MGMT ProFWise: Unlocking a New Application for Combined Feature Selection and the Rank-Based Weighting Method to Link MGMT Methylation Status to Serum Protein Expression in Patients with Glioblastoma.

Glioblastoma (GBM) is a fatal brain tumor with limited treatment options. O6-methylguanine-DNA-methyltransferase (MGMT) promoter methylation status is the central molecular biomarker linked to both the response to temozolomide, the standard chemotherapy drug employed for GBM, and to patient survival. However, MGMT status is captured on tumor tissue which, given the difficulty in acquisition, limits the use of this molecular feature for treatment monitoring. MGMT protein expression levels may offer additional insights into the mechanistic understanding of MGMT but, currently, they correlate poorly to promoter methylation. The difficulty of acquiring tumor tissue for MGMT testing drives the need for non-invasive methods to predict MGMT status. Feature selection aims to identify the most informative features to build accurate and interpretable prediction models. This study explores the new application of a combined feature selection (i.e., LASSO and mRMR) and the rank-based weighting method (i.e., MGMT ProFWise) to non-invasively link MGMT promoter methylation status and serum protein expression in patients with GBM. Our method provides promising results, reducing dimensionality (by more than 95%) when employed on two large-scale proteomic datasets (7k SomaScan® panel and CPTAC) for all our analyses. The computational results indicate that the proposed approach provides 14 shared serum biomarkers that may be helpful for diagnostic, prognostic, and/or predictive operations for GBM-related processes, given further validation.

Corrigendum: Glioblastoma survival is associated with distinct proteomic alteration signatures post chemoirradiation in a large-scale proteomic panel.

[This corrects the article DOI: 10.3389/fonc.2023.1127645.].

GradWise: A Novel Application of a Rank-Based Weighted Hybrid Filter and Embedded Feature Selection Method for Glioma Grading with Clinical and Molecular Characteristics.

Glioma grading plays a pivotal role in guiding treatment decisions, predicting patient outcomes, facilitating clinical trial participation and research, and tailoring treatment strategies. Current glioma grading in the clinic is based on tissue acquired at the time of resection, with tumor aggressiveness assessed from tumor morphology and molecular features. The increased emphasis on molecular characteristics as a guide for management and prognosis estimation underscores is driven by the need for accurate and standardized grading systems that integrate molecular and clinical information in the grading process and carry the expectation of the exposure of molecular markers that go beyond prognosis to increase understanding of tumor biology as a means of identifying druggable targets. In this study, we introduce a novel application (GradWise) that combines rank-based weighted hybrid filter (i.e., mRMR) and embedded (i.e., LASSO) feature selection methods to enhance the performance of feature selection and machine learning models for glioma grading using both clinical and molecular predictors. We utilized publicly available TCGA from the UCI ML Repository and CGGA datasets to identify the most effective scheme that allows for the selection of the minimum number of features with their names. Two popular feature selection methods with a rank-based weighting procedure were employed to conduct comprehensive experiments with the five supervised models. The computational results demonstrate that our proposed method achieves an accuracy rate of 87.007% with 13 features and an accuracy rate of 80.412% with five features on the TCGA and CGGA datasets, respectively. We also obtained four shared biomarkers for the glioma grading that emerged in both datasets and can be employed with transferable value to other datasets and data-based outcome analyses. These findings are a significant step toward highlighting the effectiveness of our approach by offering pioneering results with novel markers with prospects for understanding and targeting the biologic mechanisms of glioma progression to improve patient outcomes.

An Overview of CD133 as a Functional Unit of Prognosis and Treatment Resistance in Glioblastoma.

Biomarkers for resistance in Glioblastoma multiforme (GBM) are lacking, and progress in the clinic has been slow to arrive. CD133 (prominin-1) is a membrane-bound glycoprotein on the surface of cancer stem cells (CSCs) that has been associated with poor prognosis, therapy resistance, and tumor recurrence in GBM. Due to its connection to CSCs, to which tumor resistance and recurrence have been partially attributed in GBM, there is a growing field of research revolving around the potential role of CD133 in each of these processes. However, despite encouraging results in vitro and in vivo, the biological interplay of CD133 with these components is still unclear, causing a lack of clinical application. In parallel, omic data from biospecimens that include CD133 are beginning to emerge, increasing the importance of understanding CD133 for the effective use of these highly dimensional data sets. Given the significant mechanistic overlap, prioritization of the most robust findings is necessary to optimize the transition of CD133 to clinical applications using patient-derived biospecimens. As a result, this review aims to compile and analyze the current research regarding CD133 as a functional unit in GBM, exploring its connections to prognosis, the tumor microenvironment, tumor resistance, and tumor recurrence.

Glioblastoma survival is associated with distinct proteomic alteration signatures post chemoirradiation in a large-scale proteomic panel.

