This study determined the expression of five novel biomarker candidates in IDH wild-type glioblastoma (GBM) tissues compared to non-malign brain parenchyma, as well as their prognostic relevance for the GBM patients\' outcomes. The markers were analysed by immunohistochemistry in tumour tissues (n = 186) and healthy brain tissues (n = 54). The association with the patients\' overall survival (OS) and progression-free survival (PFS) was assessed by Kaplan-Meier and log-rank test. The prognostic value of the markers was determined using multivariate Cox proportional hazard models. AGTRAP, DIVERSIN, cytoplasmic NEDD8 (NEDD8c) and RRM1 were significantly overexpressed in tumour tissues compared to the healthy brain, while the opposite was observed for ALKBH3. AGTRAP, ALKBH3, NEDD8c and RRM1 were significantly associated with OS in univariate analysis. AGTRAP and RRM1 were also independent prognostic factors for OS in multivariate analysis. For PFS, only AGTRAP and NEDD8c reached significance in univariate analysis. Additionally, AGTRAP was an independent prognostic factor for PFS in multivariate models. Finally, combined analysis of the markers enhanced their prognostic accuracy. The combination AGTRAP/ALKBH3 had the strongest prognostic value for the OS of GBM patients. These findings contribute to a better understanding of the GBM pathophysiology and may help identify novel therapeutic targets in this type of cancer.

IDH wild-type glioblastoma (GBM) intrinsic subtypes have been linked to different molecular landscapes and outcomes. Accurate prediction of molecular subtypes of GBM is very important to guide clinical diagnosis and treatment. Leveraging machine learning technology to improve the subtype classification was considered a robust strategy. Several single machine learning models have been developed to predict survival or stratify patients. An ensemble learning strategy combines several basic learners to boost model performance. However, it still lacked a robust stacking ensemble learning model with high accuracy in clinical practice. Here, we developed a novel integrative stacking ensemble model framework (ecGBMsub) for improving IDH wild-type GBM molecular subtype classification. In the framework, nine single models with the best hyperparameters were fitted based on extrachromosomal circular DNA (eccDNA) molecular profiling. Then, the top five optimal single models were selected as base models. By randomly combining the five optimal base models, 26 different combinations were finally generated. Nine different meta-models with the best hyperparameters were fitted based on the prediction results of 26 different combinations, resulting in 234 different stacked ensemble models. All models in ecGBMsub were comprehensively evaluated and compared. Finally, the stacking ensemble model named \"XGBoost.Enet-stacking-Enet\" was chosen as the optimal model in the ecGBMsub framework. A user-friendly web tool was developed to facilitate accessibility to the XGBoost.Enet-stacking-Enet models (https://lizesheng20190820.shinyapps.io/ecGBMsub/).

To develop and validate a conventional MRI-based radiomic model for predicting prognosis in patients with IDH wild-type glioblastoma (GBM) and reveal the biological underpinning of the radiomic phenotypes.
A total of 801 adult patients (training set, N = 471; internal validation set, N = 239; external validation set, N = 91) diagnosed with IDH wild-type GBM were included. A 20-feature radiomic risk score (Radscore) was built for overall survival (OS) prediction by univariate prognostic analysis and least absolute shrinkage and selection operator (LASSO) Cox regression in the training set. GSEA and WGCNA were applied to identify the intersectional pathways underlying the prognostic radiomic features in a radiogenomic analysis set with paired MRI and RNA-seq data (N = 132). The biological meaning of the conventional MRI sequences was revealed using a Mantel test.
Radscore was demonstrated to be an independent prognostic factor (P < 0.001). Incorporating the Radscore into a clinical model resulted in a radiomic-clinical nomogram predicting survival better than either the Radscore model or the clinical model alone, with better calibration and classification accuracy (a total net reclassification improvement of 0.403, P < 0.001). Three pathway categories (proliferation, DNA damage response, and immune response) were significantly correlated with the prognostic radiomic phenotypes.
Our findings indicated that the prognostic radiomic phenotypes derived from conventional MRI are driven by distinct pathways involved in proliferation, DNA damage response, and immunity of IDH wild-type GBM.

Cyclin-dependent kinases, CDK4 and CDK6, are essential in regulating the cell cycle, which is disrupted in cancers like isocitrate dehydrogenase wild-type glioblastoma (GBM). Currently marketed CDK4/6 inhibitors, including abemaciclib, have shown preclinical efficacy in solid tumors, but factors such as poor blood-brain barrier (BBB) penetration limit their efficacy in GBM. GLR2007 is an investigational CDK4/6 inhibitor with the potential for improved BBB penetration. In vitro assays were used to assess the potency and inhibition of CDK4/6 enzymatic activity of GLR2007. Using in vivo assays, the distribution of radiolabeled GLR2007 in rats was determined through quantitative whole-body autoradiography. The antitumor efficacy of GLR2007 was evaluated in human GBM and breast cancer orthotopic mice xenograft models, and human lung, colorectal, and liver cancer in a subcutaneous xenograft model. In tumor cell line proliferation assays, GLR2007 inhibited proliferation at lower concentration values than abemaciclib in 19 of 20 GBM, five of seven breast, 20 of 21 lung, and 24 of 24 liver cancer cell lines. Total levels of radiolabeled GLR2007 in the brains of rats exceeded those in plasma by 2.3-4.5-fold from 2-6 hours after dosing. A xenograft model showed that, compared with vehicle control, 50 mg/kg GLR2007 induced 95.9% tumor growth inhibition (TGI) (P<0.001) in GBM orthotopic xenografts, 81.4% TGI (P=0.037) in breast cancer orthotopic xenografts, and 91.5% TGI (P<0.001) in colorectal cancer subcutaneous xenografts. These studies show possible BBB penetration of GLR2007 and demonstrate its potential as a CDK4/6 inhibitor for the treatment of solid tumors, including GBM.

BACKGROUND: Neoantigen based personalized immune therapies achieve promising results in melanoma and lung cancer, but few neoantigen based models perform well in IDH wild-type GBM, and the association between neoantigen intrinsic features and prognosis remain unclear in IDH wild-type GBM. We presented a novel neoantigen intrinsic feature-based deep learning model (neoDL) to stratify IDH wild-type GBMs into subgroups with different survivals.
RESULTS: We first derived intrinsic features for each neoantigen associated with survival, followed by applying neoDL in TCGA data cohort(AUC = 0.988, p value < 0.0001). Leave one out cross validation (LOOCV) in TCGA demonstrated that neoDL successfully classified IDH wild-type GBMs into different prognostic subgroups, which was further validated in an independent data cohort from Asian population. Long-term survival IDH wild-type GBMs identified by neoDL were found characterized by 12 protective neoantigen intrinsic features and enriched in development and cell cycle.
CONCLUSIONS: The model can be therapeutically exploited to identify IDH wild-type GBM with good prognosis who will most likely benefit from neoantigen based personalized immunetherapy. Furthermore, the prognostic intrinsic features of the neoantigens inferred from this study can be used for identifying neoantigens with high potentials of immunogenicity.