scholarly journals The Comprehensive Contributions of Endpoint Degree and Coreness in Link Prediction

Complexity ◽  
2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Yang Tian ◽  
Yanan Wang ◽  
Hui Tian ◽  
Qimei Cui
Keyword(s):  
Link Prediction ◽  
Prediction Models ◽  
Connected Subgraph ◽  
H Index ◽  
Benchmark Datasets

In past studies, researchers find that endpoint degree, H-index, and coreness can quantify the influence of endpoints in link prediction, especially the synthetical endpoint degree and H-index improve prediction performances compared with the traditional link prediction models. However, neither endpoint degree nor H-index can describe the aggregation degree of neighbors, which results in inaccurate expression of the endpoint influence intensity. Through abundant investigations, we find that researchers ignore the importance of coreness for the influence of endpoints. Meanwhile, we also find that the synthetical endpoint degree and coreness can not only describe the maximal connected subgraph of endpoints accurately but also express the endpoint influence intensity. In this paper, we propose the DCHI model by synthesizing endpoint degree and coreness and the HCHI model by synthesizing H-index and coreness on SRW-based models, respectively. Extensive simulations on twelve real benchmark datasets show that, in most cases, DCHI shows better prediction performances in link prediction than HCHI and other traditional models.

Roles of degree, H-index and coreness in link prediction of complex networks

2018 ◽  
Vol 32 (16) ◽  
pp. 1850197 ◽  
Author(s):  
Xuzhen Zhu ◽  
Yujie Yang ◽  
Lanxi Li ◽  
Shimin Cai
Keyword(s):  
Complex Networks ◽  
Link Prediction ◽  
H Index ◽  
Topological Similarity ◽  
Benchmark Datasets ◽  
First Time

Link prediction based on topological similarity attracts more and more interests. Traditionally, researchers almost focus on utility of the paths between two unlinked endpoints, but pay little attention to the influence of the endpoints with only degree considered. Through profound investigations, we find, besides of degree, H-index and coreness also can play important roles in link prediction as the influence of endpoint especially in models based on representative SRW which is for the first time introduce influence into link prediction. In this paper, we mainly research degree, H-index and coreness in SRW-based models to explore their roles in accurate link prediction. Extensive experiments on twelve real benchmark datasets suggest that in most cases H-index serves as a better tradeoff in accurate link prediction than either degree or coreness.

Weighted synthetical influence of degree and H-index in link prediction of complex networks

2020 ◽  
Vol 34 (31) ◽  
pp. 2050307
Author(s):  
Shu Shan Zhu ◽  
Wenya Li ◽  
Ning Chen ◽  
Xuzhen Zhu ◽  
Yuxin Wang ◽  
...  
Keyword(s):  
Complex Networks ◽  
Real World ◽  
Link Prediction ◽  
Prediction Models ◽  
Great Success ◽  
H Index ◽  
Topological Similarity ◽  
Influence Measurement

Link prediction based on traditional models have attracted many interests recently. Among all models, the ones based on topological similarity have achieved great success. However, researchers pay more attention to links, but less to endpoint influence. After profound investigation, we find that the synthesis of degree and H-index plays an important role in modeling endpoint influence. So, in this paper, we propose link prediction models based on weighted synthetical influence, exploring the role of H-index and degree in endpoint influence measurement. Experiments on 12 real-world networks show that the proposed models can provide higher accuracy.

scholarly journals DeepPurpose: a deep learning library for drug–target interaction prediction

2020 ◽  
Author(s):  
Kexin Huang ◽  
Tianfan Fu ◽  
Lucas M Glass ◽  
Marinka Zitnik ◽  
Cao Xiao ◽  
...  
Keyword(s):  
Deep Learning ◽  
Drug Target ◽  
Prediction Models ◽  
State Of The Art ◽  
Supplementary Information ◽  
Target Interaction ◽  
Interaction Prediction ◽  
Computer Scientists ◽  
Benchmark Datasets ◽  
Biomedical Field

Abstract Summary Accurate prediction of drug–target interactions (DTI) is crucial for drug discovery. Recently, deep learning (DL) models for show promising performance for DTI prediction. However, these models can be difficult to use for both computer scientists entering the biomedical field and bioinformaticians with limited DL experience. We present DeepPurpose, a comprehensive and easy-to-use DL library for DTI prediction. DeepPurpose supports training of customized DTI prediction models by implementing 15 compound and protein encoders and over 50 neural architectures, along with providing many other useful features. We demonstrate state-of-the-art performance of DeepPurpose on several benchmark datasets. Availability and implementation https://github.com/kexinhuang12345/DeepPurpose. Contact [email protected] Supplementary information Supplementary data are available at Bioinformatics online.

