Phenotype Prediction by Heterogeneous Molecular Network Embedding

MotivationRegulatory elements (REs), such as enhancers and promoters, are known as regulatory sequences functional in a heterogeneous regulatory network to control gene expression by recruiting transcription regulators and carrying genetic variants in a context specific way. Annotating those REs relies on costly and labor-intensive next-generation sequencing and RNA-guided editing technologies in many cellular contexts.ResultsWe propose a systematic Gene Ontology Annotation method for Regulatory Elements (RE-GOA) by leveraging the powerful word embedding in natural language processing. We first assemble a heterogeneous network by integrating context specific regulations, protein–protein interactions and gene ontology (GO) terms. Then we perform network embedding and associate regulatory elements with GO terms by assessing their similarity in a low dimensional vector space. With three applications, we show that RE-GOA outperforms existing methods in annotating TFs’ binding sites from ChIP-seq data, in functional enrichment analysis of differentially accessible peaks from ATAC-seq data, and in revealing genetic correlation among phenotypes from their GWAS summary statistics data.Availability and implementationThe source code and the systematic RE annotation for human and mouse are available at https://github.com/AMSSwanglab/RE-GOA.Supplementary informationSupplementary data are available at Bioinformatics online.

Many complex systems derived from nature and society consist of multiple types of entities and heterogeneous interactions, which can be effectively modeled as heterogeneous information network (HIN). Structural analysis of heterogeneous networks is of great significance by leveraging the rich semantic information of objects and links in the heterogeneous networks. And, clustering heterogeneous networks aims to group vertices into classes, which sheds light on revealing the structure–function relations of the underlying systems. The current algorithms independently perform the feature extraction and clustering, which are criticized for not fully characterizing the structure of clusters. In this study, we propose a learning model by joint <underline>G</underline>raph <underline>E</underline>mbedding and <underline>N</underline>onnegative <underline>M</underline>atrix <underline>F</underline>actorization (aka GEjNMF ), where feature extraction and clustering are simultaneously learned by exploiting the graph embedding and latent structure of networks. We formulate the objective function of GEjNMF and transform the heterogeneous network clustering problem into a constrained optimization problem, which is effectively solved by l 0 -norm optimization. The advantage of GEjNMF is that features are selected under the guidance of clustering, which improves the performance and saves the running time of algorithms at the same time. The experimental results on three benchmark heterogeneous networks demonstrate that GEjNMF achieves the best performance with the least running time compared with the best state-of-the-art methods. Furthermore, the proposed algorithm is robust across heterogeneous networks from various fields. The proposed model and method provide an effective alternative for heterogeneous network clustering.

Real-world complex networks are inherently heterogeneous; they have different types of nodes, attributes, and relationships. In recent years, various methods have been proposed to automatically learn how to encode the structural and semantic information contained in heterogeneous information networks (HINs) into low-dimensional embeddings; this task is called heterogeneous network embedding (HNE). Efficient HNE techniques can benefit various HIN-based machine learning tasks such as node classification, recommender systems, and information retrieval. Here, we provide a comprehensive survey of key advancements in the area of HNE. First, we define an encoder-decoder-based HNE model taxonomy. Then, we systematically overview, compare, and summarize various state-of-the-art HNE models and analyze the advantages and disadvantages of various model categories to identify more potentially competitive HNE frameworks. We also summarize the application fields, benchmark datasets, open source tools, and performance evaluation in the HNE area. Finally, we discuss open issues and suggest promising future directions. We anticipate that this survey will provide deep insights into research in the field of HNE.

