Knowledge discovery, especially in the field of literature mining, is often involved in searching for interconnecting concepts between two different literature domains, which might bring new understanding of the two domains. This work presents a new approach to discovering dependencies between different biological domains based on copula analysis of literature mining results. In the use case of the domains of plant defence response and redox potential literatures we have first performed relation extraction with Bio3graph, our rule-based natural language processing tool for extracting relations in the form (subject, predicate, object) triplets. The results of triplets extraction were analysed by using a copula-based approach, which showed that dependencies exist between the two domains indicating a potential for cross-domain literature exploration.
F.02 Acquisition of new scientific knowledge
COBISS.SI-ID: 29894439In this paper we propose a methodology for cross-domain literature-based discovery that focuses on outlier documents to reduce the search space of potential cross-domain links and to improve search efficiency. By using literature mining tools OntoGen for document clustering and CrossBee for cross-domain bridging term exploration we identified and explored “nitric oxide synthase” as a promising bridging term between gut microbiome and Alzheimer’s disease literatures.
F.02 Acquisition of new scientific knowledge
COBISS.SI-ID: 29481511Semantic data mining is a field of research that focuses on providing rich and highly informative descriptions of data (annotated by background knowledge in the form of ontologies), however the computational cost of searching for these descriptions is high. We propose a new methodology with which we can use network analysis algorithms to evaluate the importance of the background knowledge before running a semantic mining algorithm, thus greatly improving both the performance of the algorithm and the quality of the output descriptions.
F.02 Acquisition of new scientific knowledge
COBISS.SI-ID: 29482535