What is it about?
In this work, we aim to propose an ensemble feature selection method for biomarker discovery (abbreviated as EFSmarker) based on multiple independent feature selection methods to better approximate the optimal subset of features. Here, we first chose twelve filter feature selection methods. EFSmarker generates a feature score that is used to evaluate the importance of features by considering the feature weight and classification accuracy and integrating them into an aggregation-like framework. The results of expression validation, function enrichment analysis, literature checking and external validation demonstrate that the proposed biomarker discovery strategy is effective in identifying biomarkers in a case study of BRCA. The biomarkers allow non-invasive detection of patients with BRCA, which guides patients and doctors in selecting an alternative diagnostic approach.
Photo by Victoria Strukovskaya on Unsplash
Why is it important?
Our proposed biomarker discovery strategy not only utilizes the feature contribution but also considers the prediction accuracy simultaneously, which may also serve as a model for identifying unknown biomarkers for other diseases from high-throughput gene expression data.
Read the Original
This page is a summary of: Identifying Diagnostic Biomarkers of Breast Cancer Based on Gene
Expression Data and Ensemble Feature Selection, Current Bioinformatics, March 2023, Bentham Science Publishers, DOI: 10.2174/1574893618666230111153243.
You can read the full text:
The following have contributed to this page