Mention recommendation is the task of recommending the right candidate users in a message. Many works have been conducted on the problem of whom to mention. However, due to the sparsity and heterogeneous of mention data, none of them well solve the problem. The recent advances in network embedding representation learning provide an effective approach to model the sparsity and heterogeneous simultaneously in heterogeneous information network. To this end, we propose a novel Network Embedding Mention (NEM) recommendation model to recommend the right users in a message. NEM constructs a heterogeneous mention network based on different relationships among different entities. Then NEM learns a unified low dimensional embedding vector using random walk for users and messages by considering network structure and vertex content information. Finally, whom to mention is ranked by calculating the relevance scores from heterogeneous user and message embeddings. To evaluate the proposed method, we construct a large dataset and their corresponding social networks from a real-world social media platform. Through extensive experiments on real-world mention collection, we demonstrate that our proposed model outperforms the previous state-of-the-art methods in term of recommendation task.

Network embedding (graph embedding) has become the focus of studying graph structure in recent years. In addition to the research on homogeneous networks and heterogeneous networks, there are also some methods to attempt to solve the problem of dynamic network embedding. However, in dynamic networks, there is no research method specifically for heterogeneous networks. Therefore, this paper proposes a heterogeneous dynamic graph attention network (HDGAN), which attempts to use the attention mechanism to take the heterogeneity and dynamics of the network into account at the same time, so as to better learn network embedding. Our method is based on three levels of attention, namely structural-level attention, semantic-level attention and time-level attention. Structural-level attention pays attention to the network structure itself, and obtains the representation of structural-level nodes by learning the attention coefficients of neighbor nodes. Semantic-level attention integrates semantic information into the representation of nodes by learning the optimal weighted combination of different meta-paths. Time-level attention is based on the time decay effect, and the time feature is introduced into the node representation by neighborhood formation sequence. Through the above three levels of attention mechanism, the final network embedding can be obtained.Through experiments on two real-world heterogeneous dynamic networks, our models have the best results, proving the effectiveness of the HDGAN model.

BackgroundDrug combination, offering an insight into the increased therapeutic efficacy and reduced toxicity, plays an essential role in the therapy of many complex diseases. Although significant efforts have been devoted to the identification of drugs, the identification of drug combination is still a challenge. The current algorithms assume that the independence of feature selection and drug prediction procedures, which may result in an undesirable performance.ResultsTo address this issue, we develop a novel Semi-supervised Heterogeneous Network Embedding algorithm (called SeHNE) to predict the combination patterns of drugs by exploiting the graph embedding. Specifically, the ATC similarity of drugs, drug–target, and protein–protein interaction networks are integrated to construct the heterogeneous networks. Then, SeHNE jointly learns drug features by exploiting the topological structure of heterogeneous networks and predicting drug combination. One distinct advantage of SeHNE is that features of drugs are extracted under the guidance of classification, which improves the quality of features, thereby enhancing the performance of prediction of drugs. Experimental results demonstrate that the proposed algorithm is more accurate than state-of-the-art methods on various data, implying that the joint learning is promising for the identification of drug combination.ConclusionsThe proposed model and algorithm provide an effective strategy for the prediction of combinatorial patterns of drugs, implying that the graph-based drug prediction is promising for the discovery of drugs.

Interpretable answer retrieval based on heterogeneous network embedding

Cross-domain recommendation is critically important to construct a practical recommender system. The challenges of building a cross-domain recommender system lie in both the data sparsity issue and lacking of sufficient semantic information. Traditional approaches focus on using the user-item rating matrix or other feedback information, but the contents associated with the objects like reviews and the relationships among the objects are largely ignored. Although some works merge the content information and the user-item rating network structure, they only focus on using the attributes of the items but ignore user generated contents such as reviews. In this paper, we propose a novel cross-domain recommender framework called ECHCDR (Embedding content and heterogeneous network for cross-domain recommendation), which contains two major steps of content embedding and heterogeneous network embedding. By considering the contents of objects and their relationships, ECHCDR can effectively alleviate the data sparsity issue. To enrich the semantic information, we construct a weighted heterogeneous network whose nodes are users and items of different domains. The weight of link is defined by an adjacency matrix and represents the similarity between users, books and movies. We also propose to use adversarial training method to learn the embeddings of users and cross-domain items in the constructed heterogeneous graph. Experimental results on two real-world datasets collected from Amazon show the effectiveness of our approach compared with state-of-art recommender algorithms.

