Improving Enzyme Prediction with Chemical Reaction Equations by Hypergraph-Enhanced Knowledge Graph Embeddings
Open Access
- 20 April 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 1309-1320
Abstract
Predicting enzyme-substrate interactions has long been a fundamental problem in biochemistry and metabolic engineering. While existing methods could leverage databases of expert-curated enzyme-substrate pairs for models to learn from known pair interactions, the databases are often sparse, i.e., there are only limited and incomplete examples of such pairs, and also labor-intensive to maintain. This lack of sufficient training data significantly hinders the ability of traditional enzyme prediction models to generalize to unseen interactions. In this work, we try to exploit chemical reaction equations from domain-specific databases, given their easier accessibility and denser, more abundant data. However, interactions of multiple compounds, e.g., educts and products, with the same enzymes create complex relational data patterns that traditional models cannot easily capture. To tackle that, we represent chemical reaction equations as triples of (educt, enzyme, product) within a knowledge graph, such that we can take advantage of knowledge graph embedding (KGE) to infer missing enzyme-substrate pairs for graph completion. Particularly, in order to capture intricate relationships among compounds, we propose our knowledge-enhanced hypergraph model for enzyme prediction, i.e., Hyper-Enz, which integrates a hypergraph transformer with a KGE model to learn representations of the hyper-edges that involve multiple educts and products. Also, a multi-expert paradigm is introduced to guide the learning of enzyme-substrate interactions with both the proposed model and chemical reaction equations. Experimental results show a significant improvement, with up to a 88% relative improvement in average enzyme retrieval accuracy and 30% improvement in pair-level prediction compared to traditional models, demonstrating the effectiveness of our approach.All Related Versions
This publication has 23 references indexed in Scilit:
- FusionESP: Improved Enzyme–Substrate Pair Prediction by Fusing Protein and Chemical KnowledgeJournal of Chemical Information and Modeling, 2025
- Deep Learning-Driven Insights into Enzyme–Substrate Interaction DiscoveryJournal of Chemical Information and Modeling, 2024
- Rank-ordering of known enzymes as starting points for re-engineering novel substrate activity using a convolutional neural networkMetabolic Engineering, 2023
- A general model to predict small molecule substrates of enzymes based on machine and deep learningNature Communications, 2023
- Deep learning in drug discovery: an integrative review and future challengesArtificial Intelligence Review, 2022
- PubChem 2023 updateNucleic Acids Research, 2022
- Boost-RS: boosted embeddings for recommender systems and its application to enzyme–substrate interaction predictionBioinformatics, 2022
- Biofuels and their sources of production: A review on cleaner sustainable alternative against conventional fuel, in the framework of the food and energy nexusEnergy Nexus, 2021
- The BRENDA enzyme information system–From a database to an expert systemJournal of Biotechnology, 2017
- KEGG: new perspectives on genomes, pathways, diseases and drugsNucleic Acids Research, 2016