KGOT: Unified Knowledge Graph and Optimal Transport Pseudo-Labeling for Molecule-Protein Interaction Prediction

2025-12-10

AI Summary

To address the dual bottlenecks of scarce labeled data and insufficient exploitation of biological context in molecular–protein interaction (MPI) prediction, this paper proposes a knowledge graph-guided optimal transport pseudo-labeling framework. Methodologically, it introduces the first integration of heterogeneous multi-source biological knowledge graphs—encompassing molecules, proteins, genes, and pathways—with optimal transport theory to enable cross-modal feature alignment and self-supervised pseudo-label generation. A graph neural network fuses multi-level biological priors, substantially improving model generalization and zero-shot transferability. On multiple benchmark datasets, our method achieves AUC improvements of 3.2–5.8% and zero-shot F1 gains up to 12.4%. It also outperforms state-of-the-art methods in virtual screening and protein retrieval tasks. Overall, this work establishes a scalable, knowledge-enhanced paradigm for MPI prediction under low-resource conditions.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Search and Optimization: Metareasoning and Metaheuristics
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Predicting molecule-protein interactions (MPIs) is a fundamental task in computational biology, with crucial applications in drug discovery and molecular function annotation. However, existing MPI models face two major challenges. First, the scarcity of labeled molecule-protein pairs significantly limits model performance, as available datasets capture only a small fraction of biological relevant interactions. Second, most methods rely solely on molecular and protein features, ignoring broader biological context such as genes, metabolic pathways, and functional annotations that could provide essential complementary information. To address these limitations, our framework first aggregates diverse biological datasets, including molecular, protein, genes and pathway-level interactions, and then develop an optimal transport-based approach to generate high-quality pseudo-labels for unlabeled molecule-protein pairs, leveraging the underlying distribution of known interactions to guide label assignment. By treating pseudo-labeling as a mechanism for bridging disparate biological modalities, our approach enables the effective use of heterogeneous data to enhance MPI prediction. We evaluate our framework on multiple MPI datasets including virtual screening tasks and protein retrieval tasks, demonstrating substantial improvements over state-of-the-art methods in prediction accuracies and zero shot ability across unseen interactions. Beyond MPI prediction, our approach provides a new paradigm for leveraging diverse biological data sources to tackle problems traditionally constrained by single- or bi-modal learning, paving the way for future advances in computational biology and drug discovery.

Problem

• Addresses scarcity of labeled molecule-protein pairs for interaction prediction.
• Incorporates broader biological context beyond molecular and protein features.
• Enhances prediction accuracy and zero-shot ability across unseen interactions.

Innovation

• Unified knowledge graph aggregates diverse biological datasets
• Optimal transport generates high-quality pseudo-labels for unlabeled pairs
• Heterogeneous data integration enhances molecule-protein interaction prediction