Multi-dataset and Transfer Learning Using Gene Expression Knowledge Graphs

2025-03-26

AI Summary

To address the challenges of small-sample sizes and cross-dataset heterogeneity in gene expression data integration, this paper constructs a gene expression knowledge graph that unifies multi-omics data and biomedical prior knowledge, enabling single-dataset learning, multi-dataset joint modeling, and cross-domain transfer diagnosis. We propose the first knowledge-guided, multi-source collaborative learning framework for gene expression data by end-to-end integrating knowledge graph embedding (TransR) with graph neural networks (GNNs). Our method explicitly encodes biological relationships and functional constraints into the learning process, thereby enhancing model interpretability and generalizability. Extensive experiments demonstrate statistically significant improvements in disease diagnostic accuracy across all three learning paradigms—single-dataset, multi-dataset joint, and cross-domain transfer—validating the effectiveness and robust generalization capability of knowledge graph–driven heterogeneous data fusion for small-sample biomedical modeling.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches 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

Gene expression datasets offer insights into gene regulation mechanisms, biochemical pathways, and cellular functions. Additionally, comparing gene expression profiles between disease and control patients can deepen the understanding of disease pathology. Therefore, machine learning has been used to process gene expression data, with patient diagnosis emerging as one of the most popular applications. Although gene expression data can provide valuable insights, challenges arise because the number of patients in expression datasets is usually limited, and the data from different datasets with different gene expressions cannot be easily combined. This work proposes a novel methodology to address these challenges by integrating multiple gene expression datasets and domain-specific knowledge using knowledge graphs, a unique tool for biomedical data integration. Then, vector representations are produced using knowledge graph embedding techniques, which are used as inputs for a graph neural network and a multi-layer perceptron. We evaluate the efficacy of our methodology in three settings: single-dataset learning, multi-dataset learning, and transfer learning. The experimental results show that combining gene expression datasets and domain-specific knowledge improves patient diagnosis in all three settings.

Problem

• Integrating multiple gene expression datasets using knowledge graphs
• Overcoming limited patient data and incompatible gene expression datasets
• Improving patient diagnosis via multi-dataset and transfer learning

Innovation

• Integrates multiple gene expression datasets using knowledge graphs
• Utilizes knowledge graph embedding for vector representations
• Applies graph neural network and multi-layer perceptron