Motivation: Enormous and constantly increasing quantity of biological information is represented in metabolic and in protein interaction network databases. Most of these data are freely accessible through large public depositories. The robust analysis of these resources needs novel technologies, being developed today.
Results: Here we demonstrate a technique, originating from the PageRank computation for the World Wide Web, for analyzing large interaction networks. The method is fast, scalable and robust, and its capabilities are demonstrated on metabolic network data of the tuberculosis bacterium and the proteomics analysis of the blood of melanoma patients.
Availability: The Perl script for computing the personalized PageRank in protein networks is available for non-profit research applications (together with sample input files) at the address: http://uratim.com/pp.zip.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1093/bioinformatics/btq680 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
DPAR: Decoupled Graph Neural Networks with Node-Level Differential Privacy.
Proc Int World Wide Web Conf
May 2024
Emory University, Atlanta, GA, USA.
Graph Neural Networks (GNNs) have achieved great success in learning with graph-structured data. Privacy concerns have also been raised for the trained models which could expose the sensitive information of graphs including both node features and the structure information. In this paper, we aim to achieve node-level differential privacy (DP) for training GNNs so that a node and its edges are protected.
View Article and Find Full Text PDFRelation semantic fusion in subgraph for inductive link prediction in knowledge graphs.
PeerJ Comput Sci
October 2024
School of Cyberspace Security, Zhengzhou University, Zhengzhou, Henan, China.
Inductive link prediction (ILP) in knowledge graphs (KGs) aims to predict missing links between entities that were not seen during the training phase. Recent some subgraph-based methods have shown some advancements, but they all overlook the relational semantics between entities during subgraph extraction. To overcome this limitation, we introduce a novel inductive link prediction model named SASILP (Structure and Semantic Inductive Link Prediction), which comprehensively incorporates relational semantics in both subgraph extraction and node initialization processes.
View Article and Find Full Text PDFExGAT: Context extended graph attention neural network.
Neural Netw
January 2025
School of Economics and Management, University of Chinese Academy of Sciences, Beijing, 100190, China. Electronic address:
Article Synopsis
- Context in attention-based Graph Neural Networks (GNNs) refers to the representation nodes used for graph embedding, which traditionally only includes immediate neighbors, limiting long-distance dependency capture.
- The proposed framework improves attention-based GNNs by selecting multi-hop nodes to expand context, then employing two refinement policies to optimize computational efficiency while maintaining relevant local structures in graphs.
- Extensive testing against 23 baseline models shows that this approach significantly enhances the performance of attention-based GNNs by effectively utilizing informative multi-hop neighbors.
Quantifying hubness to predict surgical outcomes in epilepsy: Assessing resection-hub alignment in interictal intracranial EEG networks.
Epilepsia
November 2024
Department of Neurology, School of Medicine, Emory University, Atlanta, Georgia, USA.
Article Synopsis
- Intracranial EEG helps identify networks associated with focal epilepsy, but how these network structures affect post-surgery seizure outcomes is not well understood.
- The study tested whether better surgical outcomes are linked to removing key brain regions (hubs) involved in seizure activity, measured by a new metric called Resection-Hub Alignment Degree (RHAD).
- Results indicated that a significant difference in RHAD was found between patients with good and bad surgical results, suggesting that analyzing network hubs offers better insights than traditional methods in predicting post-surgery epilepsy outcomes.
Time-dependent personalized PageRank for temporal networks: Discrete and continuous scales.
Chaos
August 2024
Departamento de Matemática Aplicada, Ciencia e Ingeniería de los Materiales y Tecnología Electrónica, Universidad Rey Juan Carlos, 28933 Móstoles (Madrid), Spain.
In this paper, we explore the PageRank of temporal networks (networks that evolve with time) with time-dependent personalization vectors. We consider both continuous and discrete time intervals and show that the PageRank of a continuous-temporal network can be nicely estimated by the PageRanks of the discrete-temporal networks arising after sampling. Additionally, precise boundaries are given for the estimated influence of the personalization vector on the ranking of a particular node.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!