FRL: An Integrative Feature Selection Algorithm Based on the Fisher Score, Recursive Feature Elimination, and Logistic Regression to Identify Potential Genomic Biomarkers

Abstract

Accurate screening on cancer biomarkers contributes to health assessment, drug screening, and targeted therapy for precision medicine. The rapid development of high-throughput sequencing technology has identified abundant genomic biomarkers, but most of them are limited to single-cancer analysis. Based on the combination of Fisher score, Recursive feature elimination, and Logistic regression (FRL), this paper proposes an integrative feature selection algorithm named FRL to explore potential cancer genomic biomarkers on cancer subsets. Fisher score is initially used to calculate the weights of genes to rapidly reduce the dimension. Recursive feature elimination and Logistic regression are then jointly employed to extract the optimal subset. Compared to the current differential expression analysis tool GEO2R based on the Limma algorithm, FRL has greater classification precision than Limma. Compared with five traditional feature selection algorithms, FRL exhibits excellent performance on accuracy (ACC) and F1-score and greatly improves computational efficiency. On high-noise datasets such as esophageal cancer, the ACC of FRL is 30% superior to the average ACC achieved with other traditional algorithms. As biomarkers found in multiple studies are more reliable and reproducible, and reveal stronger association on potential clinical value than single analysis, through literature review and spatial analyses of gene functional enrichment and functional pathways, we conduct cluster analysis on 10 diverse cancers with high mortality and form a potential biomarker module comprising 19 genes. All genes in this module can serve as potential biomarkers to provide more information on the overall oncogenesis mechanism for the detection of diverse early cancers and assist in targeted anticancer therapies for further developments in precision medicine.

Metabolomics by NMR Combined with Machine Learning to Predict Neoadjuvant Chemotherapy Response for Breast Cancer

“…RFE continually removes the resources with low contribution scores based on the iterative method and then classifies each resource in each cycle to exclude the resources with low scores [ 43 ]. Studies have proposed that RFE allows the extraction of potential biomarker subsets among different cancer types [ 71 , 72 , 73 ]. Specifically, for breast cancer, RFE was applied to classify the complete pathological response and distinguish triple-negative breast cancer from other subtypes of breast cancer based on the selection of miRNA biomarkers [ 74 , 75 ].…”

Predicting pneumonia during hospitalization in flail chest patients using machine learning approaches

“…Second, the dataset with 169 records and 59 features was normalized using the Python Sklearn library. Then, the scores of each feature were computed and ranked based on the Fisher score evaluation system (21). Finally, we put features into model training, recursively deleted unimportant parts, and selected the optimal subset of each model.…”

Selection of potential cancer biomarkers based on feature selection method

“…Analysis of biological information concealed in the dataset can fulfill the ultimate goal of deepening the understanding of life, which needs the support of computer methods. Among them, the feature selection algorithms can choose subset of the genomes to help to identify biomarker genes, which can make full use of limited sample data and help to mine the pathological mechanism and structure behind the data [3,4]. As a valid and efficient method, feature selection can remove redundant features and form an understandable model between feature values and vectors.…”

“…The filter algorithm scores each feature based on specific criteria. The threshold and the final number of features to be selected need to be set manually [4]. As an open-loop method, the filter can be employed generally and function faster than the wrapper and embedded method [6].…”