KansformerEPI: a deep learning framework integrating KAN and transformer for predicting enhancer–promoter interactions
Briefings in Bioinformatics · 2025
DOI: 10.1093/bib/bbaf272 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2025. Verfasst von Tianjiao Zhang und 7 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer and Control Engineering, Northeast Forestry University, No. 26 Hexing Road, Xiangfang District, Harbin 150040, China. Hauptthemen laut MEDLINE: Deep Learning, Enhancer Elements, Genetic, Promoter Regions, Genetic, Computational Biology. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation, National Natural Science Foundation of China.
Abstract (Originalsprache)
Enhancer–promoter interaction (EPI) is a critical component of gene regulation. Accurately predicting EPIs across diverse cell types can advance our understanding of the molecular mechanisms behind transcriptional regulation and provide valuable insights into the onset and progression of related diseases. At present, large-scale genome-wide EPI predictions typically rely on computational approaches. However, most of these methods focus on predicting EPIs within a single cell line and lack a global perspective encompassing multiple cell lines. Furthermore, they often fail to fully account for the nonlinear relationships between features, leading to suboptimal prediction accuracy. In this study, we propose KansformerEPI, a global EPI prediction model designed for multiple cell lines. The model is built on Kansformer, an encoder that integrates KAN and Transformer, effectively capturing the nonlinear relationships among various epigenetic and sequence features. We utilized KansformerEPI to achieve cross-tissue prediction of EPIs across different cell types. This approach enhances the model’s scalability, eliminating the complexity of designing separate prediction models for individual tissues. As a result, our model is applicable to various tissues, thereby reducing dependency on extensive datasets. Experimental results demonstrate that KansformerEPI surpasses existing methods such as TransEPI, TargetFinder, and SPEID in both accuracy and stability of EPI predictions across datasets including HMEC, IMR90, K562, and NHEK.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Computer and Control Engineering, Northeast Forestry University, No. 26 Hexing Road, Xiangfang District, Harbin 150040, China.
- Faculty of Computing, Harbin Institute of Technology, No. 92 West Da Zhi street, Nangang District, Harbin 150001, China.
ORCID-Profile: Tianjiao Zhang, Saihong Shao, Zhongqian Zhao, Xiang Zhang, Guohua Wang
Förderung
- National Science Foundation
- National Natural Science Foundation of China
Zitieren
APA
Zhang, T., Shao, S., Zhang, H., Zhao, Z., Zhao, X., Zhang, X., Wang, Z., & Wang, G. (2025). KansformerEPI: a deep learning framework integrating KAN and transformer for predicting enhancer–promoter interactions. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbaf272
Vancouver
Zhang T, Shao S, Zhang H, Zhao Z, Zhao X, Zhang X, et al. KansformerEPI: a deep learning framework integrating KAN and transformer for predicting enhancer–promoter interactions. Briefings in Bioinformatics. 2025. doi:10.1093/bib/bbaf272
BibTeX
@article{Zhang2025,
author = {Zhang, Tianjiao and Shao, Saihong and Zhang, Hongfei and Zhao, Zhongqian and Zhao, Xingjie and Zhang, Xiang and Wang, Zhenxing and Wang, Guohua},
title = {KansformerEPI: a deep learning framework integrating KAN and transformer for predicting enhancer–promoter interactions},
journal = {Briefings in Bioinformatics},
year = {2025},
doi = {10.1093/bib/bbaf272}
}
EUVIMED