Title :
Relation Characterization Using Ontological Concepts
Author :
Abulaish, Muhammad
Author_Institution :
Center of Excellence in Inf. Assurance, King Saud Univ., Riyadh, Saudi Arabia
Abstract :
This paper presents a method using the concept of AND-OR tree to characterize relations, mined from MEDLINE abstracts, using biological ontology concepts. A biological relation is expressed as a binary relation associated to two molecular biology concepts as defined in the GENIA ontology. Since a biological relation may relate different pairs of biological concepts and vice-versa, the strength of a relation which reflects the relative frequency of occurrence of the specific association within the corpus, is calculated and stored in the underlying ontological structure. A biological relation along with the degree of association is termed as fuzzy biological relation.
Keywords :
bioinformatics; data mining; fuzzy set theory; ontologies (artificial intelligence); trees (mathematics); AND-OR tree; GENIA ontology; biological ontology concept; biological relation characterization; fuzzy biological relation; molecular biology; Abstracts; Amino acids; Biological information theory; Equations; Ontologies; Proteins; biological relation characterization; biological relation mining; fuzzy ontology structure; web intelligence;
Conference_Titel :
Information Technology: New Generations (ITNG), 2011 Eighth International Conference on
Conference_Location :
Las Vegas, NV
Print_ISBN :
978-1-61284-427-5
Electronic_ISBN :
978-0-7695-4367-3
DOI :
10.1109/ITNG.2011.107
