A Novel Multi-Stage Fusion based Approach for Gene Expression Profiling in Non-Small Cell Lung Cancer

Abstract

Background: Non-small cell lung cancer is defined at the molecular level by mutations and alterations to oncogenes, including AKT1, ALK, BRAF, EGFR, HER2, KRAS, MEK1, MET, NRAS, PIK3CA, RET, and ROS1. A better understanding of non-small cell lung cancer requires a thorough consideration of these oncogenes. However, the complexity of the problem arises from high-dimensional gene vector space, which complicates the identification of cluster boundaries, and hence gene expression cluster membership. This paper aims to analyze potential biological biomarkers for tumorigenesis in lung cancer based on different treatment solutions. Results: Genes BRAF, RET, and ROS1 show an overexpression transition by one cluster from non-treatment to treatment states, followed by a stabilization in the 3 treatment states at the same cluster. Genes MET, ALK, and PIK3CA show an overexpression transition by two clusters from non-treatment to treatment states, followed by a stabilization in the 3 treatment states at the same cluster. SME1 shows an under-expression transition by two clusters from non-treatment to the treatment states, a stabilization in the 3 treatment states at the same cluster. Conclusions: We present a novel fusion-based approach for gene expression profiling of non-small cell lung cancer under non-thermal plasma treatment. The main contribution of the proposed approach is to exploit Dempster-Shafer evidence theory-based data fusion to combine information from different samples in the considered dataset. This minimizes uncertainty and enhances the reliability and validity of decisions, leading to a better description of genes related to non-small cell lung cancer. We also propose use of fuzzy c-means-with-range clustering to track changes of genes' states under different non-thermal plasma treatments. INDEX TERMS Gene expression, Dempster Shafer, evidence theory, data fusion, clustering, non-small cell lung cancer.

A Novel Coupled Reaction-Diffusion System for Explainable Gene Expression Profiling

“…In our previous work, we proposed a ‘fusion-based’ approach to gene expression profiling for non-small cell lung cancer [ 12 ]. The proposed approach was based on three main steps: (1) clustering tendency to determine whether the considered data could be grouped into clusters; (2) evidence-based fusion to combine the clustering results in the three non-treatment (NT) samples; and (3) ‘fuzzy c-means-with-range clustering’ performed on the short-exposure (SE) and long-exposure (LE) samples.…”

“…The population abundance or concentration of mRNA in Figure 3 was discretized to four clusters based on the optimal numbers of clusters obtained from our previous work [ 12 ]. The scaling of the four clusters is displayed in Table 6 , which depicts the lower and upper bound for each cluster (the clustering boundaries).…”

“…Machine learning (ML) models have been applied to many types of datasets, e.g., gene expression, bio-imaging, and clinical datasets, and have been shown to accurately predict and diagnose cancer [ 6 , 7 , 8 , 9 , 10 , 11 , 12 ]. However, because outputs from such approaches are often used to inform a clinician’s decision-making, it is imperative that they are able to understand the rationale behind a model’s decision.…”

“…The proposed approach could potentially identify novel and improved cancer treatment. Previous studies [ 10 , 12 ] have attempted other analyses of gene expression profiles, primarily through the development of mathematical and ML-based models. However, the use of the diffusion equation to study gene expression profiling is not yet well explored, as demonstrated through a brief survey of the literature above.…”

Novel modelling of clustering for enhanced classification performance on gene expression data

“…The recent work carried out by Chen et al [11] has introduced a network model for analyzing the redundant informationin the gene expression data. Identification of the specific form of cancer was carried out by Farouq et al [12] over gene expression data. The approach uses a profiling mechanism for identification of disease condition using fusion-based mechanism.…”