GEOapplication/xmlftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE336nnn/GSE336321/primaryOK200GenomicsHomo sapiensGenome binding/occupancy profiling by high throughput sequencinghttps://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE336321GEOGSEfalseDecoding Plasticity Regulators and Transition Trajectories in Glioblastoma with Single-cell Multiomics [ATAC-seq]Glioblastoma (GB) is incurable and resistant to therapy despite genomic stability under treatment, implicating non-genetic cellular plasticity as a central driver of progression. Whether such plasticity reflects stochastic state switching or is governed by predictable gene regulation has remained unresolved. We applied scDORI, a deep-learning framework that infers enhancer-driven gene regulatory networks at single cell resolution, to single-nucleus multi-ome profiles of over one million cells from primary GBs. Integrating computational inference with systematic gain-of-function screens across patient-derived models, we show that GB cellular plasticity is governed by a structured regulatory program with an asymmetric interplay of activators and repressors. The resulting transition landscape is hierarchical and predictable, yet permits cross-lineage trajectories absent from normal neurodevelopment. Within this landscape, low-plasticity states such as the Neuronal-like state are not stable differentiation endpoints but actively maintained configurations, stabilized by a network of safeguard repressors that silence alternate fates. MYT1L emerged as the dominant member of this network, binding and repressing master regulators of every alternative state to consolidate Neuronal-like identity. MYT1L restricted plasticity even under standard-of-care therapy and suppressed tumor growth and invasion in vivo. Conversely, MYT1L loss reactivated plasticity and accelerated malignant features, demonstrating that low-plasticity identity requires continuous repression. These findings reframe malignant cell state stability as a balance between activation and continuous repression, and nominate safeguard repressors as candidate therapeutic targets distinct from differentiation-inducing activators, with potential relevance across cancers in which phenotypic switching drives therapy resistance.2026/08/24GSE336321GSM9832390GSM9832392GSM9832391GSM9832394GSM9832393GSM9832396GSM9832395GSM9832431GSM9832398GSM9832430GSM9832397GSM9832433GSM9832399GSM9832432GSM9832435GSM9832434GSM9832437GSM9832436GSM9832439GSM9832438GSM9832440GSM9832442GSM9832441GSM9832444GSM9832400GSM9832443GSM9832325GSM9832402GSM9832446GSM9832401GSM9832445GSM9832404GSM9832448GSM9832447GSM9832403GSM9832406GSM9832405GSM9832408GSM9832407GSM9832409GSM9832370GSM9832372GSM9832371GSM9832374GSM9832373GSM9832376GSM9832375GSM9832411GSM9832378GSM9832410GSM9832377GSM9832413GSM9832379GSM9832412GSM9832415GSM9832414GSM9832417GSM9832416GSM9832419GSM9832418GSM9832381GSM9832380GSM9832383GSM9832382GSM9832385GSM9832384GSM9832387GSM9832420GSM9832386GSM9832422GSM9832389GSM9832421GSM9832388GSM9832424GSM9832423GSM9832426GSM9832425GSM9832428GSM9832427GSM983242930173336321Homo sapiens