Authors
- Rikuto Kotoge SANKEN, The University of Osaka
- Ziwei Yang Bioinformatics Center, Institute for Chemical Research, Kyoto University SANKEN, The University of Osaka
- Zheng Chen SANKEN, The University of Osaka
- Yushun Dong Department of Computer Science, Florida State University
- Yasuko Matsubara SANKEN, The University of Osaka
- Jimeng Sun Department of Computer Science, University of Illinois Urbana-Champaign
- Yasushi Sakurai SANKEN, The University of Osaka
DOI:
https://doi.org/10.1609/aaai.v40i1.37017Abstract
Retrieving targeted pathways in biological knowledge bases, particularly when incorporating wet-lab experimental data, remains a challenging task and often requires downstream analyses and specialized expertise. In this paper, we frame this challenge as a solvable graph learning and explaining task and propose a novel subgraph inference framework, ExPath, that explicitly integrates experimental data to classify various graphs (bio-networks) in biological databases. The links (representing pathways) that contribute more to classification can be considered as targeted pathways. Our framework can seamlessly integrate biological foundation models to encode the experimental molecular data. We propose ML-oriented biological evaluations and a new metric. The experiments involving 301 bio-networks evaluations demonstrate that pathways inferred by ExPath are biologically meaningful, achieving up to 4.5× higher Fidelity+ (necessity) and 14× lower Fidelity- (sufficiency) than explainer baselines, while preserving signaling chains up to 4× longer.
How to Cite
Kotoge, R., Yang, Z., Chen, Z., Dong, Y., Matsubara, Y., Sun, J., & Sakurai, Y. (2026). Targeted Pathway Inference for Biological Knowledge Bases via Graph Learning and Explanation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(1), 534–542. https://doi.org/10.1609/aaai.v40i1.37017
Issue
Section
AAAI Technical Track on Application Domains I