Machine learning and bioinformatics approaches for classification and clinical detection of bevacizumab responsive glioblastoma subtypes based on miRNA expression

Abstract

For the precise treatment of patients with glioblastoma multiforme (GBM), we classified and detected bevacizumab (BVZ)-responsive subtypes of GBM and found their differential expression (DE) of miRNAs and mRNAs, clinical characteristics, and related functional pathways. Based on miR-21 and miR-10b expression z-scores, approximately 30% of GBM patients were classified as having the GBM BVZ-responsive subtype. For this subtype, GBM patients had a significantly shorter survival time than other GBM patients (p = 0.014), and vascular endothelial growth factor A (VEGF) methylation was significantly lower than that in other GBM patients (p = 0.005). It also revealed 14 DE miRNAs and 7 DE mRNAs and revealed functional characteristics between GBM BVZ subgroups. After comparing several machine learning algorithms, the construction and cross-validation of the SVM classifier were performed. For clinical use, miR-197 was optimized and added to the miRNA panel for better classification. Afterwards, we validated the classifier with several GBM datasets and discovered some key related issues. According to this study, GBM BVZ subtypes can be classified and detected by a combination of SVM classifiers and miRNA panels in existing tissue GBM datasets. With certain modifications, the classifier may be used for the classification and detection of GBM BVZ subtypes for future clinical use.

Early 2-Factor Transcription Factors Associated with Progression and Recurrence in Bevacizumab-Responsive Subtypes of Glioblastoma

“…Considering the involvement of 106 transcription factors, these findings underscore the significant role of the E2F family in tumor progression and patient survival. Notably, based on the confusion matrix, E2Fs and TreeBagger algorithms showed better predictive ability in identifying survival probabilities of BVZ-responsive versus BVZ-non-responsive GBM subtypes because, as mentioned earlier [12], compared with BVZ-non-responsive patients, these patients have lower OS.…”

“…To explore the impact of bevacizumab (BVZ) treatment on BVZ-responsive glioblastoma (GBM) subtypes, we performed a comprehensive analysis of functional assays including Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG) and transcription factors (TF).Our analysis involved comparing differentially expressed (DE) genes obtained from 426 TCGA datasets between BVZ-responsive subtypes, identified using miRNA biomarkers and machine learning approaches [12], whereas DE genes from 17 GBM patients using CT scan before and after BVZ treatment to identify BVZ-responsive subtypes [20]. While typical changes were observed in GO and KEGG pathways, striking alterations were detected in TFs expression, particularly evident in Figure 1A.…”

“…Recent research, including our own, has used miRNA biomarkers and machine learning techniques to classify different subtypes of GBM that respond to Bevacizumab (BVZ) treatment [12]. BVZ therapy targets vascular endothelial growth factor (VEGF) and inhibits angiogenesis within the tumor.…”

Comparative Insight into Microglia/Macrophages-Associated Pathways in Glioblastoma and Alzheimer’s Disease

“…Since 2008, miRNA has been established as a biomarker for diffuse large B-cell lymphoma through patented serum [ 101 ], used to diagnose a variety of cancers [ 102 , 103 ], and its use in neurodegenerative diseases, including AD, has begun to be explored [ 104 , 105 ]. For GBM studies, our recent work demonstrates the successful classification and detection of GBM BVZ-responsive subtypes using a combination of three miRNA expressions alongside AI analysis techniques, laying a foundation for personalized medicine approaches in GBM treatment [ 106 ]. Furthermore, miRNAs act as key regulators, orchestrating complex gene regulation networks.…”

High throughput biological sequence analysis using machine learning-based integrative pipeline for extracting functional annotation and visualization

“…These include support vector machines, random forest, and neural networks. 9 On the other hand, this study uses a neural network to analyze RNA sequence-expressed genes from different datasets to predict a patient's health status. 10 And in this paper, the primary objective is to classify or identify different types of cancers based on the patterns found in the gene expression data.…”