enables it to look beyond tumor cells to identify noncancerous cell types contributing to the tumor microenvironment, providing unmatched insight into cancer evolution, especially during therapy.

  • The study was published on February 17, 2026.

The players

Paul Northcott

The corresponding author of the study, director of the Center of Excellence in Neuro-Oncology Sciences (CENOS) and a member of the Department of Developmental Neurobiology at St. Jude Children's Research Hospital.

Katie Han

A co-first author of the study, a PhD student in the St. Jude Graduate School of Biomedical Sciences and Department of Developmental Neurobiology, and an MD candidate at the University of Tennessee Health Sciences Center.

Kyle Smith

A co-first author of the study, from the Department of Developmental Neurobiology at St. Jude Children's Research Hospital.

Johannes Gojo

A co-senior author of the study, from the Medical University of Vienna.

Kristian Pajtler

A co-senior author of the study, from the Hopp Children's Cancer Center, Heidelberg University Hospital, German Cancer Consortium and German Cancer Research Center, and Heidelberg University.

Got photos? Submit your photos here. ›

What they’re saying

“This is a next-generation assay and computational framework that we've optimized and applied across a range of pediatric brain tumor patients. M-PACT is about taking liquid biopsy to another level in pediatric neuro-oncology and applying the technology across many different clinical scenarios.”

— Paul Northcott, Center of Excellence in Neuro-Oncology Sciences (CENOS) director and Department of Developmental Neurobiology member

“Traditionally, methylation-based diagnostics for ctDNA use classifiers designed for tumor tissue, which have higher DNA input. We reversed the usual flow and designed M-PACT for ctDNA itself with applicability to tissue, instead of the other way around.”

— Katie Han, PhD student in the St. Jude Graduate School of Biomedical Sciences and Department of Developmental Neurobiology, and MD candidate at University of Tennessee Health Sciences Center

“We developed M-PACT by computationally mixing large reference datasets with normal cell-free DNA datasets. We trained it extensively and showed that even tiny amounts of ctDNA can be accurately classified.”

— Kyle Smith, Department of Developmental Neurobiology

What’s next

The researchers are confident that M-PACT's robust framework offers a wide range of potential use cases beyond pediatric brain tumors, and plan to expand the informatics to classify the full scope of cancer types diagnosed in children.

The takeaway

M-PACT represents a significant advancement in liquid biopsy technology, enabling noninvasive and highly accurate molecular classification of pediatric brain tumors. This tool has the potential to transform diagnostic, treatment monitoring, and surveillance capabilities in pediatric neuro-oncology and beyond.