Deep Learning-based Feature Discovery for Decoding Phenotypic Plasticity in Pediatric High-Grade Gliomas Single-Cell Transcriptomics

By use of complex network dynamics and graph-based machine learning, we identified critical determinants of lineage-specific plasticity across the single-cell transcriptomics of pediatric high-grade glioma (pHGGs) subtypes: IDHWT glioblastoma and K27M-mutant glioma. Our study identified network interactions regulating glioma morphogenesis via the tumor-immune microenvironment, including neurodevelopmental programs, calcium dynamics, iron metabolism, metabolic reprogramming, and feedback loops between MAPK/ERK and WNT signaling. These relationships highlight the emergence of a hybrid spectrum of cellular states navigating a disrupted neuro-differentiation hierarchy. We identified transition genes such as DKK3, NOTCH2, GATAD1, GFAP, and SEZ6L in IDHWT glioblastoma, and H3F3A, ANXA6, HES6/7, SIRT2, FXYD6, PTPRZ1, MEIS1, CXXC5, and NDUFAB1 in K27M subtypes. We also identified MTRNR2L1, GAPDH, IGF2, FKBP variants, and FXYD7 as transition genes that influence cell fate decision-making across both subsystems. Our findings suggest pHGGs are developmentally trapped in states exhibiting maladaptive behaviors, and hybrid cellular identities. In effect, tumor heterogeneity (metastability) and plasticity emerge as stress-response patterns to immune-inflammatory microenvironments and oxidative stress. Furthermore, we show that pHGGs are steered by developmental trajectories from radial glia predominantly favoring neocortical cell fates, in telencephalon and prefrontal cortex (PFC) differentiation. By addressing underlying patterning processes and plasticity networks as therapeutic vulnerabilities, our findings provide precision medicine strategies aimed at modulating glioma cell fates and overcoming therapeutic resistance. We suggest transition therapy toward neuronal-like lineage differentiation as a potential therapy to help stabilize pHGG plasticity and aggressivity.