BioBroker: Knowledge Discovery Framework for Heterogeneous Biomedical Ontologies and Data

Abstract

A large number of ontologies have been introduced by the biomedical community in recent years. Knowledge discovery for entity identification from ontology has become an important research area, and it is always interesting to discovery how associations are established to connect concepts in a single ontology or across multiple ontologies. However, due to the exponential growth of biomedical big data and their complicated associations, it becomes very challenging to detect key associations among entities in an inefficient dynamic manner. Therefore, there exists a gap between the increasing needs for association detection and large volume of biomedical ontologies. In this paper, to bridge this gap, we presented a knowledge discovery framework, the BioBroker, for grouping entities to facilitate the process of biomedical knowledge discovery in an intelligent way. Specifically, we developed an innovative knowledge discovery algorithm that combines a graph clustering method and an indexing technique to discovery knowledge patterns over a set of interlinked data sources in an efficient way. We have demonstrated capabilities of the BioBroker for query execution with a use case study on a subset of the Bio2RDF life science linked data.

Constructing co-occurrence network embeddings to assist association extraction for COVID-19 and other coronavirus infectious diseases

“…In this study, we used a heuristic way to determine silhouette score and the number of clusters for making clear separations over the biomedical entities. In the future, we sought to use our previously developed hierarchical clustering optimization algorithms to make dynamic balance between the optimal silhouette score and suitable cluster density [42][43][44]. Moreover, after checking top similar entities for five selected coronavirus infectious diseases, we observed that applying clustering over the network embeddings could detect both explicit and implicit associations.…”

Publishing and Interlinking COVID-19 Data Using Linked Open Data Principles: Toward Effective Healthcare Planning and Decision-Making

“…e SW technologies (i.e., RDF, RDFs, OWL, and SPARQL) are based on W3C standards, which are aimed to materialize the SW initiatives by codifying formal and explicit definitions of the basic concepts and their relationships in a domain of interest in an easily understandable manner for the computer-based agents [7]. e SW technologies provide opportunities to deal with data heterogeneity, which could hinder the organization, interlinking, and sharing of datasets generated by different providers belonging to the same context [12,13]. e Linked Data (LD) represents a set of best practices methods to take advantage of the SW by using SW technologies for publishing structured data as resources on the Web and interlinking them semantically with related datasets on the Web [14].…”

Semantics-based key concepts identification for documents indexing and retrieval on the web

“…With the growing interest in semantic resources, several recent approaches have been proposed for semantically analysing user queries and matching them at a semantics-based level to their related documents. However, these approaches either use a single semantic resource such as Lu et al (2015), , Han et al (2016), Selmi et al (2018), Boiński et al (2018) and Royo et al (2005) or multiple heterogeneous semantic resources such as Maree et al (2016), Vigneshwari and Aramudhan (2015), Shen and Lee (2018), Kmail et al (2015), Zhu and Iglesias (2018), Goldfarb and Le Franc (2017) and Wimalasuriya and Dou (2009). For instance, the system proposed in Royo et al (2005) maps query keywords to their corresponding synsets in WordNet ontology.…”

“…Recently, there has been attempts to exploit multiple semantic resources in specialised domains such as the recruitment domain (Kmail et al, 2015), biomedical information retrieval domain (Shen and Lee, 2018) and the information extraction domain (Wimalasuriya and Dou, 2009). For instance, in Wimalasuriya and Dou (2009), the authors demonstrated through experimental results that by using multiple ontologies the quality of the system's precision can be improved.…”