SaintGSE: Transformer-based efficient and explainable gene set enrichment analysis
Osteoarthritis and Cartilage · 2026-08 · 34 (8) · 1231-1242
DOI: 10.1016/j.joca.2026.04.009 ↗Kurz gefasst
Fachartikel in der Zeitschrift Osteoarthritis and Cartilage, 2026-08. Verfasst von Min-Seung Jeon und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Life Science, Chung-Ang University, Seoul 06974, South Korea. Electronic address: msjeon27@cau.ac.kr. Hauptthemen laut MEDLINE: Osteoarthritis, Chondrocytes, Gene Expression Profiling. Die Arbeit nennt 51 Literaturangaben. Gefördert von: National Research Foundation of Korea, Ministry of Oceans and Fisheries, Korea Institute of Marine Science and Technology promotion.
Abstract (Originalsprache)
OBJECTIVE Gene set enrichment analysis (GSEA) is widely used to interpret genome-wide expression data, but pathway inference from differentially expressed gene (DEG) signatures remains limited by data scarcity, model incompatibility with tabular data, and limited interpretability. We aimed to develop an efficient and explainable model that predict gene-pathway associations from a large curated DEG signature compendium and supports potential therapeutic target discovery in complex diseases such as osteoarthritis (OA) and other disease contexts. METHOD We developed SaintGSE, a supervised prediction framework combining an autoencoder for dimensionality reduction and the SAINT for modeling tabular DEG signatures. The model was trained on a large public DEG compendium with pathway labels derived from EnrichR and interpreted using Integrated Gradients (IG) to prioritize driver genes. Experimental validation was conducted using mouse (n=5) and human (n=3) chondrocyte cultures, and in vivo OA-induced mouse models (n=5 per group). RESULTS SaintGSE analysis identified key OA-related signaling pathways potentially modulated by natural extract from Senna obtusifolia, including NF-κB and p38. In vitro, the extract reduced OA catabolic factors compared with IL-1β-treated controls, including Mmp3 (mean difference 52.06, 95% CI 32.8-71.3, p
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Life Science, Chung-Ang University, Seoul 06974, South Korea. Electronic address: msjeon27@cau.ac.kr.
- Department of Biological Sciences, Sungkyunkwan University, Suwon 16419, Korea. Electronic address: yjtnng3043@g.skku.edu.
- Department of Life Science, Chung-Ang University, Seoul 06974, South Korea. Electronic address: wltjr0103@cau.ac.kr.
- Center for Systems Biology, Harvard Medical School, Boston, MA 02114, USA; Department of Molecular Medicine, Hanyang University-ERICA, Ansan 15588, Korea. Electronic address: ccho11@hanyang.ac.kr.
- Department of Biological Sciences, Sungkyunkwan University, Suwon 16419, Korea. Electronic address: yangsy@skku.edu.
- Department of Life Science, Chung-Ang University, Seoul 06974, South Korea. Electronic address: eyun@cau.ac.kr.
Förderung
- National Research Foundation of Korea
- Ministry of Oceans and Fisheries
- Korea Institute of Marine Science and Technology promotion
Zitieren
APA
Jeon, M. S., Nam, J., Lee, M., Cho, C., Yang, S., & Eyun, S. I. (2026). SaintGSE: Transformer-based efficient and explainable gene set enrichment analysis. Osteoarthritis and Cartilage, 34(8), 1231-1242. https://doi.org/10.1016/j.joca.2026.04.009
Vancouver
Jeon MS, Nam J, Lee M, Cho C, Yang S, Eyun SI. SaintGSE: Transformer-based efficient and explainable gene set enrichment analysis. Osteoarthritis and Cartilage. 2026;34(8):1231-1242. doi:10.1016/j.joca.2026.04.009
BibTeX
@article{Jeon2026,
author = {Jeon, Min-Seung and Nam, Jiho and Lee, Minseok and Cho, Chanmi and Yang, Siyoung and Eyun, Seong-Il},
title = {SaintGSE: Transformer-based efficient and explainable gene set enrichment analysis},
journal = {Osteoarthritis and Cartilage},
year = {2026},
volume = {34},
number = {8},
pages = {1231--1242},
doi = {10.1016/j.joca.2026.04.009}
}
EUVIMED