TY - JOUR

T1 - AIMarkerFinder: AI-Assisted Marker Discovery Based on an Integrated Approach of Autoencoders and Kolmogorov–Arnold Networks

AU - Demenkov, Pavel S.

AU - Ivanisenko, Timofey V.

AU - Ivanisenko, Vladimir A.

N1 - This work was supported by a grant for research centers, provided by the Ministry of Economic Development of the Russian Federation in accordance with the subsidy agreement with the Novosibirsk State University dated 17 April 2025 No. 139-15-2025-006: IGK 000000C313925P3S0002.

PY - 2026

Y1 - 2026

N2 - In modern bioinformatics, the analysis of high-dimensional data (genomic, metabolomic, etc.) remains a critical challenge due to the “curse of dimensionality,” where feature redundancy reduces classification efficiency and model interpretability. This study introduces a novel method, AIMarkerFinder (v0.1.0), for analyzing metabolomic data to identify key biomarkers. The method is based on a denoising autoencoder with an attention mechanism (DAE), enabling the extraction of informative features and the elimination of redundancy. Experiments on glioblastoma and adjacent tissue metabolomic data demonstrated that AIMarkerFinder reduces dimensionality from 446 to 4 key features while improving classification accuracy. Using the selected metabolites (Malonyl-CoA, Glycerophosphocholine, SM(d18:1/22:0 OH), GC(18:1/24:1)), the Random Forest and Kolmogorov–Arnold Networks (KAN) models achieved accuracies of 0.904 and 0.937, respectively. The analytical formulas derived by the KAN provide model interpretability, which is critical for biomedical research. The proposed approach is applicable to genomics, transcriptomics, proteomics, and the study of exogenous factors on biological processes. The study’s results open new prospects for personalized medicine and early disease diagnosis.

AB - In modern bioinformatics, the analysis of high-dimensional data (genomic, metabolomic, etc.) remains a critical challenge due to the “curse of dimensionality,” where feature redundancy reduces classification efficiency and model interpretability. This study introduces a novel method, AIMarkerFinder (v0.1.0), for analyzing metabolomic data to identify key biomarkers. The method is based on a denoising autoencoder with an attention mechanism (DAE), enabling the extraction of informative features and the elimination of redundancy. Experiments on glioblastoma and adjacent tissue metabolomic data demonstrated that AIMarkerFinder reduces dimensionality from 446 to 4 key features while improving classification accuracy. Using the selected metabolites (Malonyl-CoA, Glycerophosphocholine, SM(d18:1/22:0 OH), GC(18:1/24:1)), the Random Forest and Kolmogorov–Arnold Networks (KAN) models achieved accuracies of 0.904 and 0.937, respectively. The analytical formulas derived by the KAN provide model interpretability, which is critical for biomedical research. The proposed approach is applicable to genomics, transcriptomics, proteomics, and the study of exogenous factors on biological processes. The study’s results open new prospects for personalized medicine and early disease diagnosis.

UR - https://www.scopus.com/pages/publications/105028502128

UR - https://elibrary.ru/item.asp?id=88512051

UR - https://www.mendeley.com/catalogue/e5566334-2406-30d3-9abd-cb7c546d1666/

U2 - 10.3390/informatics13010002

DO - 10.3390/informatics13010002

M3 - Article

VL - 13

JO - Informatics

JF - Informatics

SN - 2227-9709

IS - 1

M1 - 2

ER -