Graph Embedding on Biomedical Networks: Methods, Applications, and Evaluations

Abstract

Motivation:Graph embedding learning which aims to automatically learn low-dimensional node representations has drawn increasing attention in recent years. To date, most recent graph embedding methods are mainly evaluated on social and information networks and have not yet been comprehensively studied on biomedical networks under systematic experiments and analyses. On the other hand, for a variety of biomedical network analysis tasks, traditional techniques such as matrix factorization (which can be seen as one type of graph embedding methods) have shown promising results, and hence there is a need to systematically evaluate the more recent graph embedding methods (e.g., random walk-based and neural network-based) in terms of their usability and potential to further the state-of-the-art. Results: We select 11 representative graph embedding methods and conduct a systematic comparison on three important biomedical link prediction tasks: drug-disease association (DDA) prediction, drugdrug interaction (DDI) prediction, protein-protein interaction (PPI) prediction, and two node classification tasks: medical term semantic type classification, protein function prediction. Our experimental results demonstrate that the recent graph embedding methods which have not been explored completely on biomedical tasks achieve promising results and deserve more attention in the future biomedical graph analysis. Besides, compared with three state-of-the-art methods for DDAs, DDIs and protein function predictions, the recent graph embedding methods achieve competitive performance without using any biological features and the learned embeddings can be treated as complementary representations for the biological features. By summarizing the experimental results, we provide general guidelines for properly selecting graph embedding methods and setting their hyper-parameters for different biomedical tasks. Availability: As part of our contributions in the paper, we develop an easy-to-use Python package with detailed instructions, BioNEV, available at: https://github.com/xiangyue9607/BioNEV, including all source code and datasets, to facilitate studying various graph embedding methods on biomedical tasks.

A Comprehensive Analytical Survey on Unsupervised and Semi-Supervised Graph Representation Learning Methods

“…OhmNet has been proposed for multi-cellular function prediction [120] that uses node2vec as an underlying model. BioENV 6 has been developed recently by combining several general-purpose existing methods to solve biomedical link prediction task [114]. Another recent method is MeSHHead-ing2vec that converts Medical Subject Headings (MeSH) tree structure into a relationship network and applies five existing graph embedding methods to perform several downstream analyses tasks [35].…”

“…Link prediction itself is a broadened area of research in social network analysis [4]. It has many applications in social and biological networks, such as the recommendation of new friends in Facebook [97] and drug-disease association prediction in biomedical networks [114]. For link prediction, a good embedding method should capture local information from the network and preserve it in the embedding space.…”

Drug-disease Graph: Predicting Adverse Drug Reaction Signals via Graph Neural Network with Clinical Data

“…There have been numerous studies on ADR prediction in pre-marketing phases, attempting graph-based approaches on biomedical information sources [12,15,18,22]. These studies predicted potential side-effects of drug candidate molecules based on their chemical structures [15] and additional biological properties [12].…”

Accurately Modeling Biased Random Walks on Weighted Graphs Using $\textit{Node2vec+}$

“…Node2vec is a second-order random walk based embedding method (Grover and Leskovec 2016). It is widely used for unsupervised node embedding for various tasks, particularly in computational biology (Nelson et al 2019), such as gene function prediction (Liu et al 2020;Ata et al 2018) and essential protein prediction (Wang et al 2021a;Zeng et al 2021), due to its superior performance than other matrix factorization and neural network based methods (Yue et al 2019). Some recent works built on top of node2vec aim to adapt node2vec to more specific types of networks (Wang et al 2021b;Valentini et al 2021), generalize node2vec to higher dimension (Hacker 2021), augment node2vec with additional downstream processing (Chattopadhyay and Ganguly 2020;Hu et al 2020), or even study node2vec theoretically (Grohe 2020;Davison and Austern 2021;Qiu et al 2018).…”