This paper proposes a cross-domain consumer recommendation algorithm model based on the combination of heterogeneous information network embedding and neural networks. The model first builds a heterogeneous information network and embeds various types of nodes and their complex relationships, such as users, products, and fields, into a low-dimensional vector space to fully capture the potential semantic associations of cross-domain data. Next, a feature alignment module is designed to alleviate the impact of data feature differences in different fields by normalizing and mapping embedded features, thereby ensuring consistent expression of cross-domain features. Finally, the model uses multi-layer perceptron (MLP) or graph neural network (GNN) to perform non-linear fusion and modeling of multi-modal features, and introduces an attention mechanism to dynamically capture the weight of key features to further improve user cross-domain preferences predictive ability. In order to verify the effectiveness of the model, this article carried out comparative experiments in multiple cross-domain recommendation scenarios. The results show that the model proposed in this article is significantly better than the traditional single-mode model in core indicators such as recommendation accuracy, recall rate and F1 value, modal recommendation algorithm and simple multi-modal fusion method.

With the development and maturity of electrical power system, the reliability and openness of smart grid iot system have been gradually solved and the application of iot in electrical power system has become a reality. By analyzing the influence of the introduction of electrical power system heterogeneous network on the real-time performance of the power system and studying the topological structure of electrical power system heterogeneous network, the network delay under the electrical power system heterogeneous network structure can be reduced, which has important guiding significance for the application of heterogeneous network in actual electrical power system. To this end, this paper not only presents a hierarchical integrated power system internet of things heterogeneous network architecture, but also proposes a protocol conversion method and combined with electrical power system heterogeneous network real-time analysis, from two aspects of network protocol and the driving mode of the node to electrical power system heterogeneous network wireless network nodes, the backbone network of wired/wireless heterogeneous network gateway and puts forward a method to improve real-time middleware OPC agreement.

Network embedding maps the nodes of a network to a continuous vector space, which can then be used as the input to downstream tasks, such as node classification, node clustering, link prediction, and similarity search. To learn network embedding more effectively, many technologies adopt the approach of random walk to obtain the network structure. As the meta-path of heterogeneous networks emerges, network embedding will be equipped with more semantic interpretation. Consequently, various random walks, based on meta-path strategies, have been proposed for network embedding. However, the combination of semantic and structure in a heterogeneous network cannot achieve ideal results. To overcome this challenge, we start from a task-guided issue by combining the timestamps information in the heterogeneous network, and then employing the method of temporal segmentation to decompose the network into a continuous temporal sequence. Finally, the set of context-paths between nodes is calculated in a continuous vector by the depth-first meta-path search algorithm. More precisely, we propose a Temporal Sliding Density Walk (TSDW) algorithm by combining network semantics and structure effectively. Empirical results for network data show that TSDW could significantly outperform the state-of-the-art representation learning models, including DeepWalk, LINE, Node2vec, PTE, Meapath2vec, HIN2vec, HTNE, and CTDNE by 3.02% to 44.9% of Macro-F1, 0.9% to 18.92% of Micro-F1 in multi-class node classification and 21% to 47% of NMI in node clustering.

The utilization of graph neural networks in heterogeneous networks has been rapidly increasing in recent years. The topological structure, fundamental to the nature of graphs, is often claimed to be jointly addressed with attribute information by most heterogeneous graph neural network (HGNN) approaches. However, this assertion lacks sufficient empirical validation. We empirically challenge these claims within existing evaluation frameworks. We propose a straightforward multi-layer perceptron (MLP) based model which relies solely on adjacency relationships for feature aggregation, without fully exploiting the graph's intricate topological structures. Unexpectedly, the model achieved nearly state-of-the-art performance on several real-world datasets. This discrepancy indicates that current evaluation protocols contain systemic biases and often fail to distinguish superficial adjacency exploitation from genuine structural pattern learning. It also points to the need for future benchmark datasets and metrics that more faithfully reflect the real requirements of topological learning. We hope this work stimulates further research into the role and significance of topological information in HGNNs.

Non-coding RNAs with a length of more than 200 nucleotides are long non-coding RNAs (lncRNAs), which have gained tremendous attention in recent decades. Many studies have confirmed that lncRNAs have important influence in post-transcriptional gene regulation; for example, lncRNAs affect the stability and translation of splicing factor proteins. The mutations and malfunctions of lncRNAs are closely related to human disorders. As lncRNAs interact with a variety of proteins, predicting the interaction between lncRNAs and proteins is a significant way to depth exploration functions and enrich annotations of lncRNAs. Experimental approaches for lncRNA–protein interactions are expensive and time-consuming. Computational approaches to predict lncRNA–protein interactions can be grouped into two broad categories. The first category is based on sequence, structural information and physicochemical property. The second category is based on network method through fusing heterogeneous data to construct lncRNA related heterogeneous network. The network-based methods can capture the implicit feature information in the topological structure of related biological heterogeneous networks containing lncRNAs, which is often ignored by sequence-based methods. In this paper, we summarize and discuss the materials, interaction score calculation algorithms, advantages and disadvantages of state-of-the-art algorithms of lncRNA–protein interaction prediction based on network methods to assist researchers in selecting a suitable method for acquiring more dependable results. All the related different network data are also collected and processed in convenience of users, and are available at https://github.com/HAN-Siyu/APINet/.

Protein complexes are the foundation of all cellular activities, and accurately identifying them is crucial for studying cellular systems. The efficient discovery of protein complexes is a focus of research in the field of bioinformatics. Most existing methods for protein complex identification are based on the structure of the protein-protein interaction (PPI) network, whereas some methods attempt to integrate biological information to enhance the features of the protein network for complex identification. Existing protein complex identification methods are unable to fully integrate network topology information and biological attribute information. Most of these methods are based on homogeneous networks and cannot distinguish the importance of different attributes and protein nodes. To address these issues, a GO attribute Heterogeneous Attention network Embedding (GHAE) method based on heterogeneous protein information networks is proposed. First, GHAE incorporates Gene Ontology (GO) information into the PPI network, constructing a heterogeneous protein information network. Then, GHAE uses a dual attention mechanism and heterogeneous graph convolutional representation learning method to learn protein features and to identify protein complexes. The experimental results show that building heterogeneous protein information networks can fully integrate valuable biological information. The heterogeneous graph embedding learning method can simultaneously mine the features of protein and GO attributes, thereby improving the performance of protein complex identification.

Understanding the relationship between disease phenotypes and drugs is an important issue in network medicine. With the continuous enrichment of phenotypic and drug data, scientists have proposed various approaches to explore biological information from these data. Among the existing methods, network-based ones show their advantages. However, most of the considered networks were centered on disease networks, and rarely considered networks that were composed of three or more biological entities. By integrating disease phenotypes, genes and drugs data that were extracted from three databases, a heterogeneous network that containing relationships among the three biological entities was constructed. Based on the constructed networks, we develop a new method called Relationship based on the Shortest Path (RSP) to identify disease phenotypes and drug relationships. In the RSP, we first calculated the global correlation between the 22 phenotype classes and the 14 drug classes, then the shortest path length between each disease phenotype and each drug in the heterogeneous network was used to improve such global correlation, and finally, we obtained the local correlation coefficients between drugs and phenotypes. Different indicators were used to evaluate the method, the RSP method outperforms the ProphNet and the Shortest Path (SP) methods in inferring potential phenotypic targets for drugs. Our investigations have potential implications in network medicine.