October 13, 2025Open Access

GRNFormer: A Biologically-Guided Framework for Integrating Gene Regulatory Networks into RNA Foundation Models

View Full Paper

Ask AI

Bookmark

Authors

Discussion

Framework integrates gene regulatory networks with RNA models for improved gene expression analysis and drug response outcomes.

GRNFormer shows a 3.6% increase in drug response prediction correlation, highlighting its performance advantage.
The framework enhances drug classification performance by 9.6% in AUC, demonstrating its capability with multi-omics data.
This approach utilizes a graph topological adapter for dynamic relationship weighting in gene regulatory networks.
Implications suggest that GRNFormer could advance understanding of gene expression in single-cell contexts and drug discovery.

Qiu et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark

October 13, 2025Open Access

View Full Paper

Ask AI

Bookmark

Authors

Framework integrates gene regulatory networks with RNA models for improved gene expression analysis and drug response outcomes.

GRNFormer shows a 3.6% increase in drug response prediction correlation, highlighting its performance advantage.
The framework enhances drug classification performance by 9.6% in AUC, demonstrating its capability with multi-omics data.
This approach utilizes a graph topological adapter for dynamic relationship weighting in gene regulatory networks.
Implications suggest that GRNFormer could advance understanding of gene expression in single-cell contexts and drug discovery.

Qiu et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark