Link Prediction in Protein-Protein Networks: Survey

Kurakar, Manju; Izudheen, Sminu

doi:10.14445/22312803/ijctt-v9p132

Cited by 4 publications

(3 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To verify the performance of model, we apply abundant experiments on 12 benchmark networks. A detailed description of the 12 benchmark networks exhibits as follows: (1) US Air97 (USAir) 36 represents the network of the US air transportation system; (2) Yeast PPI (Yeast) 37 shows the network composed of protein interactions of yeast; (3) Food Web of Florida ecosystem (Food) 38 contains the relationship of carbon exchanges in the cypress wetlands of South Florida during the wet season; (4) Power Grid (Power) 39 represents the network of the western US power grid, describing high voltage transmission among generators, transformers and substations; (5) Net Science (NS) 40 represents the network of co-authorships between scientists publishing on the topic of networks; (6) Jazz 41 denotes the network of Jazz musicians; (7) Email network (Email) 42 is the email communication network of University Rovira i Virgili (URV) in Tarragona, Spain; (8) Slavko 43 indicates the Facebook friendship network of Slavko Zitnik; (9) UC Irvine messages social network (Ucsocial) 44 is the communication network constructed by the messages between users of an online community of students from the University of California, Irvine; (10) Infectious (Infec) 45 indicates the face-to-face contact network of people during the exhibition "Infectious: Stay Away" in 2009 at the Science Gallery in Dublin; (11) EuroSiS web (EuroSiS) 46 maps interactions between actors in Science of Society on the network of 12 European countries; (12) C.elegans (CE) 39 represents the neural network of the nematode worm CE. The basic topological characteristics of the above networks are shown in Table 1.…”

Section: Experimental Datamentioning

confidence: 99%

“…Especially, link prediction based on the topological similarity [3][4][5][6] becomes the focus of the research fields. In the aspect of practical applications, link prediction can be widely used to do research on the relationships between proteins in the biological ecosystems, 7,8 the potential relationships in the social networks, [9][10][11][12] the user-commodity relationships in the e-commerce networks, 13 the related information in the collaborative information filtering systems, [14][15][16] the infrastructure planning in the transportation networks, the route planning in the aviation networks, 17,18 the optimal resource diffusion for suppressing disease spreading in the multiplex networks 19 and the applications in the wireless sensor networks, 20 etc.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Link prediction based on combined influence and effective path

Tian

Zhu

et al. 2019

Int. J. Mod. Phys. B

View full text Add to dashboard Cite

Link prediction based on topological similarity in complex networks obtains more and more attention both in academia and industry. Most researchers believe that two unconnected endpoints can possibly make a link when they have large influence, respectively. Through profound investigations, we find that at least one endpoint possessing large influence can easily attract other endpoints. The combined influence of two unconnected endpoints affects their mutual attractions. We consider that the greater the combined influence of endpoints is, the more the possibility of them producing a link. Therefore, we explore the contribution of combined influence for similarity-based link prediction. Furthermore, we find that the transmission capability of path determines the communication possibility between endpoints. Meanwhile, compared to the local and global path, the quasi-local path balances high accuracy and low complexity more effectually in link prediction. Therefore, we focus on the transmission capabilities of quasi-local paths between two unconnected endpoints, which is called effective paths. In this paper, we propose a link prediction index based on combined influence and effective path (CIEP). A large number of experiments on 12 real benchmark datasets show that in most cases CIEP is capable of improving the prediction performance.

show abstract

Section: Experimental Datamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Link prediction based on combined influence and effective path

Tian

Zhu

et al. 2019

Int. J. Mod. Phys. B

View full text Add to dashboard Cite

show abstract

“…The link prediction task has many practical applications in various domains. In biology, link prediction has been used for identifying protein-protein interaction [1] and for investigating brain network connections [2]. In social media, link prediction has been used for identifying both future friends and possible enemies by analyzing positive and negative links [3].…”

Section: Introductionmentioning

confidence: 99%

Improving the vector auto regression technique for time-series link prediction by using support vector machine

Fernandez

2016

MATEC Web of Conferences

View full text Add to dashboard Cite

Abstract. Predicting links between the nodes of a graph has become an important Data Mining task because of its direct applications to biology, social networking, communication surveillance, and other domains. Recent literature in time-series link prediction has shown that the Vector Auto Regression (VAR) technique is one of the most accurate for this problem. In this study, we apply Support Vector Machine (SVM) to improve the VAR technique that uses an unweighted adjacency matrix along with 5 matrices: Common Neighbor (CN), Adamic-Adar (AA), Jaccard's Coefficient (JC), Preferential Attachment (PA), and Research Allocation Index (RA). A DBLP dataset covering the years from 2003 until 2013 was collected and transformed into time-sliced graph representations. The appropriate matrices were computed from these graphs, mapped to the feature space, and then used to build baseline VAR models with lag of 2 and some corresponding SVM classifiers. Using the Area Under the Receiver Operating Characteristic Curve (AUC-ROC) as the main fitness metric, the average result of 82.04% for the VAR was improved to 84.78% with SVM. Additional experiments to handle the highly imbalanced dataset by oversampling with SMOTE and undersampling with K-means clusters, however, did not improve the average AUC-ROC of the baseline SVM.

show abstract