Fused Gromov-Wasserstein Contrastive Learning for Effective Enzyme-Reaction Screening

2025-12-09

AI Summary

Traditional computational methods for enzyme–reaction matching exhibit low efficiency, while existing deep learning models neglect the intrinsic hierarchical structures of both enzymes and chemical reactions. Method: This paper proposes FGW-CLIP, a novel framework that introduces the Gromov–Wasserstein (GW) distance into cross-domain contrastive learning. It jointly optimizes intra-domain hierarchical alignment and inter-domain structural alignment, incorporating a customized regularizer to minimize the GW distance—thereby enabling multi-level joint embedding of enzymes and reactions. Unlike baseline models that only capture pairwise interaction patterns, FGW-CLIP explicitly enforces topological consistency between their underlying structural hierarchies. Results: On the EnzymeMap and ReactZyme benchmarks, FGW-CLIP achieves state-of-the-art performance in key virtual screening metrics—including BEDROC and enrichment factor (EF)—demonstrating substantial improvements in screening efficiency and strong generalization capability across diverse enzyme–reaction tasks.

Technology Category

• Machine Learning: Ensemble Methods
• Search and Optimization: Learning to Search
• Computer Vision: Learning & Optimization for CV

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Enzymes are crucial catalysts that enable a wide range of biochemical reactions. Efficiently identifying specific enzymes from vast protein libraries is essential for advancing biocatalysis. Traditional computational methods for enzyme screening and retrieval are time-consuming and resource-intensive. Recently, deep learning approaches have shown promise. However, these methods focus solely on the interaction between enzymes and reactions, overlooking the inherent hierarchical relationships within each domain. To address these limitations, we introduce FGW-CLIP, a novel contrastive learning framework based on optimizing the fused Gromov-Wasserstein distance. FGW-CLIP incorporates multiple alignments, including inter-domain alignment between reactions and enzymes and intra-domain alignment within enzymes and reactions. By introducing a tailored regularization term, our method minimizes the Gromov-Wasserstein distance between enzyme and reaction spaces, which enhances information integration across these domains. Extensive evaluations demonstrate the superiority of FGW-CLIP in challenging enzyme-reaction tasks. On the widely-used EnzymeMap benchmark, FGW-CLIP achieves state-of-the-art performance in enzyme virtual screening, as measured by BEDROC and EF metrics. Moreover, FGW-CLIP consistently outperforms across all three splits of ReactZyme, the largest enzyme-reaction benchmark, demonstrating robust generalization to novel enzymes and reactions. These results position FGW-CLIP as a promising framework for enzyme discovery in complex biochemical settings, with strong adaptability across diverse screening scenarios.

Problem

• Traditional enzyme screening methods are inefficient and resource-intensive
• Existing deep learning approaches ignore hierarchical relationships within enzyme and reaction domains
• Current methods lack effective integration of inter-domain and intra-domain alignments

Innovation

• Fused Gromov-Wasserstein distance optimization for contrastive learning
• Multiple alignments including inter-domain and intra-domain relationships
• Tailored regularization term enhancing cross-domain information integration