Relational Graph Convolutional Networks for Glioblastoma Biomarker Discovery via ceRNA and Copy Number Variation Analysis

Abstract A040: Network Analysis and Deep Learning Identify Cascade Vulnerabilities in Glioblastoma Stem Cell Plasticity

Glioblastoma (GBM) is the most aggressive primary brain tumor and remains universally fatal despite advances in surgery, radiation, and chemotherapy. This poor prognosis is largely driven by glioblastoma stem cells (GSCs), which evade therapy through transcriptional plasticity, which reprograms their cellular state via interconnected regulatory networks. Previous targeting of single pathways has failed due to compensatory redundancy within these networks. We developed a computational framework integrating transcriptomic data, network topology analysis, and deep learning to identify multi-target strategies. RNA-seq data from 546 GBM patients across The Cancer Genome Atlas (TCGA) and Chinese Glioma Genome Atlas (CGGA) cohorts were analyzed using partial correlation and cross-cohort meta-analysis to identify stable regulatory interactions independent of major driver mutations. Network topology defined hub genes, and in silico perturbation modeled multi-gene inhibition. Two deep learning models were trained on full transcriptomes and stratified patients and predicted sensitivity to network-targeted interventions respectively. Structural modeling and molecular docking evaluated binding of a bispecific single chain fragment variable (scFv) targeting CD44 and CD133, major markers of GSCs. An HSV-1–based oncolytic virus was computationally designed to deliver shRNAs targeting EZH2, KDM1A, and DNMT1, along with miR-124 and inhibitors of NOTCH1 and STAT3 signaling. Network analysis identified reproducible hubs centered on MYC and NOTCH1. Additional hub genes (EZH2, DNMT1, KDM1A, STAT3) were associated with therapeutic resistance and poor survival. Patient stratification revealed a high-plasticity subgroup with worse survival (HR 1.53, p < 0.01) and elevated MYC and STAT3 associated programs. Molecular docking confirmed strong binding of the bispecific scFv to CD44 and CD133 (scores < −300 in HDOCK). The deep learning model demonstrated robust performance (AUC 0.96 internal; 0.857 cross-dataset). GBM resistance appears to arise from interconnected regulatory hubs rather than isolated pathways. Computational modeling suggests that simultaneous disruption of MYC and NOTCH1-centered networks may destabilize multiple resistance mechanisms. This study provides a systems-level framework for identifying multi-target therapeutic strategies and supports the conceptual development of network-directed oncolytic approaches for GSC-driven GBM. Experimental validation will be required to confirm these predictions. Generative AI was used to assist in editing and refining the text of this abstract. Darsh Dadhich. Network Analysis and Deep Learning Identify Cascade Vulnerabilities in Glioblastoma Stem Cell Plasticity [abstract]. In: Proceedings of AACR Drug Discovery and Development (AACR D3) Conference; 2026 Jul 21-24; Boston, MA. Philadelphia (PA): AACR; Clin Cancer Res 2026;32(14_Suppl):Abstract nr A040.

Graph Neural Networks for Cancer Driver Gene Prediction: From Fundamentals to Applications.

Integrative Bioinformatics and Machine Learning Analysis Identifies Novel Molecular Biomarkers in Prostate Adenocarcinoma