Background: Glioblastomas (GBM) are rapidly progressive, nearly uniformly fatal brain tumors. Proteomic analysis represents an opportunity for noninvasive GBM classification and biological understanding of treatment response. Purpose: We analyzed differential proteomic expression pre vs. post completion of concurrent chemoirradiation (CRT) in patient serum samples to explore proteomic alterations and classify GBM by integrating clinical and proteomic parameters. Materials and methods: 82 patients with GBM were clinically annotated and serum samples obtained pre- and post-CRT. Serum samples were then screened using the aptamer-based SOMAScan® proteomic assay. Significant traits from uni- and multivariate Cox models for overall survival (OS) were designated independent prognostic factors and principal component analysis (PCA) was carried out. Differential expression of protein signals was calculated using paired t-tests, with KOBAS used to identify associated KEGG pathways. GSEA pre-ranked analysis was employed on the overall list of differentially expressed proteins (DEPs) against the MSigDB Hallmark, GO Biological Process, and Reactome databases with weighted gene correlation network analysis (WGCNA) and Enrichr used to validate pathway hits internally. Results: 3 clinical clusters of patients with differential survival were identified. 389 significantly DEPs pre vs. post-treatment were identified, including 284 upregulated and 105 downregulated, representing several pathways relevant to cancer metabolism and progression. The lowest survival group (median OS 13.2 months) was associated with DEPs affiliated with proliferative pathways and exhibiting distinct oppositional response including with respect to radiation therapy related pathways, as compared to better-performing groups (intermediate, median OS 22.4 months; highest, median OS 28.7 months). Opposite signaling patterns across multiple analyses in several pathways (notably fatty acid metabolism, NOTCH, TNFα via NF-κB, Myc target V1 signaling, UV response, unfolded protein response, peroxisome, and interferon response) were distinct between clinical survival groups and supported by WGCNA. 23 proteins were statistically signficant for OS with 5 (NETO2, CST7, SEMA6D, CBLN4, NPS) supported by KM. Conclusion: Distinct proteomic alterations with hallmarks of cancer, including progression, resistance, stemness, and invasion, were identified in serum samples obtained from GBM patients pre vs. post CRT and corresponded with clinical survival. The proteome can potentially be employed for glioma classification and biological interrogation of cancer pathways.

RadWise: A Rank-Based Hybrid Feature Weighting and Selection Method for Proteomic Categorization of Chemoirradiation in Patients with Glioblastoma.

Glioblastomas (GBM) are rapidly growing, aggressive, nearly uniformly fatal, and the most common primary type of brain cancer. They exhibit significant heterogeneity and resistance to treatment, limiting the ability to analyze dynamic biological behavior that drives response and resistance, which are central to advancing outcomes in glioblastoma. Analysis of the proteome aimed at signal change over time provides a potential opportunity for non-invasive classification and examination of the response to treatment by identifying protein biomarkers associated with interventions. However, data acquired using large proteomic panels must be more intuitively interpretable, requiring computational analysis to identify trends. Machine learning is increasingly employed, however, it requires feature selection which has a critical and considerable effect on machine learning problems when applied to large-scale data to reduce the number of parameters, improve generalization, and find essential predictors. In this study, using 7k proteomic data generated from the analysis of serum obtained from 82 patients with GBM pre- and post-completion of concurrent chemoirradiation (CRT), we aimed to select the most discriminative proteomic features that define proteomic alteration that is the result of administering CRT. Thus, we present a novel rank-based feature weighting method (RadWise) to identify relevant proteomic parameters using two popular feature selection methods, least absolute shrinkage and selection operator (LASSO) and the minimum redundancy maximum relevance (mRMR). The computational results show that the proposed method yields outstanding results with very few selected proteomic features, with higher accuracy rate performance than methods that do not employ a feature selection process. While the computational method identified several proteomic signals identical to the clinical intuitive (heuristic approach), several heuristically identified proteomic signals were not selected while other novel proteomic biomarkers not selected with the heuristic approach that carry biological prognostic relevance in GBM only emerged with the novel method. The computational results show that the proposed method yields promising results, reducing 7k proteomic data to 7 selected proteomic features with a performance value of 93.921%, comparing favorably with techniques that do not employ feature selection.

Cost Matrix of Molecular Pathology in Glioma-Towards AI-Driven Rational Molecular Testing and Precision Care for the Future.

Gliomas are the most common and aggressive primary brain tumors. Gliomas carry a poor prognosis because of the tumor's resistance to radiation and chemotherapy leading to nearly universal recurrence. Recent advances in large-scale genomic research have allowed for the development of more targeted therapies to treat glioma. While precision medicine can target specific molecular features in glioma, targeted therapies are often not feasible due to the lack of actionable markers and the high cost of molecular testing. This review summarizes the clinically relevant molecular features in glioma and the current cost of care for glioma patients, focusing on the molecular markers and meaningful clinical features that are linked to clinical outcomes and have a realistic possibility of being measured, which is a promising direction for precision medicine using artificial intelligence approaches.

