Technology Category
Machine Learning: Deep Generative Models & AutoencodersCognitive Modeling & Cognitive Systems: Computational CreativityMultiagent Systems: Mechanism Design
OmniESI: A unified framework for enzyme-substrate interaction prediction with progressive conditional deep learning
🤖 AI Summary
Existing enzyme–substrate interaction prediction methods neglect prior knowledge of enzymatic catalytic mechanisms, leading to a mismatch between generic protein–ligand features and actual catalytic patterns. To address this, we propose a two-stage progressive conditional deep learning framework that dynamically modulates representations from generic to catalysis-aware via dual conditional networks, sequentially injecting reaction-specific constraints and critical catalytic interaction information into the latent space. Our method is the first to support multi-task modeling within a unified architecture, achieving substantial performance gains with only a 0.16% parameter increase. It outperforms all state-of-the-art methods across seven benchmark datasets, particularly excelling in out-of-distribution generalization. Ablation studies validate both the efficacy of the conditional modulation mechanism and the design rationale of the progressive architecture.
Technology Category
Application Category
📝 Abstract
Understanding and modeling enzyme-substrate interactions is crucial for catalytic mechanism research, enzyme engineering, and metabolic engineering. Although a large number of predictive methods have emerged, they do not incorporate prior knowledge of enzyme catalysis to rationally modulate general protein-molecule features that are misaligned with catalytic patterns. To address this issue, we introduce a two-stage progressive framework, OmniESI, for enzyme-substrate interaction prediction through conditional deep learning. By decomposing the modeling of enzyme-substrate interactions into a two-stage progressive process, OmniESI incorporates two conditional networks that respectively emphasize enzymatic reaction specificity and crucial catalysis-related interactions, facilitating a gradual feature modulation in the latent space from general protein-molecule domain to catalysis-aware domain. On top of this unified architecture, OmniESI can adapt to a variety of downstream tasks, including enzyme kinetic parameter prediction, enzyme-substrate pairing prediction, enzyme mutational effect prediction, and enzymatic active site annotation. Under the multi-perspective performance evaluation of in-distribution and out-of-distribution settings, OmniESI consistently delivered superior performance than state-of-the-art specialized methods across seven benchmarks. More importantly, the proposed conditional networks were shown to internalize the fundamental patterns of catalytic efficiency while significantly improving prediction performance, with only negligible parameter increases (0.16%), as demonstrated by ablation studies on key components. Overall, OmniESI represents a unified predictive approach for enzyme-substrate interactions, providing an effective tool for catalytic mechanism cracking and enzyme engineering with strong generalization and broad applicability.
Problem
Research questions and friction points this paper is trying to address.
Predict enzyme-substrate interactions using conditional deep learning
Modulate protein-molecule features to align with catalytic patterns
Adapt to multiple downstream tasks in enzyme research
Innovation
Methods, ideas, or system contributions that make the work stand out.
Two-stage progressive conditional deep learning framework
Emphasizes enzymatic reaction specificity and catalysis-related interactions
Adapts to multiple downstream tasks with strong generalization
🔎 Similar Papers
No similar papers found.