Prostate adenocarcinoma is characterized by substantial inter-patient heterogeneity, limiting the clinical reliability of conventional diagnostic tools, including prostate-specific antigen testing. This limitation underscores the need for robust molecular biomarkers that may complement conventional diagnostic tools, highlighting the urgent need for biomarkers capable of enhancing diagnostic accuracy and enabling more precise risk stratification. In the present study, transcriptomic data from The Cancer Genome Atlas (TCGA) were analyzed using an integrative bioinformatics and machine learning pipeline., The proposed workflow was designed as a stepwise and reproducible biomarker prioritization framework in which differential expression analysis, functional enrichment, protein–protein interaction (PPI) based network interpretation, graph-convolutional feature selection, and hybrid ensemble machine learning were sequentially integrated. Differential gene expression analysis was combined with pathway enrichment (Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG), and Reactome), protein–protein interaction network construction, and graph-convolutional feature selection. Multiple machine learning algorithms, including Random Forest, Gradient Boosting Machine, Support Vector Classifier, Artificial Neural Network, and AdaBoost, were systematically evaluated. A hybrid ensemble model integrating Gradient Boosting Machine and Random Forest (GBM+RF) was subsequently developed. Model performance was assessed using accuracy, sensitivity, specificity, and area under the Receiver Operating Characteristic (ROC) and externally validated using the independent GSE14206 dataset. The analysis revealed a coordinated molecular pattern characterized by dysregulated cell cycle activity and enhanced interferon-mediated immune signaling. Protein–protein interaction analysis identified STAT1 and PLK1 as highly connected network hub genes within immune-related and cell-cycle-associated modules. Among the evaluated models, the hybrid GBM+RF framework achieved the highest predictive performance on the TCGA dataset, with AUC: 0.9526; Accuracy: 97.49%. External validation using the GSE14206 dataset confirmed the robustness of this model (AUC: 0.9156; Accuracy: 91.53%). These findings support a broader multi-gene candidate signature in prostate adenocarcinoma, in which machine learning prioritized genes such as XAF1, APP, RPA3, IFIH1, UBE2D2, RSAD2, KIF2C, and PLK1, while STAT1 and PLK1 provided complementary network-level biological relevance. The proposed framework provides a robust and transferable strategy for biomarker discovery and precision oncology.

WGCNA and ceRNA network analysis in ovarian cancer: a review of integrative approaches for biomarker discovery

A cross-platform gene signature in glioblastoma

Glioblastoma (GBM) is a highly aggressive brain cancer with poor patient outcomes. This study uses a multi-step approach to identify reliable genetic markers for the disease. First, we analysed the GSE4290 dataset, comparing 77 tumour samples to 23 healthy brain controls to identify significantly overexpressed genes. To ensure these findings were not specific to a single study, we validated our results using the GSE147352 dataset. Finally, we correlated these gene expression levels with clinical outcomes using survival data from The Cancer Genome Atlas. Our results identified a core set of genes, including topoisomerase II alpha, maternal embryonic leucine zipper kinase, BIRC5 and abnormal spindle-like microcephaly (ASPM), which are consistently upregulated in tumours but do not significantly predict patient survival. These findings provide a validated molecular signature that defines the GBM transcriptome, though its clinical impact appears decoupled from overall survival, likely due to intensive treatment protocols or other dominant biological factors.

Multi-level Transcriptomic and Machine-learning Analyses Identify MZT1 as a Proliferation-associated Prognostic Marker in Lung Adenocarcinoma

Abstract Background/Aim: Lung adenocarcinoma (LUAD) exhibits substantial molecular heterogeneity and variable clinical outcomes, highlighting the need for biomarkers that reflect core tumor biological processes. Centrosome-associated proteins regulate mitotic fidelity and genome stability, yet their roles in LUAD remain incompletely defined. In this study, we systematically characterized mitotic spindle organizing protein 1 (MOZART1; MZT1) and related family members in LUAD. Materials and Methods: We performed integrated analyses combining bulk transcriptomic datasets, survival modeling, gene set enrichment, immune deconvolution, machine-learning based prognostic modeling, and single-cell RNA sequencing. Expression patterns and clinical associations of MZT family genes were evaluated across pan-cancer and LUAD cohorts. Results: MZT family genes were consistently upregulated in tumor tissues, with MZT1 showing the most robust expression pattern. Elevated MZT1 expression was significantly associated with reduced overall survival. Functional analyses revealed coordinated activation of proliferative and genome maintenance pathways, including G2/M checkpoint regulation, E2F and MYC signaling, and DNA repair. A multivariable analysis indicated that the prognostic association of MZT1 was reduced after adjusting for canonical proliferation markers, suggesting partial overlap with established proliferation signals. The LASSO-based Cox model demonstrated stable time-dependent predictive performance at 1-, 3-, and 5-year survival. Immune analyses indicated associations between MZT1 expression and tumor microenvironmental features. Single-cell analysis showed that MZT1 expression was predominantly enriched in malignant epithelial cells and associated with proliferative cellular states. Protein-level validation supported concordance with transcriptomic findings. Conclusion: MZT1 is a proliferation-associated marker that integrates clinical risk, transcriptional programs, cellular heterogeneity, and predictive modeling in LUAD, providing a potential framework for biomarker development and risk stratification.