Gene expression inference based on graph neural networks using L1000 data
Briefings in Bioinformatics · 2025
DOI: 10.1093/bib/bbaf273 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2025. Verfasst von Tae Hyun Kim und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Regulatory Science, Graduate School, Kyung Hee University, 26 Kyungheedae-ro, Dongdaemun District, Seoul 02447, South Korea. Hauptthemen laut MEDLINE: Neural Networks, Computer, Gene Expression Profiling, Computational Biology, Transcriptome. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: National Research Foundation of Korea, Kyung Hee University, Institute of Information & Communication Technology Planning & Evaluation.
Abstract (Originalsprache)
Gene expression profiles can serve as proxies for cellular states and provide valuable insights into the discovery of functional connections across diverse cellular contexts. A cost-effective method called L1000 has been developed to generate gene expression profiles for over a million different conditions. Since gene expression inference of this method relies on linear regression, nonlinear regression methods, including deep learning models, have been assessed. However, these approaches process gene expression data as a vector structure, motivating us to investigate whether nonlinear models based on a graph structure are more effective in capturing the relationships between genes underlying gene expression profiles. In this work, we show that the graph neural network (GNN) model with genes as nodes outperforms both linear and nonlinear non-GNN models in predicting gene expression values and expression-based gene rankings. Importantly, our GNN model requires ~10-fold less information than other models to achieve comparable performance. A strategic selection of input features, or incorporating an organ feature, from which the gene expression data are derived, further improves gene expression inference performance of the GNN model. Additionally, we evaluate the cross-platform generality of gene expression inference. Our study demonstrates that the transformation of RNA expression data into a graph structure effectively captures nonlinear correlations between genes, thereby enabling highly accurate and efficient prediction of gene expression profiles.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Regulatory Science, Graduate School, Kyung Hee University, 26 Kyungheedae-ro, Dongdaemun District, Seoul 02447, South Korea.
- College of Pharmacy, Kyung Hee University, 26 Kyungheedae-ro, Dongdaemun District, Seoul 02447, South Korea.
- Kim Jaechul Graduate School of AI, Korea Advanced Institute of Science & Technology, 85 Hoegi-ro, Dongdaemun District, Seoul 02455, South Korea.
- Institute of Regulatory Innovation through Science (IRIS), Kyung Hee University, 26 Kyungheedae-ro, Dongdaemun District, Seoul 02447, South Korea.
Förderung
- National Research Foundation of Korea
- Kyung Hee University
- Institute of Information & Communication Technology Planning & Evaluation
Zitieren
APA
Kim, T. H., Kim, H., Hwang, H., Kang, S., Shin, K., & Baek, I. (2025). Gene expression inference based on graph neural networks using L1000 data. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbaf273
Vancouver
Kim TH, Kim H, Hwang H, Kang S, Shin K, Baek I. Gene expression inference based on graph neural networks using L1000 data. Briefings in Bioinformatics. 2025. doi:10.1093/bib/bbaf273
BibTeX
@article{Kim2025,
author = {Kim, Tae Hyun and Kim, Harim and Hwang, Hyunjin and Kang, Shinwhan and Shin, Kijung and Baek, Inwha},
title = {Gene expression inference based on graph neural networks using L1000 data},
journal = {Briefings in Bioinformatics},
year = {2025},
doi = {10.1093/bib/bbaf273}
}
EUVIMED