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

Abstract

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.

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

“…In this study, we employ a hybrid method for weighting and selecting of features based on ranks [ 19 ] which can be used to categorize glioma grades. Our used methodology consists of two main phases: (i) feature selection (FS) and (ii) feature-weighting (FW) [ 19 ].…”

“…In this study, we employ a hybrid method for weighting and selecting of features based on ranks [ 19 ] which can be used to categorize glioma grades. Our used methodology consists of two main phases: (i) feature selection (FS) and (ii) feature-weighting (FW) [ 19 ]. Figure 1 and Table 1 provide a sample algorithmic diagram of our utilized architecture and related processes, showcasing the two feature selection methods used: LASSO and mRMR.…”

“…Feature selection methods are generally classified into three categories, depending on the evaluation metric of the feature subset: filter, wrapper, or embedded methods [ 18 ]. Univariate filter and multivariate filter FS methods are two subcategories of filter methods that consider relationships between features and/or between features and the target/class or output variable [ 19 ]. In this study, we utilized a multivariate filter FS method called minimum redundancy maximum relevance (mRMR) and an embedded-based FS method called LASSO to select the clinical and molecular features of glioma patients’ data.…”

“…We chose to avoid the computational load of the wrapper FS method and the dependence on model-specific features associated with this approach in order to enhance the transferability of our used approach. In the feature-weighting stage, the importance level of each selected feature in discriminating pattern classes is typically represented by a weight value, which can be added or multiplied to feature values [ 19 , 23 ]. In this study, a rank-based feature-weighting approach was adopted.…”

“…However, identifying molecular feature names is crucial to being able to leverage the identified features biologically and clinically. To this end, feature-weighting, counting, or rank-based approaches can be used [ 19 ]. While several markers are being used in the clinic and additional markers are being proposed, given evolving research, there is currently no robust biomarker list or panel that defines glioma grading and employs data from TCGA and CGGA, which are the most commonly available and utilized datasets of clinical and molecular data.…”