Acute leukemia requires precise molecular classification and urgent treatment. However, standard-of-care diagnostic tests are time-intensive and do not capture the full spectrum of acute leukemia heterogeneity.
Here, we developed a neural network (MARLIN; methylation- and AI-guided rapid leukemia subtype inference) for acute leukemia classification from sparse DNA methylation profiles.
When coupling MARLIN to nanopore sequencing, results can be generated rapidly and in real-time, setting a realistic timeframe of hours or even minutes for generating preliminary molecular classifications.
Methylation-based classification may resolve blind spots of conventional molecular diagnostic and cytogenetic testing, including classes associated with cryptic rearrangements (for example, DUX4-r) or molecular drivers of lineage-ambiguous cases (for example, MPAL with BCL11B activation).
Methylation-based profiling may reveal novel predictive signatures of drug response. For example, methylation-based classification can identify HOX-activated subgroups directly regardless of genetic driver.
Ultimately, we envision methylation-based acute leukemia classifications complementing standard-of-care diagnostic tests to provide more comprehensive and timely information to pathologists, clinicians and patients.
【MORE】