Link prediction based on weighted synthetical influence of degree and H-index on complex networks

2019 ◽  
Vol 527 ◽  
pp. 121184
Author(s):  
Zhenbao Wang ◽  
Yuxin Wang ◽  
Jinming Ma ◽  
Wenya Li ◽  
Ning Chen ◽  
...  
Keyword(s):  
Complex Networks ◽  
Link Prediction ◽  
H Index

scholarly journals Quantitative Toxicity Prediction via Ensembling of Heterogeneous Predictors

2019 ◽  
Author(s):  
Abdul Karim ◽  
Vahid Riahi ◽  
Avinash Mishra ◽  
Abdollah Dehzangi ◽  
M. A. Hakim Newton ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Prediction Models ◽  
Individual Performance ◽  
Learning Model ◽  
Data Representation ◽  
Toxicity Prediction ◽  
Machine Learning Model ◽  
Machine Learning Approach ◽  
Benchmark Datasets

Abstract Representing molecules in the form of only one type of features and using those features to predict their activities is one of the most important approaches for machine-learning-based chemical-activity-prediction. For molecular activities like quantitative toxicity prediction, the performance depends on the type of features extracted and the machine learning approach used. For such cases, using one type of features and machine learning model restricts the prediction performance to specific representation and model used. In this paper, we study quantitative toxicity prediction and propose a machine learning model for the same. Our model uses an ensemble of heterogeneous predictors instead of typically using homogeneous predictors. The predictors that we use vary either on the type of features used or on the deep learning architecture employed. Each of these predictors presumably has its own strengths and weaknesses in terms of toxicity prediction. Our motivation is to make a combined model that utilizes different types of features and architectures to obtain better collective performance that could go beyond the performance of each individual predictor. We use six predictors in our model and test the model on four standard quantitative toxicity benchmark datasets. Experimental results show that our model outperforms the state-of-the-art toxicity prediction models in 8 out of 12 accuracy measures. Our experiments show that ensembling heterogeneous predictor improves the performance over single predictors and homogeneous ensembling of single predictors.The results show that each data representation or deep learning based predictor has its own strengths and weaknesses, thus employing a model ensembling multiple heterogeneous predictors could go beyond individual performance of each data representation or each predictor type.

scholarly journals Link prediction based on hybrid influence of neighbors

2019 ◽  
Vol 34 (05) ◽  
pp. 2050018 ◽  
Author(s):  
Tianrun Gao ◽  
Xuzhen Zhu
Keyword(s):  
Link Prediction ◽  
Prediction Accuracy ◽  
Large Scale ◽  
H Index

In previous link prediction researches, most scholars evaluate the influence of endpoints by the degree or H-index of endpoints, resulting in limited prediction accuracy. Through abundant investigations, we can evaluate the influence of endpoints accurately by the hybrid influence of neighbor nodes. Meanwhile, we calculate the hybrid influence of neighbors (HIN) by the average values of degree and H-index. In the paper, we conceive a HIN model. Large-scale experiments on 12 real datasets indicate that the conceived methods can significantly enhance the accuracy of link prediction.

scholarly journals Link prediction based on combined influence and effective path

2019 ◽  
Vol 33 (22) ◽  
pp. 1950249 ◽  
Author(s):  
Yang Tian ◽  
Han Li ◽  
Xuzhen Zhu ◽  
Hui Tian
Keyword(s):  
Link Prediction ◽  
Low Complexity ◽  
High Accuracy ◽  
Prediction Performance ◽  
Topological Similarity ◽  
Large Influence ◽  
Benchmark Datasets ◽  
Local Path ◽  
Transmission Capability ◽  
Effective Path

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.

TargetMM: accurate missense mutation prediction by utilizing local and global sequence information with classifier ensemble

2020 ◽  
Vol 23 ◽  
Author(s):  
Fang Ge ◽  
Jun Hu ◽  
Yi-Heng Zhu ◽  
Muhammad Arif ◽  
Dong-Jun Yu
Keyword(s):  
Missense Mutation ◽  
Prediction Models ◽  
Feature Representation ◽  
Classifier Ensemble ◽  
Sequence Information ◽  
Mutation Site ◽  
Feature Extracting ◽  
Independent Test ◽  
Benchmark Datasets ◽  
The Impact

Aim and Objective: Missense mutation (MM) may lead to various human diseases by disabling proteins. Accurate prediction of MM is important and challenging for both protein function annotation and drug design. Although several computational methods yielded acceptable success rates, there is still room for further enhancing the prediction performance of MM. Materials and Methods: In the present study, we designed a new feature extracting method, which considers the impact degree of residues in the microenvironment range to the mutation site. Stringent cross-validation and independent test on benchmark datasets were performed to evaluate the efficacy of the proposed feature extracting method. Furthermore, three heterogeneous prediction models were trained and then ensembled for the final prediction. Results: By combining the feature representation method and classifier ensemble technique, we reported a novel MM predictor called TargetMM for identifying the pathogenic mutations from the neutral ones. Conclusion: Comparison outcomes based on statistical evaluation demonstrate that TargetMM outperforms the prior advanced methods on the independent test data. The source code and benchmark datasets of TargetMM are freely available at https://github.com/sera616/TargetMM.git for academic use.

h-Index-based link prediction methods in citation network

2018 ◽  
Vol 117 (1) ◽  
pp. 381-390 ◽  
Author(s):  
Wen Zhou ◽  
Jiayi Gu ◽  
Yifan Jia
Keyword(s):  
Link Prediction ◽  
Citation Network ◽  
Prediction Methods ◽  
H Index
Sign in / Sign up

Export Citation Format

Share Document