· · Single source ·Updated

Researchers decode regulatory programs governing glioblastoma plasticity using deep learning

Scientists have introduced a new deep-learning framework to analyze gene regulation in over one million cells from primary glioblastoma tumors.

Decoding the regulatory programs governing glioblastoma plasticity
File photo Decoding the regulatory programs governing glioblastoma plasticity Photo: Nature

New computational tool reveals hidden networks

The study presents scDORI, a system that infers enhancer-driven gene-regulatory networks at single-cell resolution. This approach applies to single-nucleus multiome profiles derived from more than one million cells collected from primary glioblastomas.

Structured programs drive tumor progression

Integration of computational inference with systematic perturbation screens shows that a structured regulatory program governs cellular plasticity. This landscape is hierarchical and predictable yet allows cross-lineage trajectories absent from normal neurodevelopment.

MYT1L maintains neuronal-like identity states

Low-plasticity states such as the neuronal-like state are actively maintained configurations rather than stable differentiation end points. The protein MYT1L acts as the dominant member of a network that silences alternative fates by repressing master regulators.

Reported by one outlet

Only one outlet has published this. Nothing here has been checked against a second report, so read it as that outlet's account and follow the link below for the original.

Reported by

1 independent outlet. Headline as published. Links open the original report.