| Sumario: | Simple Summary: Novel cancer biomarker discoveries are enabled by the application and analysis of omics technologies. This vast quantity of high-dimensional data necessitates the implementation of feature selection for analysis. The mathematical basis of selection methods varies considerably, which may influence subsequent inference. The aim of the study was to identify signature gene sets of grade 2 and 3 astrocytoma (brain cancer) and determine their impact on the classification and discovery of biological patterns. The application of feature selection methods reduced the number of genes and led to an increase in classification accuracy. Notably, no single gene was selected by all methods. Significant differences in Gene Ontology terms as well as KEGG pathways were discovered. Results demonstrated a significant difference in outcomes when classification-type algorithms were utilised compared to mixed types (selection and classification). This may result in the inadvertent omission of biological phenomena, while simultaneously achieving enhanced classification outcomes. Novel cancer biomarkers discoveries are driven by the application of omics technologies. The vast quantity of highly dimensional data necessitates the implementation of feature selection. The mathematical basis of different selection methods varies considerably, which may influence subsequent inferences. In the study, feature selection and classification methods were employed to identify six signature gene sets of grade 2 and 3 astrocytoma samples from the Rembrandt repository. Subsequently, the impact of these variables on classification and further discovery of biological patterns was analysed. Principal component analysis (PCA), uniform manifold approximation and projection (UMAP), and hierarchical clustering revealed that the data set (10,096 genes) exhibited a high degree of noise, feature redundancy, and lack of distinct patterns. The application of feature selection methods resulted in a reduction in the number of genes to between 28 and 128. Notably, no single gene was selected by all of the methods tested. Selection led to an increase in classification accuracy and noise reduction. Significant differences in the Gene Ontology terms were discovered, with only 13 terms overlapping. One selection method did not result in any enriched terms. KEGG pathway analysis revealed only one pathway in common (cell cycle), while the two methods did not yield any enriched pathways. The results demonstrated a significant difference in outcomes when classification-type algorithms were utilised in comparison to mixed types (selection and classification). This may result in the inadvertent omission of biological phenomena, while simultaneously achieving enhanced classification outcomes.
|
|---|