ExPath: Targeted Pathway Inference for Biological Knowledge Bases via Graph Learning and Explanation

TL;DR

ExPath is a novel graph learning framework that infers biologically meaningful pathways from knowledge bases by integrating experimental data and explaining graph classifications.

Contribution

It introduces a new subgraph inference method that combines biological data with graph learning to identify targeted pathways more accurately.

Findings

Pathways inferred by ExPath show up to 4.5x higher Fidelity+.

ExPath achieves 14x lower Fidelity- compared to baselines.

The method preserves signaling chains up to 4x longer.

Abstract

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 4.5x higher Fidelity+ (necessity) and 14x lower Fidelity- (sufficiency) than explainer baselines, while preserving signaling chains up to 4x longer.