STLBRF: an improved random forest algorithm based on standardized-threshold for feature screening of gene expression data
Open Access
- 30 December 2024
- journal article
- research article
- Published by Oxford University Press (OUP) in Briefings in Functional Genomics
- Vol. 24
Abstract
When the traditional random forest (RF) algorithm is used to select feature elements in biostatistical data, a large amount of noise data and parameters can affect the importance of the selected feature elements, making the control of feature selection difficult. Therefore, it is a challenge for the traditional RF algorithm to preserve the accuracy of algorithm results in the presence of noise data. Generally, directly removing noise data can result in significant bias in the results. In this study, we develop a new algorithm, standardized threshold, and loops based random forest (STLBRF), and apply it to the field of gene expression data for feature gene selection. This algorithm, based on the traditional RF algorithm, combines backward elimination and K-fold cross-validation to construct a cyclic system and set a standardized threshold: error increment. The algorithm overcomes the shortcomings of existing gene selection methods. We compare ridge regression, lasso regression, elastic net regression, the traditional RF algorithm, and our improved RF algorithm using three real gene expression datasets and conducting a quantitative analysis. To ensure the reliability of the results, we validate the effectiveness of the genes selected by these methods using the Random Forest classifier. The results indicate that, compared to other methods, the STLBRF algorithm achieves not only higher effectiveness in feature gene selection but also better control over the number of selected genes. Our method offers reliable technical support for feature expression analysis and research on biomarker selection.Keywords
Funding Information
- National Natural Scientific Foundation of China (62072385)
This publication has 71 references indexed in Scilit:
- Single-cell transcriptomic analysis reveals crucial oncogenic signatures and its associative cell types involved in gastric cancerMedical Oncology, 2023
- CGB5, INHBA and TRAJ19 Hold Prognostic Potential as Immune Genes for Patients with Gastric CancerDigestive Diseases and Sciences, 2022
- MIDGET:Detecting differential gene expression on microarray dataComputer Methods and Programs in Biomedicine, 2021
- An integrated mRNA–microRNA regulatory network identified INHBA and has-miR-135a-5p as predictors of gastric cancer recurrenceMolecular & Cellular Toxicology, 2021
- CTHRC1 promotes gastric cancer metastasis via HIF-1α/CXCR4 signaling pathwayBiomedicine & Pharmacotherapy, 2020
- Exponentially Weighted Random Forest2019
- Geographically weighted elastic net logistic regressionJournal of Geographical Systems, 2018
- Structure-based design of competitive ligands to target Spon2 in gastric cancer: An integration of molecular modeling and in vitro assayBioorganic Chemistry, 2017
- Feature selection for outcome prediction in oesophageal cancer using genetic algorithm and random forest classifierComputerized Medical Imaging and Graphics, 2017
- Genome‐wide analysis of DNA copy number alterations and gene expression in gastric cancerThe Journal of Pathology, 2008