Link Prediction for Annotation Graphs Using Graph Summarization

Thor, Andreas; Anderson, Philip D.; Raschid, Louiqa; Navlakha, Saket; Saha, Barna; Khuller, Samir; Zhang, Xiaoning

doi:10.1007/978-3-642-25073-6_45

Cited by 33 publications

(28 citation statements)

References 26 publications

(33 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Chart outline and thick subgraph strategy were proposed to channel the diagram and discover promising subgraphs. A scoring capacity in view of various heuristics was proposed to rank the expectations in light of these separated subgraphs [23]. Amakrishnan [24] proposed a strategy to find the educational association subgraphs that relate two substances in the chart.…”

Section: F Ontology Based Information Extractionmentioning

confidence: 99%

Ontology-Based Approaches for Data Mining: A Survey

2017

IJRTER

View full text Add to dashboard Cite

Abstract-Data Mining alludes to the information mining assignments that deliberately consolidate area learning, particularly formal semantics, into the procedure. Numerous exploration endeavors have validated the advantages of fusing area learning in information mining and in the meantime, the expansion of information building has enhanced the group of space learning, particularly formal semantics and Semantic Web ontology. Ontology is an explicit specification of conceptualization and a formal approach to characterize the semantics of information and data. The formal structure of ontology makes it a nature approach to encode area information for the information mining utilization. Keywords -information mining; ontology; data mining I. INTRODUCTION Data mining, otherwise called knowledge discovery from database (KDD), is the methodology of nontrivial extraction of verifiable, beforehand obscure, and possibly valuable data from information [1]. With the recent advances in data mining strategies lead to numerous momentous upsets in information investigation and big data. Data mining likewise joins methods from insights, computerized reasoning, machine learning, database framework, and numerous different controls to examine substantial information sets. Semantic Data Mining alludes to data mining errands that deliberately fuse space learning, particularly formal semantics, into the methodology. Past semantic data mining exploration has bore witness to the positive impact of space learning on data mining. Amid the seeking and pattern generating procedure, area learning can function as an arrangement of former information of requirements to help decrease hunt space and aide the inquiry way [2], [3].To make utilization of area information in the data mining process, the first step must record for speaking to and building the learning by models that the PC can further get to and process. The multiplication of knowledge engineering (KE) has astoundingly improved the group of space learning with strategies that fabricate and utilization area information in a formal manner [4]. Ontology is one of effective knowledge engineering advances, which is the unequivocal determination of a conceptualization [5], [6]. Ontology is created to determine a specific area. Such a ontology, regularly known as space ontology, formally determines the ideas and connections in that area. The encoded formal semantics in ontologies is essentially utilized for viably imparting and reusing of learning and information. Research in the region of the Semantic Web [7] has prompted truly develop benchmarks for demonstrating and arranging area information. At present, Semantic Web ontologies turn into a key innovation for wise learning handling, giving a system to offering calculated models about an area. The Web Ontology Language (OWL) [8], which has developed as the true standard for characterizing Semantic Web ontologies, is broadly utilized for this reason. The Semantic Web advancements that speak to space learning including organized gathering of ...

show abstract

Section: F Ontology Based Information Extractionmentioning

confidence: 99%

Ontology-Based Approaches for Data Mining: A Survey

2017

IJRTER

View full text Add to dashboard Cite

show abstract

“…First, we have to find patterns in annotation graph datasets. On this challenge, we can report some initial success [1,22,27].…”

Section: Introductionmentioning

confidence: 99%

Finding Cross Genome Patterns in Annotation Graphs

Benik

Chang

Raschid

et al. 2012

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. Annotation graph datasets are a natural representation of scientific knowledge. They are common in the life sciences where concepts such as genes and proteins are annotated with controlled vocabulary terms from ontologies. Scientists are interested in analyzing or mining these annotations, in synergy with the literature, to discover patterns. Further, annotated datasets provide an avenue for scientists to explore shared annotations across genomes to support cross genome discovery. We present a tool, PAnG (Patterns in Annotation Graphs), that is based on a complementary methodology of graph summarization and dense subgraphs. The elements of a graph summary correspond to a pattern and its visualization can provide an explanation of the underlying knowledge. We present and analyze two distance metrics to identify related concepts in ontologies. We present preliminary results using groups of Arabidopsis and C. elegans genes to illustrate the potential benefits of cross genome pattern discovery.

show abstract

“…Semantically enriched datasets, as the one delivered by Biotea, facilitate literature-base knowledge discovery as semantic annotations make it possible to find hidden relations [12,14,15]. For instance, patterns across the MeSH terms have been used to identify potential new associations between drugs and diseases [12].…”

Section: Discussionmentioning

confidence: 99%

“…For instance, patterns across the MeSH terms have been used to identify potential new associations between drugs and diseases [12]. Also, annotations shared by a group of genes have contributed to identify possible relationships between these genes [14,15]. Broader possibilities become possible in Biotea.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Biotea-Biolinks: A semantic infrastructure for exploring and analyzing scientific publications

Castro¹,

Jael²

View full text Add to dashboard Cite

Link Prediction for Annotation Graphs Using Graph Summarization

Cited by 33 publications

References 26 publications

Ontology-Based Approaches for Data Mining: A Survey

Ontology-Based Approaches for Data Mining: A Survey

Finding Cross Genome Patterns in Annotation Graphs

Biotea-Biolinks: A semantic infrastructure for exploring and analyzing scientific publications

Contact Info

Product

Resources

About