Rapid Epigenomic Classification of Acute Leukemia
Ontology highlight
ABSTRACT: Acute leukemias (AL) are aggressive blood cancers that require precise molecular classification and urgent treatment. However, standard-of-care diagnostic tests are time and resource intensive and do not capture the full spectrum of AL heterogeneity. Here, we developed a machine learning framework to classify AL using genome-wide DNA methylation profiling. We first assembled a large reference cohort (n=2,540 samples) and defined 38 distinct methylation classes across AL lineages and age groups. A subset of methylation classes mirrored established AL categories defined by genetics, such as AML with CBFB::MYH11 and B-ALL with ETV6::RUNX1, while others revealed epigenetic heterogeneity not captured by standard-of-care testing alone, including four methylation classes associated with NPM1-mutant AML (HOXA/B-activated) and four with KMT2A-rearranged AML (HOXA-activated). Using this reference, we next developed a deep neural network model (MARLIN) for methylation-based AL classification from extremely sparse data, and applied this for rapid analysis of clinical samples profiled by nanopore sequencing. In a retrospective AL cohort, MARLIN-based classifications were concordant with standard-of-care diagnoses in 25/26 (96.2%) cases with high-confidence prediction scores, including samples of diverse lineages and molecular subtypes. In five additional patients presenting with suspected AL, we performed nanopore sequencing and MARLIN classification of clinical blood and bone marrow samples in real-time, typically achieving an accurate methylation class prediction in less than two hours from sample receipt and less than one hour of sequencing time. In summary, we present a DNA methylation-based machine learning framework for rapid AL classification in the clinic that can complement and enhance standard-of-care diagnostics.
ORGANISM(S): Homo sapiens
PROVIDER: GSE280090 | GEO | 2025/06/16
REPOSITORIES: GEO
ACCESS DATA