Hierarchical Voting-Based Feature Selection and Ensemble Learning Model Scheme for Glioma Grading with Clinical and Molecular Characteristics.

Determining the aggressiveness of gliomas, termed grading, is a critical step toward treatment optimization to increase the survival rate and decrease treatment toxicity for patients. Streamlined grading using molecular information has the potential to facilitate decision making in the clinic and aid in treatment planning. In recent years, molecular markers have increasingly gained importance in the classification of tumors. In this study, we propose a novel hierarchical voting-based methodology for improving the performance results of the feature selection stage and machine learning models for glioma grading with clinical and molecular predictors. To identify the best scheme for the given soft-voting-based ensemble learning model selections, we utilized publicly available TCGA and CGGA datasets and employed four dimensionality reduction methods to carry out a voting-based ensemble feature selection and five supervised models, with a total of sixteen combination sets. We also compared our proposed feature selection method with the LASSO feature selection method in isolation. The computational results indicate that the proposed method achieves 87.606% and 79.668% accuracy rates on TCGA and CGGA datasets, respectively, outperforming the LASSO feature selection method.

Optimizing management of the elderly patient with glioblastoma: Survival prediction online tool based on BC Cancer Registry real-world data.

Background: Glioblastoma (GBM) is associated with fatal outcomes and devastating neurological presentations especially impacting the elderly. Management remains controversial and representation in clinical trials poor. We generated 2 nomograms and a clinical decision making web tool using real-world data. Methods: Patients ≥60 years of age with histologically confirmed GBM (ICD-O-3 histology codes 9440/3, 9441/3, and 9442/3) diagnosed 2005-2015 were identified from the BC Cancer Registry (n = 822). Seven hundred and twenty-nine patients for which performance status was captured were included in the analysis. Age, performance and resection status, administration of radiation therapy (RT), and chemotherapy were reviewed. Nomograms predicting 6- and 12-month overall survival (OS) probability were developed using Cox proportional hazards regression internally validated by c-index. A web tool powered by JavaScript was developed to calculate the survival probability. Results: Median OS was 6.6 months (95% confidence interval [CI] 6-7.2 months). Management involved concurrent chemoradiation (34%), RT alone (42%), and chemo alone (2.3%). Twenty-one percent of patients did not receive treatment beyond surgical intervention. Age, performance status, extent of resection, chemotherapy, and RT administration were all significant independent predictors of OS. Patients <80 years old who received RT had a significant survival advantage, regardless of extent of resection (hazard ratio range from 0.22 to 0.60, CI 0.15-0.95). A nomogram was constructed from all 729 patients (Harrell's Concordance Index = 0.78 [CI 0.71-0.84]) with a second nomogram based on subgroup analysis of the 452 patients who underwent RT (Harrell's Concordance Index = 0.81 [CI 0.70-0.90]). An online calculator based on both nomograms was generated for clinical use. Conclusions: Two nomograms and accompanying web tool incorporating commonly captured clinical features were generated based on real-world data to optimize decision making in the clinic.

Re-irradiation for recurrent glioma- the NCI experience in tumor control, OAR toxicity and proposal of a novel prognostic scoring system.

PURPOSE/OBJECTIVES: Despite mounting evidence for the use of re-irradiation (re-RT) in recurrent high grade glioma, optimal patient selection criteria for re-RT remain unknown. We present a novel scoring system based on radiobiology principles including target independent factors, the likelihood of target control, and the anticipated organ at risk (OAR) toxicity to allow for proper patient selection in the setting of recurrent glioma. MATERIALS/METHODS: Thirty one patients with recurrent glioma who received re-RT (2008-2016) at NCI - NIH were included in the analysis. A novel scoring system for overall survival (OS) and progression free survival (PFS) was designed to include:1) target independent factors (age, KPS (Karnofsky Performance Status), histology, presence of symptoms), 2) target control, and 3) OAR toxicity risk. Normal tissue complication probability (NTCP) calculations were performed using the Lyman model. Kaplan-Meier analysis was performed for overall survival (OS) and progression free survival (PFS) for comparison amongst variables. RESULTS: No patient, including those who received dose to OAR above the published tolerance dose, experienced any treatment related grade 3-5 toxicity with a median PFS and OS from re-RT of 4 months (0.5-103) and 6 months (0.7-103) respectively. Based on cumulative maximum doses the average NTCP was 25% (0-99%) for the chiasm, 21% (0-99%) for the right optic nerve, 6% (0-92%) for the left optic nerve, and 59% (0-100%) for the brainstem. The independent factor and target control scores were each statistically significant for OS and the combination of independent factors plus target control was also significant for both OS (p = 0.02) and PFS (p = 0.006). The anticipated toxicity risk score was not statistically significant. CONCLUSION: Our scoring system may represent a novel approach to patient selection for re-RT in recurrent high grade glioma. Further validation in larger patient cohorts including compilation of doses to tumor and OAR may help refine this further for inclusion into clinical trials and general practice.