Macaulay Oladimeji, Servilla Michael, Arredondo David, Virupakshappa Kushal, Hu Yue, Tafoya Luis, Zhang Yanfu, Sahu Avinash
Comprehensive Cancer Center, The University of New Mexico.
Department of Computer Science, William and Mary.
Proc Mach Learn Res. 2024 Sep;261:162-182.
Genetic, molecular, and environmental factors influence diseases through complex interactions with genes, phenotypes, and drugs. Current methods often fail to integrate diverse multi-relational biological data meaningfully, limiting the discovery of novel risk genes and drugs. To address this, we present , a multi-relational Graph Neural Network (GNN) model designed to infer relationships among drugs, genes, diseases, and phenotypes. initializes nodes using informative embeddings from existing text knowledge, allowing for robust integration of various data types and improved generalizability. Our results demonstrate that matches and often outperforms traditional single-relation approaches, particularly in scenarios with isolated or sparsely connected nodes. The model shows generalizability to external datasets, achieving high accuracy in identifying disease-gene associations and drug-phenotype relationships. Notably, accurately inferred drug side effects without direct training on such data. Using Alzheimer's disease as a case study, successfully identified relevant phenotypes, genes, and drugs, corroborated by existing literature. These findings demonstrate the potential of integrating multi-relational data with text knowledge to enhance biomedical predictions and drug repurposing for diseases. code is available at https://github.com/vinash85/MedGraphNet.
遗传、分子和环境因素通过与基因、表型和药物的复杂相互作用影响疾病。当前的方法常常无法有效地整合多样的多关系生物数据，限制了新型风险基因和药物的发现。为了解决这一问题，我们提出了MedGraphNet，这是一种多关系图神经网络（GNN）模型，旨在推断药物、基因、疾病和表型之间的关系。MedGraphNet使用来自现有文本知识的信息嵌入初始化节点，从而能够强大地整合各种数据类型并提高泛化能力。我们的结果表明，MedGraphNet与传统的单关系方法相匹配，并且常常优于它们，特别是在节点孤立或连接稀疏的场景中。该模型对外部数据集具有泛化能力，在识别疾病-基因关联和药物-表型关系方面达到了高精度。值得注意的是，MedGraphNet在没有直接针对此类数据进行训练的情况下准确推断出了药物副作用。以阿尔茨海默病为例进行研究，MedGraphNet成功识别出了相关的表型、基因和药物，现有文献也证实了这一点。这些发现证明了将多关系数据与文本知识相结合以增强生物医学预测和疾病药物再利用的潜力。MedGraphNet的代码可在https://github.com/vinash85/MedGraphNet获取。
