EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Integrating Prior Knowledge Using Transformer for Gene Regulatory Network Inference

Guangzheng Weng iD, Patrick Martin, Hyobin Kim, Kyoung Jae Won iD

Advanced Science · 2025

DOI: 10.1002/advs.202409990 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Science, 2025. Verfasst von Guangzheng Weng und 3 weiteren Autor:innen. Beteiligte Einrichtung: Biotech Research and Innovation Centre (BRIC), University of Copenhagen, Ole Maaløes Vej 5, Copenhagen, 2200, Denmark. Hauptthemen laut MEDLINE: Gene Regulatory Networks, Computational Biology. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Gene regulatory network (GRN) inference, a process of reconstructing gene regulatory rules from experimental data, has the potential to discover new regulatory rules. However, existing methods often struggle to generalize across diverse cell types and account for unseen regulators. Here, this work presents GRNPT, a novel Transformer‐based framework that integrates large language model (LLM) embeddings from publicly accessible biological data and a temporal convolutional network (TCN) autoencoder to capture regulatory patterns from single‐cell RNA sequencing (scRNA‐seq) trajectories. GRNPT significantly outperforms both supervised and unsupervised methods in inferring GRNs, particularly when training data is limited. Notably, GRNPT exhibits exceptional generalizability, accurately predicting regulatory relationships in previously unseen cell types and even regulators. By combining LLMs ability to distillate biological knowledge from text and deep learning methodologies capturing complex patterns in gene expression data, GRNPT overcomes the limitations of traditional GRN inference methods and enables more accurate and comprehensive understanding of gene regulatory dynamics.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Gene Regulatory NetworksComputational BiologySingle-Cell AnalysisHumansDeep LearningAlgorithms

Stichwörter der Autor:innen

deep learninggene regulatory networksinferencelarge language modeltemporal convolutional networktransformer

Autor:innen und Institutionen

  • Biotech Research and Innovation Centre (BRIC), University of Copenhagen, Ole Maaløes Vej 5, Copenhagen, 2200, Denmark.
  • Department of Computational Biomedicine, Cedars-Sinai Medical Center, Los Angeles, CA, 90069, USA.

ORCID-Profile: Guangzheng Weng, Kyoung Jae Won

Zitieren

APA

Weng, G., Martin, P., Kim, H., & Won, K. J. (2025). Integrating Prior Knowledge Using Transformer for Gene Regulatory Network Inference. Advanced Science. https://doi.org/10.1002/advs.202409990

Vancouver

Weng G, Martin P, Kim H, Won KJ. Integrating Prior Knowledge Using Transformer for Gene Regulatory Network Inference. Advanced Science. 2025. doi:10.1002/advs.202409990

BibTeX
@article{Weng2025,
  author = {Weng, Guangzheng and Martin, Patrick and Kim, Hyobin and Won, Kyoung Jae},
  title = {Integrating Prior Knowledge Using Transformer for Gene Regulatory Network Inference},
  journal = {Advanced Science},
  year = {2025},
  doi = {10.1002/advs.202409990}
}
Kostenlos starten →