New heuristic method for cancer classification using gene expression data.
4 affiliations
- 1Huizhou University, Huizhou, China. [email protected].
- 2Department of Polyclinic Therapy, Institute of Clinical Medicine Named After N.V. Sklifosovsky, Sechenov First Moscow State Medical University, Moscow, Russian Federation.
- 3Department of Anaesthesiology and Intensive Care, Medical University Sofia, Sofia, Bulgaria.
- 4Department of Biology and General Genetics, Sechenov First Moscow State Medical University, Moscow, Russian Federation.
Abstract
Background
The aim of this research is to develop and evaluate a novel feature selection method based on a local search algorithm (LSFS) in combination with a genetic algorithm (GA) for cancer classification using high-dimensional gene expression data.Methods
The study spanned a period between 2022 and 2024, using data from two medical research centers (Sofia, Bulgaria, and Moscow, Russia). More than 30,000 patient records were analyzed using six open datasets as source data. These datasets included information on blood, breast, colon, and other types of cancer from the GEO and TCGA databases. To prepare the data for analysis, the study employed techniques such as normalization, outlier elimination, and logarithmic transformation. Modern machine learning algorithms, such as random forests, support vector machines, and neural networks, were utilized to assess the effectiveness of the proposed method.Results
The LSFS + GA method demonstrated the ability to maximize accuracy, sensitivity, and specificity, as well as other classification metrics. Specifically, classification accuracy improved by 8-15% depending on the dataset, sensitivity by 10-20%, and specificity by 5-10%. Additionally, there was a 12-18% reduction in noise in the data. The effectiveness of the model was demonstrated by a reduction in entropy, indicating an increase in classification confidence of 6-9%. Statistical analysis, including cross-validation and ANOVA, confirmed the statistical significance of the improvements achieved with the new method (p < 0.05).Conclusions
The developed algorithm enables a substantial reduction in computational complexity while maintaining, or even improving, classification accuracy. This is important for analyzing cancer data, as it helps to ensure more reliable results. The study's findings demonstrate the potential of combining local search methods with genetic algorithms to address high-dimensional classification problems in bioinformatics.
Related
- Cis-TERN: a graph-based method to integrate single-cell chromatin accessibility with gene expression data to infer the pseudotime ordering of cells
- Integrated DNA methylation and gene expression analysis identifies CpG biomarkers in breast cancer
- Exploratory analysis of Notch and Wnt pathway gene expression across biofluids and tumor tissue in gynecologic cancer
- Podophyllotoxin suppresses growth of MFC gastric cancer cells by modulating DNA damage response-related gene expression
- CellPatch: a flexible and efficient framework for single-cell foundation models empowered by heuristic gene patching
BibTeX
@article{gu2026heuristic,
title = {{New heuristic method for cancer classification using gene expression data.}},
author = {Shengyu Gu and Tamara Savina and Dimitar Monov and Elena Gorozhanina},
journal = {Cancer imaging : the official publication of the International Cancer Imaging Society},
year = {2026},
month = aug,
doi = {10.1186/s40644-026-01111-y},
url = {https://europepmc.org/article/MED/42963784},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - New heuristic method for cancer classification using gene expression data.
AU - Shengyu Gu
AU - Tamara Savina
AU - Dimitar Monov
AU - Elena Gorozhanina
PY - 2026
DA - 2026/08/19
JO - Cancer imaging : the official publication of the International Cancer Imaging Society
DO - 10.1186/s40644-026-01111-y
UR - https://europepmc.org/article/MED/42963784
AB - Background The aim of this research is to develop and evaluate a novel feature selection method based on a local search algorithm (LSFS) in combination with a genetic algorithm (GA) for cancer classification using high-dimensional gene expression data.Methods The study spanned a period between 2022 and 2024, using data from two medical research centers (Sofia, Bulgaria, and Moscow, Russia). More than 30,000 patient records were analyzed using six open datasets as source data. These datasets included information on blood, breast, colon, and other types of cancer from the GEO and TCGA databases. To prepare the data for analysis, the study employed techniques such as normalization, outlier elimination, and logarithmic transformation. Modern machine learning algorithms, such as random forests, support vector machines, and neural networks, were utilized to assess the effectiveness of the proposed method.Results The LSFS + GA method demonstrated the ability to maximize accuracy, sensitivity, and specificity, as well as other classification metrics. Specifically, classification accuracy improved by 8-15% depending on the dataset, sensitivity by 10-20%, and specificity by 5-10%. Additionally, there was a 12-18% reduction in noise in the data. The effectiveness of the model was demonstrated by a reduction in entropy, indicating an increase in classification confidence of 6-9%. Statistical analysis, including cross-validation and ANOVA, confirmed the statistical significance of the improvements achieved with the new method (p < 0.05).Conclusions The developed algorithm enables a substantial reduction in computational complexity while maintaining, or even improving, classification accuracy. This is important for analyzing cancer data, as it helps to ensure more reliable results. The study's findings demonstrate the potential of combining local search methods with genetic algorithms to address high-dimensional classification problems in bioinformatics.
SN - 1740-5025
SN - 1470-7330
ER -