Clustering of proteins in interaction networks based on motif features

Patra, Sabyasachi; Mohapatra, Anjali

doi:10.1109/bsb.2018.8770648

“…In this application, the correctness of evolutionary trees is validated by finding under‐represented network motifs called holes in the character overlap graphs [ 39 ]. Clustering of proteins: Features extracted from network motifs can be used for clustering the proteins in an interaction network [ 40 ]. …”

Section: Some Applications Of Network Motifsmentioning

confidence: 99%

“…Clustering of proteins: Features extracted from network motifs can be used for clustering the proteins in an interaction network [ 40 ].…”

Section: Some Applications Of Network Motifsmentioning

confidence: 99%

Review of tools and algorithms for network motif discovery in biological networks

Patra

¹

,

Mohapatra

²

2020

Self Cite

View full text Add to dashboard Cite

Network motifs are recurrent and over‐represented patterns having biological relevance. This is one of the important local properties of biological networks. Network motif discovery finds important applications in many areas such as functional analysis of biological components, the validity of network composition, classification of networks, disease discovery, identification of unique subunits etc. The discovery of network motifs is a computationally challenging task due to the large size of real networks, and the exponential increase of search space with respect to network size and motif size. This problem also includes the subgraph isomorphism check, which is Nondeterministic Polynomial (NP)‐complete. Several tools and algorithms have been designed in the last few years to address this problem with encouraging results. These tools and algorithms can be classified into various categories based on exact census, mapping, pattern growth, and so on. In this study, critical aspects of network motif discovery, design principles of background algorithms, and their functionality have been reviewed with their strengths and limitations. The performances of state‐of‐art algorithms are discussed in terms of runtime efficiency, scalability, and space requirement. The future scope, research direction, and challenges of the existing algorithms are presented at the end of the study.

show abstract

“…However, in the corresponding low-dimensional vector space, such multivariate relationships are barely represented due to the limitation of vectors. Real-world networks consist of various complex relationships, in which most entities are in multivariate relationships with others [2,5]. Comparing with pairwise relationships, multivariate relationships are even more significant but complicated.…”

Section: Introductionmentioning

confidence: 99%

OFFER: A Motif Dimensional Framework for Network Representation Learning

Yu

¹

,

Xia

²

,

Xu

³

et al. 2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

Aiming at better representing multivariate relationships, this paper investigates a motif dimensional framework for higher-order graph learning. The graph learning effectiveness can be improved through OFFER. The proposed framework mainly aims at accelerating and improving higher-order graph learning results. We apply the acceleration procedure from the dimensional of network motifs. Specifically, the refined degree for nodes and edges are conducted in two stages: (1) employ motif degree of nodes to refine the adjacency matrix of the network; and (2) employ motif degree of edges to refine the transition probability matrix in the learning process. In order to assess the efficiency of the proposed framework, four popular network representation algorithms are modified and examined. By evaluating the performance of OFFER, both link prediction results and clustering results demonstrate that the graph representation learning algorithms enhanced with OFFER consistently outperform the original algorithms with higher efficiency.

show abstract

OFFER: A Motif Dimensional Framework for Network Representation Learning

Yu

¹

,

Xia

²

,

Xu

³

et al. 2020

Preprint

0

View full text Add to dashboard Cite

Aiming at better representing multivariate relationships, this paper investigates a motif dimensional framework for higher-order graph learning. The graph learning effectiveness can be improved through OFFER. The proposed framework mainly aims at accelerating and improving higher-order graph learning results. We apply the acceleration procedure from the dimensional of network motifs. Specifically, the refined degree for nodes and edges are conducted in two stages: (1) employ motif degree of nodes to refine the adjacency matrix of the network; and (2) employ motif degree of edges to refine the transition probability matrix in the learning process. In order to assess the efficiency of the proposed framework, four popular network representation algorithms are modified and examined. By evaluating the performance of OFFER, both link prediction results and clustering results demonstrate that the graph representation learning algorithms enhanced with OFFER consistently outperform the original algorithms with higher efficiency. CCS Concepts: • Mathematics of computing; • Computing methodologies → Knowledge representation and reasoning; Machine learning;

show abstract

Clustering of proteins in interaction networks based on motif features

Cited by 3 publications

References 15 publications

Review of tools and algorithms for network motif discovery in biological networks

Review of tools and algorithms for network motif discovery in biological networks

OFFER: A Motif Dimensional Framework for Network Representation Learning

OFFER: A Motif Dimensional Framework for Network Representation Learning

Contact Info

Product

Resources

About