GOProteinGNN: Leveraging Protein Knowledge Graphs for Protein Representation Learning

2024-07-31

arXiv.org

AI Summary

Existing protein representation methods predominantly rely on amino acid sequences, neglecting functional semantics and biological prior knowledge, thereby limiting their efficacy in drug discovery. To address this, we propose a multi-granularity knowledge-enhanced protein language model that integrates Gene Ontology (GO) annotations and protein–protein interaction networks. Our approach is the first to perform end-to-end modeling of the full knowledge graph structure—not merely triples—during training, enabling joint optimization of amino acid–level and whole-protein–level representations. It synergistically combines graph neural networks, multi-granularity knowledge graph embedding, and cross-modal alignment mechanisms. Extensive experiments demonstrate state-of-the-art performance on downstream tasks including protein function prediction and mutation effect assessment. Moreover, our model significantly improves representation robustness and biological interpretability, offering mechanistic insights grounded in structured biological knowledge.

Technology Category

• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Machine Learning: Representation Learning
• Knowledge Representation and Reasoning: Ontologies

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: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Proteins play a vital role in biological processes and are indispensable for living organisms. Accurate representation of proteins is crucial, especially in drug development. Recently, there has been a notable increase in interest in utilizing machine learning and deep learning techniques for unsupervised learning of protein representations. However, these approaches often focus solely on the amino acid sequence of proteins and lack factual knowledge about proteins and their interactions, thus limiting their performance. In this study, we present GOProteinGNN, a novel architecture that enhances protein language models by integrating protein knowledge graph information during the creation of amino acid level representations. Our approach allows for the integration of information at both the individual amino acid level and the entire protein level, enabling a comprehensive and effective learning process through graph-based learning. By doing so, we can capture complex relationships and dependencies between proteins and their functional annotations, resulting in more robust and contextually enriched protein representations. Unlike previous methods, GOProteinGNN uniquely learns the entire protein knowledge graph during training, which allows it to capture broader relational nuances and dependencies beyond mere triplets as done in previous work. We perform a comprehensive evaluation on several downstream tasks demonstrating that GOProteinGNN consistently outperforms previous methods, showcasing its effectiveness and establishing it as a state-of-the-art solution for protein representation learning.

Problem

• Enhance protein representation learning
• Integrate protein knowledge graphs
• Improve drug development accuracy

Innovation

• Integrates protein knowledge graphs
• Enhances amino acid representations
• Captures complex protein relationships