Machine-learning-assisted integration of single-cell and bulk transcriptomics characterizes glioblastoma ecosystem states and immune-associated programs
4 affiliations
- 1Department of Neurosurgery, The Second Affiliated Hospital of Anhui Medical University, Anhui Medical University , ,
- 2Department of Neurosurgery, The First Affiliated Hospital of Wannan Medical University (Yijishan Hospital of Wannan Medical University) , ,
- 3Department of Neurosurgery, Shanghai Ninth People’s Hospital, Shanghai Jiao Tong University School of Medicine , ,
- 4Department of Neurosurgery, The First Affiliated Hospital of Wannan Medical University (Yijishan Hospita) , ,
Abstract
Background
Glioblastoma (GBM) is characterized by marked malignant-cell plasticity and a complex tumor ecosystem composed of heterogeneous malignant and microenvironmental cell populations. We integrated single-cell and bulk transcriptomic data to characterize reproducible GBM cell and ecosystem-associated states, evaluate cross-platform concordance, and examine immune-associated transcriptional programs while distinguishing descriptive associations from mechanistic inference.Methods
The deposited Smart-seq2 (7,930 cells) and 10x (16,201 cells) expression matrices from GSE131928/SCP393 were analyzed on their verified expression scales. Official annotations and malignant-state modules were audited, four broad malignant states were recomputed, and a tumor-held-out machine-learning label-transfer framework was applied to the 10x dataset. Public TCGA-GBM RNA-seq data were used to evaluate state- and microenvironment-associated transcriptional programs and to perform nested prediction benchmarking. Selected ecosystem-associated genes were additionally examined by RT-qPCR in glioma cell lines and normal human astrocytes.Results
Among Smart-seq2 cells, 6,576 malignant cells had valid state scores, whereas 287 alias-affected records were excluded from state-score denominators. The machine-learning label-transfer model achieved an out-of-fold accuracy of 0.998, and malignant-state fractions showed moderate-to-strong concordance across six shared tumor labels. At the tumor-label level, MES-like fraction was not significantly associated with macrophage fraction (Spearman rho = 0.171, P = 0.395), indicating that ecosystem-level transcriptional association should not be interpreted as a simple directional immune-to-state mechanism. In TCGA-GBM, MES and myeloid-associated programs correlated with immune and stromal expression signatures, whereas survival and 12-month prediction performance remained modest and specification-sensitive. RT-qPCR further demonstrated increased STAT3, CHI3L1, SPP1, and VEGFA expression in glioma cell lines relative to normal human astrocytes.Conclusion
Integrated single-cell and bulk transcriptomic analysis supports reproducible characterization of malignant-cell heterogeneity and immune-associated ecosystem features in IDH-wildtype GBM. Machine-learning-assisted cross-platform analysis provides a reproducible framework for evaluating tumor ecosystem-associated states, while the observed immune-mesenchymal associations remain descriptive rather than causal. Experimental RT-qPCR provides expression-level support for selected ecosystem-associated genes and highlights testable hypotheses for future functional and spatial studies.
Related
- Morphodynamic domains enable integration of live morphometrics and spatial transcriptomics
- Identification of Survival-Associated miRNA Signatures in Glioblastoma Using Next-Generation Sequencing
- TENASCIN-Dependent Mesenchymal–Epithelial Interactions Associated with Interstitial Microenvironment Remodeling in Cattle-Yak Lung: Insights from Single-Nucleus Transcriptomics
- LncRNA CCDC152 coordinates a tumor-associated selenoprotein P cycle that sustains selenium-dependent redox homeostasis in glioblastoma.
- EIF3B is associated with m⁶A-related regulation of E2F7 and promotes stemness in glioblastoma multiforme.
BibTeX
@article{cao2026machinelearningassisted,
title = {{Machine-learning-assisted integration of single-cell and bulk transcriptomics characterizes glioblastoma ecosystem states and immune-associated programs}},
author = {Jun Cao and Hao Cheng and Yu Wang and Bing Zhao and Yang Wang and Xiaochun Jiang},
journal = {Frontiers in cell and developmental biology},
year = {2026},
month = oct,
doi = {10.3389/fcell.2026.1967483},
url = {https://europepmc.org/article/PMC/PMC13716947},
note = {CC BY},
}
RIS
TY - JOUR
TI - Machine-learning-assisted integration of single-cell and bulk transcriptomics characterizes glioblastoma ecosystem states and immune-associated programs
AU - Jun Cao
AU - Hao Cheng
AU - Yu Wang
AU - Bing Zhao
AU - Yang Wang
AU - Xiaochun Jiang
PY - 2026
DA - 2026/10/14
JO - Frontiers in cell and developmental biology
DO - 10.3389/fcell.2026.1967483
UR - https://europepmc.org/article/PMC/PMC13716947
AB - Background Glioblastoma (GBM) is characterized by marked malignant-cell plasticity and a complex tumor ecosystem composed of heterogeneous malignant and microenvironmental cell populations. We integrated single-cell and bulk transcriptomic data to characterize reproducible GBM cell and ecosystem-associated states, evaluate cross-platform concordance, and examine immune-associated transcriptional programs while distinguishing descriptive associations from mechanistic inference.Methods The deposited Smart-seq2 (7,930 cells) and 10x (16,201 cells) expression matrices from GSE131928/SCP393 were analyzed on their verified expression scales. Official annotations and malignant-state modules were audited, four broad malignant states were recomputed, and a tumor-held-out machine-learning label-transfer framework was applied to the 10x dataset. Public TCGA-GBM RNA-seq data were used to evaluate state- and microenvironment-associated transcriptional programs and to perform nested prediction benchmarking. Selected ecosystem-associated genes were additionally examined by RT-qPCR in glioma cell lines and normal human astrocytes.Results Among Smart-seq2 cells, 6,576 malignant cells had valid state scores, whereas 287 alias-affected records were excluded from state-score denominators. The machine-learning label-transfer model achieved an out-of-fold accuracy of 0.998, and malignant-state fractions showed moderate-to-strong concordance across six shared tumor labels. At the tumor-label level, MES-like fraction was not significantly associated with macrophage fraction (Spearman rho = 0.171, P = 0.395), indicating that ecosystem-level transcriptional association should not be interpreted as a simple directional immune-to-state mechanism. In TCGA-GBM, MES and myeloid-associated programs correlated with immune and stromal expression signatures, whereas survival and 12-month prediction performance remained modest and specification-sensitive. RT-qPCR further demonstrated increased STAT3, CHI3L1, SPP1, and VEGFA expression in glioma cell lines relative to normal human astrocytes.Conclusion Integrated single-cell and bulk transcriptomic analysis supports reproducible characterization of malignant-cell heterogeneity and immune-associated ecosystem features in IDH-wildtype GBM. Machine-learning-assisted cross-platform analysis provides a reproducible framework for evaluating tumor ecosystem-associated states, while the observed immune-mesenchymal associations remain descriptive rather than causal. Experimental RT-qPCR provides expression-level support for selected ecosystem-associated genes and highlights testable hypotheses for future functional and spatial studies.
SN - 2296-634X
ER -