Prior knowledge embedded dynamic multi-objective optimization algorithm for identifying cancer critical biomarkers

For cancer precision medicine, designing optimization method for identifying critical biomarkers is essential for early clinical intervention. However, existing optimization methods rely on static network analysis, ignoring the temporal dynamics of gene interaction networks and lacking effective integration of biological prior knowledge during the optimization process, leading to limited performance. To address these issues, this paper proposes a novel prior knowledge embedded dynamic multi-objective optimization algorithm termed TRDMO-P for disease critical biomarker identification. Our TRDMO-P algorithm fully exploits temporal dynamics of gene interaction network with two core strategies, i.e., prior biological gene-guided population initialization for effective optimization search and faster convergence, as well as network topology degree-guided evolution to retain effective biological genes and ensure biologically consistent optimization. Experiments on The Cancer Genome Atlas cancer datasets, and esophageal single-cell transcriptome data demonstrate that TRDMO-P significantly improves the detection accuracy of early warning signals compared with state-of-the-art methods, and ablation studies validate the effectiveness of the two proposed strategies, indicating that the proposed method enables reliable and biologically meaningful identification of critical biomarkers and shows strong potential for applications in cancer precision medicine.

Authors

Institutions

Publication Details

Journal
Frontiers in Bioinformatics
Published
2026-11-17
DOI
https://doi.org/10.3389/fbinf.2026.1950833
Primary Topic
Bioinformatics and Genomic Networks
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Prior knowledge embedded dynamic multi-objective optimization algorithm for identifying cancer critical biomarkers

任向阳, Guangzhen Jia, Zhao Mengtong, Peilin Cheng et al.
2 links
Frontiers in Bioinformatics
Bioinformatics and Genomic Networks
article

Prior knowledge embedded dynamic multi-objective optimization algorithm for identifying cancer critical biomarkers

任向阳, Guangzhen Jia, Zhao Mengtong, Peilin Cheng, Wei-Feng Guo, Chaoyuan Ma
article en

Abstract

For cancer precision medicine, designing optimization method for identifying critical biomarkers is essential for early clinical intervention. However, existing optimization methods rely on static network analysis, ignoring the temporal dynamics of gene interaction networks and lacking effective integration of biological prior knowledge during the optimization process, leading to limited performance. To address these issues, this paper proposes a novel prior knowledge embedded dynamic multi-objective optimization algorithm termed TRDMO-P for disease critical biomarker identification. Our TRDMO-P algorithm fully exploits temporal dynamics of gene interaction network with two core strategies, i.e., prior biological gene-guided population initialization for effective optimization search and faster convergence, as well as network topology degree-guided evolution to retain effective biological genes and ensure biologically consistent optimization. Experiments on The Cancer Genome Atlas cancer datasets, and esophageal single-cell transcriptome data demonstrate that TRDMO-P significantly improves the detection accuracy of early warning signals compared with state-of-the-art methods, and ablation studies validate the effectiveness of the two proposed strategies, indicating that the proposed method enables reliable and biologically meaningful identification of critical biomarkers and shows strong potential for applications in cancer precision medicine.

Frontiers in BioinformaticsVol. 6
Zhengzhou University (CN), Zhejiang Business Technology Institute (CN)
Natural Science Foundation of Henan Province
Good health and well-being
Bioinformatics and Genomic Networks
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon