Heterogeneous Types of miRNA-Disease Associations Stratified by Multi-Layer Network Embedding and Prediction

Yu, Dongling; Yu, Zu-Guo; Han, Gangwen; Li, Jinyan; Anh, Vo

doi:10.3390/biomedicines9091152

Cited by 7 publications

(7 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Complex networks have attracted the attention of scholars in the fields of computer technology [1,2], biological information [3][4][5][6], physical science [7][8][9][10], social relations [11,12] and so on. Complex networks describe realworld networks as mathematical models.…”

Section: Introductionmentioning

confidence: 99%

“…As an important research object in the random walk process, the trapping problem [20] describes the physical phenomenon that wandering particles on the network are absorbed by the trap node. This problem is widely used in the capture of attackers on the Internet [1], the repair of paralyzed sites in the transportation network [21], the optimization of signal transmission in the communication network [2], the prediction and prevention of virus transmission [4,5] and so on. As an indicator of trap efficiency, the average trapping time (ATT) represents the dynamic exploration of a random walk on a network containing trap nodes, meaning the average sum of the time taken by all nodes in the network to reach the trap node.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The average trapping time of non-nearest-neighbor jumps on nested networks

Han,

2023

Phys. Scr.

View full text Add to dashboard Cite

In this paper, we consider the trapping problem on the nearest-neighbor (NN) and non-nearest-neighbor (NNN) jumps on nested networks. Based on the nested construction of the network and the use of probability generating function tool, the iterative rules of two successive generations of the network are found, and the analytical expression of the average trapping time (ATT) is finally obtained. We allow two jump modes in the network at the same time, and the results show that the choice probability of the jump mode is not related to the exponential term of the scaling expression, but to its leading factor term. According to the analytic solution of ATT, we can find that the value of ATT expands superlinearly with the increase of network size. In addition, the numerical simulation results of parameters q (the probability of choosing NNN jump) and n (the generation of the network) show that with fixed n, ATT decreases with the increase of q; while with fixed q, ATT increases with the increase of n. In summary, this work can observe the effect of different hopping modes on random walk efficiency in complex networks.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

The average trapping time of non-nearest-neighbor jumps on nested networks

Han,

2023

Phys. Scr.

View full text Add to dashboard Cite

show abstract

“…Ha et al [ 32 ] designed a metric learning model to fuse heterogeneous features for predicting miRNA-disease associations. Yu et al [ 33 ] proposed a multi-layer heterogeneous network embedding model to predict potential miRNA-disease associations.…”

Section: Introductionmentioning

confidence: 99%

“…Deep learning methods. Neural networks have been widely used for detecting potential associations among biological entities [ 28 , 33 , 34 ]. Zeng et al [ 35 ] adopted a neural network-based model to identify potential miRNA-disease associations.…”

Section: Introductionmentioning

confidence: 99%

Predicting miRNA-Disease Association Based on Neural Inductive Matrix Completion with Graph Autoencoders and Self-Attention Mechanism

et al. 2022

View full text Add to dashboard Cite

Many studies have clarified that microRNAs (miRNAs) are associated with many human diseases. Therefore, it is essential to predict potential miRNA-disease associations for disease pathogenesis and treatment. Numerous machine learning and deep learning approaches have been adopted to this problem. In this paper, we propose a Neural Inductive Matrix completion-based method with Graph Autoencoders (GAE) and Self-Attention mechanism for miRNA-disease associations prediction (NIMGSA). Some of the previous works based on matrix completion ignore the importance of label propagation procedure for inferring miRNA-disease associations, while others cannot integrate matrix completion and label propagation effectively. Varying from previous studies, NIMGSA unifies inductive matrix completion and label propagation via neural network architecture, through the collaborative training of two graph autoencoders. This neural inductive matrix completion-based method is also an implementation of self-attention mechanism for miRNA-disease associations prediction. This end-to-end framework can strengthen the robustness and preciseness of both matrix completion and label propagation. Cross validations indicate that NIMGSA outperforms current miRNA-disease prediction methods. Case studies demonstrate that NIMGSA is competent in detecting potential miRNA-disease associations.

show abstract

“…(2) protein-related applications, such as protein-protein interactions (PPIs) (21)(22)(23)(24) and protein/gene disease interactions (25)(26)(27)(28)(29)(30)(31); and (3) transcriptomics-related applications, such as lncRNAs-diseases associations (32)(33)(34)(35) and miRNAdisease associations (36)(37)(38)(39)(40)(41)(42)(43) and many other applications (44)(45)(46)(47)(48)(49)(50). Since network embedding methods were not originally developed for biological networks, their performance in obtaining different biological network features is yet to be established.…”

Section: Introductionmentioning

confidence: 99%

BioNE: Integration of network embeddings for supervised learning

Parvizi

Azuaje

Τheodoratou

et al. 2022

Preprint

View full text Add to dashboard Cite

SummaryA network embedding approach reduces the analysis complexity of large biological networks by converting them to lowdimensional vector representations (features/embeddings). These lower-dimensional vectors can then be used in machine learning prediction tasks with a wide range of applications in computational biology and bioinformatics. Several network embedding approaches have been proposed with different methods of generating vector representations. These network embedding approaches can be quite diverse in terms of data representation and implementation. Moreover, most were not originally developed for biological networks. Therefore comparing and assessing the performance of these diverse models in practice, in biological contexts, can be challenging. To facilitate such comparisons, we have developed the BioNE framework for integration of different embedding methods in prediction tasks. Using this framework one can easily assess, for instance, whether combined vector representations from multiple embedding methods offer complementary information with regards to the network features and thus better performance on prediction tasks. In this paper, we present the BioNE software suite for embedding integration, which applies network embedding methods following standardised network preparation steps, and integrates the vector representations achieved by these methods using three different techniques. BioNE enables selection of prediction models, oversampling methods, feature selection methods, cross-validation type and cross-validation parameters.Availability and implementationBioNE pipeline and detailed explanation of implementation is freely available on GitHub, at https://github.com/pooryaparvizi/BioNE

show abstract

Heterogeneous Types of miRNA-Disease Associations Stratified by Multi-Layer Network Embedding and Prediction

Cited by 7 publications

References 34 publications

The average trapping time of non-nearest-neighbor jumps on nested networks

The average trapping time of non-nearest-neighbor jumps on nested networks

Predicting miRNA-Disease Association Based on Neural Inductive Matrix Completion with Graph Autoencoders and Self-Attention Mechanism

BioNE: Integration of network embeddings for supervised learning

Contact Info

Product

Resources

About