Heterogeneous Graph based Deep Learning for Biomedical Network Link Prediction

2021/01/28 by Jinjiang Guo, Jie Li, Guo, Jinjiang +5
Biochemistry, Genetics and Molecular Biology · Computer Science · #Artificial Intelligence (cs.AI) #Artificial intelligence #Bioinformatics #Bioinformatics and Genomic Networks #Biological network #Bipartite graph #Computational Drug Discovery Methods #Computer science #Data mining #FOS: Computer and information sciences #Graph #Heterogeneous network #Information Retrieval (cs.IR) #Machine Learning (cs.LG) #Machine Learning in Bioinformatics #Machine learning #Protocol (science) #Robustness (evolution) #Social and Information Networks (cs.SI) #Theoretical computer science #Wireless network #cs.AI #cs.IR #cs.LG #cs.SI

paper · pdf · doi:10.48550/arxiv.2102.01649

openalex publication_date 2021/01/28 · openalex created_date 2021/02/15 · arxiv created 2022/02/24 · arxiv updated 2022/02/25 · openalex updated_date 2026/08/06

Abstract

Multi-scale biomedical knowledge networks are expanding with emerging experimental technologies that generates multi-scale biomedical big data. Link prediction is increasingly used especially in bipartite biomedical networks to identify hidden biological interactions and relationshipts between key entities such as compounds, targets, gene and diseases. We propose a Graph Neural Networks (GNN) method, namely Graph Pair based Link Prediction model (GPLP), for predicting biomedical network links simply based on their topological interaction information. In GPLP, 1-hop subgraphs extracted from known network interaction matrix is learnt to predict missing links. To evaluate our method, three heterogeneous biomedical networks were used, i.e. Drug-Target Interaction network (DTI), Compound-Protein Interaction network (CPI) from NIH Tox21, and Compound-Virus Inhibition network (CVI). Our proposed GPLP method significantly outperforms over the state-of-the-art baselines. In addition, different network incompleteness is analysed with our devised protocol, and we also design an effective approach to improve the model robustness towards incomplete networks. Our method demonstrates the potential applications in other biomedical networks.

Citations

• Adam: A Method for Stochastic Optimization
• Convergence and efficiency of subgradient methods for quasiconvex minimization
• AutoDock4 and AutoDockTools4: Automated docking with selective receptor flexibility
• Drug Target Identification Using Side-Effect Similarity
• DeepTox: Toxicity Prediction using Deep Learning
• Gated Graph Sequence Neural Networks
• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• How Powerful are Graph Neural Networks?
• Inductive Matrix Completion Based on Graph Neural Networks

Related

• Bi-Level Graph Neural Networks for Drug-Drug Interaction Prediction
• A Review of Link Prediction Applications in Network Biology
• Few-shot link prediction via graph neural networks for Covid-19 drug-repurposing
• Predicting Biomedical Interactions with Probabilistic Model Selection for Graph Neural Networks
• Predicting Molecule-Target Interaction by Learning Biomedical Network and Molecule Representations