Uncertainty-Aware Metabolic Stability Prediction with Dual-View Contrastive Learning

2025-06-01

AI Summary

Predicting metabolic stability (MS) of drug-like molecules remains challenging due to incomplete modeling of complex intermolecular interactions and difficulty in quantifying prediction uncertainty. To address these issues, we propose a novel graph neural network framework. First, we design a molecular graph topological remapping mechanism that explicitly encodes bond-order topological features—overcoming the limitations of conventional atom-centered message passing. Second, we introduce a topology-bond pattern contrastive alignment module to enhance structural representation robustness. Third, we pioneer the integration of a Beta-Binomial model to quantify epistemic uncertainty and calibrate predictive confidence. Our method synergizes edge-induced feature propagation with dual-view contrastive learning. Extensive experiments on multiple benchmark datasets demonstrate significant improvements over state-of-the-art methods, achieving both higher prediction accuracy and superior uncertainty calibration performance.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Reasoning under Uncertainty: Graphical Models
• Data Mining & Knowledge Management: Graph Mining, Social Network Analysis & Community

Application Category

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

Abstract

Accurate prediction of molecular metabolic stability (MS) is critical for drug research and development but remains challenging due to the complex interplay of molecular interactions. Despite recent advances in graph neural networks (GNNs) for MS prediction, current approaches face two critical limitations: (1) incomplete molecular modeling due to atom-centric message-passing mechanisms that disregard bond-level topological features, and (2) prediction frameworks that lack reliable uncertainty quantification. To address these challenges, we propose TrustworthyMS, a novel contrastive learning framework designed for uncertainty-aware metabolic stability prediction. First, a molecular graph topology remapping mechanism synchronizes atom-bond interactions through edge-induced feature propagation, capturing both localized electronic effects and global conformational constraints. Second, contrastive topology-bond alignment enforces consistency between molecular topology views and bond patterns via feature alignment, enhancing representation robustness. Third, uncertainty modeling through Beta-Binomial uncertainty quantification enables simultaneous prediction and confidence calibration under epistemic uncertainty. Through extensive experiments, our results demonstrate that TrustworthyMS outperforms current state-of-the-art methods in terms of predictive performance.

Problem

• Incomplete molecular modeling in metabolic stability prediction
• Lack of reliable uncertainty quantification in prediction frameworks
• Challenges in capturing atom-bond interactions and global constraints

Innovation

• Edge-induced feature propagation for atom-bond synchronization
• Contrastive topology-bond alignment for robust representation
• Beta-Binomial uncertainty quantification for confidence calibration